{ "cells": [ { "cell_type": "markdown", "id": "4a867836", "metadata": {}, "source": [ "Bayesian Neural Network model traning and prediction data generation." ] }, { "cell_type": "code", "execution_count": 1, "id": "210da263", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.neural_network import MLPRegressor\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import r2_score\n", "\n", "import pickle" ] }, { "cell_type": "code", "execution_count": 2, "id": "edbf3b27", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "from tensorflow.keras import layers\n", "import tensorflow_datasets as tfds\n", "import tensorflow_probability as tfp\n", "\n", "tfk = tf.keras\n", "tf.keras.backend.set_floatx(\"float32\")\n", "import tensorflow_probability as tfp\n", "tfd = tfp.distributions\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.ensemble import IsolationForest\n", "\n", "from scipy.stats import norm" ] }, { "cell_type": "markdown", "id": "9dadf6ec", "metadata": {}, "source": [ "Load the training databases, generated in player_match_database_creation" ] }, { "cell_type": "code", "execution_count": 40, "id": "fa098fa4", "metadata": {}, "outputs": [], "source": [ "db1 = pd.read_excel('mid_outputs/database_entries.xlsx', index_col = 0) \n", "db2 = pd.read_excel('mid_outputs/season2021/database_entries.xlsx', index_col = 0) \n", "db3 = pd.read_excel('mid_outputs/season2122/database_entries.xlsx', index_col = 0) " ] }, { "cell_type": "code", "execution_count": 41, "id": "f71fa9a4", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...touches_live_balldribbles_completeddribblespasses_receivedmiscontrolsdispossessedfoulsfouledaerials_wonaerials_lost
01ToloiAtalantaSampdoria07.0100.010.0...0.6842110.0008490.0050930.4074700.0076400.0008490.0067910.0050930.0161290.011885
11DjimsitiAtalantaSampdoria06.0000.06.0...0.7535410.0000000.0028330.5212460.0028330.0084990.0028330.0028330.0056660.008499
21HateboerAtalantaSampdoria06.0000.55.5...0.5860900.0033930.0067850.3570820.0067850.0042410.0127230.0016960.0152670.011874
31OkoliAtalantaSampdoria05.5000.55.0...0.6071010.0000000.0011830.2792900.0130180.0035500.0153850.0082840.0473370.027219
41ZorteaAtalantaSampdoria06.0000.55.5...0.6486490.0450450.0945950.3648650.0270270.0090090.0180180.0000000.0225230.004505
..................................................................
2413138TamezeVeronaLazio05.5000.05.5...0.6293710.0132090.0233100.3581970.0198140.0101010.0128210.0132090.0236990.021368
2413238HonglaVeronaLazio07.0100.59.5...0.5821810.0015360.0076800.3410140.0184330.0122890.0230410.0076800.0230410.026114
2413338LasagnaVeronaLazio07.0100.59.5...0.3699320.0084460.0160470.2626690.0464530.0228040.0160470.0084460.0261820.041385
2413438CaprariVeronaLazio06.0000.06.0...0.6024100.0237310.0434470.4538150.0339540.0197150.0153340.0270170.0029210.009858
2413538SimeoneVeronaLazio07.0100.010.0...0.4070860.0086690.0229930.3203920.0512630.0301550.0211080.0218620.0226160.040709
\n", "

24136 rows × 131 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote goals assists \\\n", "0 1 Toloi Atalanta Sampdoria 0 7.0 1 0 \n", "1 1 Djimsiti Atalanta Sampdoria 0 6.0 0 0 \n", "2 1 Hateboer Atalanta Sampdoria 0 6.0 0 0 \n", "3 1 Okoli Atalanta Sampdoria 0 5.5 0 0 \n", "4 1 Zortea Atalanta Sampdoria 0 6.0 0 0 \n", "... ... ... ... ... ... ... ... ... \n", "24131 38 Tameze Verona Lazio 0 5.5 0 0 \n", "24132 38 Hongla Verona Lazio 0 7.0 1 0 \n", "24133 38 Lasagna Verona Lazio 0 7.0 1 0 \n", "24134 38 Caprari Verona Lazio 0 6.0 0 0 \n", "24135 38 Simeone Verona Lazio 0 7.0 1 0 \n", "\n", " cards_malus fantavote ... touches_live_ball dribbles_completed \\\n", "0 0.0 10.0 ... 0.684211 0.000849 \n", "1 0.0 6.0 ... 0.753541 0.000000 \n", "2 0.5 5.5 ... 0.586090 0.003393 \n", "3 0.5 5.0 ... 0.607101 0.000000 \n", "4 0.5 5.5 ... 0.648649 0.045045 \n", "... ... ... ... ... ... \n", "24131 0.0 5.5 ... 0.629371 0.013209 \n", "24132 0.5 9.5 ... 0.582181 0.001536 \n", "24133 0.5 9.5 ... 0.369932 0.008446 \n", "24134 0.0 6.0 ... 0.602410 0.023731 \n", "24135 0.0 10.0 ... 0.407086 0.008669 \n", "\n", " dribbles passes_received miscontrols dispossessed fouls \\\n", "0 0.005093 0.407470 0.007640 0.000849 0.006791 \n", "1 0.002833 0.521246 0.002833 0.008499 0.002833 \n", "2 0.006785 0.357082 0.006785 0.004241 0.012723 \n", "3 0.001183 0.279290 0.013018 0.003550 0.015385 \n", "4 0.094595 0.364865 0.027027 0.009009 0.018018 \n", "... ... ... ... ... ... \n", "24131 0.023310 0.358197 0.019814 0.010101 0.012821 \n", "24132 0.007680 0.341014 0.018433 0.012289 0.023041 \n", "24133 0.016047 0.262669 0.046453 0.022804 0.016047 \n", "24134 0.043447 0.453815 0.033954 0.019715 0.015334 \n", "24135 0.022993 0.320392 0.051263 0.030155 0.021108 \n", "\n", " fouled aerials_won aerials_lost \n", "0 0.005093 0.016129 0.011885 \n", "1 0.002833 0.005666 0.008499 \n", "2 0.001696 0.015267 0.011874 \n", "3 0.008284 0.047337 0.027219 \n", "4 0.000000 0.022523 0.004505 \n", "... ... ... ... \n", "24131 0.013209 0.023699 0.021368 \n", "24132 0.007680 0.023041 0.026114 \n", "24133 0.008446 0.026182 0.041385 \n", "24134 0.027017 0.002921 0.009858 \n", "24135 0.021862 0.022616 0.040709 \n", "\n", "[24136 rows x 131 columns]" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db = pd.concat([db1, db2, db3], ignore_index = True) \n", "\n", "db" ] }, { "cell_type": "code", "execution_count": 42, "id": "1d024554", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...gk_psxggk_psnpxg_per_shot_on_target_againstgk_psxg_netgk_passes_completed_launchedgk_passes_launchedgk_passesgk_passes_throwsgk_goal_kicksgk_crossesgk_crosses_stopped
01MussoAtalantaSampdoria06.0000.55.5...10.4000000.220000-2.60000078.000000167.000000321.00000093.00000086.0147.08.000000
11SkorupskiBolognaLazio06.5-200.04.5...28.7000000.2800000.70000087.000000219.000000545.000000116.000000141.0280.018.000000
21VicarioEmpoliSpezia05.5-100.04.5...24.0000000.2700002.00000088.000000277.000000690.000000108.000000103.0399.025.000000
31GolliniFiorentinaCremonese15.0-200.03.0...15.6000000.2700001.60000034.00000092.000000425.00000069.000000114.0197.06.000000
41HandanovicInterLecce06.5-100.05.5...10.6000000.300000-1.40000027.00000052.000000266.00000046.00000045.079.02.000000
..................................................................
112019PegoloSassuoloMonza06.5-100.05.5...15.4666670.373333-2.86666769.666667167.333333434.33333361.333333110.0156.09.333333
112119DragowskiSpeziaRoma16.0-200.04.0...26.0000000.280000-3.00000085.000000255.000000479.00000087.000000106.0235.09.000000
112219Milinkovic-Savic V.TorinoFiorentina07.0000.07.0...20.3000000.2400000.300000138.000000493.000000746.00000085.000000142.0232.018.000000
112319SilvestriUdineseSampdoria06.0000.06.0...22.1000000.3200001.10000076.000000200.000000406.00000072.000000153.0253.04.000000
112419Montipo'VeronaLecce16.5000.06.5...25.2000000.250000-4.800000176.000000358.000000447.00000062.000000153.0261.010.000000
\n", "

1125 rows × 108 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote \\\n", "0 1 Musso Atalanta Sampdoria 0 6.0 \n", "1 1 Skorupski Bologna Lazio 0 6.5 \n", "2 1 Vicario Empoli Spezia 0 5.5 \n", "3 1 Gollini Fiorentina Cremonese 1 5.0 \n", "4 1 Handanovic Inter Lecce 0 6.5 \n", "... ... ... ... ... ... ... \n", "1120 19 Pegolo Sassuolo Monza 0 6.5 \n", "1121 19 Dragowski Spezia Roma 1 6.0 \n", "1122 19 Milinkovic-Savic V. Torino Fiorentina 0 7.0 \n", "1123 19 Silvestri Udinese Sampdoria 0 6.0 \n", "1124 19 Montipo' Verona Lecce 1 6.5 \n", "\n", " goals assists cards_malus fantavote ... gk_psxg \\\n", "0 0 0 0.5 5.5 ... 10.400000 \n", "1 -2 0 0.0 4.5 ... 28.700000 \n", "2 -1 0 0.0 4.5 ... 24.000000 \n", "3 -2 0 0.0 3.0 ... 15.600000 \n", "4 -1 0 0.0 5.5 ... 10.600000 \n", "... ... ... ... ... ... ... \n", "1120 -1 0 0.0 5.5 ... 15.466667 \n", "1121 -2 0 0.0 4.0 ... 26.000000 \n", "1122 0 0 0.0 7.0 ... 20.300000 \n", "1123 0 0 0.0 6.0 ... 22.100000 \n", "1124 0 0 0.0 6.5 ... 25.200000 \n", "\n", " gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n", "0 0.220000 -2.600000 \n", "1 0.280000 0.700000 \n", "2 0.270000 2.000000 \n", "3 0.270000 1.600000 \n", "4 0.300000 -1.400000 \n", "... ... ... \n", "1120 0.373333 -2.866667 \n", "1121 0.280000 -3.000000 \n", "1122 0.240000 0.300000 \n", "1123 0.320000 1.100000 \n", "1124 0.250000 -4.800000 \n", "\n", " gk_passes_completed_launched gk_passes_launched gk_passes \\\n", "0 78.000000 167.000000 321.000000 \n", "1 87.000000 219.000000 545.000000 \n", "2 88.000000 277.000000 690.000000 \n", "3 34.000000 92.000000 425.000000 \n", "4 27.000000 52.000000 266.000000 \n", "... ... ... ... \n", "1120 69.666667 167.333333 434.333333 \n", "1121 85.000000 255.000000 479.000000 \n", "1122 138.000000 493.000000 746.000000 \n", "1123 76.000000 200.000000 406.000000 \n", "1124 176.000000 358.000000 447.000000 \n", "\n", " gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n", "0 93.000000 86.0 147.0 8.000000 \n", "1 116.000000 141.0 280.0 18.000000 \n", "2 108.000000 103.0 399.0 25.000000 \n", "3 69.000000 114.0 197.0 6.000000 \n", "4 46.000000 45.0 79.0 2.000000 \n", "... ... ... ... ... \n", "1120 61.333333 110.0 156.0 9.333333 \n", "1121 87.000000 106.0 235.0 9.000000 \n", "1122 85.000000 142.0 232.0 18.000000 \n", "1123 72.000000 153.0 253.0 4.000000 \n", "1124 62.000000 153.0 261.0 10.000000 \n", "\n", "[1125 rows x 108 columns]" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db_gk1 = pd.read_excel('mid_outputs/database_entries_gk.xlsx', index_col = 0) \n", "db_gk2 = pd.read_excel('mid_outputs/season2021/database_entries_gk.xlsx', index_col = 0) \n", "db_gk3 = pd.read_excel('mid_outputs/season2122/database_entries_gk.xlsx', index_col = 0) \n", "\n", "db_gk = pd.concat([db_gk1, db_gk1, db_gk1], ignore_index = True) \n", "\n", "db_gk" ] }, { "cell_type": "markdown", "id": "04df0936", "metadata": {}, "source": [ "Load player stats from current season and past seasons" ] }, { "cell_type": "code", "execution_count": 43, "id": "bc9dae87", "metadata": {}, "outputs": [], "source": [ "players_orig = pd.read_excel('mid_outputs/players_stats.xlsx', index_col = 3)\n", "#players = pd.read_excel('mid_outputs/players_stats_rwk.xlsx', index_col = 3) # reworked stats to account for past season\n", "\n", "players_old = pd.read_excel('mid_outputs/season2122/players_stats.xlsx', index_col = 3)\n", "players_old_2 = pd.read_excel('mid_outputs/season2021/players_stats.xlsx', index_col = 3)\n", "\n", "players = players_orig" ] }, { "cell_type": "markdown", "id": "397babf2", "metadata": {}, "source": [ "Load team data from current season and add an average Serie A team row" ] }, { "cell_type": "code", "execution_count": 44, "id": "493b0495", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_19096\\661405348.py:3: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction.\n", " avg_row = pd.DataFrame(index = ['Avg'], data = [team_data.mean()], columns = team_data.columns)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
teamteam_players_usedteam_possessionteam_gamesteam_games_startsteam_minutesteam_goalsteam_assiststeam_pens_madeteam_pens_att...vs_team_foulsvs_team_fouledvs_team_offsidesvs_team_pens_wonvs_team_pens_concededvs_team_own_goalsvs_team_ball_recoveriesvs_team_aerials_wonvs_team_aerials_lostvs_team_aerials_won_pct
AtalantaAtalanta24.0048.4019.0209.01710.036.025.06.08.00...209.00218.025.001.008.01.001165.00239.00279.0046.100
BolognaBologna24.0052.6020.0220.01800.025.019.03.03.00...252.00229.033.003.003.01.001081.00224.00180.0055.400
CremoneseCremonese29.0044.0019.0209.01710.014.06.02.04.00...205.00247.029.003.004.00.001052.00348.00267.0056.600
EmpoliEmpoli26.0046.3019.0209.01710.017.09.00.00.00...251.00214.031.002.000.00.00999.00217.00189.0053.400
FiorentinaFiorentina27.0057.2019.0209.01710.021.017.02.04.00...259.00229.052.001.004.00.00942.00249.00289.0046.300
VeronaHellas Verona29.0043.4019.0209.01710.016.013.00.00.00...192.00276.022.001.000.01.001038.00345.00388.0047.100
InterInter23.0052.9019.0209.01710.037.025.02.02.00...242.00214.018.002.002.01.00869.00198.00232.0046.000
JuventusJuventus26.0049.5019.0209.01710.030.023.02.03.00...210.00210.025.000.003.00.00947.00230.00230.0050.000
LazioLazio21.0051.2019.0209.01710.034.025.03.04.00...261.00185.042.001.004.01.001021.00183.00181.0050.300
LecceLecce26.0042.5020.0220.01800.018.012.01.02.00...263.00265.043.003.002.01.001072.00373.00294.0055.900
MilanMilan27.0054.5019.0209.01710.033.028.02.02.00...234.00226.020.003.002.02.00964.00224.00275.0044.900
MonzaMonza29.0055.1019.0209.01710.022.013.03.03.00...279.00242.034.000.003.01.00958.00197.00215.0047.800
NapoliNapoli24.0061.3019.0209.01710.046.037.04.05.00...258.00167.027.001.004.00.00933.00201.00231.0046.500
RomaRoma25.0049.4019.0209.01710.025.016.03.05.00...266.00214.010.000.005.00.00981.00184.00225.0045.000
SalernitanaSalernitana28.0044.8020.0220.01800.024.016.01.01.00...226.00233.049.007.001.01.001084.00257.00240.0051.700
SampdoriaSampdoria29.0049.4019.0209.01710.08.07.00.00.00...299.00266.055.003.000.00.001017.00300.00318.0048.500
SassuoloSassuolo27.0048.7019.0209.01710.018.013.03.04.00...249.00182.062.002.004.00.00986.00216.00173.0055.500
SpeziaSpezia30.0046.7020.0220.01800.015.010.02.02.00...207.00261.046.001.002.02.001182.00322.00281.0053.400
TorinoTorino23.0052.8019.0209.01710.019.014.01.01.00...209.00265.021.003.001.00.00998.00323.00295.0052.300
UdineseUdinese22.0050.1019.0209.01710.026.022.00.00.00...250.00227.029.002.000.01.00950.00189.00237.0044.400
AvgAvg25.9550.0419.2211.21728.024.217.52.02.65...241.05228.533.651.952.60.651011.95250.95250.9549.855
\n", "

21 rows × 313 columns

\n", "
" ], "text/plain": [ " team team_players_used team_possession team_games \\\n", "Atalanta Atalanta 24.00 48.40 19.0 \n", "Bologna Bologna 24.00 52.60 20.0 \n", "Cremonese Cremonese 29.00 44.00 19.0 \n", "Empoli Empoli 26.00 46.30 19.0 \n", "Fiorentina Fiorentina 27.00 57.20 19.0 \n", "Verona Hellas Verona 29.00 43.40 19.0 \n", "Inter Inter 23.00 52.90 19.0 \n", "Juventus Juventus 26.00 49.50 19.0 \n", "Lazio Lazio 21.00 51.20 19.0 \n", "Lecce Lecce 26.00 42.50 20.0 \n", "Milan Milan 27.00 54.50 19.0 \n", "Monza Monza 29.00 55.10 19.0 \n", "Napoli Napoli 24.00 61.30 19.0 \n", "Roma Roma 25.00 49.40 19.0 \n", "Salernitana Salernitana 28.00 44.80 20.0 \n", "Sampdoria Sampdoria 29.00 49.40 19.0 \n", "Sassuolo Sassuolo 27.00 48.70 19.0 \n", "Spezia Spezia 30.00 46.70 20.0 \n", "Torino Torino 23.00 52.80 19.0 \n", "Udinese Udinese 22.00 50.10 19.0 \n", "Avg Avg 25.95 50.04 19.2 \n", "\n", " team_games_starts team_minutes team_goals team_assists \\\n", "Atalanta 209.0 1710.0 36.0 25.0 \n", "Bologna 220.0 1800.0 25.0 19.0 \n", "Cremonese 209.0 1710.0 14.0 6.0 \n", "Empoli 209.0 1710.0 17.0 9.0 \n", "Fiorentina 209.0 1710.0 21.0 17.0 \n", "Verona 209.0 1710.0 16.0 13.0 \n", "Inter 209.0 1710.0 37.0 25.0 \n", "Juventus 209.0 1710.0 30.0 23.0 \n", "Lazio 209.0 1710.0 34.0 25.0 \n", "Lecce 220.0 1800.0 18.0 12.0 \n", "Milan 209.0 1710.0 33.0 28.0 \n", "Monza 209.0 1710.0 22.0 13.0 \n", "Napoli 209.0 1710.0 46.0 37.0 \n", "Roma 209.0 1710.0 25.0 16.0 \n", "Salernitana 220.0 1800.0 24.0 16.0 \n", "Sampdoria 209.0 1710.0 8.0 7.0 \n", "Sassuolo 209.0 1710.0 18.0 13.0 \n", "Spezia 220.0 1800.0 15.0 10.0 \n", "Torino 209.0 1710.0 19.0 14.0 \n", "Udinese 209.0 1710.0 26.0 22.0 \n", "Avg 211.2 1728.0 24.2 17.5 \n", "\n", " team_pens_made team_pens_att ... vs_team_fouls \\\n", "Atalanta 6.0 8.00 ... 209.00 \n", "Bologna 3.0 3.00 ... 252.00 \n", "Cremonese 2.0 4.00 ... 205.00 \n", "Empoli 0.0 0.00 ... 251.00 \n", "Fiorentina 2.0 4.00 ... 259.00 \n", "Verona 0.0 0.00 ... 192.00 \n", "Inter 2.0 2.00 ... 242.00 \n", "Juventus 2.0 3.00 ... 210.00 \n", "Lazio 3.0 4.00 ... 261.00 \n", "Lecce 1.0 2.00 ... 263.00 \n", "Milan 2.0 2.00 ... 234.00 \n", "Monza 3.0 3.00 ... 279.00 \n", "Napoli 4.0 5.00 ... 258.00 \n", "Roma 3.0 5.00 ... 266.00 \n", "Salernitana 1.0 1.00 ... 226.00 \n", "Sampdoria 0.0 0.00 ... 299.00 \n", "Sassuolo 3.0 4.00 ... 249.00 \n", "Spezia 2.0 2.00 ... 207.00 \n", "Torino 1.0 1.00 ... 209.00 \n", "Udinese 0.0 0.00 ... 250.00 \n", "Avg 2.0 2.65 ... 241.05 \n", "\n", " vs_team_fouled vs_team_offsides vs_team_pens_won \\\n", "Atalanta 218.0 25.00 1.00 \n", "Bologna 229.0 33.00 3.00 \n", "Cremonese 247.0 29.00 3.00 \n", "Empoli 214.0 31.00 2.00 \n", "Fiorentina 229.0 52.00 1.00 \n", "Verona 276.0 22.00 1.00 \n", "Inter 214.0 18.00 2.00 \n", "Juventus 210.0 25.00 0.00 \n", "Lazio 185.0 42.00 1.00 \n", "Lecce 265.0 43.00 3.00 \n", "Milan 226.0 20.00 3.00 \n", "Monza 242.0 34.00 0.00 \n", "Napoli 167.0 27.00 1.00 \n", "Roma 214.0 10.00 0.00 \n", "Salernitana 233.0 49.00 7.00 \n", "Sampdoria 266.0 55.00 3.00 \n", "Sassuolo 182.0 62.00 2.00 \n", "Spezia 261.0 46.00 1.00 \n", "Torino 265.0 21.00 3.00 \n", "Udinese 227.0 29.00 2.00 \n", "Avg 228.5 33.65 1.95 \n", "\n", " vs_team_pens_conceded vs_team_own_goals \\\n", "Atalanta 8.0 1.00 \n", "Bologna 3.0 1.00 \n", "Cremonese 4.0 0.00 \n", "Empoli 0.0 0.00 \n", "Fiorentina 4.0 0.00 \n", "Verona 0.0 1.00 \n", "Inter 2.0 1.00 \n", "Juventus 3.0 0.00 \n", "Lazio 4.0 1.00 \n", "Lecce 2.0 1.00 \n", "Milan 2.0 2.00 \n", "Monza 3.0 1.00 \n", "Napoli 4.0 0.00 \n", "Roma 5.0 0.00 \n", "Salernitana 1.0 1.00 \n", "Sampdoria 0.0 0.00 \n", "Sassuolo 4.0 0.00 \n", "Spezia 2.0 2.00 \n", "Torino 1.0 0.00 \n", "Udinese 0.0 1.00 \n", "Avg 2.6 0.65 \n", "\n", " vs_team_ball_recoveries vs_team_aerials_won \\\n", "Atalanta 1165.00 239.00 \n", "Bologna 1081.00 224.00 \n", "Cremonese 1052.00 348.00 \n", "Empoli 999.00 217.00 \n", "Fiorentina 942.00 249.00 \n", "Verona 1038.00 345.00 \n", "Inter 869.00 198.00 \n", "Juventus 947.00 230.00 \n", "Lazio 1021.00 183.00 \n", "Lecce 1072.00 373.00 \n", "Milan 964.00 224.00 \n", "Monza 958.00 197.00 \n", "Napoli 933.00 201.00 \n", "Roma 981.00 184.00 \n", "Salernitana 1084.00 257.00 \n", "Sampdoria 1017.00 300.00 \n", "Sassuolo 986.00 216.00 \n", "Spezia 1182.00 322.00 \n", "Torino 998.00 323.00 \n", "Udinese 950.00 189.00 \n", "Avg 1011.95 250.95 \n", "\n", " vs_team_aerials_lost vs_team_aerials_won_pct \n", "Atalanta 279.00 46.100 \n", "Bologna 180.00 55.400 \n", "Cremonese 267.00 56.600 \n", "Empoli 189.00 53.400 \n", "Fiorentina 289.00 46.300 \n", "Verona 388.00 47.100 \n", "Inter 232.00 46.000 \n", "Juventus 230.00 50.000 \n", "Lazio 181.00 50.300 \n", "Lecce 294.00 55.900 \n", "Milan 275.00 44.900 \n", "Monza 215.00 47.800 \n", "Napoli 231.00 46.500 \n", "Roma 225.00 45.000 \n", "Salernitana 240.00 51.700 \n", "Sampdoria 318.00 48.500 \n", "Sassuolo 173.00 55.500 \n", "Spezia 281.00 53.400 \n", "Torino 295.00 52.300 \n", "Udinese 237.00 44.400 \n", "Avg 250.95 49.855 \n", "\n", "[21 rows x 313 columns]" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "team_data = pd.read_excel('mid_outputs/team_data.xlsx', index_col = 0)\n", "\n", "avg_row = pd.DataFrame(index = ['Avg'], data = [team_data.mean()], columns = team_data.columns)\n", "avg_row['team']['Avg'] = 'Avg'\n", "\n", "team_data = pd.concat([team_data, avg_row])\n", "\n", "team_data" ] }, { "cell_type": "markdown", "id": "cc1cd13d", "metadata": {}, "source": [ "Data processing functions copied from player_match_dataset_creation" ] }, { "cell_type": "code", "execution_count": 45, "id": "f4017b2f", "metadata": {}, "outputs": [], "source": [ "features_abs = ['r',\n", " 'games',\n", " 'games_starts', \n", " 'minutes',\n", " 'shots_on_target_pct',\n", " 'goals_per_shot',\n", " 'goals_per_shot_on_target',\n", " 'passes_pct',\n", " 'dribble_tackles_pct',\n", " 'dribbles_completed_pct',\n", " 'aerials_won_pct',\n", " 'team_possession',\n", " 'team_goals_assists_per90',\n", " 'team_goals_pens_per90',\n", " 'team_goals_assists_pens_per90',\n", " 'team_xg_per90',\n", " 'team_gk_goals_against_per90',\n", " 'team_gk_save_pct',\n", " 'team_gk_clean_sheets_pct',\n", " 'team_passes_pct',\n", " 'team_passes_pct_medium',\n", " 'team_passes_pct_long',\n", " 'team_sca_per90',\n", " 'team_gca_per90',\n", " 'team_dribble_tackles_pct',\n", " 'team_aerials_won_pct',\n", " 'vs_team_possession',\n", " 'vs_team_goals_per90',\n", " 'vs_team_assists_per90',\n", " 'vs_team_xg_per90',\n", " 'vs_team_gk_save_pct',\n", " 'vs_team_gk_clean_sheets_pct',\n", " 'vs_team_gk_pct_passes_launched',\n", " 'vs_team_gk_crosses_stopped_pct',\n", " 'vs_team_shots_on_target_per90',\n", " 'vs_team_passes_pct',\n", " 'vs_team_passes_pct_short',\n", " 'vs_team_passes_pct_medium',\n", " 'vs_team_passes_pct_long',\n", " 'vs_team_sca_per90',\n", " 'vs_team_gca_per90',\n", " 'vs_team_dribble_tackles_pct',\n", " 'vs_team_dribbles_completed_pct',\n", " 'vs_team_aerials_won_pct',\n", " 'opp_team_possession',\n", " 'opp_team_goals_assists_per90',\n", " 'opp_team_goals_pens_per90',\n", " 'opp_team_goals_assists_pens_per90',\n", " 'opp_team_xg_per90',\n", " 'opp_team_gk_goals_against_per90',\n", " 'opp_team_gk_save_pct',\n", " 'opp_team_gk_clean_sheets_pct',\n", " 'opp_team_passes_pct',\n", " 'opp_team_passes_pct_medium',\n", " 'opp_team_passes_pct_long',\n", " 'opp_team_sca_per90',\n", " 'opp_team_gca_per90',\n", " 'opp_team_dribble_tackles_pct',\n", " 'opp_team_aerials_won_pct',\n", " 'opp_vs_team_possession',\n", " 'opp_vs_team_goals_per90',\n", " 'opp_vs_team_assists_per90',\n", " 'opp_vs_team_xg_per90',\n", " 'opp_vs_team_gk_save_pct',\n", " 'opp_vs_team_gk_clean_sheets_pct',\n", " 'opp_vs_team_gk_pct_passes_launched',\n", " 'opp_vs_team_gk_crosses_stopped_pct',\n", " 'opp_vs_team_shots_on_target_per90',\n", " 'opp_vs_team_passes_pct',\n", " 'opp_vs_team_passes_pct_short',\n", " 'opp_vs_team_passes_pct_medium',\n", " 'opp_vs_team_passes_pct_long',\n", " 'opp_vs_team_sca_per90',\n", " 'opp_vs_team_gca_per90',\n", " 'opp_vs_team_dribble_tackles_pct',\n", " 'opp_vs_team_dribbles_completed_pct',\n", " 'opp_vs_team_aerials_won_pct',\n", " \n", " 'vote_avg',\n", " 'vote_std']\n", "\n", "features_rel = [\n", " 'goals',\n", " 'assists',\n", " 'cards_yellow',\n", " 'cards_red',\n", " 'xg',\n", " 'npxg',\n", " 'shots_on_target',\n", " 'passes_completed',\n", " 'passes_into_final_third',\n", " 'passes_into_penalty_area',\n", " 'progressive_passes',\n", " 'passes_live',\n", " 'passes_dead',\n", " 'through_balls',\n", " 'passes_switches',\n", " 'crosses',\n", " 'corner_kicks',\n", " 'dribble_tackles',\n", " 'dribbles_vs',\n", " 'dribbled_past',\n", " 'blocks',\n", " 'blocked_shots',\n", " 'blocked_passes',\n", " 'interceptions',\n", " 'clearances',\n", " 'errors',\n", " 'touches',\n", " 'touches_def_pen_area',\n", " 'touches_def_3rd',\n", " 'touches_mid_3rd',\n", " 'touches_att_3rd',\n", " 'touches_att_pen_area',\n", " 'touches_live_ball',\n", " 'dribbles_completed',\n", " 'dribbles',\n", " 'passes_received',\n", " 'miscontrols',\n", " 'dispossessed',\n", " 'fouls',\n", " 'fouled',\n", " 'aerials_won',\n", " 'aerials_lost']\n", "\n", "features_rel_gamecorr = [\n", " 'goals',\n", " 'xg',\n", " 'npxg',\n", " 'assists',\n", " 'cards_yellow',\n", " 'cards_red'\n", "]\n", "\n", "DEL_G = False\n", "\n", "features_to_del = [\n", " 'goals',\n", " 'assists',\n", " 'xg',\n", " 'npxg'\n", "]\n", "\n", "def player_match_data(player, pteam, oppteam, oldseason = False):\n", " if(not(player in players.index)):\n", " return None\n", " \n", " if(oldseason):\n", " pdata = players_old.loc[[player]]\n", " else:\n", " pdata = players.loc[[player]]\n", " \n", " pteam_stats = team_data.loc[[pteam]].rename(index = {pteam : player})\n", " \n", " oppteam_stats = team_data.loc[[oppteam]].rename(index = {oppteam : player})\n", " \n", " oppteam_stats = oppteam_stats.rename(lambda x: 'opp_' + x, axis='columns')\n", " \n", " out = pd.concat([pdata, pteam_stats, oppteam_stats], axis = 1)\n", " \n", " return(out)\n", "\n", "def player_match_data_ext(player, pteam, oppteam, oldseason = False):\n", " pdata = player_match_data(player, pteam, oppteam, oldseason = oldseason)\n", " \n", " if(not isinstance(pdata, pd.DataFrame)):\n", " return None\n", " \n", " assert pdata['games'][0] > 0\n", " \n", " out = pd.concat([pdata[features_abs], pdata[features_rel]], axis = 1)\n", " \n", " out[features_rel] = out[features_rel] / max(pdata['minutes'][0], 1)\n", " \n", " out[features_rel_gamecorr] = out[features_rel_gamecorr] * (pdata['minutes'][0] / max(pdata['games'][0], 1) / 90)\n", " \n", " if(DEL_G):\n", " out[features_to_del] = 0\n", " \n", " return out\n", "\n", "\n", "\n", "\n", "features_abs_gk = [\n", " 'gk_games',\n", " 'gk_games_starts',\n", " 'gk_minutes',\n", " 'gk_goals_against_per90', \n", " 'gk_save_pct',\n", " 'gk_clean_sheets_pct',\n", " 'gk_psxg_net_per90',\n", " 'gk_passes_pct_launched',\n", " 'gk_pct_passes_launched',\n", " 'gk_passes_length_avg',\n", " 'gk_pct_goal_kicks_launched',\n", " 'gk_goal_kick_length_avg',\n", " 'gk_crosses_stopped_pct',\n", " 'gk_def_actions_outside_pen_area_per90',\n", " 'gk_avg_distance_def_actions',\n", " \n", " 'team_possession',\n", " 'team_goals_assists_per90',\n", " 'team_goals_pens_per90',\n", " 'team_goals_assists_pens_per90',\n", " 'team_xg_per90',\n", " 'team_gk_goals_against_per90',\n", " 'team_gk_save_pct',\n", " 'team_gk_clean_sheets_pct',\n", " 'team_passes_pct',\n", " 'team_passes_pct_medium',\n", " 'team_passes_pct_long',\n", " 'team_sca_per90',\n", " 'team_gca_per90',\n", " 'team_dribble_tackles_pct',\n", " 'team_aerials_won_pct',\n", " 'vs_team_possession',\n", " 'vs_team_goals_per90',\n", " 'vs_team_assists_per90',\n", " 'vs_team_xg_per90',\n", " 'vs_team_gk_save_pct',\n", " 'vs_team_gk_clean_sheets_pct',\n", " 'vs_team_gk_pct_passes_launched',\n", " 'vs_team_gk_crosses_stopped_pct',\n", " 'vs_team_shots_on_target_per90',\n", " 'vs_team_passes_pct',\n", " 'vs_team_passes_pct_short',\n", " 'vs_team_passes_pct_medium',\n", " 'vs_team_passes_pct_long',\n", " 'vs_team_sca_per90',\n", " 'vs_team_gca_per90',\n", " 'vs_team_dribble_tackles_pct',\n", " 'vs_team_dribbles_completed_pct',\n", " 'vs_team_aerials_won_pct',\n", " 'opp_team_possession',\n", " 'opp_team_goals_assists_per90',\n", " 'opp_team_goals_pens_per90',\n", " 'opp_team_goals_assists_pens_per90',\n", " 'opp_team_xg_per90',\n", " 'opp_team_gk_goals_against_per90',\n", " 'opp_team_gk_save_pct',\n", " 'opp_team_gk_clean_sheets_pct',\n", " 'opp_team_passes_pct',\n", " 'opp_team_passes_pct_medium',\n", " 'opp_team_passes_pct_long',\n", " 'opp_team_sca_per90',\n", " 'opp_team_gca_per90',\n", " 'opp_team_dribble_tackles_pct',\n", " 'opp_team_aerials_won_pct',\n", " 'opp_vs_team_possession',\n", " 'opp_vs_team_goals_per90',\n", " 'opp_vs_team_assists_per90',\n", " 'opp_vs_team_xg_per90',\n", " 'opp_vs_team_gk_save_pct',\n", " 'opp_vs_team_gk_clean_sheets_pct',\n", " 'opp_vs_team_gk_pct_passes_launched',\n", " 'opp_vs_team_gk_crosses_stopped_pct',\n", " 'opp_vs_team_shots_on_target_per90',\n", " 'opp_vs_team_passes_pct',\n", " 'opp_vs_team_passes_pct_short',\n", " 'opp_vs_team_passes_pct_medium',\n", " 'opp_vs_team_passes_pct_long',\n", " 'opp_vs_team_sca_per90',\n", " 'opp_vs_team_gca_per90',\n", " 'opp_vs_team_dribble_tackles_pct',\n", " 'opp_vs_team_dribbles_completed_pct',\n", " 'opp_vs_team_aerials_won_pct',\n", " \n", " 'vote_avg',\n", " 'vote_std']\n", "\n", "features_rel_gk = [\n", " 'gk_shots_on_target_against',\n", " 'gk_saves',\n", " 'gk_free_kick_goals_against',\n", " 'gk_corner_kick_goals_against',\n", " 'gk_own_goals_against',\n", " 'gk_psxg',\n", " 'gk_psnpxg_per_shot_on_target_against',\n", " 'gk_psxg_net',\n", " 'gk_passes_completed_launched',\n", " 'gk_passes_launched',\n", " 'gk_passes',\n", " 'gk_passes_throws',\n", " 'gk_goal_kicks',\n", " 'gk_crosses',\n", " 'gk_crosses_stopped',\n", "]\n", "\n", "def player_match_data_ext_gk(player, pteam, oppteam, oldseason = False):\n", " pdata = player_match_data(player, pteam, oppteam, oldseason = oldseason)\n", " \n", " if(not isinstance(pdata, pd.DataFrame)):\n", " return None\n", " \n", " if(pdata['gk_games'][0] <= 0):\n", " return None\n", " \n", " out = pd.concat([pdata[features_abs_gk], pdata[features_rel_gk]], axis = 1)\n", " \n", " out[features_rel_gk] = out[features_rel_gk] / max(pdata['minutes'][0], 1)\n", "\n", " return out\n", " " ] }, { "cell_type": "markdown", "id": "21fef3ae", "metadata": {}, "source": [ "Players stats rework:\n", "the current season stats are averaged (according to a calculated weight) with the past season data.\n", "In case a player doesn't have past season data, a config file (affine_players) can be used to load the data from an affine player (past season), e.g. Doig affine to Lazovic.\n", "In case, after this process, the player doesn't result in having a minimum amount of games, its stats are averaged with the average Serie A (defensive) player stat, depending on the games remaining to reach the minimum amount. This allows to use players who still haven't played a single game.\n", "\n", "These modified stats are used only for prediction, not for model traning.\n", "\n", "WEIGHT_0 = weight given to the current season in respect to the previous; if the player has a low amount of games this season, the weight is lowered\n", "min_games = minimum games so that the players stats are not averaged with the avg Serie A player stats" ] }, { "cell_type": "code", "execution_count": 46, "id": "6f8707b8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " \n", "Averaging players stats with past seasons:\n", "Meret 1\n", "Provedel 1\n", "Vicario 1\n", "Szczesny 1\n", "Falcone 1\n", "Silvestri 1\n", "Rui Patricio 1\n", "Milinkovic-Savic V. 1\n", "Sepe 1\n", "Maignan 0.7353365384615383\n", "Audero 1\n", "Musso 1\n", "Montipo' 1\n", "Tatarusanu 1\n", "Consigli 1\n", "Dragowski 1\n", "Terracciano 1\n", "Sportiello 1\n", "Skorupski 1\n", "Perin 1\n", "Handanovic 0.7268191268191269\n", "Zoet 1\n", "Pegolo 1\n", "Mirante 0.7353365384615383\n", "Ujkani 1\n", "Berisha 1\n", "Marchetti 1\n", "Padelli 1\n", "Bardi 1\n", "Cordaz 0.9993762993762995\n", "Pinsoglio 1\n", "Fiorillo 1\n", "Cragno 1\n", "Sirigu 1\n", "Rossi F. 1\n", "Berardi A. 1\n", "Gemello 1\n", "Ravaglia 1\n", "Boer 1\n", "Adamonis 1\n", "Marfella 1\n", "Zovko 1\n", "Piana 1\n", "Dimarco 0.9979567307692307\n", "Smalling 1\n", "Doig affine to Lazovic\n", "Doig 0.6426470588235293\n", "Hernandez T. 0.8403846153846155\n", "Udogie 0.7203296703296703\n", "Parisi 1\n", "Romagnoli 1\n", "Di Lorenzo 0.9677156177156175\n", "Danilo 1\n", "Mazzocchi 1\n", "Mario Rui 0.7415158371040723\n", "Bastoni S. 0.7048387096774194\n", "Rodrigo Becao 0.6242857142857142\n", "Tomori 1\n", "Juan Jesus 0.5602564102564102\n", "Ibanez 0.8898190045248868\n", "Demiral 0.9604395604395606\n", "Scalvini 1\n", "Bijol affine to Rodrigo Becao\n", "Bijol 0.7203296703296703\n", "Toloi 1\n", "Depaoli 1\n", "Mancini 0.9677156177156175\n", "Bremer 0.8326340326340327\n", "Ebuehi 0.9038461538461539\n", "Dumfries 0.8658508158508158\n", "Darmian 0.941230769230769\n", "Kalulu 1\n", "Vojvoda 0.7534482758620689\n", "Maehle 1\n", "Bastoni 0.8132754342431762\n", "Gosens 1\n", "Milenkovic 0.6920814479638008\n", "Rodriguez R. 0.8403846153846154\n", "Reca 1\n", "Rrahmani 0.6111888111888112\n", "Kyriakopoulos 0.6375331564986738\n", "Martinez Quarta 1\n", "Perez N. 1\n", "Calabria 0.7110946745562131\n", "Skriniar 0.9124175824175823\n", "Marusic 0.9677156177156175\n", "Lazzari 0.8674937965260546\n", "Augello 0.8403846153846154\n", "Ampadu 0.888262599469496\n", "Ismajli 1\n", "Cambiaso 1\n", "Hysaj 0.8693633952254641\n", "Izzo 1\n", "Biraghi 0.8176715176715176\n", "Medel 0.8658508158508158\n", "Bonucci 0.6302884615384615\n", "Acerbi 0.6869230769230769\n", "Spinazzola 1\n", "Lykogiannis 0.9813186813186815\n", "Djidji 1\n", "Singo 0.6723076923076923\n", "Mari' 1\n", "Casale 0.5724358974358974\n", "De Vrij 0.7283333333333333\n", "Patric 0.7003205128205129\n", "Luperto 1\n", "Faraoni 0.42019230769230775\n", "Ceccherini 0.6426470588235293\n", "Aina 0.8003663003663003\n", "Soppy 0.6133241758241759\n", "Ferrari A. 0.2986622073578596\n", "Zappacosta 0.24717194570135745\n", "Ferrari G. 0.8403846153846154\n", "Fazio 1\n", "Hateboer 1\n", "Rogerio 1\n", "Buongiorno 1\n", "Gunter 0.7283333333333333\n", "Colley 0.787860576923077\n", "Terzic 1\n", "Toljan 1\n", "Zortea 0.5329575596816976\n", "Soumaoro 0.9004120879120879\n", "Amian 0.6828124999999999\n", "Gyomber 0.7590570719602977\n", "Alex Sandro 0.9604395604395606\n", "Pezzella Giu. 0.7359890109890109\n", "Bereszynski 0.0\n", "Venuti 0.6576923076923077\n", "Palomino 0.24717194570135745\n", "Nuytinck 0.25441595441595444\n", "Nikolaou 0.8403846153846154\n", "Igor 0.7843589743589743\n", "Dawidowicz 1\n", "Bellanova 0.5539702233250621\n", "Erlic 0.6869230769230769\n", "Ballo-Toure' affine to Calabria\n", "Ballo-Toure' 0.19393491124260354\n", "Stojanovic 0.763986013986014\n", "Zima 0.7563461538461539\n", "Ghiglione 0.7926035502958579\n", "Rugani 0.4201923076923077\n", "De Sciglio 0.6723076923076924\n", "Djimsiti 0.37952853598014885\n", "Caldara 0.7201612903225807\n", "Murru 0.5347902097902096\n", "Karsdorp 0.4201923076923077\n", "Bonifazi 0.5347902097902096\n", "Kjaer 1\n", "Magnani 1\n", "Walukiewicz 0.9813186813186815\n", "Walukiewicz 0.3666039729501268\n", "Ayhan 0.7307692307692307\n", "Ruggeri 0.9813186813186815\n", "De Winter 1\n", "Ostigard 1\n", "Radovanovic 1\n", "D'ambrosio 0.3361538461538462\n", "De Silvestri 0.48796526054590567\n", "Sala 0.5602564102564103\n", "Chiriches 0.35530503978779837\n", "Gabbia 1\n", "Kumbulla 0.395475113122172\n", "Lovato 0.6439903846153846\n", "Tuia 0.1908119658119658\n", "Ferrer 0.12450142450142451\n", "Antov 1\n", "Vasquez 0.49065934065934075\n", "Zanoli 0.42932692307692305\n", "Conti 0.24010989010989015\n", "Conti 0.8679180434949665\n", "Marrone 0.16355311355311355\n", "Tonelli 0.0\n", "Radu 0.0\n", "Florenzi 0.14006410256410257\n", "Fares 0.0\n", "Fares 0.0\n", "Marchizza 0.1807692307692308\n", "Romagna 0.0\n", "Romagna 0.0\n", "Ranieri L. 0.06360398860398861\n", "Muldur 0.054218362282878414\n", "Carboni 0.228974358974359\n", "Amey 0.0\n", "Vina 0.19393491124260354\n", "Ruan 1\n", "Coppola D. 1\n", "Cacace 0.5042307692307693\n", "Zaccagni 0.9852785145888594\n", "Milinkovic-Savic 0.8176715176715176\n", "Barella 0.8870726495726495\n", "Zielinski 0.9124175824175823\n", "Luis Alberto 0.790950226244344\n", "Felipe Anderson 0.8403846153846153\n", "Diaz B. 0.921712158808933\n", "Koopmeiners 1\n", "Calhanoglu 0.8898190045248868\n", "Frattesi 0.8870726495726495\n", "Zambo Anguissa 1\n", "Elmas 0.8176715176715176\n", "Pereyra 1\n", "Miranchuk 1\n", "Samardzic 1\n", "Politano 0.9167832167832167\n", "Rabiot 0.787860576923077\n", "Lobotka 1\n", "Tonali 0.7470085470085471\n", "Lazovic 0.7415158371040723\n", "Bonaventura 0.8674937965260546\n", "Pellegrini Lo. 0.9604395604395606\n", "Pessina 1\n", "Ferguson affine to Svanberg\n", "Ferguson 0.6536324786324785\n", "Ikone' 1\n", "Candreva 0.9063568376068376\n", "Bennacer 1\n", "El Shaarawy 0.8092592592592592\n", "Pasalic 0.7722453222453222\n", "Orsolini 0.9852785145888594\n", "Bandinelli 0.9124175824175823\n", "Mkhitaryan 0.8863523573200994\n", "Sensi 1\n", "Chiesa 0.7203296703296703\n", "Lukic 0.7203296703296703\n", "Fagioli affine to Henderson L.\n", "Fagioli 0.4423076923076923\n", "Messias 0.8403846153846153\n", "Arslan 1\n", "Brozovic 0.48021978021978023\n", "Verdi 1\n", "Barak 0.888262599469496\n", "Soriano 0.9124175824175823\n", "Dominguez 1\n", "Ranocchia F. affine to Henderson L.\n", "Ranocchia F. 0.4423076923076923\n", "Cristante 0.9392533936651583\n", "Bajrami 0.8643956043956044\n", "Ricci S. 1\n", "Saponara 0.8693633952254641\n", "Vecino 1\n", "Locatelli 0.8674937965260546\n", "Zaniolo 0.7803571428571429\n", "Traore' Hj. 0.5421836228287841\n", "Maldini 1\n", "Coulibaly L. 1\n", "De Roon 0.9524358974358974\n", "Mandragora 1\n", "Haas 1\n", "Bourabia 1\n", "Sottil 0.49022435897435895\n", "Agudelo 1\n", "Makengo 0.8149184149184149\n", "Zalewski 1\n", "Aebischer 1\n", "Ederson D.s. 1\n", "Miretti 1\n", "Cataldi 0.8929086538461539\n", "Djuricic 1\n", "Linetty 1\n", "Walace 0.8870726495726495\n", "Marin 0.8586538461538462\n", "Mckennie 1\n", "Pobega 0.5724358974358975\n", "Volpato 1\n", "Cuadrado 0.763986013986014\n", "Amrabat 1\n", "Tameze 0.7961538461538461\n", "Gyasi 0.8403846153846154\n", "Ilic 0.5777644230769232\n", "Harroui 0.9167832167832167\n", "Duncan 0.662121212121212\n", "Miguel Veloso 1\n", "Ekdal 0.9247041420118343\n", "Nicolussi Caviglia 1\n", "Schouten 1\n", "Rovella 0.8177655677655677\n", "Crnigoj 0.050509049773755664\n", "Romero L. 1\n", "Basic 0.8114058355437664\n", "Sabiri 1\n", "Grassi 0.6296794871794873\n", "Krunic 0.4802197802197803\n", "Rincon 1\n", "Vieira 1\n", "Henderson L. 0.6192307692307691\n", "Obiang 1\n", "Lopez M. 0.6723076923076923\n", "Saelemaekers 0.5135683760683761\n", "Maggiore 0.4906593406593407\n", "Akpa Akpro 0.0\n", "Akpa Akpro 0.0\n", "Kovalenko 0.6464497041420117\n", "Maleh 0.30666208791208793\n", "Matheus Henrique 0.7395384615384616\n", "Asllani 0.7466555183946488\n", "Ceide 1\n", "Gagliardini 0.7470085470085471\n", "Bove 1\n", "Bianco 1\n", "Benassi 0.14310897435897438\n", "Kastanos 0.6847578347578348\n", "Vignato 0.5602564102564103\n", "Zurkowski 0.049065934065934076\n", "Castrovilli 0.21923076923076923\n", "Bohinen 1\n", "Capezzi 0.0\n", "Molina S. 0.29608753315649866\n", "Bakayoko 0.0\n", "Demme 0.2653846153846154\n", "Askildsen 1\n", "Darboe 0.0\n", "Darboe 0.3361538461538462\n", "Urbanski 0.0\n", "Hongla 0.8403846153846154\n", "Yepes 1\n", "Osimhen 0.9337606837606838\n", "Dybala 0.7698275862068965\n", "Martinez L. 0.9124175824175823\n", "Rafael Leao 0.8898190045248868\n", "Immobile 0.7590570719602977\n", "Vlahovic 1\n", "Arnautovic 0.7130536130536129\n", "Dzeko 0.8870726495726495\n", "Nzola 1\n", "Beto 1\n", "Abraham 0.863097713097713\n", "Giroud 0.9852785145888594\n", "Deulofeu 0.790950226244344\n", "Correa 1\n", "Pedro 0.8929086538461539\n", "Lozano 1\n", "Simeone 0.4906593406593407\n", "Cabral 1\n", "Rebic 0.7703525641025643\n", "Bonazzoli 0.9454326923076923\n", "Berardi 0.5602564102564103\n", "Caprari 0.9322527472527472\n", "Di Maria affine to Chiesa\n", "Di Maria 1\n", "Piatek 1\n", "Sanabria 0.8114058355437664\n", "Zapata D. 0.8403846153846154\n", "Kean 0.8929086538461539\n", "Pinamonti 0.8109508547008547\n", "Gonzalez N. 0.45839160839160836\n", "Muriel 0.6847578347578348\n", "Okereke 1\n", "Alvarez A. affine to Raspadori\n", "Alvarez A. 0.6536324786324785\n", "Barrow 0.6920814479638008\n", "Caputo 0.19081196581196586\n", "Petagna 1\n", "Di Francesco F. 1\n", "Boga 1\n", "Djuric 1\n", "Henry 0.8326340326340327\n", "Success 1\n", "Gabbiadini 1\n", "Origi affine to Rebic\n", "Origi 0.8403846153846154\n", "Lammers 0.457948717948718\n", "Kallon 1\n", "Lasagna 0.9004120879120879\n", "Nestorovski 1\n", "Pellegri 1\n", "Belotti 1\n", "Raspadori 0.6201388888888889\n", "Verde 0.5093240093240092\n", "Destro 0.636039886039886\n", "Sansone 0.6225071225071225\n", "Pjaca 0.6439903846153846\n", "Strelec 1\n", "Seck 1\n", "Quagliarella 0.662121212121212\n", "Piccoli affine to Lasagna\n", "Piccoli 0.36016483516483516\n", "Shomurodov 0.36016483516483516\n", "Cancellieri 1\n", "Antiste 0.19081196581196586\n", "Afena-Gyan 1\n", "Defrel 0.35384615384615387\n", "Ibrahimovic 0.0\n", "Pussetto 0.30666208791208793\n", "Edera 0.0\n", "Oddei 0.0\n", "Oddei 0.6723076923076924\n", "Braaf 0.0\n", "Raimondo 0.0\n", "Kaio Jorge 0.0\n", "Lazetic 1\n", "Players with low quantity of games:\n", "Troost-Ekong 0.16666666666666663\n", "Masina 0.6666666666666667\n", "Aiwu 0.0\n", "Thiaw 0.6666666666666667\n", "Zeefuik 0.0\n", "Ostigard 0.6666666666666667\n", "Wisniewski 0.0\n", "Dermaku 0.16666666666666663\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Donati 0.6666666666666667\n", "Adopo 0.8333333333333334\n", "Antov 0.6666666666666667\n", "Gatti 0.8333333333333334\n", "Gila 0.6666666666666667\n", "Moutinho J. 0.6666666666666667\n", "Paletta 0.0\n", "Romagna 0.0\n", "Cassandro 0.0\n", "Amey 0.16666666666666663\n", "Ferrarini 0.0\n", "Zanotti 0.0\n", "Bayeye 0.0\n", "Ebosele 0.5\n", "Buta 0.0\n", "Abankwah 0.0\n", "Guessand A. 0.0\n", "Cabal 0.5\n", "Sosa 0.6666666666666667\n", "Guarino 0.0\n", "Carboni F. 0.6666666666666667\n", "Pogba 0.0\n", "Wijnaldum 0.16666666666666663\n", "Volpato 0.6666666666666667\n", "Nicolussi Caviglia 0.6666666666666667\n", "Romero L. 0.8333333333333334\n", "Machin 0.0\n", "Esposito Sa. 0.33333333333333337\n", "Akpa Akpro 0.0\n", "Bianco 0.5\n", "D'andrea 0.8333333333333334\n", "Tahirovic 0.6666666666666667\n", "Winks 0.33333333333333337\n", "Gaetano 0.5\n", "Iling-Junior 0.6666666666666667\n", "Capezzi 0.8333333333333334\n", "Scozzarella 0.0\n", "Darboe 0.6092307692307692\n", "Urbanski 0.16666666666666663\n", "Bertini 0.0\n", "Yepes 0.8333333333333334\n", "Trimboli 0.0\n", "Pafundi 0.0\n", "Milanese 0.33333333333333337\n", "Adli 0.6666666666666667\n", "Vignato S. 0.5\n", "Bondo 0.6666666666666667\n", "Samek 0.0\n", "Zerbin 0.6666666666666667\n", "Ilkhan 0.6666666666666667\n", "Degli Innocenti 0.16666666666666663\n", "Acella 0.0\n", "Garbett 0.0\n", "Carboni V. 0.33333333333333337\n", "Cipot 0.16666666666666663\n", "Solbakken 0.33333333333333337\n", "Ngonge 0.0\n", "Voelkerling Persson 0.33333333333333337\n", "Edera 0.0\n", "Oddei 0.4971794871794871\n", "Braaf 0.6666666666666667\n", "Raimondo 0.16666666666666663\n", "De Luca 0.16666666666666663\n", "Lazetic 0.16666666666666663\n", "Krollis 0.0\n" ] } ], "source": [ "#for i in range(players.columns.shape[0]):\n", "# print(str(i) + ' - ' + players.columns[i])\n", "\n", "cols_toadapt = players.columns[9:]\n", "\n", "players = players_orig.copy()\n", "\n", "min_games = 6\n", "\n", "current_season_games = max(players_orig['games'])\n", "\n", "# weight_0 as function of current_season_games --> 1 as match day reachs 30 ? \n", "WEIGHT_0_same_team = (1 - (1 - 0.7) * (30 - current_season_games) / (38 - 12)) # 0.7\n", "WEIGHT_0_different_team = (1 - (1 - 0.75) * (30 - current_season_games) / (38 - 12)) # 0.75\n", "WEIGHT_mul_gk = 2\n", "\n", "rcsv = pd.read_csv('config/affine_players.txt') \n", "affine_players = pd.DataFrame(rcsv)\n", "affine_players = affine_players.set_index('player')\n", "\n", "\n", "def calc_weight(games_curr, games_old, same_team = 1, maxgames = current_season_games):\n", " if(same_team):\n", " weight_0 = WEIGHT_0_same_team\n", " else:\n", " weight_0 = WEIGHT_0_different_team\n", "\n", " weight = weight_0 * (games_curr / maxgames) / (max(games_old, 1) / 38)\n", " weight = min(weight, 1)\n", "\n", " return abs(weight)\n", "\n", "print(' ')\n", "print('Averaging players stats with past seasons:')\n", "\n", "for i in range(players.shape[0]):\n", " p = players.index[i]\n", " \n", "\n", " if(p in players_old.index or p in affine_players.index):\n", " p_ = p\n", " affine = 0\n", " \n", " if(p in affine_players.index):\n", " affine = 1\n", " p_ = affine_players.loc[p]['alike']\n", " \n", " print(p + ' affine to ' + p_)\n", " \n", " if(players.loc[p]['r'] == 'P'):\n", " weight = calc_weight(players.loc[p]['gk_games'], players_old.loc[p_]['gk_games'], affine == 1 or players.loc[p]['team'] == players_old.loc[p]['team'])\n", " weight *= WEIGHT_mul_gk\n", " weight = min(weight, 1)\n", " else:\n", " weight = calc_weight(players.loc[p]['games'], players_old.loc[p_]['games'], affine == 1 or players.loc[p]['team'] == players_old.loc[p]['team'])\n", "\n", " players.at[p, cols_toadapt] = (players.loc[p][cols_toadapt] * weight + (1-weight) * players_old.loc[p_][cols_toadapt])\n", " \n", " print(p + ' ' + str(weight)) \n", " \n", " # to handle players like Lukaku, who only played 2 seasons ago; only outfield players\n", " if(players.loc[p]['r'] != 'P' and players.loc[p]['games'] < min_games and p in players_old_2.index): \n", " weight = calc_weight(players.loc[p]['games'], players_old_2.loc[p]['games'], players.loc[p]['team'] == players_old_2.loc[p]['team'])\n", " \n", " players.at[p, cols_toadapt] = (players.loc[p][cols_toadapt] * weight + (1-weight) * players_old_2.loc[p][cols_toadapt])\n", " \n", " print(p + ' ' + str(weight))\n", " \n", " \n", "# handle players with low quantitites of games\n", "\n", "print('Players with low quantity of games:')\n", "\n", "def calc_weight_low(current_games, min_games = min_games):\n", " weight = 1 - (min_games - current_games)/min_games\n", " \n", " weight = min(weight, 1)\n", "\n", " return abs(weight)\n", "\n", "#mean_players_stats = players_orig[players_orig['games'] >= min_games][cols_toadapt].mean()\n", "\n", "mean_players_stats = players_orig.loc[players_orig.index[0]][cols_toadapt] * 0\n", "count = 0\n", "\n", "for i in range(players_orig.shape[0]):\n", " if(players_orig['games'][i] >= min_games and (players_orig['r'][i] == 'D')): # counting only defenders, to add a penalty\n", " mean_players_stats += players_orig.loc[players_orig.index[i]][cols_toadapt]\n", " count = count + 1\n", " \n", "mean_players_stats /= count\n", "\n", "for i in range(players.shape[0]):\n", " p = players.index[i]\n", " \n", " if(players.loc[p]['games'] < min_games and players.loc[p]['r'] != 'P'):\n", " weight = calc_weight_low(players.loc[p]['games'])\n", " \n", " players.at[p, cols_toadapt] = players.loc[p][cols_toadapt] * weight + (1-weight) * mean_players_stats\n", " \n", " print(p + ' ' + str(weight))\n", " \n", " \n", "players_out = players.copy()\n", "players_out = players_out.set_index(players_out.columns[0])\n", "players_out.insert(2, 'name', players_out.index)\n", "players_out.to_excel('mid_outputs/players_stats_rwk.xlsx')\n" ] }, { "cell_type": "code", "execution_count": 47, "id": "49c28b07", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['games', 'games_starts', 'minutes', 'goals', 'assists', 'pens_made',\n", " 'pens_att', 'cards_yellow', 'cards_red', 'goals_per90',\n", " ...\n", " 'gk_pct_goal_kicks_launched', 'gk_goal_kick_length_avg', 'gk_crosses',\n", " 'gk_crosses_stopped', 'gk_crosses_stopped_pct',\n", " 'gk_def_actions_outside_pen_area',\n", " 'gk_def_actions_outside_pen_area_per90', 'gk_avg_distance_def_actions',\n", " 'vote_avg', 'vote_std'],\n", " dtype='object', length=156)" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "players.columns[9:]" ] }, { "cell_type": "code", "execution_count": 48, "id": "d29102e5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 - matchday\n", "1 - player\n", "2 - team\n", "3 - oppteam\n", "4 - home\n", "5 - vote\n", "6 - goals\n", "7 - assists\n", "8 - cards_malus\n", "9 - fantavote\n", "10 - r\n", "11 - games\n", "12 - games_starts\n", "13 - minutes\n", "14 - shots_on_target_pct\n", "15 - goals_per_shot\n", "16 - goals_per_shot_on_target\n", "17 - passes_pct\n", "18 - dribble_tackles_pct\n", "19 - dribbles_completed_pct\n", "20 - aerials_won_pct\n", "21 - team_possession\n", "22 - team_goals_assists_per90\n", "23 - team_goals_pens_per90\n", "24 - team_goals_assists_pens_per90\n", "25 - team_xg_per90\n", "26 - team_gk_goals_against_per90\n", "27 - team_gk_save_pct\n", "28 - team_gk_clean_sheets_pct\n", "29 - team_passes_pct\n", "30 - team_passes_pct_medium\n", "31 - team_passes_pct_long\n", "32 - team_sca_per90\n", "33 - team_gca_per90\n", "34 - team_dribble_tackles_pct\n", "35 - team_aerials_won_pct\n", "36 - vs_team_possession\n", "37 - vs_team_goals_per90\n", "38 - vs_team_assists_per90\n", "39 - vs_team_xg_per90\n", "40 - vs_team_gk_save_pct\n", "41 - vs_team_gk_clean_sheets_pct\n", "42 - vs_team_gk_pct_passes_launched\n", "43 - vs_team_gk_crosses_stopped_pct\n", "44 - vs_team_shots_on_target_per90\n", "45 - vs_team_passes_pct\n", "46 - vs_team_passes_pct_short\n", "47 - vs_team_passes_pct_medium\n", "48 - vs_team_passes_pct_long\n", "49 - vs_team_sca_per90\n", "50 - vs_team_gca_per90\n", "51 - vs_team_dribble_tackles_pct\n", "52 - vs_team_dribbles_completed_pct\n", "53 - vs_team_aerials_won_pct\n", "54 - opp_team_possession\n", "55 - opp_team_goals_assists_per90\n", "56 - opp_team_goals_pens_per90\n", "57 - opp_team_goals_assists_pens_per90\n", "58 - opp_team_xg_per90\n", "59 - opp_team_gk_goals_against_per90\n", "60 - opp_team_gk_save_pct\n", "61 - opp_team_gk_clean_sheets_pct\n", "62 - opp_team_passes_pct\n", "63 - opp_team_passes_pct_medium\n", "64 - opp_team_passes_pct_long\n", "65 - opp_team_sca_per90\n", "66 - opp_team_gca_per90\n", "67 - opp_team_dribble_tackles_pct\n", "68 - opp_team_aerials_won_pct\n", "69 - opp_vs_team_possession\n", "70 - opp_vs_team_goals_per90\n", "71 - opp_vs_team_assists_per90\n", "72 - opp_vs_team_xg_per90\n", "73 - opp_vs_team_gk_save_pct\n", "74 - opp_vs_team_gk_clean_sheets_pct\n", "75 - opp_vs_team_gk_pct_passes_launched\n", "76 - opp_vs_team_gk_crosses_stopped_pct\n", "77 - opp_vs_team_shots_on_target_per90\n", "78 - opp_vs_team_passes_pct\n", "79 - opp_vs_team_passes_pct_short\n", "80 - opp_vs_team_passes_pct_medium\n", "81 - opp_vs_team_passes_pct_long\n", "82 - opp_vs_team_sca_per90\n", "83 - opp_vs_team_gca_per90\n", "84 - opp_vs_team_dribble_tackles_pct\n", "85 - opp_vs_team_dribbles_completed_pct\n", "86 - opp_vs_team_aerials_won_pct\n", "87 - vote_avg\n", "88 - vote_std\n", "89 - goals.1\n", "90 - assists.1\n", "91 - cards_yellow\n", "92 - cards_red\n", "93 - xg\n", "94 - npxg\n", "95 - shots_on_target\n", "96 - passes_completed\n", "97 - passes_into_final_third\n", "98 - passes_into_penalty_area\n", "99 - progressive_passes\n", "100 - passes_live\n", "101 - passes_dead\n", "102 - through_balls\n", "103 - passes_switches\n", "104 - crosses\n", "105 - corner_kicks\n", "106 - dribble_tackles\n", "107 - dribbles_vs\n", "108 - dribbled_past\n", "109 - blocks\n", "110 - blocked_shots\n", "111 - blocked_passes\n", "112 - interceptions\n", "113 - clearances\n", "114 - errors\n", "115 - touches\n", "116 - touches_def_pen_area\n", "117 - touches_def_3rd\n", "118 - touches_mid_3rd\n", "119 - touches_att_3rd\n", "120 - touches_att_pen_area\n", "121 - touches_live_ball\n", "122 - dribbles_completed\n", "123 - dribbles\n", "124 - passes_received\n", "125 - miscontrols\n", "126 - dispossessed\n", "127 - fouls\n", "128 - fouled\n", "129 - aerials_won\n", "130 - aerials_lost\n" ] } ], "source": [ "for i in range(db.columns.shape[0]):\n", " print(str(i) + \" - \" + str(db.columns[i]))" ] }, { "cell_type": "markdown", "id": "089690d6", "metadata": {}, "source": [ "Elaborate databases data to have X and y for training, and split into a train test and a validation test.\n", "\n", "For outfield players: X -> y = [vote, fantavote]\n", "\n", "For goalkeepers: X -> y = [vote, fantavote, clean sheet probability]" ] }, { "cell_type": "code", "execution_count": 49, "id": "f19304f6", "metadata": {}, "outputs": [], "source": [ "npdb = np.array(db)\n", "\n", "y = npdb[:, [5,9]] # vote, fantavote\n", "\n", "#y[:, 1] = y[:, 1] - y[:, 0] # target = difference between fantavote and vote\n", "\n", "f_start = 14\n", "\n", "X = npdb[:, f_start:]\n", "\n", "if(DEL_G): \n", " del_g_idx = [\n", " list(db.columns).index('goals.1') - f_start,\n", " list(db.columns).index('assists.1') - f_start,\n", " list(db.columns).index('xg') - f_start,\n", " list(db.columns).index('npxg') - f_start,\n", " list(db.columns).index('shots_on_target') - f_start]\n", " \n", " X[:, del_g_idx] = 0\n", "\n", "\n", "# add role and home factor\n", "toadd = np.zeros((X.shape[0], 4))\n", "toadd[:, 0] = npdb[:, 4] # home\n", "\n", "toadd[:, 1] = npdb[:, 10] == 'D'\n", "toadd[:, 2] = npdb[:, 10] == 'C'\n", "toadd[:, 3] = npdb[:, 10] == 'A'\n", "\n", "X = np.concatenate((X, toadd), axis = 1)\n", "\n" ] }, { "cell_type": "code", "execution_count": 50, "id": "370d41d2", "metadata": {}, "outputs": [], "source": [ "scaler = StandardScaler()\n", "scaler.fit(X)\n", "\n", "X_train_, X_test_, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 12)\n", "\n", "X_train = scaler.transform(X_train_)\n", "X_test = scaler.transform(X_test_)" ] }, { "cell_type": "code", "execution_count": 51, "id": "a7b1fb52", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 - matchday\n", "1 - player\n", "2 - team\n", "3 - oppteam\n", "4 - home\n", "5 - vote\n", "6 - goals\n", "7 - assists\n", "8 - cards_malus\n", "9 - fantavote\n", "10 - gk_games\n", "11 - gk_games_starts\n", "12 - gk_minutes\n", "13 - gk_goals_against_per90\n", "14 - gk_save_pct\n", "15 - gk_clean_sheets_pct\n", "16 - gk_psxg_net_per90\n", "17 - gk_passes_pct_launched\n", "18 - gk_pct_passes_launched\n", "19 - gk_passes_length_avg\n", "20 - gk_pct_goal_kicks_launched\n", "21 - gk_goal_kick_length_avg\n", "22 - gk_crosses_stopped_pct\n", "23 - gk_def_actions_outside_pen_area_per90\n", "24 - gk_avg_distance_def_actions\n", "25 - team_possession\n", "26 - team_goals_assists_per90\n", "27 - team_goals_pens_per90\n", "28 - team_goals_assists_pens_per90\n", "29 - team_xg_per90\n", "30 - team_gk_goals_against_per90\n", "31 - team_gk_save_pct\n", "32 - team_gk_clean_sheets_pct\n", "33 - team_passes_pct\n", "34 - team_passes_pct_medium\n", "35 - team_passes_pct_long\n", "36 - team_sca_per90\n", "37 - team_gca_per90\n", "38 - team_dribble_tackles_pct\n", "39 - team_aerials_won_pct\n", "40 - vs_team_possession\n", "41 - vs_team_goals_per90\n", "42 - vs_team_assists_per90\n", "43 - vs_team_xg_per90\n", "44 - vs_team_gk_save_pct\n", "45 - vs_team_gk_clean_sheets_pct\n", "46 - vs_team_gk_pct_passes_launched\n", "47 - vs_team_gk_crosses_stopped_pct\n", "48 - vs_team_shots_on_target_per90\n", "49 - vs_team_passes_pct\n", "50 - vs_team_passes_pct_short\n", "51 - vs_team_passes_pct_medium\n", "52 - vs_team_passes_pct_long\n", "53 - vs_team_sca_per90\n", "54 - vs_team_gca_per90\n", "55 - vs_team_dribble_tackles_pct\n", "56 - vs_team_dribbles_completed_pct\n", "57 - vs_team_aerials_won_pct\n", "58 - opp_team_possession\n", "59 - opp_team_goals_assists_per90\n", "60 - opp_team_goals_pens_per90\n", "61 - opp_team_goals_assists_pens_per90\n", "62 - opp_team_xg_per90\n", "63 - opp_team_gk_goals_against_per90\n", "64 - opp_team_gk_save_pct\n", "65 - opp_team_gk_clean_sheets_pct\n", "66 - opp_team_passes_pct\n", "67 - opp_team_passes_pct_medium\n", "68 - opp_team_passes_pct_long\n", "69 - opp_team_sca_per90\n", "70 - opp_team_gca_per90\n", "71 - opp_team_dribble_tackles_pct\n", "72 - opp_team_aerials_won_pct\n", "73 - opp_vs_team_possession\n", "74 - opp_vs_team_goals_per90\n", "75 - opp_vs_team_assists_per90\n", "76 - opp_vs_team_xg_per90\n", "77 - opp_vs_team_gk_save_pct\n", "78 - opp_vs_team_gk_clean_sheets_pct\n", "79 - opp_vs_team_gk_pct_passes_launched\n", "80 - opp_vs_team_gk_crosses_stopped_pct\n", "81 - opp_vs_team_shots_on_target_per90\n", "82 - opp_vs_team_passes_pct\n", "83 - opp_vs_team_passes_pct_short\n", "84 - opp_vs_team_passes_pct_medium\n", "85 - opp_vs_team_passes_pct_long\n", "86 - opp_vs_team_sca_per90\n", "87 - opp_vs_team_gca_per90\n", "88 - opp_vs_team_dribble_tackles_pct\n", "89 - opp_vs_team_dribbles_completed_pct\n", "90 - opp_vs_team_aerials_won_pct\n", "91 - vote_avg\n", "92 - vote_std\n", "93 - gk_shots_on_target_against\n", "94 - gk_saves\n", "95 - gk_free_kick_goals_against\n", "96 - gk_corner_kick_goals_against\n", "97 - gk_own_goals_against\n", "98 - gk_psxg\n", "99 - gk_psnpxg_per_shot_on_target_against\n", "100 - gk_psxg_net\n", "101 - gk_passes_completed_launched\n", "102 - gk_passes_launched\n", "103 - gk_passes\n", "104 - gk_passes_throws\n", "105 - gk_goal_kicks\n", "106 - gk_crosses\n", "107 - gk_crosses_stopped\n" ] } ], "source": [ "for i in range(db_gk.columns.shape[0]):\n", " print(str(i) + \" - \" + str(db_gk.columns[i]))" ] }, { "cell_type": "code", "execution_count": 52, "id": "5a7cf079", "metadata": {}, "outputs": [], "source": [ "npdb_gk= np.array(db_gk)\n", "\n", "y_gk = npdb_gk[:, [5,9,6]] # vote, fantavote, goals == 0 (clean sheet)\n", "y_gk[:, 2] = (y_gk[:, 2] == 0) * 1\n", "\n", "f_start_gk = 13\n", "\n", "X_gk = npdb_gk[:, f_start_gk:]\n", "\n", "# add home factor\n", "toadd_gk = np.zeros((X_gk.shape[0], 1))\n", "toadd_gk[:, 0] = npdb_gk[:, 4] # home\n", "\n", "X_gk = np.concatenate((X_gk, toadd_gk), axis = 1)\n", "\n" ] }, { "cell_type": "code", "execution_count": 53, "id": "0bc0568b", "metadata": {}, "outputs": [], "source": [ "scaler_gk = StandardScaler()\n", "scaler_gk.fit(X_gk)\n", "\n", "X_gk_train_, X_gk_test_, y_gk_train, y_gk_test = train_test_split(X_gk, y_gk, test_size = 0.2, random_state = 18)\n", "\n", "X_gk_train = scaler_gk.transform(X_gk_train_)\n", "X_gk_test = scaler_gk.transform(X_gk_test_)" ] }, { "cell_type": "markdown", "id": "ebd27493", "metadata": {}, "source": [ "MLP Regressor , to see performance of a simple neural network" ] }, { "cell_type": "code", "execution_count": 17, "id": "04564bee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.1569906306642661\n", "0.19152381866355805\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.1532751047011487\n", "0.17630547391900842\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "regr = MLPRegressor(max_iter = 400000, solver = 'lbfgs', hidden_layer_sizes = (8, 8), alpha = 500, verbose = True)\n", "\n", "regr.fit(X_train, y_train)\n", "\n", "\n", "y_train_predict = regr.predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "\n", "plt.show()\n", "\n", "y_test_predict = regr.predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "f9513b25", "metadata": {}, "source": [ "Train neural network for outfield players.\n", "\n", "The outputs of the NN are probability distribution of SinhArcsinh type (a skewed distribution, which is a generalization of Gaussian)" ] }, { "cell_type": "code", "execution_count": 54, "id": "8aad9652", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/1000\n", "76/76 [==============================] - 4s 10ms/step - loss: 12.8341 - distribution_lambda_12_loss: 8.9192 - distribution_lambda_13_loss: 3.9149 - val_loss: 8.0652 - val_distribution_lambda_12_loss: 4.9531 - val_distribution_lambda_13_loss: 3.1121\n", "Epoch 2/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 7.1683 - distribution_lambda_12_loss: 4.2146 - distribution_lambda_13_loss: 2.9537 - val_loss: 6.4110 - val_distribution_lambda_12_loss: 3.6377 - val_distribution_lambda_13_loss: 2.7734\n", "Epoch 3/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 6.0331 - distribution_lambda_12_loss: 3.4393 - distribution_lambda_13_loss: 2.5938 - val_loss: 5.5737 - val_distribution_lambda_12_loss: 3.1841 - val_distribution_lambda_13_loss: 2.3896\n", "Epoch 4/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 5.3082 - distribution_lambda_12_loss: 3.0704 - distribution_lambda_13_loss: 2.2379 - val_loss: 4.9987 - val_distribution_lambda_12_loss: 2.9208 - val_distribution_lambda_13_loss: 2.0779\n", "Epoch 5/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.8167 - distribution_lambda_12_loss: 2.8554 - distribution_lambda_13_loss: 1.9613 - val_loss: 4.6358 - val_distribution_lambda_12_loss: 2.7649 - val_distribution_lambda_13_loss: 1.8709\n", "Epoch 6/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.5134 - distribution_lambda_12_loss: 2.7167 - distribution_lambda_13_loss: 1.7967 - val_loss: 4.4295 - val_distribution_lambda_12_loss: 2.6518 - val_distribution_lambda_13_loss: 1.7776\n", "Epoch 7/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.3409 - distribution_lambda_12_loss: 2.6134 - distribution_lambda_13_loss: 1.7276 - val_loss: 4.3182 - val_distribution_lambda_12_loss: 2.5636 - val_distribution_lambda_13_loss: 1.7545\n", "Epoch 8/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.2465 - distribution_lambda_12_loss: 2.5330 - distribution_lambda_13_loss: 1.7135 - val_loss: 4.2311 - val_distribution_lambda_12_loss: 2.4926 - val_distribution_lambda_13_loss: 1.7386\n", "Epoch 9/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.1537 - distribution_lambda_12_loss: 2.4667 - distribution_lambda_13_loss: 1.6871 - val_loss: 4.1427 - val_distribution_lambda_12_loss: 2.4336 - val_distribution_lambda_13_loss: 1.7091\n", "Epoch 10/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 4.0734 - distribution_lambda_12_loss: 2.4106 - distribution_lambda_13_loss: 1.6628 - val_loss: 4.0660 - val_distribution_lambda_12_loss: 2.3824 - val_distribution_lambda_13_loss: 1.6835\n", "Epoch 11/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.9964 - distribution_lambda_12_loss: 2.3612 - distribution_lambda_13_loss: 1.6353 - val_loss: 3.9936 - val_distribution_lambda_12_loss: 2.3362 - val_distribution_lambda_13_loss: 1.6574\n", "Epoch 12/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.9316 - distribution_lambda_12_loss: 2.3158 - distribution_lambda_13_loss: 1.6157 - val_loss: 3.9286 - val_distribution_lambda_12_loss: 2.2923 - val_distribution_lambda_13_loss: 1.6363\n", "Epoch 13/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.8708 - distribution_lambda_12_loss: 2.2727 - distribution_lambda_13_loss: 1.5982 - val_loss: 3.8628 - val_distribution_lambda_12_loss: 2.2490 - val_distribution_lambda_13_loss: 1.6139\n", "Epoch 14/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.7999 - distribution_lambda_12_loss: 2.2287 - distribution_lambda_13_loss: 1.5712 - val_loss: 3.7954 - val_distribution_lambda_12_loss: 2.2048 - val_distribution_lambda_13_loss: 1.5906\n", "Epoch 15/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.7305 - distribution_lambda_12_loss: 2.1833 - distribution_lambda_13_loss: 1.5471 - val_loss: 3.7208 - val_distribution_lambda_12_loss: 2.1584 - val_distribution_lambda_13_loss: 1.5624\n", "Epoch 16/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.6551 - distribution_lambda_12_loss: 2.1352 - distribution_lambda_13_loss: 1.5199 - val_loss: 3.6394 - val_distribution_lambda_12_loss: 2.1088 - val_distribution_lambda_13_loss: 1.5307\n", "Epoch 17/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.5726 - distribution_lambda_12_loss: 2.0833 - distribution_lambda_13_loss: 1.4893 - val_loss: 3.5597 - val_distribution_lambda_12_loss: 2.0548 - val_distribution_lambda_13_loss: 1.5049\n", "Epoch 18/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.4921 - distribution_lambda_12_loss: 2.0266 - distribution_lambda_13_loss: 1.4655 - val_loss: 3.4779 - val_distribution_lambda_12_loss: 1.9953 - val_distribution_lambda_13_loss: 1.4826\n", "Epoch 19/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.4119 - distribution_lambda_12_loss: 1.9637 - distribution_lambda_13_loss: 1.4482 - val_loss: 3.3954 - val_distribution_lambda_12_loss: 1.9291 - val_distribution_lambda_13_loss: 1.4663\n", "Epoch 20/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.3297 - distribution_lambda_12_loss: 1.8935 - distribution_lambda_13_loss: 1.4361 - val_loss: 3.3096 - val_distribution_lambda_12_loss: 1.8544 - val_distribution_lambda_13_loss: 1.4552\n", "Epoch 21/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.2391 - distribution_lambda_12_loss: 1.8133 - distribution_lambda_13_loss: 1.4258 - val_loss: 3.2163 - val_distribution_lambda_12_loss: 1.7693 - val_distribution_lambda_13_loss: 1.4470\n", "Epoch 22/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.1395 - distribution_lambda_12_loss: 1.7220 - distribution_lambda_13_loss: 1.4175 - val_loss: 3.1121 - val_distribution_lambda_12_loss: 1.6714 - val_distribution_lambda_13_loss: 1.4407\n", "Epoch 23/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 3.0265 - distribution_lambda_12_loss: 1.6156 - distribution_lambda_13_loss: 1.4109 - val_loss: 2.9937 - val_distribution_lambda_12_loss: 1.5578 - val_distribution_lambda_13_loss: 1.4359\n", "Epoch 24/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.9002 - distribution_lambda_12_loss: 1.4926 - distribution_lambda_13_loss: 1.4076 - val_loss: 2.8601 - val_distribution_lambda_12_loss: 1.4280 - val_distribution_lambda_13_loss: 1.4321\n", "Epoch 25/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.7594 - distribution_lambda_12_loss: 1.3533 - distribution_lambda_13_loss: 1.4060 - val_loss: 2.7183 - val_distribution_lambda_12_loss: 1.2900 - val_distribution_lambda_13_loss: 1.4283\n", "Epoch 26/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.6168 - distribution_lambda_12_loss: 1.2157 - distribution_lambda_13_loss: 1.4010 - val_loss: 2.6055 - val_distribution_lambda_12_loss: 1.1803 - val_distribution_lambda_13_loss: 1.4252\n", "Epoch 27/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.5196 - distribution_lambda_12_loss: 1.1218 - distribution_lambda_13_loss: 1.3979 - val_loss: 2.5622 - val_distribution_lambda_12_loss: 1.1391 - val_distribution_lambda_13_loss: 1.4231\n", "Epoch 28/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4808 - distribution_lambda_12_loss: 1.0858 - distribution_lambda_13_loss: 1.3950 - val_loss: 2.5577 - val_distribution_lambda_12_loss: 1.1358 - val_distribution_lambda_13_loss: 1.4219\n", "Epoch 29/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4699 - distribution_lambda_12_loss: 1.0764 - distribution_lambda_13_loss: 1.3935 - val_loss: 2.5489 - val_distribution_lambda_12_loss: 1.1296 - val_distribution_lambda_13_loss: 1.4193\n", "Epoch 30/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4645 - distribution_lambda_12_loss: 1.0722 - distribution_lambda_13_loss: 1.3923 - val_loss: 2.5412 - val_distribution_lambda_12_loss: 1.1224 - val_distribution_lambda_13_loss: 1.4188\n", "Epoch 31/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4567 - distribution_lambda_12_loss: 1.0674 - distribution_lambda_13_loss: 1.3893 - val_loss: 2.5333 - val_distribution_lambda_12_loss: 1.1171 - val_distribution_lambda_13_loss: 1.4162\n", "Epoch 32/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 3ms/step - loss: 2.4466 - distribution_lambda_12_loss: 1.0616 - distribution_lambda_13_loss: 1.3850 - val_loss: 2.5225 - val_distribution_lambda_12_loss: 1.1082 - val_distribution_lambda_13_loss: 1.4143\n", "Epoch 33/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4434 - distribution_lambda_12_loss: 1.0580 - distribution_lambda_13_loss: 1.3854 - val_loss: 2.5097 - val_distribution_lambda_12_loss: 1.0974 - val_distribution_lambda_13_loss: 1.4123\n", "Epoch 34/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4377 - distribution_lambda_12_loss: 1.0533 - distribution_lambda_13_loss: 1.3844 - val_loss: 2.4975 - val_distribution_lambda_12_loss: 1.0863 - val_distribution_lambda_13_loss: 1.4111\n", "Epoch 35/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4332 - distribution_lambda_12_loss: 1.0496 - distribution_lambda_13_loss: 1.3835 - val_loss: 2.4882 - val_distribution_lambda_12_loss: 1.0795 - val_distribution_lambda_13_loss: 1.4087\n", "Epoch 36/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.4238 - distribution_lambda_12_loss: 1.0413 - distribution_lambda_13_loss: 1.3824 - val_loss: 2.4680 - val_distribution_lambda_12_loss: 1.0602 - val_distribution_lambda_13_loss: 1.4077\n", "Epoch 37/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.4105 - distribution_lambda_12_loss: 1.0282 - distribution_lambda_13_loss: 1.3823 - val_loss: 2.4538 - val_distribution_lambda_12_loss: 1.0478 - val_distribution_lambda_13_loss: 1.4060\n", "Epoch 38/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3869 - distribution_lambda_12_loss: 1.0109 - distribution_lambda_13_loss: 1.3760 - val_loss: 2.4418 - val_distribution_lambda_12_loss: 1.0376 - val_distribution_lambda_13_loss: 1.4042\n", "Epoch 39/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.3665 - distribution_lambda_12_loss: 0.9920 - distribution_lambda_13_loss: 1.3745 - val_loss: 2.4332 - val_distribution_lambda_12_loss: 1.0307 - val_distribution_lambda_13_loss: 1.4025\n", "Epoch 40/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3638 - distribution_lambda_12_loss: 0.9897 - distribution_lambda_13_loss: 1.3741 - val_loss: 2.4290 - val_distribution_lambda_12_loss: 1.0260 - val_distribution_lambda_13_loss: 1.4030\n", "Epoch 41/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.3505 - distribution_lambda_12_loss: 0.9806 - distribution_lambda_13_loss: 1.3699 - val_loss: 2.4175 - val_distribution_lambda_12_loss: 1.0162 - val_distribution_lambda_13_loss: 1.4013\n", "Epoch 42/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3415 - distribution_lambda_12_loss: 0.9726 - distribution_lambda_13_loss: 1.3689 - val_loss: 2.4015 - val_distribution_lambda_12_loss: 1.0032 - val_distribution_lambda_13_loss: 1.3983\n", "Epoch 43/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3361 - distribution_lambda_12_loss: 0.9658 - distribution_lambda_13_loss: 1.3703 - val_loss: 2.3865 - val_distribution_lambda_12_loss: 0.9906 - val_distribution_lambda_13_loss: 1.3959\n", "Epoch 44/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3253 - distribution_lambda_12_loss: 0.9585 - distribution_lambda_13_loss: 1.3668 - val_loss: 2.3791 - val_distribution_lambda_12_loss: 0.9836 - val_distribution_lambda_13_loss: 1.3955\n", "Epoch 45/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3204 - distribution_lambda_12_loss: 0.9539 - distribution_lambda_13_loss: 1.3665 - val_loss: 2.3708 - val_distribution_lambda_12_loss: 0.9769 - val_distribution_lambda_13_loss: 1.3939\n", "Epoch 46/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3146 - distribution_lambda_12_loss: 0.9509 - distribution_lambda_13_loss: 1.3637 - val_loss: 2.3686 - val_distribution_lambda_12_loss: 0.9753 - val_distribution_lambda_13_loss: 1.3933\n", "Epoch 47/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3065 - distribution_lambda_12_loss: 0.9441 - distribution_lambda_13_loss: 1.3625 - val_loss: 2.3636 - val_distribution_lambda_12_loss: 0.9724 - val_distribution_lambda_13_loss: 1.3912\n", "Epoch 48/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3039 - distribution_lambda_12_loss: 0.9424 - distribution_lambda_13_loss: 1.3615 - val_loss: 2.3613 - val_distribution_lambda_12_loss: 0.9699 - val_distribution_lambda_13_loss: 1.3915\n", "Epoch 49/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3028 - distribution_lambda_12_loss: 0.9410 - distribution_lambda_13_loss: 1.3618 - val_loss: 2.3564 - val_distribution_lambda_12_loss: 0.9670 - val_distribution_lambda_13_loss: 1.3894\n", "Epoch 50/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.3005 - distribution_lambda_12_loss: 0.9393 - distribution_lambda_13_loss: 1.3612 - val_loss: 2.3538 - val_distribution_lambda_12_loss: 0.9658 - val_distribution_lambda_13_loss: 1.3881\n", "Epoch 51/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2954 - distribution_lambda_12_loss: 0.9373 - distribution_lambda_13_loss: 1.3581 - val_loss: 2.3502 - val_distribution_lambda_12_loss: 0.9625 - val_distribution_lambda_13_loss: 1.3876\n", "Epoch 52/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2902 - distribution_lambda_12_loss: 0.9327 - distribution_lambda_13_loss: 1.3576 - val_loss: 2.3479 - val_distribution_lambda_12_loss: 0.9624 - val_distribution_lambda_13_loss: 1.3855\n", "Epoch 53/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2880 - distribution_lambda_12_loss: 0.9316 - distribution_lambda_13_loss: 1.3565 - val_loss: 2.3454 - val_distribution_lambda_12_loss: 0.9599 - val_distribution_lambda_13_loss: 1.3855\n", "Epoch 54/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2850 - distribution_lambda_12_loss: 0.9296 - distribution_lambda_13_loss: 1.3554 - val_loss: 2.3373 - val_distribution_lambda_12_loss: 0.9558 - val_distribution_lambda_13_loss: 1.3816\n", "Epoch 55/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2802 - distribution_lambda_12_loss: 0.9281 - distribution_lambda_13_loss: 1.3521 - val_loss: 2.3330 - val_distribution_lambda_12_loss: 0.9538 - val_distribution_lambda_13_loss: 1.3792\n", "Epoch 56/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2766 - distribution_lambda_12_loss: 0.9257 - distribution_lambda_13_loss: 1.3509 - val_loss: 2.3297 - val_distribution_lambda_12_loss: 0.9513 - val_distribution_lambda_13_loss: 1.3784\n", "Epoch 57/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2735 - distribution_lambda_12_loss: 0.9243 - distribution_lambda_13_loss: 1.3492 - val_loss: 2.3232 - val_distribution_lambda_12_loss: 0.9486 - val_distribution_lambda_13_loss: 1.3746\n", "Epoch 58/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2655 - distribution_lambda_12_loss: 0.9203 - distribution_lambda_13_loss: 1.3452 - val_loss: 2.3195 - val_distribution_lambda_12_loss: 0.9467 - val_distribution_lambda_13_loss: 1.3728\n", "Epoch 59/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2607 - distribution_lambda_12_loss: 0.9164 - distribution_lambda_13_loss: 1.3443 - val_loss: 2.3106 - val_distribution_lambda_12_loss: 0.9407 - val_distribution_lambda_13_loss: 1.3699\n", "Epoch 60/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2532 - distribution_lambda_12_loss: 0.9076 - distribution_lambda_13_loss: 1.3456 - val_loss: 2.2986 - val_distribution_lambda_12_loss: 0.9295 - val_distribution_lambda_13_loss: 1.3691\n", "Epoch 61/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2421 - distribution_lambda_12_loss: 0.9008 - distribution_lambda_13_loss: 1.3413 - val_loss: 2.2877 - val_distribution_lambda_12_loss: 0.9211 - val_distribution_lambda_13_loss: 1.3666\n", "Epoch 62/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2354 - distribution_lambda_12_loss: 0.8951 - distribution_lambda_13_loss: 1.3403 - val_loss: 2.2802 - val_distribution_lambda_12_loss: 0.9152 - val_distribution_lambda_13_loss: 1.3650\n", "Epoch 63/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 2ms/step - loss: 2.2364 - distribution_lambda_12_loss: 0.8931 - distribution_lambda_13_loss: 1.3433 - val_loss: 2.2746 - val_distribution_lambda_12_loss: 0.9102 - val_distribution_lambda_13_loss: 1.3644\n", "Epoch 64/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2316 - distribution_lambda_12_loss: 0.8921 - distribution_lambda_13_loss: 1.3394 - val_loss: 2.2724 - val_distribution_lambda_12_loss: 0.9084 - val_distribution_lambda_13_loss: 1.3640\n", "Epoch 65/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2215 - distribution_lambda_12_loss: 0.8830 - distribution_lambda_13_loss: 1.3385 - val_loss: 2.2647 - val_distribution_lambda_12_loss: 0.9028 - val_distribution_lambda_13_loss: 1.3620\n", "Epoch 66/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2184 - distribution_lambda_12_loss: 0.8801 - distribution_lambda_13_loss: 1.3383 - val_loss: 2.2607 - val_distribution_lambda_12_loss: 0.8989 - val_distribution_lambda_13_loss: 1.3618\n", "Epoch 67/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2159 - distribution_lambda_12_loss: 0.8780 - distribution_lambda_13_loss: 1.3379 - val_loss: 2.2577 - val_distribution_lambda_12_loss: 0.8965 - val_distribution_lambda_13_loss: 1.3612\n", "Epoch 68/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2116 - distribution_lambda_12_loss: 0.8747 - distribution_lambda_13_loss: 1.3369 - val_loss: 2.2512 - val_distribution_lambda_12_loss: 0.8917 - val_distribution_lambda_13_loss: 1.3595\n", "Epoch 69/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2076 - distribution_lambda_12_loss: 0.8710 - distribution_lambda_13_loss: 1.3366 - val_loss: 2.2468 - val_distribution_lambda_12_loss: 0.8868 - val_distribution_lambda_13_loss: 1.3600\n", "Epoch 70/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.2065 - distribution_lambda_12_loss: 0.8691 - distribution_lambda_13_loss: 1.3374 - val_loss: 2.2424 - val_distribution_lambda_12_loss: 0.8834 - val_distribution_lambda_13_loss: 1.3590\n", "Epoch 71/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.2041 - distribution_lambda_12_loss: 0.8671 - distribution_lambda_13_loss: 1.3370 - val_loss: 2.2384 - val_distribution_lambda_12_loss: 0.8813 - val_distribution_lambda_13_loss: 1.3571\n", "Epoch 72/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1977 - distribution_lambda_12_loss: 0.8646 - distribution_lambda_13_loss: 1.3331 - val_loss: 2.2362 - val_distribution_lambda_12_loss: 0.8793 - val_distribution_lambda_13_loss: 1.3569\n", "Epoch 73/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1973 - distribution_lambda_12_loss: 0.8632 - distribution_lambda_13_loss: 1.3341 - val_loss: 2.2334 - val_distribution_lambda_12_loss: 0.8772 - val_distribution_lambda_13_loss: 1.3561\n", "Epoch 74/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1949 - distribution_lambda_12_loss: 0.8615 - distribution_lambda_13_loss: 1.3333 - val_loss: 2.2320 - val_distribution_lambda_12_loss: 0.8760 - val_distribution_lambda_13_loss: 1.3560\n", "Epoch 75/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1963 - distribution_lambda_12_loss: 0.8623 - distribution_lambda_13_loss: 1.3339 - val_loss: 2.2340 - val_distribution_lambda_12_loss: 0.8763 - val_distribution_lambda_13_loss: 1.3576\n", "Epoch 76/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1948 - distribution_lambda_12_loss: 0.8623 - distribution_lambda_13_loss: 1.3325 - val_loss: 2.2317 - val_distribution_lambda_12_loss: 0.8752 - val_distribution_lambda_13_loss: 1.3565\n", "Epoch 77/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1912 - distribution_lambda_12_loss: 0.8594 - distribution_lambda_13_loss: 1.3319 - val_loss: 2.2323 - val_distribution_lambda_12_loss: 0.8753 - val_distribution_lambda_13_loss: 1.3570\n", "Epoch 78/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1898 - distribution_lambda_12_loss: 0.8583 - distribution_lambda_13_loss: 1.3315 - val_loss: 2.2296 - val_distribution_lambda_12_loss: 0.8738 - val_distribution_lambda_13_loss: 1.3559\n", "Epoch 79/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1891 - distribution_lambda_12_loss: 0.8567 - distribution_lambda_13_loss: 1.3323 - val_loss: 2.2273 - val_distribution_lambda_12_loss: 0.8729 - val_distribution_lambda_13_loss: 1.3545\n", "Epoch 80/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1853 - distribution_lambda_12_loss: 0.8552 - distribution_lambda_13_loss: 1.3301 - val_loss: 2.2264 - val_distribution_lambda_12_loss: 0.8726 - val_distribution_lambda_13_loss: 1.3538\n", "Epoch 81/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1853 - distribution_lambda_12_loss: 0.8564 - distribution_lambda_13_loss: 1.3290 - val_loss: 2.2289 - val_distribution_lambda_12_loss: 0.8731 - val_distribution_lambda_13_loss: 1.3558\n", "Epoch 82/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1871 - distribution_lambda_12_loss: 0.8568 - distribution_lambda_13_loss: 1.3302 - val_loss: 2.2248 - val_distribution_lambda_12_loss: 0.8713 - val_distribution_lambda_13_loss: 1.3536\n", "Epoch 83/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1855 - distribution_lambda_12_loss: 0.8555 - distribution_lambda_13_loss: 1.3300 - val_loss: 2.2249 - val_distribution_lambda_12_loss: 0.8720 - val_distribution_lambda_13_loss: 1.3529\n", "Epoch 84/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1844 - distribution_lambda_12_loss: 0.8535 - distribution_lambda_13_loss: 1.3309 - val_loss: 2.2247 - val_distribution_lambda_12_loss: 0.8718 - val_distribution_lambda_13_loss: 1.3530\n", "Epoch 85/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1822 - distribution_lambda_12_loss: 0.8527 - distribution_lambda_13_loss: 1.3295 - val_loss: 2.2234 - val_distribution_lambda_12_loss: 0.8710 - val_distribution_lambda_13_loss: 1.3524\n", "Epoch 86/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1854 - distribution_lambda_12_loss: 0.8549 - distribution_lambda_13_loss: 1.3305 - val_loss: 2.2254 - val_distribution_lambda_12_loss: 0.8722 - val_distribution_lambda_13_loss: 1.3532\n", "Epoch 87/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1806 - distribution_lambda_12_loss: 0.8516 - distribution_lambda_13_loss: 1.3290 - val_loss: 2.2225 - val_distribution_lambda_12_loss: 0.8691 - val_distribution_lambda_13_loss: 1.3534\n", "Epoch 88/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1781 - distribution_lambda_12_loss: 0.8505 - distribution_lambda_13_loss: 1.3276 - val_loss: 2.2225 - val_distribution_lambda_12_loss: 0.8699 - val_distribution_lambda_13_loss: 1.3526\n", "Epoch 89/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1816 - distribution_lambda_12_loss: 0.8534 - distribution_lambda_13_loss: 1.3283 - val_loss: 2.2207 - val_distribution_lambda_12_loss: 0.8682 - val_distribution_lambda_13_loss: 1.3525\n", "Epoch 90/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1837 - distribution_lambda_12_loss: 0.8532 - distribution_lambda_13_loss: 1.3305 - val_loss: 2.2210 - val_distribution_lambda_12_loss: 0.8676 - val_distribution_lambda_13_loss: 1.3534\n", "Epoch 91/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1748 - distribution_lambda_12_loss: 0.8497 - distribution_lambda_13_loss: 1.3251 - val_loss: 2.2195 - val_distribution_lambda_12_loss: 0.8671 - val_distribution_lambda_13_loss: 1.3524\n", "Epoch 92/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1805 - distribution_lambda_12_loss: 0.8515 - distribution_lambda_13_loss: 1.3291 - val_loss: 2.2187 - val_distribution_lambda_12_loss: 0.8673 - val_distribution_lambda_13_loss: 1.3513\n", "Epoch 93/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1720 - distribution_lambda_12_loss: 0.8476 - distribution_lambda_13_loss: 1.3244 - val_loss: 2.2176 - val_distribution_lambda_12_loss: 0.8662 - val_distribution_lambda_13_loss: 1.3514\n", "Epoch 94/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 3ms/step - loss: 2.1730 - distribution_lambda_12_loss: 0.8489 - distribution_lambda_13_loss: 1.3241 - val_loss: 2.2181 - val_distribution_lambda_12_loss: 0.8669 - val_distribution_lambda_13_loss: 1.3512\n", "Epoch 95/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1680 - distribution_lambda_12_loss: 0.8462 - distribution_lambda_13_loss: 1.3218 - val_loss: 2.2175 - val_distribution_lambda_12_loss: 0.8658 - val_distribution_lambda_13_loss: 1.3517\n", "Epoch 96/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1755 - distribution_lambda_12_loss: 0.8498 - distribution_lambda_13_loss: 1.3257 - val_loss: 2.2183 - val_distribution_lambda_12_loss: 0.8659 - val_distribution_lambda_13_loss: 1.3525\n", "Epoch 97/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1722 - distribution_lambda_12_loss: 0.8463 - distribution_lambda_13_loss: 1.3259 - val_loss: 2.2143 - val_distribution_lambda_12_loss: 0.8640 - val_distribution_lambda_13_loss: 1.3503\n", "Epoch 98/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1753 - distribution_lambda_12_loss: 0.8490 - distribution_lambda_13_loss: 1.3263 - val_loss: 2.2187 - val_distribution_lambda_12_loss: 0.8670 - val_distribution_lambda_13_loss: 1.3517\n", "Epoch 99/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1757 - distribution_lambda_12_loss: 0.8476 - distribution_lambda_13_loss: 1.3282 - val_loss: 2.2191 - val_distribution_lambda_12_loss: 0.8666 - val_distribution_lambda_13_loss: 1.3525\n", "Epoch 100/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1716 - distribution_lambda_12_loss: 0.8469 - distribution_lambda_13_loss: 1.3247 - val_loss: 2.2164 - val_distribution_lambda_12_loss: 0.8644 - val_distribution_lambda_13_loss: 1.3520\n", "Epoch 101/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1713 - distribution_lambda_12_loss: 0.8470 - distribution_lambda_13_loss: 1.3243 - val_loss: 2.2136 - val_distribution_lambda_12_loss: 0.8636 - val_distribution_lambda_13_loss: 1.3500\n", "Epoch 102/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1691 - distribution_lambda_12_loss: 0.8457 - distribution_lambda_13_loss: 1.3234 - val_loss: 2.2176 - val_distribution_lambda_12_loss: 0.8667 - val_distribution_lambda_13_loss: 1.3509\n", "Epoch 103/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1707 - distribution_lambda_12_loss: 0.8455 - distribution_lambda_13_loss: 1.3252 - val_loss: 2.2126 - val_distribution_lambda_12_loss: 0.8636 - val_distribution_lambda_13_loss: 1.3490\n", "Epoch 104/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1716 - distribution_lambda_12_loss: 0.8473 - distribution_lambda_13_loss: 1.3243 - val_loss: 2.2176 - val_distribution_lambda_12_loss: 0.8659 - val_distribution_lambda_13_loss: 1.3517\n", "Epoch 105/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1667 - distribution_lambda_12_loss: 0.8440 - distribution_lambda_13_loss: 1.3227 - val_loss: 2.2117 - val_distribution_lambda_12_loss: 0.8629 - val_distribution_lambda_13_loss: 1.3489\n", "Epoch 106/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1750 - distribution_lambda_12_loss: 0.8480 - distribution_lambda_13_loss: 1.3270 - val_loss: 2.2118 - val_distribution_lambda_12_loss: 0.8636 - val_distribution_lambda_13_loss: 1.3481\n", "Epoch 107/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1682 - distribution_lambda_12_loss: 0.8449 - distribution_lambda_13_loss: 1.3233 - val_loss: 2.2119 - val_distribution_lambda_12_loss: 0.8637 - val_distribution_lambda_13_loss: 1.3482\n", "Epoch 108/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1677 - distribution_lambda_12_loss: 0.8440 - distribution_lambda_13_loss: 1.3237 - val_loss: 2.2118 - val_distribution_lambda_12_loss: 0.8632 - val_distribution_lambda_13_loss: 1.3486\n", "Epoch 109/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1663 - distribution_lambda_12_loss: 0.8437 - distribution_lambda_13_loss: 1.3226 - val_loss: 2.2103 - val_distribution_lambda_12_loss: 0.8610 - val_distribution_lambda_13_loss: 1.3493\n", "Epoch 110/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1662 - distribution_lambda_12_loss: 0.8438 - distribution_lambda_13_loss: 1.3224 - val_loss: 2.2101 - val_distribution_lambda_12_loss: 0.8615 - val_distribution_lambda_13_loss: 1.3486\n", "Epoch 111/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1620 - distribution_lambda_12_loss: 0.8406 - distribution_lambda_13_loss: 1.3215 - val_loss: 2.2118 - val_distribution_lambda_12_loss: 0.8632 - val_distribution_lambda_13_loss: 1.3486\n", "Epoch 112/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1708 - distribution_lambda_12_loss: 0.8466 - distribution_lambda_13_loss: 1.3242 - val_loss: 2.2097 - val_distribution_lambda_12_loss: 0.8607 - val_distribution_lambda_13_loss: 1.3491\n", "Epoch 113/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1686 - distribution_lambda_12_loss: 0.8438 - distribution_lambda_13_loss: 1.3249 - val_loss: 2.2075 - val_distribution_lambda_12_loss: 0.8598 - val_distribution_lambda_13_loss: 1.3476\n", "Epoch 114/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1628 - distribution_lambda_12_loss: 0.8426 - distribution_lambda_13_loss: 1.3202 - val_loss: 2.2113 - val_distribution_lambda_12_loss: 0.8636 - val_distribution_lambda_13_loss: 1.3477\n", "Epoch 115/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1609 - distribution_lambda_12_loss: 0.8409 - distribution_lambda_13_loss: 1.3200 - val_loss: 2.2079 - val_distribution_lambda_12_loss: 0.8603 - val_distribution_lambda_13_loss: 1.3476\n", "Epoch 116/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1707 - distribution_lambda_12_loss: 0.8450 - distribution_lambda_13_loss: 1.3256 - val_loss: 2.2086 - val_distribution_lambda_12_loss: 0.8607 - val_distribution_lambda_13_loss: 1.3480\n", "Epoch 117/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1668 - distribution_lambda_12_loss: 0.8438 - distribution_lambda_13_loss: 1.3230 - val_loss: 2.2069 - val_distribution_lambda_12_loss: 0.8588 - val_distribution_lambda_13_loss: 1.3481\n", "Epoch 118/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1628 - distribution_lambda_12_loss: 0.8413 - distribution_lambda_13_loss: 1.3216 - val_loss: 2.2086 - val_distribution_lambda_12_loss: 0.8608 - val_distribution_lambda_13_loss: 1.3477\n", "Epoch 119/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1623 - distribution_lambda_12_loss: 0.8403 - distribution_lambda_13_loss: 1.3221 - val_loss: 2.2062 - val_distribution_lambda_12_loss: 0.8594 - val_distribution_lambda_13_loss: 1.3468\n", "Epoch 120/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1618 - distribution_lambda_12_loss: 0.8411 - distribution_lambda_13_loss: 1.3207 - val_loss: 2.2061 - val_distribution_lambda_12_loss: 0.8590 - val_distribution_lambda_13_loss: 1.3472\n", "Epoch 121/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1646 - distribution_lambda_12_loss: 0.8423 - distribution_lambda_13_loss: 1.3223 - val_loss: 2.2046 - val_distribution_lambda_12_loss: 0.8584 - val_distribution_lambda_13_loss: 1.3462\n", "Epoch 122/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1599 - distribution_lambda_12_loss: 0.8391 - distribution_lambda_13_loss: 1.3208 - val_loss: 2.2052 - val_distribution_lambda_12_loss: 0.8581 - val_distribution_lambda_13_loss: 1.3470\n", "Epoch 123/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1586 - distribution_lambda_12_loss: 0.8395 - distribution_lambda_13_loss: 1.3190 - val_loss: 2.2044 - val_distribution_lambda_12_loss: 0.8579 - val_distribution_lambda_13_loss: 1.3465\n", "Epoch 124/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1645 - distribution_lambda_12_loss: 0.8417 - distribution_lambda_13_loss: 1.3228 - val_loss: 2.2066 - val_distribution_lambda_12_loss: 0.8591 - val_distribution_lambda_13_loss: 1.3475\n", "Epoch 125/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 3ms/step - loss: 2.1604 - distribution_lambda_12_loss: 0.8405 - distribution_lambda_13_loss: 1.3199 - val_loss: 2.2030 - val_distribution_lambda_12_loss: 0.8571 - val_distribution_lambda_13_loss: 1.3458\n", "Epoch 126/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1584 - distribution_lambda_12_loss: 0.8378 - distribution_lambda_13_loss: 1.3207 - val_loss: 2.2044 - val_distribution_lambda_12_loss: 0.8585 - val_distribution_lambda_13_loss: 1.3459\n", "Epoch 127/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1594 - distribution_lambda_12_loss: 0.8398 - distribution_lambda_13_loss: 1.3196 - val_loss: 2.2031 - val_distribution_lambda_12_loss: 0.8575 - val_distribution_lambda_13_loss: 1.3456\n", "Epoch 128/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1633 - distribution_lambda_12_loss: 0.8415 - distribution_lambda_13_loss: 1.3219 - val_loss: 2.2064 - val_distribution_lambda_12_loss: 0.8591 - val_distribution_lambda_13_loss: 1.3473\n", "Epoch 129/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1558 - distribution_lambda_12_loss: 0.8389 - distribution_lambda_13_loss: 1.3169 - val_loss: 2.2050 - val_distribution_lambda_12_loss: 0.8584 - val_distribution_lambda_13_loss: 1.3466\n", "Epoch 130/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1573 - distribution_lambda_12_loss: 0.8393 - distribution_lambda_13_loss: 1.3180 - val_loss: 2.2019 - val_distribution_lambda_12_loss: 0.8558 - val_distribution_lambda_13_loss: 1.3461\n", "Epoch 131/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1552 - distribution_lambda_12_loss: 0.8380 - distribution_lambda_13_loss: 1.3172 - val_loss: 2.2105 - val_distribution_lambda_12_loss: 0.8604 - val_distribution_lambda_13_loss: 1.3501\n", "Epoch 132/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1609 - distribution_lambda_12_loss: 0.8411 - distribution_lambda_13_loss: 1.3198 - val_loss: 2.2014 - val_distribution_lambda_12_loss: 0.8555 - val_distribution_lambda_13_loss: 1.3459\n", "Epoch 133/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1573 - distribution_lambda_12_loss: 0.8400 - distribution_lambda_13_loss: 1.3173 - val_loss: 2.1997 - val_distribution_lambda_12_loss: 0.8548 - val_distribution_lambda_13_loss: 1.3449\n", "Epoch 134/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1539 - distribution_lambda_12_loss: 0.8384 - distribution_lambda_13_loss: 1.3155 - val_loss: 2.2013 - val_distribution_lambda_12_loss: 0.8555 - val_distribution_lambda_13_loss: 1.3458\n", "Epoch 135/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1580 - distribution_lambda_12_loss: 0.8386 - distribution_lambda_13_loss: 1.3195 - val_loss: 2.2028 - val_distribution_lambda_12_loss: 0.8567 - val_distribution_lambda_13_loss: 1.3460\n", "Epoch 136/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1564 - distribution_lambda_12_loss: 0.8391 - distribution_lambda_13_loss: 1.3173 - val_loss: 2.2017 - val_distribution_lambda_12_loss: 0.8554 - val_distribution_lambda_13_loss: 1.3463\n", "Epoch 137/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1583 - distribution_lambda_12_loss: 0.8379 - distribution_lambda_13_loss: 1.3204 - val_loss: 2.2001 - val_distribution_lambda_12_loss: 0.8548 - val_distribution_lambda_13_loss: 1.3452\n", "Epoch 138/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1536 - distribution_lambda_12_loss: 0.8367 - distribution_lambda_13_loss: 1.3169 - val_loss: 2.2005 - val_distribution_lambda_12_loss: 0.8549 - val_distribution_lambda_13_loss: 1.3456\n", "Epoch 139/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1522 - distribution_lambda_12_loss: 0.8369 - distribution_lambda_13_loss: 1.3153 - val_loss: 2.1998 - val_distribution_lambda_12_loss: 0.8547 - val_distribution_lambda_13_loss: 1.3451\n", "Epoch 140/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1535 - distribution_lambda_12_loss: 0.8360 - distribution_lambda_13_loss: 1.3175 - val_loss: 2.1996 - val_distribution_lambda_12_loss: 0.8540 - val_distribution_lambda_13_loss: 1.3456\n", "Epoch 141/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1540 - distribution_lambda_12_loss: 0.8361 - distribution_lambda_13_loss: 1.3179 - val_loss: 2.2089 - val_distribution_lambda_12_loss: 0.8578 - val_distribution_lambda_13_loss: 1.3511\n", "Epoch 142/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1515 - distribution_lambda_12_loss: 0.8355 - distribution_lambda_13_loss: 1.3160 - val_loss: 2.2015 - val_distribution_lambda_12_loss: 0.8558 - val_distribution_lambda_13_loss: 1.3457\n", "Epoch 143/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1544 - distribution_lambda_12_loss: 0.8371 - distribution_lambda_13_loss: 1.3172 - val_loss: 2.2006 - val_distribution_lambda_12_loss: 0.8554 - val_distribution_lambda_13_loss: 1.3452\n", "Epoch 144/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1521 - distribution_lambda_12_loss: 0.8346 - distribution_lambda_13_loss: 1.3175 - val_loss: 2.1992 - val_distribution_lambda_12_loss: 0.8544 - val_distribution_lambda_13_loss: 1.3448\n", "Epoch 145/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1508 - distribution_lambda_12_loss: 0.8344 - distribution_lambda_13_loss: 1.3164 - val_loss: 2.2004 - val_distribution_lambda_12_loss: 0.8550 - val_distribution_lambda_13_loss: 1.3454\n", "Epoch 146/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1538 - distribution_lambda_12_loss: 0.8369 - distribution_lambda_13_loss: 1.3170 - val_loss: 2.2000 - val_distribution_lambda_12_loss: 0.8557 - val_distribution_lambda_13_loss: 1.3443\n", "Epoch 147/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1543 - distribution_lambda_12_loss: 0.8372 - distribution_lambda_13_loss: 1.3171 - val_loss: 2.1987 - val_distribution_lambda_12_loss: 0.8548 - val_distribution_lambda_13_loss: 1.3439\n", "Epoch 148/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1516 - distribution_lambda_12_loss: 0.8365 - distribution_lambda_13_loss: 1.3152 - val_loss: 2.1981 - val_distribution_lambda_12_loss: 0.8545 - val_distribution_lambda_13_loss: 1.3435\n", "Epoch 149/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1521 - distribution_lambda_12_loss: 0.8346 - distribution_lambda_13_loss: 1.3175 - val_loss: 2.2036 - val_distribution_lambda_12_loss: 0.8573 - val_distribution_lambda_13_loss: 1.3463\n", "Epoch 150/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1543 - distribution_lambda_12_loss: 0.8384 - distribution_lambda_13_loss: 1.3160 - val_loss: 2.1992 - val_distribution_lambda_12_loss: 0.8559 - val_distribution_lambda_13_loss: 1.3432\n", "Epoch 151/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1528 - distribution_lambda_12_loss: 0.8355 - distribution_lambda_13_loss: 1.3173 - val_loss: 2.1968 - val_distribution_lambda_12_loss: 0.8538 - val_distribution_lambda_13_loss: 1.3430\n", "Epoch 152/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1493 - distribution_lambda_12_loss: 0.8337 - distribution_lambda_13_loss: 1.3156 - val_loss: 2.1991 - val_distribution_lambda_12_loss: 0.8549 - val_distribution_lambda_13_loss: 1.3441\n", "Epoch 153/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1478 - distribution_lambda_12_loss: 0.8336 - distribution_lambda_13_loss: 1.3142 - val_loss: 2.1979 - val_distribution_lambda_12_loss: 0.8542 - val_distribution_lambda_13_loss: 1.3437\n", "Epoch 154/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1544 - distribution_lambda_12_loss: 0.8371 - distribution_lambda_13_loss: 1.3173 - val_loss: 2.2053 - val_distribution_lambda_12_loss: 0.8585 - val_distribution_lambda_13_loss: 1.3467\n", "Epoch 155/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1541 - distribution_lambda_12_loss: 0.8368 - distribution_lambda_13_loss: 1.3173 - val_loss: 2.2016 - val_distribution_lambda_12_loss: 0.8564 - val_distribution_lambda_13_loss: 1.3452\n", "Epoch 156/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 3ms/step - loss: 2.1500 - distribution_lambda_12_loss: 0.8341 - distribution_lambda_13_loss: 1.3159 - val_loss: 2.2007 - val_distribution_lambda_12_loss: 0.8552 - val_distribution_lambda_13_loss: 1.3455\n", "Epoch 157/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1556 - distribution_lambda_12_loss: 0.8377 - distribution_lambda_13_loss: 1.3179 - val_loss: 2.2004 - val_distribution_lambda_12_loss: 0.8558 - val_distribution_lambda_13_loss: 1.3447\n", "Epoch 158/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1500 - distribution_lambda_12_loss: 0.8343 - distribution_lambda_13_loss: 1.3158 - val_loss: 2.1984 - val_distribution_lambda_12_loss: 0.8543 - val_distribution_lambda_13_loss: 1.3441\n", "Epoch 159/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1529 - distribution_lambda_12_loss: 0.8363 - distribution_lambda_13_loss: 1.3166 - val_loss: 2.2004 - val_distribution_lambda_12_loss: 0.8554 - val_distribution_lambda_13_loss: 1.3450\n", "Epoch 160/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1505 - distribution_lambda_12_loss: 0.8361 - distribution_lambda_13_loss: 1.3144 - val_loss: 2.1972 - val_distribution_lambda_12_loss: 0.8540 - val_distribution_lambda_13_loss: 1.3432\n", "Epoch 161/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1527 - distribution_lambda_12_loss: 0.8363 - distribution_lambda_13_loss: 1.3164 - val_loss: 2.1964 - val_distribution_lambda_12_loss: 0.8533 - val_distribution_lambda_13_loss: 1.3431\n", "Epoch 162/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1470 - distribution_lambda_12_loss: 0.8339 - distribution_lambda_13_loss: 1.3131 - val_loss: 2.1996 - val_distribution_lambda_12_loss: 0.8544 - val_distribution_lambda_13_loss: 1.3452\n", "Epoch 163/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1449 - distribution_lambda_12_loss: 0.8317 - distribution_lambda_13_loss: 1.3132 - val_loss: 2.1967 - val_distribution_lambda_12_loss: 0.8537 - val_distribution_lambda_13_loss: 1.3431\n", "Epoch 164/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1493 - distribution_lambda_12_loss: 0.8349 - distribution_lambda_13_loss: 1.3144 - val_loss: 2.2004 - val_distribution_lambda_12_loss: 0.8565 - val_distribution_lambda_13_loss: 1.3439\n", "Epoch 165/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1499 - distribution_lambda_12_loss: 0.8341 - distribution_lambda_13_loss: 1.3158 - val_loss: 2.1997 - val_distribution_lambda_12_loss: 0.8556 - val_distribution_lambda_13_loss: 1.3441\n", "Epoch 166/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1483 - distribution_lambda_12_loss: 0.8344 - distribution_lambda_13_loss: 1.3139 - val_loss: 2.1983 - val_distribution_lambda_12_loss: 0.8540 - val_distribution_lambda_13_loss: 1.3442\n", "Epoch 167/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1455 - distribution_lambda_12_loss: 0.8324 - distribution_lambda_13_loss: 1.3132 - val_loss: 2.2018 - val_distribution_lambda_12_loss: 0.8561 - val_distribution_lambda_13_loss: 1.3457\n", "Epoch 168/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1472 - distribution_lambda_12_loss: 0.8340 - distribution_lambda_13_loss: 1.3132 - val_loss: 2.1961 - val_distribution_lambda_12_loss: 0.8541 - val_distribution_lambda_13_loss: 1.3420\n", "Epoch 169/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1440 - distribution_lambda_12_loss: 0.8318 - distribution_lambda_13_loss: 1.3123 - val_loss: 2.1959 - val_distribution_lambda_12_loss: 0.8535 - val_distribution_lambda_13_loss: 1.3424\n", "Epoch 170/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1478 - distribution_lambda_12_loss: 0.8338 - distribution_lambda_13_loss: 1.3139 - val_loss: 2.1983 - val_distribution_lambda_12_loss: 0.8552 - val_distribution_lambda_13_loss: 1.3431\n", "Epoch 171/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1441 - distribution_lambda_12_loss: 0.8324 - distribution_lambda_13_loss: 1.3117 - val_loss: 2.1968 - val_distribution_lambda_12_loss: 0.8537 - val_distribution_lambda_13_loss: 1.3431\n", "Epoch 172/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1481 - distribution_lambda_12_loss: 0.8335 - distribution_lambda_13_loss: 1.3146 - val_loss: 2.1962 - val_distribution_lambda_12_loss: 0.8529 - val_distribution_lambda_13_loss: 1.3433\n", "Epoch 173/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1460 - distribution_lambda_12_loss: 0.8318 - distribution_lambda_13_loss: 1.3141 - val_loss: 2.1953 - val_distribution_lambda_12_loss: 0.8538 - val_distribution_lambda_13_loss: 1.3416\n", "Epoch 174/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1431 - distribution_lambda_12_loss: 0.8323 - distribution_lambda_13_loss: 1.3109 - val_loss: 2.1961 - val_distribution_lambda_12_loss: 0.8549 - val_distribution_lambda_13_loss: 1.3411\n", "Epoch 175/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1449 - distribution_lambda_12_loss: 0.8330 - distribution_lambda_13_loss: 1.3119 - val_loss: 2.1976 - val_distribution_lambda_12_loss: 0.8555 - val_distribution_lambda_13_loss: 1.3421\n", "Epoch 176/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1435 - distribution_lambda_12_loss: 0.8319 - distribution_lambda_13_loss: 1.3116 - val_loss: 2.1981 - val_distribution_lambda_12_loss: 0.8557 - val_distribution_lambda_13_loss: 1.3424\n", "Epoch 177/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1494 - distribution_lambda_12_loss: 0.8363 - distribution_lambda_13_loss: 1.3131 - val_loss: 2.1996 - val_distribution_lambda_12_loss: 0.8549 - val_distribution_lambda_13_loss: 1.3446\n", "Epoch 178/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1500 - distribution_lambda_12_loss: 0.8342 - distribution_lambda_13_loss: 1.3158 - val_loss: 2.1991 - val_distribution_lambda_12_loss: 0.8560 - val_distribution_lambda_13_loss: 1.3431\n", "Epoch 179/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1446 - distribution_lambda_12_loss: 0.8331 - distribution_lambda_13_loss: 1.3114 - val_loss: 2.1982 - val_distribution_lambda_12_loss: 0.8555 - val_distribution_lambda_13_loss: 1.3428\n", "Epoch 180/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1434 - distribution_lambda_12_loss: 0.8324 - distribution_lambda_13_loss: 1.3110 - val_loss: 2.2006 - val_distribution_lambda_12_loss: 0.8570 - val_distribution_lambda_13_loss: 1.3437\n", "Epoch 181/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1460 - distribution_lambda_12_loss: 0.8332 - distribution_lambda_13_loss: 1.3128 - val_loss: 2.1947 - val_distribution_lambda_12_loss: 0.8537 - val_distribution_lambda_13_loss: 1.3410\n", "Epoch 182/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1406 - distribution_lambda_12_loss: 0.8307 - distribution_lambda_13_loss: 1.3100 - val_loss: 2.1989 - val_distribution_lambda_12_loss: 0.8559 - val_distribution_lambda_13_loss: 1.3430\n", "Epoch 183/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1449 - distribution_lambda_12_loss: 0.8334 - distribution_lambda_13_loss: 1.3115 - val_loss: 2.1946 - val_distribution_lambda_12_loss: 0.8538 - val_distribution_lambda_13_loss: 1.3408\n", "Epoch 184/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1458 - distribution_lambda_12_loss: 0.8330 - distribution_lambda_13_loss: 1.3128 - val_loss: 2.1980 - val_distribution_lambda_12_loss: 0.8553 - val_distribution_lambda_13_loss: 1.3427\n", "Epoch 185/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1485 - distribution_lambda_12_loss: 0.8349 - distribution_lambda_13_loss: 1.3136 - val_loss: 2.1963 - val_distribution_lambda_12_loss: 0.8546 - val_distribution_lambda_13_loss: 1.3417\n", "Epoch 186/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1478 - distribution_lambda_12_loss: 0.8353 - distribution_lambda_13_loss: 1.3125 - val_loss: 2.1992 - val_distribution_lambda_12_loss: 0.8572 - val_distribution_lambda_13_loss: 1.3420\n", "Epoch 187/1000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76/76 [==============================] - 0s 4ms/step - loss: 2.1432 - distribution_lambda_12_loss: 0.8323 - distribution_lambda_13_loss: 1.3109 - val_loss: 2.1961 - val_distribution_lambda_12_loss: 0.8543 - val_distribution_lambda_13_loss: 1.3418\n", "Epoch 188/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1436 - distribution_lambda_12_loss: 0.8323 - distribution_lambda_13_loss: 1.3113 - val_loss: 2.1936 - val_distribution_lambda_12_loss: 0.8533 - val_distribution_lambda_13_loss: 1.3403\n", "Epoch 189/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1432 - distribution_lambda_12_loss: 0.8327 - distribution_lambda_13_loss: 1.3105 - val_loss: 2.1990 - val_distribution_lambda_12_loss: 0.8566 - val_distribution_lambda_13_loss: 1.3424\n", "Epoch 190/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1449 - distribution_lambda_12_loss: 0.8326 - distribution_lambda_13_loss: 1.3123 - val_loss: 2.1978 - val_distribution_lambda_12_loss: 0.8558 - val_distribution_lambda_13_loss: 1.3420\n", "Epoch 191/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1435 - distribution_lambda_12_loss: 0.8310 - distribution_lambda_13_loss: 1.3125 - val_loss: 2.1946 - val_distribution_lambda_12_loss: 0.8546 - val_distribution_lambda_13_loss: 1.3400\n", "Epoch 192/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1410 - distribution_lambda_12_loss: 0.8311 - distribution_lambda_13_loss: 1.3099 - val_loss: 2.1949 - val_distribution_lambda_12_loss: 0.8538 - val_distribution_lambda_13_loss: 1.3411\n", "Epoch 193/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1414 - distribution_lambda_12_loss: 0.8312 - distribution_lambda_13_loss: 1.3103 - val_loss: 2.1955 - val_distribution_lambda_12_loss: 0.8535 - val_distribution_lambda_13_loss: 1.3419\n", "Epoch 194/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1446 - distribution_lambda_12_loss: 0.8337 - distribution_lambda_13_loss: 1.3109 - val_loss: 2.1932 - val_distribution_lambda_12_loss: 0.8525 - val_distribution_lambda_13_loss: 1.3406\n", "Epoch 195/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1402 - distribution_lambda_12_loss: 0.8308 - distribution_lambda_13_loss: 1.3095 - val_loss: 2.1940 - val_distribution_lambda_12_loss: 0.8537 - val_distribution_lambda_13_loss: 1.3403\n", "Epoch 196/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1403 - distribution_lambda_12_loss: 0.8309 - distribution_lambda_13_loss: 1.3095 - val_loss: 2.1921 - val_distribution_lambda_12_loss: 0.8534 - val_distribution_lambda_13_loss: 1.3388\n", "Epoch 197/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1374 - distribution_lambda_12_loss: 0.8295 - distribution_lambda_13_loss: 1.3078 - val_loss: 2.1945 - val_distribution_lambda_12_loss: 0.8548 - val_distribution_lambda_13_loss: 1.3397\n", "Epoch 198/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1404 - distribution_lambda_12_loss: 0.8309 - distribution_lambda_13_loss: 1.3096 - val_loss: 2.1911 - val_distribution_lambda_12_loss: 0.8519 - val_distribution_lambda_13_loss: 1.3392\n", "Epoch 199/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1400 - distribution_lambda_12_loss: 0.8303 - distribution_lambda_13_loss: 1.3097 - val_loss: 2.1945 - val_distribution_lambda_12_loss: 0.8531 - val_distribution_lambda_13_loss: 1.3414\n", "Epoch 200/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1445 - distribution_lambda_12_loss: 0.8329 - distribution_lambda_13_loss: 1.3116 - val_loss: 2.1994 - val_distribution_lambda_12_loss: 0.8569 - val_distribution_lambda_13_loss: 1.3425\n", "Epoch 201/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1441 - distribution_lambda_12_loss: 0.8340 - distribution_lambda_13_loss: 1.3101 - val_loss: 2.1946 - val_distribution_lambda_12_loss: 0.8533 - val_distribution_lambda_13_loss: 1.3413\n", "Epoch 202/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1414 - distribution_lambda_12_loss: 0.8313 - distribution_lambda_13_loss: 1.3101 - val_loss: 2.1939 - val_distribution_lambda_12_loss: 0.8534 - val_distribution_lambda_13_loss: 1.3404\n", "Epoch 203/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1446 - distribution_lambda_12_loss: 0.8336 - distribution_lambda_13_loss: 1.3110 - val_loss: 2.1946 - val_distribution_lambda_12_loss: 0.8549 - val_distribution_lambda_13_loss: 1.3397\n", "Epoch 204/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1388 - distribution_lambda_12_loss: 0.8299 - distribution_lambda_13_loss: 1.3088 - val_loss: 2.1922 - val_distribution_lambda_12_loss: 0.8528 - val_distribution_lambda_13_loss: 1.3394\n", "Epoch 205/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1458 - distribution_lambda_12_loss: 0.8343 - distribution_lambda_13_loss: 1.3115 - val_loss: 2.1919 - val_distribution_lambda_12_loss: 0.8525 - val_distribution_lambda_13_loss: 1.3394\n", "Epoch 206/1000\n", "76/76 [==============================] - 0s 4ms/step - loss: 2.1375 - distribution_lambda_12_loss: 0.8311 - distribution_lambda_13_loss: 1.3063 - val_loss: 2.1907 - val_distribution_lambda_12_loss: 0.8526 - val_distribution_lambda_13_loss: 1.3381\n", "Epoch 207/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1470 - distribution_lambda_12_loss: 0.8343 - distribution_lambda_13_loss: 1.3127 - val_loss: 2.1926 - val_distribution_lambda_12_loss: 0.8541 - val_distribution_lambda_13_loss: 1.3385\n", "Epoch 208/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1409 - distribution_lambda_12_loss: 0.8325 - distribution_lambda_13_loss: 1.3084 - val_loss: 2.1932 - val_distribution_lambda_12_loss: 0.8533 - val_distribution_lambda_13_loss: 1.3399\n", "Epoch 209/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1399 - distribution_lambda_12_loss: 0.8318 - distribution_lambda_13_loss: 1.3082 - val_loss: 2.1922 - val_distribution_lambda_12_loss: 0.8527 - val_distribution_lambda_13_loss: 1.3395\n", "Epoch 210/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1428 - distribution_lambda_12_loss: 0.8327 - distribution_lambda_13_loss: 1.3101 - val_loss: 2.1942 - val_distribution_lambda_12_loss: 0.8535 - val_distribution_lambda_13_loss: 1.3406\n", "Epoch 211/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1352 - distribution_lambda_12_loss: 0.8294 - distribution_lambda_13_loss: 1.3058 - val_loss: 2.1940 - val_distribution_lambda_12_loss: 0.8540 - val_distribution_lambda_13_loss: 1.3400\n", "Epoch 212/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1441 - distribution_lambda_12_loss: 0.8342 - distribution_lambda_13_loss: 1.3100 - val_loss: 2.1911 - val_distribution_lambda_12_loss: 0.8528 - val_distribution_lambda_13_loss: 1.3382\n", "Epoch 213/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1378 - distribution_lambda_12_loss: 0.8309 - distribution_lambda_13_loss: 1.3068 - val_loss: 2.1943 - val_distribution_lambda_12_loss: 0.8545 - val_distribution_lambda_13_loss: 1.3397\n", "Epoch 214/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1360 - distribution_lambda_12_loss: 0.8297 - distribution_lambda_13_loss: 1.3063 - val_loss: 2.1919 - val_distribution_lambda_12_loss: 0.8534 - val_distribution_lambda_13_loss: 1.3386\n", "Epoch 215/1000\n", "76/76 [==============================] - 0s 2ms/step - loss: 2.1359 - distribution_lambda_12_loss: 0.8296 - distribution_lambda_13_loss: 1.3064 - val_loss: 2.1907 - val_distribution_lambda_12_loss: 0.8527 - val_distribution_lambda_13_loss: 1.3380\n", "Epoch 216/1000\n", "76/76 [==============================] - 0s 3ms/step - loss: 2.1396 - distribution_lambda_12_loss: 0.8319 - distribution_lambda_13_loss: 1.3077 - val_loss: 2.1937 - val_distribution_lambda_12_loss: 0.8543 - val_distribution_lambda_13_loss: 1.3393\n" ] } ], "source": [ "load_model_of = False# load scaler and model weights for outfield player predictor\n", "refit_model_of = True\n", "\n", "if(load_model_of):\n", " scaler = pickle.load(open('saves/scaler.pkl', 'rb'))\n", " \n", " X_train = scaler.transform(X_train_)\n", " X_test = scaler.transform(X_test_)\n", "\n", "\n", "n_epochs = 1000\n", "\n", "n_samples = X_train.shape[0]\n", "\n", "batch_size = 256\n", "\n", "X_len = X_train.shape[1]\n", "y_len = y_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 1.2\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 10)\n", "neg_log_likelihood = lambda x, rv_x: -rv_x.log_prob(x)\n", "\n", "\n", "inputs = tfk.layers.Input(shape=(X_len,), name=\"input\")\n", "x = tfk.layers.Dropout(0.2)(inputs)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "x = tfk.layers.Dropout(0.2)(x)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "\n", "\n", "prob_dist_params = 4\n", "\n", "def prob_dist(t): \n", " return tfp.distributions.SinhArcsinh(loc=t[..., 0], scale=1e-3 + tf.math.softplus(t[..., 1]), skewness = t[..., 2], \n", " tailweight = tailweight_min + tailweight_range * tf.math.sigmoid(t[..., 3]),\n", " allow_nan_stats = False)\n", "\n", "x1 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x1)\n", "out_1 = tfp.layers.DistributionLambda(prob_dist)(x1)\n", "\n", "x2 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x2 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x2)\n", "\n", "\n", "modelb = tf.keras.Model(inputs, [out_1, out_2])\n", "\n", "modelb.compile(optimizer=tf.keras.optimizers.Nadam(learning_rate = 0.001), \n", " loss=neg_log_likelihood)\n", "\n", "if(load_model_of):\n", " modelb.load_weights('saves/modelb')\n", " \n", "if( (not load_model_of) or refit_model_of):\n", " modelb.fit(X_train.astype('float32'), [y_train[:, 0].astype('float32'), y_train[:, 1].astype('float32')], \n", " validation_data = (X_test.astype('float32'), [y_test[:, 0].astype('float32'), y_test[:, 1].astype('float32')]),\n", " batch_size = batch_size, shuffle = True, epochs=n_epochs, verbose=True, callbacks = [callback])" ] }, { "cell_type": "code", "execution_count": 55, "id": "4e2bf9dc", "metadata": {}, "outputs": [], "source": [ "def sample_predict(X, iterations = 100):\n", " y = np.zeros((2, X.shape[0]))\n", " \n", " dist = modelb(X)\n", " \n", " for i in range(iterations):\n", " y[0, :] += dist[0].sample()\n", " y[1, :] += dist[1].sample()\n", " \n", " return y.transpose() / iterations\n", " " ] }, { "cell_type": "code", "execution_count": 56, "id": "c2674211", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.14844599198900188\n", "0.17323732717963714\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiwAAAGdCAYAAAAxCSikAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB7FklEQVR4nO3deVyU1f4H8M+wDYuAgKyKuASaSwiumLspYpmWqWk3664tLqm30rZfdetmezfT293Kbrc0K9cS19xzSRNwF1QUXFABWZV1zu+PBx6eWZ5hBhlmBj7v14sXMHPm4Twzw5zvc873nKMRQggQEREROTAXe1eAiIiIqD4MWIiIiMjhMWAhIiIih8eAhYiIiBweAxYiIiJyeAxYiIiIyOExYCEiIiKHx4CFiIiIHJ6bvSvQWHQ6HS5fvgxfX19oNBp7V4eIiIgsIIRAcXExIiIi4OKi3o/SbAKWy5cvIzIy0t7VICIiogbIzs5Gu3btVO9vNgGLr68vAOmE/fz87FwbIiIiskRRUREiIyPldlxNswlYaoeB/Pz8GLAQERE5mfrSOZh0S0RERA6PAQsRERE5PAYsRERE5PAYsBAREZHDY8BCREREDo8BCxERETk8BixERETk8BiwEBERkcNjwEJEREQOz6qAZeHChejbty98fX0REhKCCRMm4PTp03plhBB47bXXEBERAS8vLwwbNgzHjx+v99grV65Et27doNVq0a1bN6xevdq6MyEiIqJmy6qAZefOnZgxYwb279+PLVu2oKqqCqNHj0Zpaalc5t1338WHH36IxYsX4+DBgwgLC8OoUaNQXFysetx9+/ZhypQpePTRR5GWloZHH30UkydPxoEDBxp+ZkRERNRsaIQQoqEPvn79OkJCQrBz504MGTIEQghERERgzpw5mD9/PgCgvLwcoaGheOedd/DEE0+YPM6UKVNQVFSEDRs2yLeNGTMGAQEBWL58uUV1KSoqgr+/PwoLC7mXEBERkZOwtP2+rRyWwsJCAEBgYCAAIDMzEzk5ORg9erRcRqvVYujQodi7d6/qcfbt26f3GABITEw0+5jy8nIUFRXpfREREVHj23jsCp7836+o1jW4j+O2NThgEUJg3rx5GDRoEHr06AEAyMnJAQCEhobqlQ0NDZXvMyUnJ8fqxyxcuBD+/v7yV2RkZENPhYiIiEwoq6zGq2uP4cmvDmPj8Rx8dyjbbnVpcMAyc+ZMHDlyxOSQjeEW0UKIereNtvYxL7zwAgoLC+Wv7Gz7PYlERETNzfncUkz8dC/+u+8CAOCJoZ0wsXc7u9XHrSEPmjVrFtatW4ddu3ahXbu6yoeFhQGQekzCw8Pl269du2bUg6IUFhZm1JtS32O0Wi20Wm1Dqk9ERERm/JB2GS+sOoqS8ioE+njgg8mxGN4lxK51sqqHRQiBmTNnYtWqVdi2bRs6duyod3/Hjh0RFhaGLVu2yLdVVFRg586dGDhwoOpxExIS9B4DAJs3bzb7GCIiImpcZZXVeGHVUcxanoKS8ir06xCI5NmD7R6sAFb2sMyYMQPLli3D2rVr4evrK/eK+Pv7w8vLCxqNBnPmzMFbb72F6OhoREdH46233oK3tzemTZsmH2f69Olo27YtFi5cCAB45plnMGTIELzzzjsYP3481q5di61bt2LPnj2NeKpERESk5uz1Esz4+jBO5RRDowFmDr8Dz4yMhpurY6wxa1XA8umnnwIAhg0bpnf70qVL8fjjjwMAnn/+edy6dQtPP/00bty4gf79+2Pz5s3w9fWVy2dlZcHFpe4JGDhwIL755hu8/PLLeOWVV9C5c2esWLEC/fv3b+BpERERkaVWp1zES6uP4WZFNdq08sBHU3phcHSwvaul57bWYXEkXIeFiIjIOrcqqvF/a4/hu18vAgASOgXh44d7IcTPs8nqYGn73aCkWyIiInJu6VeLMePrw8i4VgKNBnhmZDRmjYiGq4v5Wb32woCFiIioBRFC4LtfL+L/1h5DWaUOwb5afPxwLwzs3MbeVTOLAQsREVELUVpehVfWHMOqlEsAgMHRbfDRlF5o08rxlwlhwEJERNQCnLxShBnLDuPc9VK4aIA/j+6Cp4Z2houDDgEZYsBCRETUjAkhsPyXbLz+w3GUV+kQ5ueJRVPj0K9joL2rZhUGLERERM1UcVklXlx9DD+kXQYADO8SjA8m90Kgj4eda2Y9BixERETN0LFLhZi57DDO592Em4sGzyV2wR8Hd3KaISBDDFiIiIiaESEE/rf/At788SQqqnVo29oLi6bGoXdUgL2rdlsYsBARETUThbcqsWDlEWw4Jm2dc8+doXh/0l1o7e18Q0CGGLAQERE1A2nZBZi5/DCy82/B3VWDBUl34nd3d4BG45xDQIYYsBARETkxIQQ+//k83t5wEpXVApGBXlg8NR6xka3tXbVGxYCFiIjISRXcrMCz3x3B1pNXAQBJPcLw9sS74O/lbueaNT4GLERERE7o1ws3MHt5Ci4V3IKHqwtevu9OPDogqtkMARliwEJEROREdDqBf+8+h/c2nUaVTqBDkDcWT4tHj7b+9q6aTTFgISIichL5pRX487ep2H76OgBgXGwE3nqgB3w9m98QkCEGLERERE7gl8x8zF6egpyiMmjdXPDquO6Y2i+y2Q4BGWLAQkRE5MB0OoFPd57Fh1vSUa0T6BTsgyXT4nFnuJ+9q9akGLAQERE5qNyScsxdkYrdGbkAgAfj2uKNCT3go215zXfLO2MiIiInsPdsLp75JhXXi8vh6e6Cv4zvgUm927WYISBDDFiIiIgcSLVO4JNtGVj0UwZ0AogOaYUlj8QjJtTX3lWzKwYsREREDuJaURnmrEjF3rN5AIDJfdrh9ft7wMvD1c41sz8GLERERA5gd8Z1zF2RitySCnh7uOLNCT3wYHw7e1fLYTBgISIisqOqah3+tjUDS3acgRBA1zBfLJ4WjztCWtm7ag6FAQsREZGd5BSWYfbyFPxyPh8AMK1/e/zffd3g6c4hIEMMWIiIiOxg++lr+PO3acgvrUArrRveerAn7o+NsHe1HBYDFiIioiZUWa3D+5tP4587zwEAukf4Ycm0eHRo42Pnmjk2BixERERN5FLBLcxadhiHswoAAI8lROGFsXdyCMgCDFiIiIiawJYTV/Hsd2kovFUJX083vDvxLiT1DLd3tZwGAxYiIiIbqqjS4Z2Np/DZnkwAQGw7f3wyNR7tg7ztXDPnwoCFiIjIRrLzb2Lm8hSkZRcAAH53d0csSOoKDzcX+1bMCTFgISIisoGNx67gue+PoLisCv5e7nh/UixGdQu1d7WcltUh3q5duzBu3DhERERAo9FgzZo1evdrNBqTX++9957qMb/44guTjykrK7P6hIiIiOypvKoar649hie/OozisirEtW+N9bMHMVi5TVb3sJSWliI2Nha//e1vMXHiRKP7r1y5ovf7hg0b8Pvf/95kWSU/Pz+cPn1a7zZPT09rq0dERGQ353NLMXP5YRy7VAQAeGJoJzw7ugvcXTkEdLusDliSkpKQlJSken9YWJje72vXrsXw4cPRqVMns8fVaDRGjyUiInIWPx65jAUrj6KkvAoB3u74cHIvDO8aYu9qNRs2zWG5evUq1q9fj//+97/1li0pKUFUVBSqq6vRq1cvvPHGG4iLi1MtX15ejvLycvn3oqKiRqkzERGRNcoqq/GXH09g2YEsAEDfDgFYNDUO4f5edq5Z82LTPqr//ve/8PX1xYMPPmi2XNeuXfHFF19g3bp1WL58OTw9PXH33XcjIyND9TELFy6Ev7+//BUZGdnY1SciIjLr7PUSTFjyM5YdyIJGA8wcfgeW/3EAgxUb0AghRIMfrNFg9erVmDBhgsn7u3btilGjRuGTTz6x6rg6nQ7x8fEYMmQIFi1aZLKMqR6WyMhIFBYWws/Pz6q/R0REZK3VKRfx0upjuFlRjSAfD/zt4V4YHB1s72o5naKiIvj7+9fbfttsSGj37t04ffo0VqxYYfVjXVxc0LdvX7M9LFqtFlqt9naqSEREZLVbFdV4dd0xfHvoIgAgoVMQPn64F0L8OFHElmwWsHz22Wfo3bs3YmNjrX6sEAKpqano2bOnDWpGRETUMBlXizFj2WGkXy2BRgPMHhGN2SOj4eqisXfVmj2rA5aSkhKcOXNG/j0zMxOpqakIDAxE+/btAUjdO9999x0++OADk8eYPn062rZti4ULFwIAXn/9dQwYMADR0dEoKirCokWLkJqaiiVLljTknIiIiBrdd4ey8craYyir1CHYV4uPp/TCwDva2LtaLYbVAcuhQ4cwfPhw+fd58+YBAB577DF88cUXAIBvvvkGQghMnTrV5DGysrLg4lKX71tQUIA//elPyMnJgb+/P+Li4rBr1y7069fP2uoRERE1qtLyKryy9hhWHb4EABgc3QYfTu6FYF+mJTSl20q6dSSWJu0QERFZ6lROEWZ8fRhnr5fCRQPMGxWDp4fdARcOATUauyfdEhEROSshBL45mI3X1h1HeZUOYX6eWDQ1Dv06Btq7ai0WAxYiIiKF4rJKvLj6GH5IuwwAGNYlGB9O7oVAHw8716xlY8BCRERU49ilQsxcdhjn827C1UWD5xO74I+DO3EIyAEwYCEiohZPCIGv9l/AGz+eREW1DhH+nvhkWjx6RwXYu2pUgwELERG1aEVllViw8giSj+YAAO65MxTvT7oLrb05BORIGLAQEVGLlZZdgJnLDyM7/xbcXTWYP6Yrfj+oIzQaDgE5GgYsRETU4gghsPTn81i44SQqqwXaBXhh8bR49Ipsbe+qkQoGLERE1KIU3KzAc98fwZYTVwEAY7qH4Z2H7oK/l7uda0bmMGAhIqIW43DWDcxaloJLBbfg4eqCl+69E9MTojgE5AQYsBARUbOn0wn8Z885vLvxNKp0AlFB3lgyLR492vrbu2pkIQYsRETUrOWXVuDZ79Kw7dQ1AMB9d4Vj4YM94evJISBnwoCFiIiarYPn8zF7eQquFJbBw80Fr43rjqn9IjkE5IQYsBARUbOj0wl8uvMsPtySjmqdQKc2PljySDzuDOfmuM6KAQsRETUruSXlmLsiFbszcgEAD8S1xZsTesBHyybPmfHVIyKiZmPf2Tw8800KrhWXw9PdBX+5vwcm9WnHIaBmgAELERE5vWqdwOJtZ/DxT+nQCSA6pBWWPBKPmFBfe1eNGgkDFiIicmrXissw55tU7D2bBwCY1LsdXh/fHd4ebOKaE76aRETktPZk5GLOihTkllTA28MVb07ogQfj29m7WmQDDFiIiMjpVFXr8PFPGVi8/QyEALqG+WLxtHjcEdLK3lUjG2HAQkRETiWnsAyzv0nBL5n5AICp/drj1XHd4OnuaueakS0xYCEiIqex4/Q1zPs2DfmlFfDxcMXCiXfh/tgIe1eLmgADFiIicniV1Tp8sDkd/9h5FgDQPcIPi6fFo2MbHzvXjJoKAxYiInJolwtuYdbyFPx64QYAYHpCFF4ceyeHgFoYBixEROSwtp64ime/T0PBzUr4at3wzkN3YWzPcHtXi+yAAQsRETmciiod3t14Cv/ZkwkAuKudPxZPjUf7IG8714zshQELERE5lOz8m5i5PAVp2QUAgN/d3RELkrrCw83FvhUju2LAQkREDmPjsRw8930aisuq4OfphvcnxWJ09zB7V4scAAMWIiKyu/KqaixMPoUv9p4HAMS1b41PpsahXQCHgEjCgIWIiOzqQl4pZi5LwdFLhQCAJ4Z0wrOJXeDuyiEgqsOAhYiI7ObHI5exYOVRlJRXIcDbHR9MjsWIrqH2rhY5IAYsRETU5Moqq/HGjyfw9YEsAEDfDgFYNDUO4f5edq4ZOSqr+9t27dqFcePGISIiAhqNBmvWrNG7//HHH4dGo9H7GjBgQL3HXblyJbp16watVotu3bph9erV1laNiIicwLnrJXjg73vx9YEsaDTAjOGdsfyPAxiskFlWByylpaWIjY3F4sWLVcuMGTMGV65ckb+Sk5PNHnPfvn2YMmUKHn30UaSlpeHRRx/F5MmTceDAAWurR0REDmxNyiXc98kenLxShCAfD/z3t/3wXGJXuDFfheqhEUKIBj9Yo8Hq1asxYcIE+bbHH38cBQUFRj0v5kyZMgVFRUXYsGGDfNuYMWMQEBCA5cuXW3SMoqIi+Pv7o7CwEH5+fhb/bSIisr1bFdV4bd1xrDiUDQAY0CkQHz8ch1A/TzvXjOzN0vbbJiHtjh07EBISgpiYGPzxj3/EtWvXzJbft28fRo8erXdbYmIi9u7dq/qY8vJyFBUV6X0REZHjybhajPFL9mDFoWxoNMAzI6Px9R8GMFghqzR60m1SUhImTZqEqKgoZGZm4pVXXsGIESPw66+/QqvVmnxMTk4OQkP1s8JDQ0ORk5Oj+ncWLlyI119/vVHrTkREjeu7Q9n4v7XHcauyGsG+Wnw8pRcG3tHG3tUiJ9ToAcuUKVPkn3v06IE+ffogKioK69evx4MPPqj6OI1Go/e7EMLoNqUXXngB8+bNk38vKipCZGTkbdSciIgaS2l5FV5ZewyrDl8CAAy6ow0+mtILwb6mL1yJ6mPzac3h4eGIiopCRkaGapmwsDCj3pRr164Z9booabVa1R4bIiKyn1M5RZjx9WGcvV4KFw0wb1QMnhp2B1xd1C9Ciepj87TsvLw8ZGdnIzxcfTvwhIQEbNmyRe+2zZs3Y+DAgbauHhERNRIhBL75JQvjF/+Ms9dLEeqnxfI/DsDMEdEMVui2Wd3DUlJSgjNnzsi/Z2ZmIjU1FYGBgQgMDMRrr72GiRMnIjw8HOfPn8eLL76INm3a4IEHHpAfM336dLRt2xYLFy4EADzzzDMYMmQI3nnnHYwfPx5r167F1q1bsWfPnkY4RSIisrWS8iq8uOoo1qVdBgAMjQnGh5NjEdSKPeHUOKwOWA4dOoThw4fLv9fmkTz22GP49NNPcfToUXz55ZcoKChAeHg4hg8fjhUrVsDX11d+TFZWFlxc6jp3Bg4ciG+++QYvv/wyXnnlFXTu3BkrVqxA//79b+fciIioCRy/XIiZy1KQmVsKVxcNnkvsgj8N7gQX9qpQI7qtdVgcCddhISJqWkIIfHUgC2/8eAIVVTpE+Hvik2lx6B0VaO+qkROxtP3mXkJERGS1orJKvLDyKNYfvQIAuOfOELz3UCwCfDzsXDNqrhiwEBGRVY5cLMDMZSnIyr8JNxcNFiR1xe8HdTS7FAXR7WLAQkREFhFCYOnP57Fww0lUVgu0C/DC4mnx6BXZ2t5VoxaAAQsREdWr8GYlnvs+DZtPXAUAJHYPxbsPxcLfy93ONaOWggELERGZlZJ1AzOXpeBSwS14uLrgpXvvxPSEKA4BUZNiwEJERCbpdAKf7cnEOxtPoUonEBXkjcVT49Gznb+9q0YtEAMWIiIycqO0An/+Lg3bTl0DANx7VzgWPtgTfp4cAiL7YMBCRER6Dp3Px6zlKbhSWAYPNxe8Oq4bpvVrzyEgsisGLEREBEAaAvrHrrP4YHM6qnUCndr4YPG0eHSL4GKcZH8MWIiICLkl5Zj3bRp2pV8HAEzoFYE3H+iJVlo2E+QY+E4kImrh9p/Lw+zlKbhWXA5Pdxf85f4emNSnHYeAyKEwYCEiaqGqdQJLtp/B37amQyeAO0JaYcm0eHQJ863/wURNjAELEVELdK24DHNXpOLnM3kAgId6t8NfxneHtwebBXJMfGcSEbUwP5/JxTPfpCK3pBxe7q54c0IPTOzdzt7VIjKLAQsRUQtRVa3Dop8y8Mn2MxAC6BLqiyWPxOOOkFb2rhpRvRiwEBG1AFeLyjBreQp+ycwHAEztF4lXx3WHp7urnWtGZBkGLEREzdyO09cw79s05JdWwMfDFW892BPje7W1d7WIrMKAhYiomaqq1uGDLen4dMdZAEC3cD8seSQeHdv42LlmRNZjwEJE1AxdLriF2ctTcOjCDQDAowOi8NK9d3IIiJwWAxYiombmp5NX8efv0lBwsxK+Wje889BdGNsz3N7VIrotDFiIiJqJiiod3tt0Cv/enQkAuKudPxZPjUf7IG8714zo9jFgISJqBrLzb2LW8hSkZhcAAH57dwcsSOoKrRuHgKh5YMBCROTkNh3PwXPfpaGorAp+nm54b1IsEruH2btaRI2KAQsRkZMqr6rGwuRT+GLveQBAr8jWWDwtDu0COAREzQ8DFiIiJ3QhrxQzl6Xg6KVCAMCfhnTCc4ld4O7qYueaEdkGAxYiIiez/sgVLFh5BMXlVWjt7Y4PJ8diRNdQe1eLyKYYsBAROYmyymq8uf4EvtqfBQDoExWARVPjENHay841I7I9BixERE7g3PUSzFiWgpNXigAATw/rjHmjYuDGISBqIRiwEBE5uLWpl/DiqqMorahGkI8HPpzSC0Njgu1dLaImxYCFiMhB3aqoxus/HMc3B7MBAAM6BeLjh+MQ6udp55oRNT0GLEREDujMtWLM+DoFp68WQ6MBZo2IxjMjo+HqorF31YjswurBz127dmHcuHGIiIiARqPBmjVr5PsqKysxf/589OzZEz4+PoiIiMD06dNx+fJls8f84osvoNFojL7KysqsPiEiImf3/a8XMe6Tn3H6ajHatNLiq9/3x7xRMQxWqEWzOmApLS1FbGwsFi9ebHTfzZs3cfjwYbzyyis4fPgwVq1ahfT0dNx///31HtfPzw9XrlzR+/L0ZLcnEbUcNyuq8Odv0/Dsd2m4VVmNu+8IQvIzg3D3HW3sXTUiu7N6SCgpKQlJSUkm7/P398eWLVv0bvvkk0/Qr18/ZGVloX379qrH1Wg0CAvjUtJE1DKdzinG01//irPXS+GiAebeE4Onh9/BXhWiGjbPYSksLIRGo0Hr1q3NlispKUFUVBSqq6vRq1cvvPHGG4iLi1MtX15ejvLycvn3oqKixqoyEVGTEUJgxcFsvLruOMqrdAj10+Ljh+MwoFOQvatG5FBsOoG/rKwMCxYswLRp0+Dn56darmvXrvjiiy+wbt06LF++HJ6enrj77ruRkZGh+piFCxfC399f/oqMjLTFKRAR2UxJeRXmrEjFglVHUV6lw9CYYCTPHsxghcgEjRBCNPjBGg1Wr16NCRMmGN1XWVmJSZMmISsrCzt27DAbsBjS6XSIj4/HkCFDsGjRIpNlTPWwREZGorCw0Kq/RURkD8cvF2LWshScyy2Fq4sGz47ugieGdIILh4CohSkqKoK/v3+97bdNhoQqKysxefJkZGZmYtu2bVYHEC4uLujbt6/ZHhatVgutVnu7VSUialJCCHx1IAtv/HgCFVU6hPt74pOpcejTIdDeVSNyaI0esNQGKxkZGdi+fTuCgqzv2hRCIDU1FT179mzs6hER2U1RWSVeWHUU649cAQCM7BqC9yfFIsDHw841I3J8VgcsJSUlOHPmjPx7ZmYmUlNTERgYiIiICDz00EM4fPgwfvzxR1RXVyMnJwcAEBgYCA8P6Z9y+vTpaNu2LRYuXAgAeP311zFgwABER0ejqKgIixYtQmpqKpYsWdIY50hEZHdHLxZixrLDyMq/CTcXDRYkdcXvB3WERsMhICJLWB2wHDp0CMOHD5d/nzdvHgDgsccew2uvvYZ169YBAHr16qX3uO3bt2PYsGEAgKysLLi41OX7FhQU4E9/+hNycnLg7++PuLg47Nq1C/369bO2ekREDkUIgf/uPY+3kk+holqHtq29sHhaHOLaB9i7akRO5baSbh2JpUk7RERNpfBmJZ5fmYZNx68CAEZ3C8V7D8XC39vdzjUjchx2TbolImrpUrJuYOayFFwquAUPVxe8OLYrHhvYgUNARA3EgIWIqBEJIfCf3Zl4Z+MpVOkE2gd6Y8m0ePRs52/vqhE5NQYsRESN5EZpBZ79Lg0/nboGALi3ZzgWTuwJP08OARHdLgYsRESN4ND5fMxenoLLhWXwcHPB/93XDY/0b88hIKJGwoCFiOg26HQC/9h1Fh9sTke1TqBjGx8snhaH7hEcAiJqTAxYiIgaKK+kHPO+TcPO9OsAgPG9IvDXB3qilZYfrUSNjf9VREQNcOBcHmZ/k4KrReXQurngL+O7Y3KfSA4BEdkIAxYiIitU6wT+vv0MPtqaDp0A7ghphSXT4tElzNfeVSNq1hiwEBFZ6HpxOeasSMHPZ/IAABPj2+GNCd3h7cGPUiJb438ZEZEFfj6Ti2e+SUVuSTm83F3xxoQeeKh3O3tXi6jFYMBCRGRGtU7g458y8Mm2DAgBdAn1xZJH4nBHCIeAiJoSAxYiIhVXi8owe3kKDmTmAwAe7huJV8d1h5eHq51rRtTyMGAhIjJhZ/p1zFuRirzSCvh4uOKtB3tifK+29q4WUYvFgIWISKGqWocPtqTj0x1nAQB3hvthybQ4dApuZeeaEbVsDFiIiGpcLriF2ctTcOjCDQDAowOi8NK9d8LTnUNARPbGgIWICMC2U1cx79s0FNyshK/WDW9PvAv33hVu72oRUQ0GLETUolVW6/DeptP4165zAICebf2xeFocooJ87FwzIlJiwEJELdbFGzcxc1kKUrMLAACPD+yAF8Z2hdaNQ0BEjoYBCxG1SJuO5+C579JQVFYFP083vDcpFondw+xdLSJSwYCFiFqU8qpqvL3hFJb+fB4A0CuyNT6ZGofIQG/7VoyIzGLAQkQtRlbeTcxYdhhHLxUCAP44uCOeS+wKDzcXO9eMiOrDgIWIWoTko1cw//sjKC6vQmtvd3wwKRYj7wy1d7WIyEIMWIioWSurrMZf15/E//ZfAAD0iQrAoqlxiGjtZeeaEZE1GLAQUbOVmVuKGV8fxokrRQCAp4d1xtxRMXB35RAQkbNhwEJEzdLa1Et4cdVRlFZUI9DHAx9N6YWhMcH2rhYRNRADFiJqVsoqq/H6D8ex/JdsAED/joFYNDUOoX6edq4ZEd0OBixE1GycuVaCGV8fxumrxdBogFnD78DskdFw4xAQkdNjwEJEzcLKXy/i5TXHcKuyGm1aafG3Kb0wKLqNvatFRI2EAQsRObWbFVX4v7XH8f2vFwEAd98RhI+m9EKIL4eAiJoTBixE5LTSrxZjxteHkXGtBC4aYM49MZgx/A64umjsXTUiamQMWIjI6Qgh8O2hbLy67jjKKnUI8dVi0dQ4DOgUZO+qEZGNWJ2JtmvXLowbNw4RERHQaDRYs2aN3v1CCLz22muIiIiAl5cXhg0bhuPHj9d73JUrV6Jbt27QarXo1q0bVq9ebW3ViKgFKCmvwtwVqZi/8ijKKnUYEhOM5GcGM1ghauasDlhKS0sRGxuLxYsXm7z/3XffxYcffojFixfj4MGDCAsLw6hRo1BcXKx6zH379mHKlCl49NFHkZaWhkcffRSTJ0/GgQMHrK0eETVjJy4X4f5P9mBN6mW4umjw/Jgu+OLxvmjTSmvvqhGRjWmEEKLBD9ZosHr1akyYMAGA1LsSERGBOXPmYP78+QCA8vJyhIaG4p133sETTzxh8jhTpkxBUVERNmzYIN82ZswYBAQEYPny5RbVpaioCP7+/igsLISfn19DT4mIHJAQAl8fyMJffjyBiiodwv09sWhqHPp2CLR31YjoNlnafjfq4gSZmZnIycnB6NGj5du0Wi2GDh2KvXv3qj5u3759eo8BgMTERLOPKS8vR1FRkd4XETU/xWWVmLk8BS+vOYaKKh1Gdg1B8uzBDFaIWphGDVhycnIAAKGh+jughoaGyvepPc7axyxcuBD+/v7yV2Rk5G3UnIgc0dGLhbjvkz1Yf+QK3Fw0eGnsnfjPY30Q4ONh76oRUROzyfKPGo3+lEIhhNFtt/uYF154AYWFhfJXdnZ2wytMRA5FCIEvfs7ExE/34kLeTbRt7YVvn0zAH4d0qvezhIiap0ad1hwWFgZA6jEJDw+Xb7927ZpRD4rh4wx7U+p7jFarhVbLRDui5qbwViXmf38EG49Lnwmju4XivYdi4e/tbueaEZE9NWoPS8eOHREWFoYtW7bIt1VUVGDnzp0YOHCg6uMSEhL0HgMAmzdvNvsYImp+UrMLcO+i3dh4PAfurhq8Oq4b/vlobwYrRGR9D0tJSQnOnDkj/56ZmYnU1FQEBgaiffv2mDNnDt566y1ER0cjOjoab731Fry9vTFt2jT5MdOnT0fbtm2xcOFCAMAzzzyDIUOG4J133sH48eOxdu1abN26FXv27GmEUyQiRyeEwGd7MvH2hlOo0gm0D/TG4mlxuKtda3tXjYgchNUBy6FDhzB8+HD593nz5gEAHnvsMXzxxRd4/vnncevWLTz99NO4ceMG+vfvj82bN8PX11d+TFZWFlxc6jp3Bg4ciG+++QYvv/wyXnnlFXTu3BkrVqxA//79b+fciMgJFNyswLPfpWHryWsAgLE9w/D2xLvg58leFSKqc1vrsDgSrsNC5Hx+vZCPWctScLmwDB5uLnjlvm74Tf/2TKwlakEsbb+5lxARNTmdTuCfu87h/c2nUa0T6NjGB4unxaF7hL+9q0ZEDooBCxE1qbyScvz5uzTsOH0dADC+VwT++kBPtNLy48je0tPTcfbsWdxxxx2Ijo62d3WI9PATgoiazIFzeZj9TQquFpVD6+aC1+/vjil9IzkEZGf5+fmY9ptp2LRhk3xbYlIiln+9HAEBAXasGVEdBixEZHPVOoG/bz+Dj7amQyeAzsE+WPJIPLqGOVe+WXPtgZj2m2nYumsr8CCAKAAXgK2btmLqI1OxMXmjvatHBIABCxHZ2PXicsxdkYo9Z3IBABPj2+GNCd3h7eE8Hz/NuQciPT1dOq8HAdxVc+NdQLWoxqbVm5CRkdGsgjNyXjZZmp+ICAD2nsnF2EW7sedMLrzcXfH+pFh8MDnWqYIVwKAHYi6AB4Gtu6QeCGd39uxZ6Ycogzs6SN+U624R2ZNzfWoQkVOo1gl8/FMGPtmWASGAmNBWWDItHtGhvvU/2ME09x6Izp07Sz9cQN35AcB56dsdd9zRxDVyHM11CNBZsYeFiBrV1aIyPPKf/Vj0kxSsPNw3EmtnDLqtYCU9PR0bNmxARkZGI9bUMs29ByImJgaJSYlw3eQKpAEoBJAGuG52RWJSYotsqPPz8zFm7Bh06dIFY8eORUxMDMaMHYMbN27Yu2otGgMWIlJlbaCwK/06xn68G/vP5cPHwxUfP9wLb0+8C14erg36+47QcOj1QCidl741hx6I5V8vxz1D7gFWA/gIwGrgniH3YPnXy+1dNbtozkOAzowBCxEZsTZQqKrW4d2NpzD981+QV1qBO8P98MOsQRjfq+1t1cMRGo6W0APRTBY8bxS1Q4DVidXSEJk/pCHA0dXYtGGTXXr5SMKAhYiMWBMoXCm8han/3o+/75CGTn4zoD1WPz0QnYJb3VYdHKnhaO49EI4QGDqK5j4E6MwYsBApbNq0CX/5y1+wZcsWe1fFbqwJFLafuoaxH+/GwfM30ErrhsXT4vDmhJ7wdG/YEJCSIzUcztwDUd+wniMFho6gJQwBOivOEiKC1Dj2T+iPvOt58m1BwUE4eOAgOnbsqPq4TZs24cCBA0hISMCoUaPM/g1nmXFgSaDQoVNnvL/pNP656xwAoGdbf/w5oTVuXUpDhldpvednyfMm7+h+AUAEgBsAAgFclG52c2u6jy9nXFjN0rVjLHm9m/r9as//ldohwK2btqJaVEvPw3lpCPCepHsc+n+32RPNRGFhoQAgCgsL7V0VckJ+rf0EXCEAxZcrhF9rP5Plz5w5I4KCg/TKBwUHiXPnzhmVzcvLE4lJiXplE5MSRX5+vq1Py6TTp0+L5ORkkZ6erno/AIEHIfCa4usBqe67fz0uJizZI6Lm/yii5v8o5q84JEaNTbLo/Kx53pKTk+XXwfB1ASCSk5MbdH7Wqu/5aKy/09gGDxls8rkbPHSwXjlHOj9H+V/Jz893iHq0FJa23wxYqNmrrwHbuHGjgAYC2poP7bk137UQ0EBs3rzZ6DGtA1ubLB8QGGBUdsTIEULjqdErq/HUiBH3jGiU89u4caN4/fXXTdZTyZrGIDEpUbj6uEqN1lyp8XL1cRUDpzwp7nptk4ia/6Po+epGseHolbqyivNz9XEViUmJRscNbBNo8nkLbBNoVPY///mP2ddl6dKlDT4/a8iB01yDBn2u+cDJnk6fPm32uTP8X1B7vU29hrZkzXupKaSnp1sc/DZ2oNySMGAhu7P3P7ClDdj48ePNXmFOmDBBr/zGjRvNllcGDra8erWmt0II6wInoytMFzfR63dvyr0q9y/eI7LySq06P2ueN6PXZSYEHoHALPXXpSGNnSXvUUfqgbDUG2+8Yfa5e/PNN/XKO0KPgjM+z0I4Tq+QM7O0/WYOCzU6R9l3xdK8g/Pnz0s/qIzhy/fX+Prrr82W/+qrr+S8jJ07d5otu3PnzgaPifft3xc3CvSnGefl56F3397Iz83Xuz09PR3bftpmtFqrEALbVm8zWq01ICAAG5M3IiMjA/uOZuCrcx5Izy0HAPxxcEc8l9gVHm4u2HBAkf+Qi7o8k5rzU+Y/rF+/3uxz8eOPP+rlsxw9elT6IQXAKkX5mpSiI0eO6J2fNavRWvMejYmJQWCbQOSvzwfOASgD4AXgBBDYJtAhcxoOHTok/aDy3B08eFCvvPL1PnPmjF1yRxwxl8YSzpjf5Kw4S4ganSNMkdSb+RAB4BqAtqZnPnTo0EH6QWVWgHx/jcLCQrPli4qKjCt0AVKDngEgr65sQ23atAk38m9IafOjAEwAMBqAG3Aj/4bRLCdLAidTMspa4b00V6TnlqO1tzv+M70PXrq3GzzcpI8OeUbFcgCLAXwN4BMAy6SblTMqQkJCpB9Unjf5/hru7u6ABsBl6L2XcBmABvDw8JDLWjujyJr3aHp6uhQAVgBIBXAKUiBQAeTn5jvkLBpRO6spy+COmt81Go3Jx0VHRyMpKanRAwNLFiB0xtk5nGHVtBiwUKNylH9guQFLgX5DmirdrGzAxo0bJzWMydBbGAwbAGiA8ePH6x27devWUvn1BuWTpfKtW7eWyw4dOlT6Ya1BPdYZ3G+l9evXS53PAQC2AFgDYDOA1gCE1FthkkpjYKisshqvrDmGp78+jOLyKvSOCsD62YNxT7dQvXIxMTHwD/CXAkKl64B/gL9ewzd58mSzz9vkyZP1DjFgwADpHO+F3nsJY6VzHDhwoFxWr7EzERgqGztr36M7d+6U6u0B/cDJQ6q3WrBnTx07dpTq7A79OrsD0BgH4bZizQKEzrhAnyNNvW8JGLBQo3KUf2AXFxfpA/sK9D+wrwDQ6E+J3bVrl9QwVkJvYTBUAhDAjh079I595MiRumBBWb61VD41NVUuGxMTA7/WflJ5JQH4tfZr8IewfH6FBudXJJ2fq6v+OihDhw41GywoA6fM3FJM/HQv/rdfim6eHNoZ3/xpANq29jKqR3p6OgoLCk02jIUFhXqNf0xMDPxb+5t8nv1b+xs9FwUFBdIPKu+lvLy6KegxMTEYPnK4FAgqA8MfgBH3jNA7trXv0eTk5LrASdFbVxs4JScnGz0v1mrsvZLatGkj1Xks9IO9JACi5v4mYG1vq7Mt0OeMvULOjDks1KgcZefXrKysug9sZSOTBGA1cOFC3SfMgQMHpB/aA8hUHKTm9/379+sdOzs7W/phKoAqAPmQ8jbcAHwEXLx4US6bnp6OosIi6Wr8Xshj3FgPFBUW3d5Ov6LmfBQ5GxDS+QmDhc4yMzP1g6xaoQCuSnk60dHRWJd2GS+sPILSimoE+njgw8mxGNZFf6hG6dtvv9XvBTGox7fffouXXnpJfi4KbxQCnpDyQGq5A4U3Co2ei9OnT0s/XICUM3IJQCSAEsjHU7p165bJwPDWzVt6N1n7Hj158qT0g0o+iHy/AUvWErFVvldoaE1PmEpukXx/A+psqYbscl2bS7N582bs37/fovWN7IlrtjQtBizUqBzuH1ilkVFq27at1DjeMrjjpvQtMjJS72Yvr5qehtoGL6jmjjSD+2HQoBtenRs06NbQ6XTSDyq9BPL9NeSgbCqAs5ACs041Xx8Bu/fux7biMCz/RUpy6NcxEIsejkOYv6fZely7ds1sPeT7oejZqDQoWyV9M0yqlIcN1gBQno6Lwf2QGsf9+/YDWgDjURcYJgP79u3TaxytfY+2a9cOp9NP1/XWKY4NjfT+UbImCGlIwqYlQUX79u2lH5YDyFHcURvHROm/YLYInBqSROsoCfvWWP71ckx9ZCo2ra6r8z1Jjtsr5Mw4JESNzhG6ddu3b292SEj5gT1ixAip7A2DsgVS2ZEjR+odu1WrVmaHV1q1qttDRx5OUsml2b59e4POLzY2VvpBJWcjLi5Or3z//v2lHz6FNGxyFFJezd8Bt8B2+Mm1N5b/kgWNBpg14g4s+0P/eoMVALj33nvr6qFUU4/77rtPvkkexlLJqzBcuVYeEjLMD9UY3A9FYKgyBPLtt9/qHcKa9+jw4cPNHvuee+7RK2/pMIi1uTTW5IPodDqz7+mqqqoG1dka1uQV2bIetlbbK5Seno7k5GSkp6djY/JGhw2wnBl7WKjRNcUUyfqWdj948KB+IwPoDVX88ssv8uPksiq9IHLvRI3i4mKpvCv0h1e8peOXlJTIN+Xm5uoHTgZX57m5uSbPr76r6IiICOmHtQCqFXfUpK4YdvknJiZK9ajQP45P9HAEjnoal0oE2rTS4m9TemFQtOX5DXJy53pIz0kHSA1SzfkpkzuteU0AoLy8vC7AMeg1gQ4oK6sbV7Kmpwew7j0qD02pHFs5JGTNMIi1PRDW9Ma4uLiYfU8rg8OGDN3UPs7cezQmJgaDhwzG7rW7jd6jg4cONnpMQ+thS9YMkUVHR3MIyMYYsJDN2OIf2NI9f+R1KFQaA+U6FHv27JF+UBk+ku+vIU8JHQPAB0A26nIrVusVhbe3t9lG2sfHR6+8pV3ily9flhpzN+g35usB6ICrV6/qHXfTpprjuQO4F9BEaRF460m08pcChK4BGnz59CCE+Nbfq6J09uxZ6VwqDM5dI52jstGVc05U8ioMc1IAmH3ulO6991588sknqnkpyp4eJUveo5cuXZJ+UDn25cuX5ZusCUKsyaWxtjHPyqqZv6zynlbmcFkbOFkzbHP8xHGT79Hjx4/DkF496lnTx9accWiqJeCQEDmV/gn9kVeUp9dlnFeUh779++qVkz+QVYYq5A90KNZVUVmzQjn0IJev7VU4CilH4BjkXgX5eFCsLaLSGAQHB+vd/NDkh7Bpyya92zZt2YSHJj+kd9sPP/xgdsrv2rVr9cp/9dVXcnn3Hu0Rpv0QrfxHQYhqFOz+CiEnvrU6WAEUwzxaSOvATKj5roXRME9gYKD0g8qaLfL9NeSZTirPnfLYFy9eNDtMJwcdDdC2bVvp2BsMjr1ROrbc2wXrhkGsmcZr7cymPXv2mB0SVQbh1s50sfQ9umnTJmn9GhPv0fzcfKO1gqxZ08fWGjI01dgzvcgYAxZyGps2bZJ6Vkx8AOZdz9P7ALx165bZRubmzZtyWcMEVUOG95eWltb1KqRCbyExwyGh0tJS6QeVxuDWrbpM3/T0dGzftl26IlU2Mm7Atp+26X0Qyqu81l6N1jaMHQzur1FcXAwA8Ok4CmHlH8JDRKEKebha9TIK936D4qJCNITeMM9AAL1qvtfkd/zyyy9y2ePHj5vNqzC86tbbrVnpvPRNufjZjh07pHpUQ3/KdLVUj59++slk/S1pZIKCgqRj+xsc2086tjLojImJQUBQgMl1dwKCAox6CCzNpanvuTDM/8nOzjabdyPPdKulgeo6RErWvEfloVSVIGvfvn16N8fExCAoOMjk+yMoOKjJeldsmVtEt4cBCzkNaz4AIyMjzTYy8iwKWB+wyAmNKguJKcsfOnTI7JW/cmhq586dZhsZkwuUqVyNGort3Q9B9/0ZbdyegQs8ccvlMK54zkZ5prT8fZ8+fcw+B2r0ckdMBE7K3JEzZ87U9Qp5QQryfCD3Chn2ElRWVpp97ior66YbDRs2TPpBGFSw5nfDxGlrGpkjR47UBVq1qwqPghxopaSkyGXT09PrViA2aNBv5N8wauwsTdiU33MqQYVhEq08s03lf0X5/pffd+HQ/18Jh9H7zpr3qJzorRJkJSQk6N2cnp5u9oKkyRedtLA3yxkThZ0Vc1jIaeh9AJoY81d+APr4+NQ1MgMhfchqAPwqfTfMHTGX3GnUCAJm1x5RKikpkW6vMrjPVSpf2/OhR+WDUik2NhaZ5zPrrkaVOSwaoFevXnLZE5eLsFEXi1bdAaGrRkHeVyjy/x44JeTGv1+/fiZOsv6kQzl3RGX6rDJ3xNOzZshpI+Qp4wCkZGXoTweXCUhJo8rnriP018sBMHjwYJP1r3X33Xfr/T5p8iRs/3m7FHj4SPXZvH0zHpr8EH7aot8bk5eXV9d7oxzFcJPqpwxy5AZd5b2htndUfbk0chKtYa6Qi3Rswx4W+VgXID1/tfkgNUsEmRxeiQNwH+rWFboIo+dZZsF7NDExEUHBQchbn2eUkB0UHGSULO8oewnZMreIbg8DFnIaiYmJdZvQGXwABrYJNJ4tJCCt+bFXcVvNB7wRC5M79VjwoS0PW4yHNEtD2Ris1h/W0Ov2N/FBqWyU5JlKKg1jSUkJhBBY9ksWXv/hBCqqgKriXOT+8C7Ks0/UHbvm+VAmYQKWJx3Ks49UAiflayKEkMpWmy6r2tMVB6An6taOcYFRQyovn68SdCoDBXkjyDDoBSAiVGDbVuONIIOCguoSnEdACrBuAtglnYvJJEwL3htK9QWGWVlZdb16QwzqUG78+snWwuQsMiV5FeRkAIMAtII0q2g3jFZBln9WeY8abjVx8MBB9O3fF3mrjZPkDTnKopPWrNPjKEFWS8EhIXIqnTt1ruutqO26rlJ82NW4cOGC2TU/TH7AW9nIWLIvT3V1dd2xzwM4AimZt4PB/ahJDDXT7a9MFD516pTZOp9IP4dZy1Pw0upjqKjSIdK1EFeWzkZ55Qn98jXpF4aziiZNnoTN2zfrPXe1PRBKf/3rX80m/7799ttyWY1GY7as4YZ88u9roL92zFqD+6FYPl9lqGLDhg1yWTm4KYTU+5YA4G7I2xoYDr35+fnVHTsGUo9Ml7pjKwMWeahF5b1hasE2S4amrl69arYOhq+fPJ3exNCUyen0tb03WyE931sg52QpxcTEYMQ9I6BJ1ui9RzUbNEZbIACAv7+/0XBjnz599PbbUh7b1nsJWZoYa6vcIro9jR6wdOjQARqNxuhrxowZJsvv2LHDZHn5A5moRnp6Og7+clC6gp4F4JGa7/dLV3LKD6HTp0+bbRzltTWULAhAZGZyK5TkXoNFAH5AXaO7yOB+1AwtCEh7EikDMn+pzspdoLVarWqdPUI7w/Xel/DjkStwc9HgxbFdMdrzHHS3iqSVbn8DYBiARwFMMz612h4IMVboPXciqa4HopaczKoSOG3evFm+qaKiwmzZ8vJyvZvlHhmVoFO5/UBmZqbZY8tXwqhJ7hWQvvYC2AfgZ8jDf4bJv3pL85tY/E9Z3tpcE0vzH+R1dVTqYLjuzrFjx8y+/48dOyaX/fbbb80+z4aL7n3/7fcYPXy03nt09PDR+P7b72HI0hlFtWy16KS1ibFW5xapJPcbvt50exo9/Dt48KDeVeOxY8cwatQoTJo0yezjTp8+LV3J1DCc7kkkf3BGQfoArl0S363u/tpl7uXGT6UBUy46BsDs4meqQ0ga6A8ZaVXKWigtLU364brBHTUXw8pNFSsqKuo+KBV19r18HwJ+83vAzR1tW3vhk2lxiG8fgDd31TxQJddESe5hUHnulMMrsbGx0mq9Kt348fHx8k3Xr9ecmEpZk4voWZgr5O3tbfbYytWH5UZGwKKhKTn5V2XxP2Xyb+fOnfU30qxVk7PU0PwHeahFZeq94VCM/FyqvIbya4GaxHAzz7O8plENSxfdk2cUaQHcD73nrXZGkdpeQo296GRDtkAAjPfkMiS/3v4w3qPrFjc/bGyNHrAYBhpvv/02OnfubPQPZSgkJMRkNyFRLXnGyQVIDcJ51OU0QH9GijxcoJJ0aDj80KAA5ClIwUTtwnFtIF0VGrIwoVfuXrZAYWGh3gelRuuDoKTZ8BkmJZdWZB5C8tIX4e/tDkAxRKCSa2IyWFBp/JVGjx6Nv338N+k4RZDyH0oh5VZo9GfnyIGCSmCovNDREwWTC4kpeXp6mgzgaq905YRf1PRGmGmgw8PD9Y7t4eFhNsfJw8PDuELjYTJnScma/IfMzEyz76PazStrBQXVRPMqr6HJC0KVeqg12vUlCuvNKDKxAalaArIlx7ZGQxJjLc3hkvNddm1F9ahqaaiuFHDdy80PbcGmA2wVFRX46quvMG/ePOMGwkBcXBzKysrQrVs3vPzyy9L+HWaUl5frdSEru8vJMVizrLUlZeUZKatR19AfhTwMo5yRIr/fVJIOjd6Pmpqv0ahLaKxJOlQNWmqDIR2kYZzzKuXMfGgr+fr6qhxAouyBlBv/QsBjfAyCOz0PN48wiOpK3NixFOLUNvh7vyqX/+WXX8w20srtB+QkTJXAQnnxIc9eqYSU/yDfAaPZK56entK6NCqBoclZQoBFvULycJrKlW5+fr58k15ekYlASB66qiE32CrllQ26XhBiohewoSvdrl+/3mzQ9OOPP+olOPv6+poN4JTvpT59+kgLDarUo29f/UUZrZaCejcgtaWGJMZa0yMjb36oCG64+aFt2DRgWbNmDQoKCvD444+rlgkPD8e//vUv9O7dG+Xl5fjf//6HkSNHYseOHRgyZIjq4xYuXIjXX3/dBrWm22XNstbWlJX3rfGA1PAqewkq9PetkfMfVJauN7pqFJCCCOUHtg/MzxJSCYZMsuBDOycnp+4qegTk6bbYJdU5J6eu1XZ1dQUE4JswHgHRj0Pj6o7Kghzk7n4HFScy9BokQLGAncqHtnIhvZiYGAQEBuBGwQ2jYY2AQP3Fz+REYMPrkdoOLkVysxwoGOxnVLt7s8nx/tpeIcX0Y+yEUSApLxRYqChbCmAPjBYKlKfHqwRChuuDyMGtSnllz5g1M71iYmIwYuQIbE/eLr0fO0jlNBs0GH7PcL3nub4Vk+X7axQVFZkN4JSrN+fl5dXl3SiDm5q8m4YugGa0AanBUJphArKtWDv7yNoemabYO40kNg1YPvvsMyQlJektXW2oS5cu6NKli/x7QkICsrOz8f7775sNWF544QXMmzdP/r2oqKhusSSyK2uuTh6a/BC279yud1ttUp7hehjz588320swf/58rFolRQU6na6urInN30xOoVVpDG6bmQ9tZaNbVlZWl3SrXO8jFMBV/VVxdW6eCH5wNryjBwAASk/tQd6GRRBVUsNsOLxSX0MqL4OPmsXP8m5I9fWGNJxRs1fSjdU39D6wr169anaoQjl7RQ6aVIIb+X4lASDA9POhdOedd0qJ1P4myt4CevToId+UmJgIN60bqm5UGQ2PuWndjKbH5+fnmx1Oy8urm7IrTz9W6dkwmp2mAUSV0AsqhJtxl548TKXy+rVt21avfGRkpNl1iJSflWlpafoLx9XqCCATOHz4sFF9AAunYpvpFVKdim0LZgIyQw2dqlxfvgvdPpsFLBcuXMDWrVvlBsQaAwYMkPY+MUOr1dbNlCCHYc3VibVJefKqsCpd88pVY+UPD5WeDZMfLhbkbMgszEuR/hgsWuNF7hUqhH7DWPPBWlvnXy/ko/WUd+DqFwxRVYn8/H+jpFOytOhXTW+TYW9FRkaG2Q9t5awp+QM7BfrrndQ8d0Yf2BaenzI51RST95t5PpTPc3FxsXFvjCKXRrm/U3p6OqrKq4zeoxBA1eoqo/ddRUWF2UBZOYQkTz9W6dlQBnDp6enYtrVmPRhlz00QjNaD0ZvybuL1U055B2pe79ogRbkOUc3wm3K1VjlxOg7Sa3wOQGdIq0Jn6idOAw3YGNBWFwIWkjfoVAnIDN/P1vbIONpGidYMxTsbmwUsS5cuRUhICO69916rH5uSkmKU+EbOwZqrE6NlvgGzq4IGBwdLH9wqXfNt2rTR/5sW9mzIZdWuwExdOFnYSMss+NAuLy83HppSHLe8ohL/2HkW7206DVe/YFTmX8b1krdRGXTOqAfJsIelqqrK7Ie2MsCRNzRUee6UwxryFGczr7ceM0Neqs+zyvOhdO7cOcgrCit7WGpm55w7d06+yZpZUHosbXg1kJbtVwZOtflQCmfPnjUbkCn/V9q2bVv3/CjPvSYAUS61D9RMxa7NyzJxbOVU7G7dutUdt/ZvnK+rb9euXfWObWkPqrWLzNmKHIDEweRKvoYBiDULxwENn4HU2BwtcLIFmwQsOp0OS5cuxWOPPWa0cM4LL7yAS5cu4csvvwQA/O1vf0OHDh3QvXt3OUl35cqVWLlypS2qRjbWoNUqLWwIJk6ciNS0VNWu+YceMljbwZqgQkB12XNVKj09JlnQeyNvmmji+XDx8sPNPtPx9gZpfaJbp3bj+oZFEG1vmewFMfy/Cw4OlnY0VvnQVuZAWNOVL/fMqJyf0XpKZoa8VFnw/ujUqZO0VYEHgHhIAZALgMMAyqT7jVjYo9aqVSsp50OlvHLKtDwDqQL651jzXlKulyInLKsEZMrXUG8qtjIxvCafx2T+j5ljm0w6V8kNU7J6xo0G6ssFNBG9AGR0/QEIoEikXW0+kdaRluZ3lMDJlmwSsGzduhVZWVn43e9+Z3TflStX9LovKyoq8Oyzz+LSpUvw8vJC9+7dsX79eowdO9YWVSMbs+bqRG9VUBMNgWFSnryni0rXvMnkQEuDitor/6HQbwxMrPYps2D2inxsC3pv1NYp0V7tjja/fR4a3yBo3Vzw2v3dMWvsYxCVt1R7QZSNKCBdoV+8dFFqPMbCqPFo166dcb0tCBRatWpl9vyM9mwCVNeZUWVBYNGuXbu6Blo5jT0EwGr9Hgi9pehN1Nnwyl8+R5W8FOXsLvnYKu8l5bHlPCqV51kZhMhDTcr3PiAnhhuudCtP41Y5tnI4XV4lWOX/auPGjfjDH/4AwLoeVHkoRmUvqKZctt7SAKSWpYm0jrI0vyMFTrZkk4Bl9OjRqglIX3zxhd7vzz//PJ5//nlbVIPsxNIPB71VIk00BIZXjdu3b5d+UPlw2Lp1K4xYGlTUfmDXNnaRMD9LyEwSpskcFpWhGCW9xeCKALTSwM93Elq3fQQaF1dU5mVj4xvT0DXMD3+sTdBV6QVRJugCNY2qgJTAqqxHTe+GstG1JpDs0aOHtNpta9PH7dmzp/5JWpP7U1veggX99FajNZGzZLh6rTU9atevX7c4L0U+tgXvJVv2RsoLI6ocW7kkhF5umIlj79+/v0F1tnYoxpYaOpPHok0pAYtmhdmSowROtsaNDqjRWfrhIHeJqzQEhv/s8jodKh8OJndgtjSoAKxbL8LMFalJtwx+v2lcRA7yBeCytzXa3DcPXhFSwmPJ0Z+Qv+VTdP33kwDqn6ZsOONGXop9KqQ8j9rGww3AR8CRI0fksvJMF5VAwdRMF7XZKCYX6LMm98dMkKXk5+cn/d3LMDkFWjnNW84d8QDQG3XDR78CKDf+cL9586bZvBRlcCjnx6i8l4zyY8z1vilPuXYoSeW9b7g0v7w6r8rFgDLBWc4Ns+DY1vSgNmQoxtYac0E6oP7FEJtqaX5H2TjS1hiwkM3U9+EgN4w3YHJmh2HDGBoaavbDISwsTP8PWBNUWJOgW8vCq12rAicN4Nn2LgRNeBZuboHQ6cqQv/VTlKb+ZLoeFuZh6K0SfBfqFjRLM7gfwJ49e8wGCnv27JGHCOTp4xXQn41Sc24mV6+19HmrpRJkKQkhzE6BVk5jlwPl1pD2EDIoaxgoV1ZW1vWSKY9d00tmuNCc2feSgjWzV+Q1TVSCG8PhUy8vLyloVbkYUK786+XlZfb/SlkWsG54xdqhGGcjv5dU/leaqofF2kRhZ8WAhexLQHVmh6GcnByzHw6XL182fpCljaO1V/6A5dOgLQycNC6u8EuYAv+7H4ZG44IKzQXker2Nyg7ZQIpKoqSF+x/pbcqnXEK/ppfAaBNGQDVQUOYKxcbGmk3YjIuLM34+LH3eDMsbBFlK8tYDhdDvYak5P+VaKcpVgk3NoDG8KpaDrjgAPSEN5dVuCZGpH5S1b9/e7HtJGVhYM2QiB4YqexQZ1jkoKAi5ebmqFwPKpfnlVYINh8hq3kfKVYIB64ZXmvuianI+psr/SlOuNdPcg0OAAQvZkZwrMR5GC5QZfrgDikTSqQDOoq7h6ATgI5UET2saR2uu/M10t5vsCann2NeKyhAy+S/wjIoFABS7bsIN939BaMrV93SpHX5RNjIq+x9pNBrp8S7QX0LfWyqvDIbGjx+PH374QTVQeOCBB+SyP/74o37OhsH06nXr1umvdG1FkCWXtyBhWZ4S7g+TC8cpczY2b95sdgbNTz/9hKSkJOO6rIE0fARIW0LUpC8onzu5AVN5vZUNmDVDJnJwEwz9nKw2AK4ad/mXlpaa7XGSZ6RBmrZ86tQp6b2j3BPUA0C5YtqzAWuGVxp7KMbhWBBU21pzDw4BBixkJWsWJdq0aRMOHDiAhIQEo9VDAcVVfQpMTs01vGqUG4ZPUffBehTSBy1MbB5obeNoTXBT2zia6G43ycyxd6Vfx9wVqfCMioWu4hby85egtOOO+utRex5xNX/XC8AJmDw/V1dXVFVXSQ2uiaEK5Uq38rEtyK3Yt2+f9INKzoZ8f63aHjUTvQQmmRkyUbp+/brZXhPl7sRynVSCij179ujd7OHhgfKKcilZ2EQvkru7u3G9LXwvWXpVbO0me3JejcqVv3KrgqioKLNrtjTVEvrOyNoZZ02hOQeHDFjIItYsSnT27Fn0T+iPvOt13fBBwUE4eOCgtB9QDfmqUX+RTvl3w6tGOVlSwGQ+iJwpX8uaxrEhV/43YDLR1FReiskPNBcXtL77ETy29BcIAVRcy8T1dW+jquSSyanHJmcfaSAFC7VUeljk4E9lqEIZHK5du9ZsoLB69Wq518THx8dszobJXi9rWZCwLO+do9Jrolzp1tpl7vW2eTBxbOVwmrUNmDVXxdZsshccHCwNg6lc+SsTaeXlAlSeO+VwGumr3Q9q245t+v8rbsCIkSOabeBgLwxYyCLWLErUP6E/8ory9Mrmrc9D3/59kXvNYNENDdSnuRrIzc0123Dk5ppY0GM8pCEKZX7AauNi1gyv6JU3sey5ybIGjb9rtyC06fUcPCN7QAjgkf7tsXDygxBVFVJQZWmQBdQFTbUzXW4zUVjubVEJFJSJhKGhodIqsiqBkFEiNCC93spcXDeD35VqA8N6Nj+sb00TZVAxduxYrFm7RjWoMDkcZObYJmdCqeSaqLHkqrg2uNm8eTP279+v2nMJAP7+/maDcH9/f7lsUFBNNKNyfvL9ZNL3335vFEgmjkpsVrkjjoIBC9XLmkWJNm3aJPWsmNinJW91HrZs2SJ/yFq7NL+5lWCBmv1kDEVBGrqp/cw1945X2UXYJDNd6CYbJkXj79mpD9qMmgtXT3/oym9iyeN3Y1xsBN6qqqmApQ167d+xJGiqZcFQhZyUegMme7KUjb+ckKnympi8On8KJnOQTDKTh6Hk4uIiJb+qnJ9yuHDo0KFm12Ex7AWJjIyUgjKVYys3EjTq5TNwO+thWNPL2apVK7NBuLe3t3yTvKWFyvkxYDGvJeSOOAoGLFQvaxYlOnDggNmy+/btkwMWecEtlbKGC3LJSacqH6y3taFhbU+PqaXJ1XpNaldVrU00HQP1WUXXAbi4ovWQ6fDvPxEAUJ5zBrlr38G4jxSzm8wMeZkcarK0bG15lVlCyvLy0vwqPVnKxFG5d0HleTbqfQD0F/M7CvXF/GrrrJKXYvHQm0EVYmJi6gJOw8drYNTYjBs3Dh8v+li1t2LcuHFyWTkwUunZu51prpMmT8L2n7frPRebkzeb3Nm8bdu2deenzHE6KdVZubKxvDGmyvnJ+0WRWc05d8RRMGChelmzKFH//v3Nlk1ISDD+A9Yku1o4a0Qua2leipkGWlUKLF5oztU3GG3uex6ebe8EABQdXocb2z4Hqg0WlrKmHtbWWQAoh/4sIRPPhTy0phJIKofetFqt2efZ5I7q1izNbya3QsnPz0/qzVEZilEOgXz22Wdmh/q++OILvZlNFy5cMNtbodxqRG9oykTPXkMXEktPT8e2n7YZ9VwKIbBttfHO5v7+/nXDhCmKA9XMClM+H+np6WbzvdLT0xtUZ6LGxoCF6mXNokSJiYlw17qjcn2lUQPmrnXXG3OX185QCUAMc1LkqbkqjZJFuQTmNjS0IL+jrjKweKE5r+h+CBo7F66evtCJEuRe+Ri3du8zmadjdT2srbPaBneKOsszTFQCSeXKrsXFxWYbc6NhutqerP7Qz7tRW5ofsOgcY2NjsW3bNtVpv7169ZJvWrdundncKWVSMQAcOnRI+kFlKEte2h62W3FUb4dpE3tjGQ6f3nvvvfhk8Seqs8Luu+8+uay8jL/KUKThNg9E9sKAhSxize6lleWVQBiMpvxWXq3UuxLMz8+va7SUZWuuAg0XrFLbn0r1/toGOgLSsEJrAJcg9TKYOpQ1PT1mcm9qVVTpEDDiD/DrOwEAUK5JR672HVR1vir1Gqj1hFhTD2vrbEGPTFFRkdlAUjnjpry8vG54RZn8e1i6Tbn+iVwHoNHzbuQhDi+DO7wN7odidVKV18/kSreA6lCWcqVbW604Kg+PquyNZTh82rFjR7Pn2KFDB7lsQECA2eFFtRwWa5Y4IGoMDFjIIlbvXlpkcEfNhbYy3+XKlSvSjQZtWu3vOTk5MMnUcI5auQoA52p+z4N6D4s1w0e1zFz5Z+ffxMxlh+Vgpah6NW74/BfQVBmVbXA9NLBu8bp66lxLXuZeZVqzMjDUaDRSWX/oByE1a9KYXJ3X2rwbC56PgoICs71eBQUFclm510fluVAGZADQqVMnXL12VTUJuVOnTnrlbbbiqJlEaEN6PTJKHerur/0/jI2NlTYWVQlmlb1TgHXJv0SNiQELWaW+Xo7OnTtLH6DVMDkVVdklrty/xhSjXXCtZU0irZlhDVUqV/5eMQkYu2g3isuqUH2rGHnrP8Kt2F8sX8Y/AEa9U4azYuSy/ibKmuvBv4C6XYRrk0ENhIWF4eLFi6pLxsvrmEAxc0slL0W5oqpcZ2vzbixYS0feUVmlR0H5XpPzTCxM3o6OjpYWm1Opd0xMjF55m80aseK5k/93VM5R+b8lby2gEtwoN0oErFvigKgxMWAhi1h6VZWZmWl2Kur58+flD++KigopSHCDfi7BegA6E5vKAdYHIdZsfqgBMBrSMIJiHxqzM26UV/6b3RFwz+/g13scisuqEN++NdYt+C2qS65Ljb2lvTdTIQUAtVsVtIH6tF/DmM8wcDC0Fvp5Cq7GRTw8POp6b+6GNKPoGoA9Up2VK7tWV1fXvSYjUBeg7gKga6TND8fD5NYNSvIGfSrHlnf6BjBy5Ehs37FdtefGcG0TOYBRObZaEF9fcG8NeaE3lToY7tZszcwfeWaTSnCjnBJuzRIHRI2NAQtZxNKrqvfee69uKqqJTejeffdduUGQNzNUCSpMDglZe4VuaeMooD8bBTV1N3flrxgycWsdjjaPzIc2QOpBemJoJzw7ugs8ZtREENYsR6+Sp2DEmuCttrxKcGg0vCJqblPOKKrpcVIOmXh4eEjlWsNkgOrh4WFcD2vybgDVrRuURo4cKQ1rqBz7nnvukW+Sh7xUXhPDICswMNBsveX7a9hiyEReG0alDoZrx2RnZ5vtrcvOzpZvatOmjdngRl6nBdYtcUDU2BiwUL2suao6e/Zs3VCFiU3ozp07J98k96BY2BUts+YK3ZrGMQomZ2Coqhky8b41BEGBM+Gi8Ub1zULkrv8QL7x9qJ4HqzCXp3A7PUhWlPf29kb+jXzVXBPlomORkZHIy89TXStFuaiafH6WTkuvLW/BbCx5LyGVYyuHQORZP1roL/Nf87ty1g8AdO/e3WyD3r17d73yNhsyMffcGbjrrrukAE5lL6HY2Fi5bGhoqNkhUWXvja1mQRFZggEL1cuaq6rOnTvj/PnzqjkNyr2E5CtZlQ8/1YDF0iDE2kRaS3s2ao6t2eSBgN/8Eb5B0lLuZZeOIXfte6guzjMqCzfoD5nshOmpvLVBhYmdj02yNsiyINjz8fExWw/l/kAdOnRAamqq6lopytko8vlZsJmhXvl6ZmMBwJEjR8we++jRo3WHrB2qGQPp9ciG3lCTYaKwPKtIpUFXziqy1ZCJfCGgcn6GPRtPP/00Pv74Y9W9hJ566im5rLz/EaC/N1bNTC9l742tZkERWYIBC9Xr8uWalVgvQJo2egl1H/DQv3rt2bMnftr2k+oaF8oZB/KUWJXVV42mxALWXaGb6fY3edwbqHfPmlpuAW0RPH4BPFp3hBA6FO77FoV7lwHVJhZXqe2ar2d5eVkKLF6QzqogC7Ao2Ovfvz9Onz6tWo8BAwbIN2Vm1kQaKoGQskdNppLMq8qCIEvuyVE5tnJac9++fbHuh3XS+2ZMzWPOQ55h1adPH71j//DDD9IPT0EKDmsDnJrcojVr1sjrtthqyETu2VA5P5M9Gxb2yOht4Kec6aWygZ/NZkER1YMBC9UrLa3msmwN9Bc7q8nFS0lJkT+w09LSzF4Vp6Sk6B9cQMq5UOZKmFvczdor9PGwfPNDC4MKn27DEJg4Ay4eXqiuvIHcnA9Q5pUq/TeZ6jWpzemxdHl5Cxeks2r4qLa8BT1OL730Er7835eq9XjxxRflsnKyq9qMKUWyq1yHZEg9MrV1MDckZObYStHR0WaPrWx0+/bta3aGVb9+/fSObTTjpiZ2qO2tUM5AstWQiV7Pxuj6ezas7ZGxZgM/7p1D9sKAheqVnZ1dl+A5BPo9EBX6CXzy2ioqV5hGibRmjqvagFlzhR4FyzY/tCCouFVRjf9bewxtxj0LACi7mYbcwPdR7XcDiIF6kq6ARcvLy2UtGAKRy1qbw6KShNnQeiQkJODALwdUA6G7777b+LitLawDYP32ChYEs/LmjgWo61FT9OwZLp/fv39/7D+wX7W3Qt6OArYdMrGmZ8PaHpmGBCHcO4eaGgMWqteVK1fM9kDIQQpqkh8B1StMo7VXrB0uqW3AxsKyvBRL813qCSrSrxZjxteHkXGtBEJXjcKfl6Ow/7dAns6y/BELhjVsWbZ169bS7B+VJEzl7BVrhjX0prGbCEJM7l5s7V5CrgbHrlkJWUlODFVpoI0SR2sDJxPvO8PGXM4HUdkS4umnn9Yrb6shE2uCCmt7ZGoxCCFHxoCF6l1iW6PRmO2BUK7TUFpaavaquLS01ODgkK50LRkCAazrJbA26ValgfbpeQ/uX7wHZZU6BPtqcfSf81CefVRaQdfS/BFLAycblW3VqpUUsKgkYbZq1UouW9+6HMok0/Pna25UCYTk+2vVJiAr85tMTK3Wo5IcqyQnjqoMCZlMHN21FdWjquUeFte9phvzmJgYDBg4APv379f/owIYMHCAUXlbD5lYGlQw14SaGwYsLZil60XIy69bMKxRVVVlNqgwmvljzRBILUsXVrMmuAGMGmjNBU8E3vs0WvUYgbJKHQZHt8FHU3oh+OWj1uWPWBM42aisvBicSnnlYnBZWVlml/2/cOGCXFae4qwSCCmnQMu9PCrDWIZrlLi5uaGquqquR602Obamzm6udR9feomjyte7vsTRDZY15sk/JhvneCSazvGoZe/eCuaaUHPDgKUFs3S9iJs3axarUOmBkO+HYtlzlStu+X4la4ZAAOtmxqjUw4hBY+5+uQOCg+bDPTASQleN55O64amhneHiUjPFwpr8EQHLl/23cAhE3rm6wqBsTbBiODXX19dXOkYETOZ4+Pn5GddDJSlVydvb22xwo0y6dXWtWVZX5fVW9tQBUnLsvn37VJ+7vn376pW3ZeKoMzf+9g6ciBoLA5YWypr1Ijp06CDN/lEZIlCutaHVaqXt6FWuuLVarXFlrBkCsXZmjEo9jAhIS9avBlrFJiLwniegcfNAVXEucte9hxnvHjN+jDWBlsqUWJMsGAJxdXWVerNcoL/Ufs3vcnBQIzY2VnoNVXI8lAuJycMrBTCZlKocXgkPDzcb3LRt21a+KTg4GHl5eaqvd0hIiF6dO3fujH3790nHV64P8iuMZv4ATZM4ysafyH5c6i9CzZEliZW1nnrqqboeiDRIuSxpkLvmlUmHbm5udbkEyrI1uQTKoQcAdVfnyrK1Ow6bouzZ8K/5Phbmp/GaqLMpmgleaPPUcwgaMwsaNw/cLDmIK0tno/zicdMPuGDw+3mVOteW7QxgWM13tbK1z10JpOCiBCbXzlAul26K4f2DBg2qO/ZFACE132uOPWjQILls7fAKqiAlpa6p+V5lPLwybNgw/eBmQs33Qum4w4cPl8s+8sgjZl/vRx55RK/Ov/nNb+rW0tkLYF/N9yoAouZ+E6Kjo5GUlMTAgqiZYQ9LC2XNehGJiYnSD6YWYYP+ZnHyqqAqMyoMr/wtHXrQY2nPhhVDMe6hnRActADufhEQogoFuV+iaPlqoEwlE9RWeSlmnjulmTNn4uWXXwaCoT881gbAVeCZZ57RKz906FCzU4oN96KxdHglIiKirs7KGTc1dVbOzpk8eTJeeeUV1dd78uTJesdOTEyEq4eryQ0UXT1cjTYpJKLmjQFLC2XNehGbNm2SGqXxMLkI25YtW+TGw9fXV9ocT6WscjYKAOMVZksh7fSrNsQDWLc0vwZmd2AWQqBV3L0IHPEHaNzcUVV4DdfXvYuKy6fMB07WJPRaWLZTp07SyrDtob92SM3vnTp1km+Kj4+vm7mlfO5qdlRWDvEANb0m94zA9j3bIUYJubxmtwbD7xne4OEVOfB1h/7QlJv0uzLwjYmJwZChQ7Br/y6j13vI0CFGx09PT0d1RbU0/GfwXqpeXc2dgYlaGAYsLZil0x4PHDgg/RAFk4uw7du3Tw5YgoKCcPHiRdWyQUG1N0hX31evXpUSR5VX5zUBRVhYmHGla4c1lL0V5pbmN7MDc+GtSixYeQRBo6V9VW6e24+84r9B169Er/G3aCl/lUDLy8tLyulRSf5VJqW++OKL+MMf/qCaZ/LKK6/IZeW1RPxhcpNJUyuq/vuf/0a/Af2Qt6Vur6PA4ED851//MXGCkvpyNvSmCA+slnu1XNNccc8I4ynCa1avMe65STKdGKs3bGnivcSdgYlaFgYsLZilV9HySp4qPRsJCQnyTcOGDTOboDts2DD5psTERHz55ZdS4KHsUaj5fcyYMXr1kKfFqgyZGE6LBaA6fOQRFo37PtmN7PxbENWVuLF9KYovrTOefWSuh0Ul0FKKjY2V1u9QSf6Ni4uTy0ZERJhdGE85vGLtWiIA8PTMp1Fws0Cvx6ng5wI8NeOp29pF2JopwtYkxnJnYCLSIxrZq6++KiB9bMtfoaGhZh+zY8cOER8fL7RarejYsaP49NNPrf67hYWFAoAoLCxsaNXJjKDgIAEtBB6AwNya71qIoOAgvXKnT58W0EDA06CsJwQ0EOnp6XLZf/3rX9J75EEIzILAIzXfH5DeN//+97/1jv2b3/xGKh+m//5CqPR9+vTpctk2bdrUHfs1xdcDEL597hftn10joub/KAa985MIiomvq/MoCEyo+V5T54CAAL169OrVq+7YCRAIqfleU++4uDi57MaNG6Vjm3juoIHYvHmz/nOHmr+rPD+t9F353AkhRH5+vkhMStQrm5iUKPLz841eP/nYJp4PU8duiPT0dJGcnNwox6qVmJQoXH1c9Z47Vx9XkZiU2Gh/g4jsy9L22yYBS/fu3cWVK1fkr2vXrqmWP3funPD29hbPPPOMOHHihPj3v/8t3N3dxffff2/V32XAYlvnzp2TghZF4xgUHCTOnTtnVDZhYIKAq0Gj6wqRMDBBr5wc3Kg05oYN3xtvvCGV9zIILLyk8m+++aZc9v777zc6tsvEViL4oZdF1PwfRdT8H8WT/zskCm5WiGeeeUauo2GdAYg5c+bcVr39fFtJ5ZXH1kD4+bYyeu7kBnpgTRA0sP4G2pJAITk5Wfq7cw0ClrlSfZKTk1Ufa0/WBGVE5JzsGrDExsZaXP75558XXbt21bvtiSeeEAMGDLDq7zJgaRqbN28Wr7/+ul7PgCFrGpkR94wQcDNozN0gRtwzwqis3Eug0sOibLA3btyoF3R4RHQVbZ/8XETN/1G0//Nq8cJnG4ROp9M/rovBcV3Uex9iusSYDEJiusQYlT137pwIDdEP9kJDTAd7tmqgm6KHxZZs0XtDRI7BrgGLt7e3CA8PFx06dBBTpkwRZ8+eVS0/ePBgMXv2bL3bVq1aJdzc3ERFRYXq48rKykRhYaH8lZ2dzYDFwVjSyFjbQA8ZOkTqyVD2sGghhgwdYlTWr7WfgItG+PV7UB4CivjTv0RA555GZS3tFWpovYWwLNirxeEVImop7BawJCcni++//14cOXJEbNmyRQwdOlSEhoaK3Nxck+Wjo6PFX//6V73bfv75ZwFAXL58WfXvmMqVYcDivCxtoK0JFFKOp4u2096Uh4DajHtOBEW0bdSeDWe68ufwChE5IksDFo0QwtSkzUZTWlqKzp074/nnn8e8efOM7o+JicFvf/tbvPDCC/JtP//8MwYNGoQrV66YntoKoLy8HOXl5fLvRUVFiIyMRGFhofG+KNTs1DfL5JfMfMxenoKcojK4uwB93S7g8UF3YPTo0bd13OagJZwjETmPoqIi+Pv719t+23xas4+PD3r27ImMjAyT94eFhSEnJ0fvtmvXrsHNzU1vzQ5DWq3W9L401CKorQ+i0wl8uvMsPtySjmqdQKdgHyyZFo87w++9reM2Jy3hHImo+bF5wFJeXo6TJ09i8ODBJu9PSEjADz/8oHfb5s2b0adPH+N9Z4jMyC0px9wVqdidkQsAeDCuLd6Y0AM+Wi43RETk7Bp988Nnn30WO3fuRGZmJg4cOICHHnoIRUVFeOyxxwAAL7zwAqZPny6Xf/LJJ3HhwgXMmzcPJ0+exOeff47PPvsMzz77bGNXjZqxvWdzkfTxbuzOyIWnuwvefegufDA5lsEKEVEz0eif5hcvXsTUqVORm5uL4OBgDBgwAPv370dUlLTk6JUrV5CVlSWX79ixI5KTkzF37lwsWbIEERERWLRoESZOnNjYVaNmqFon8Mm2DCz6KQM6AUSHtMLfH4lHdKivvatGRESNyOZJt03F0qQdaj6uFZVhzopU7D0r7Y0zuU87vH5/D3h5uNbzSCIichQOk3RLZAu7M65j7opU5JZUwNvDFX99oAceiGtn72oREZGNMGAhp1JVrcPftmZgyY4zEALoGuaLxdPicUdIK3tXjYiIbIgBCzmNK4W38MzyVPxyPh8AMK1/e/zffd3g6c4hICKi5o4BCzmF7aevYd6KVNy4WYlWWje89WBP3B8bYe9qERFRE2HAQg6tslqH9zefxj93ngMA9Gjrh8VT49GhjY+da0ZERE2JAQs5rEsFtzBr2WEczioAADyWEIUX770TWjcOARERtTQMWMghbTlxFc9+l4bCW5Xw9XTDuxPvQlLPcHtXi4iI7IQBCzmUiiod3tl4Cp/tyQQAxLbzx+Jp8YgM9LZzzYiIyJ4YsJDDyM6/iZnLU5CWXQAA+P2gjpg/pis83Bp9BwkiInIyDFjIIWw8dgXPfX8ExWVV8Pdyx/uTYjGqW6i9q0VERA6CAQvZVXlVNd5afxL/3XcBABDfvjUWTY1DuwAOARERUR0GLGQ353NLMXP5YRy7VAQAeGJoJzw7ugvcXTkERERE+hiwkF38eOQyFqw8ipLyKgR4u+PDyb0wvGuIvatFREQOigELNamyymr85ccTWHYgCwDQt0MAFk2NQ7i/l51rRkREjowBCzWZs9dLMOPrwziVUwyNBpgx7A7MuScabhwCIiKiejBgoSaxOuUiXlp9DDcrqtGmlQc+mtILg6OD7V0tIiJyEgxYyKZuVVTj1XXH8O2hiwCAhE5B+PjhXgjx87RzzYiIyJkwYCGbybhajBnLDiP9agk0GuCZkdGYNSIari4ae1eNiIicDAMWsonvDmXjlbXHUFapQ7CvFh8/3AsDO7exd7WIiMhJMWChRlVaXoVX1h7DqsOXAACDo9vgw8m9EOyrtXPNiIjImTFgoUZzKqcIM74+jLPXS+GiAf48ugueGtoZLhwCIiKi28SAhW6bEALfHMzGa+uOo7xKhzA/TyyaGod+HQPtXTUiImomGLDQbSkuq8SLq4/hh7TLAIBhXYLx4eReCPTxsHPNiIioOWHAQg127FIhZi47jPN5N+HqosHziV3wx8GdOARERESNjgELWU0Iga/2X8AbP55ERbUObVt7YdHUOPSOCrB31YiIqJliwEJWKSqrxIKVR5B8NAcAcM+doXh/0l1o7c0hICIish0GLGSxtOwCzFx+GNn5t+DuqsGCpDvxu7s7QKPhEBAREdkWAxaqlxACS38+j4UbTqKyWqBdgBeWTItHbGRre1eNiIhaCAYsZFbBzQo89/0RbDlxFQAwpnsY3nnoLvh7udu5ZkRE1JIwYCFVh7NuYNayFFwquAUPVxe8fN+deHRAFIeAiIioyTFgISM6ncB/9pzDuxtPo0onEBXkjSXT4tGjrb+9q0ZERC2US2MfcOHChejbty98fX0REhKCCRMm4PTp02Yfs2PHDmg0GqOvU6dONXb1qB75pRX4w5eH8FbyKVTpBO67Kxw/zhrEYIWIiOyq0XtYdu7ciRkzZqBv376oqqrCSy+9hNGjR+PEiRPw8fEx+9jTp0/Dz89P/j04OLixq0dmHDyfj9nLU3ClsAwebi54bVx3TO0XySEgIiKyu0YPWDZu3Kj3+9KlSxESEoJff/0VQ4YMMfvYkJAQtG7durGrRPXQ6QQ+3XkWH25JR7VOoFOwD5ZMi8ed4X71P5iIiKgJ2DyHpbCwEAAQGFj/RnhxcXEoKytDt27d8PLLL2P48OGqZcvLy1FeXi7/XlRUdPuVbYFyS8oxd0UqdmfkAgAeiGuLNyf0gI+W6U1EROQ4Gj2HRUkIgXnz5mHQoEHo0aOHarnw8HD861//wsqVK7Fq1Sp06dIFI0eOxK5du1Qfs3DhQvj7+8tfkZGRtjiFZm3f2TyM/Xg3dmfkwtPdBe8+dBc+nBzLYIWIiByORgghbHXwGTNmYP369dizZw/atWtn1WPHjRsHjUaDdevWmbzfVA9LZGQkCgsL9fJgyFi1TmDxtjP4+Kd06AQQHdIKSx6JR0yor72rRkRELUxRURH8/f3rbb9tdik9a9YsrFu3Drt27bI6WAGAAQMG4KuvvlK9X6vVQqvV3k4VW6RrxWWY800q9p7NAwBM6t0Or4/vDm8P9qoQEZHjavRWSgiBWbNmYfXq1dixYwc6duzYoOOkpKQgPDy8kWvXsu3JyMWcFSnILamAt4cr3pzQAw/GWx9MEhERNbVGD1hmzJiBZcuWYe3atfD19UVOjrSrr7+/P7y8vAAAL7zwAi5duoQvv/wSAPC3v/0NHTp0QPfu3VFRUYGvvvoKK1euxMqVKxu7ei1SVbUOH/+UgcXbz0AIoGuYLxZPi8cdIa3sXTUiIiKLNHrA8umnnwIAhg0bpnf70qVL8fjjjwMArly5gqysLPm+iooKPPvss7h06RK8vLzQvXt3rF+/HmPHjm3s6rU4OYVlmP1NCn7JzAcATO3XHq+O6wZPd1c714yIiMhyNk26bUqWJu20JDtOX8O8b9OQX1oBHw9XLJx4F+6PjbB3tYiIiGR2T7ol+6ms1uGDzen4x86zAIDuEX5YPC0eHduYX2mYiIjIUTFgaWYuFdzC7OUp+PXCDQDA9IQovDj2Tg4BERGRU2PA0oxsPXEVz36fhoKblfD1dMO7E+9CUk/OtCIiIufHgKUZqKjS4d2Np/CfPZkAgNh2/vhkajzaB3nbuWZERESNgwGLk8vOv4mZy1OQll0AAPjd3R2xIKkrPNxsuusCERFRk2LA4sQ2HsvBc9+nobisCn6ebnh/UixGdw+zd7WIiIgaHQMWJ1ReVY2Fyafwxd7zAIC49q3xydQ4tAvgEBARETVPDFiczIW8UsxcloKjlwoBAE8M6YRnE7vA3ZVDQERE1HwxYHEiPx65jAUrj6KkvAoB3u74YHIsRnQNtXe1iIiIbI4BixMoq6zGGz+ewNcHpO0M+nYIwKKpcQj397JzzYiIiJoGAxYHd+56CWYsS8HJK0XQaICnh3XG3Hti4MYhICIiakEYsDiwNSmX8OLqo7hZUY0gHw98NKUXhsQE27taRERETY4BiwO6VVGN19Ydx4pD2QCAAZ0CsejhOIT4edq5ZkRERPbBgMXBZFwtxoxlh5F+tQQaDTB7RDRmj4yGq4vG3lUjIiKyGwYsDuS7Q9n4v7XHcauyGsG+Wnw8pRcG3tHG3tUiIiKyOwYsDqC0vAqvrD2GVYcvAQAG3dEGH03phWBfrZ1rRkRE5BgYsNjZqZwizPj6MM5eL4WLBpg3KgZPD7sDLhwCIiIikjFgsRMhBFYczMar646jvEqHUD8tFj0ch/6dguxdNSIiIofDgMUOSsqr8OKqo1iXdhkAMDQmGB9OjkVQKw4BERERmcKApYkdv1yImctSkJlbClcXDZ5L7II/De7EISAiIiIzGLA0ESEEvtp/AW+sP4mKKh0i/D3xybQ49I4KtHfViIiIHB4DliZQVFaJBSuPIPloDgDgnjtD8N5DsQjw8bBzzYiIiJwDAxYbO3KxADOXpSAr/ybcXTWYP6Yrfj+oIzQaDgERERFZigGLjQghsPTn81i44SQqqwXaBXhh8bR49Ipsbe+qEREROR0GLDZQeLMSz32fhs0nrgIAxnQPwzsP3QV/L3c714yIiMg5MWBpZClZNzBzWQouFdyCh6sLXrr3TkxPiOIQEBER0W1gwNJIdDqBz/Zk4p2Np1ClE4gK8sbiqfHo2c7f3lUjIiJyegxYGsGN0gr8+bs0bDt1DQBw713hePvBnvD15BAQERFRY2DAcpsOnc/HrOUpuFJYBg83F7w6rhum9WvPISAiIqJGxIClgXQ6gX/sOosPNqejWifQqY0PFk+LR7cIP3tXjYiIqNlhwNIAuSXlmPdtGnalXwcATOgVgTcf6IlWWj6dREREtuBiqwP//e9/R8eOHeHp6YnevXtj9+7dZsvv3LkTvXv3hqenJzp16oR//OMftqrabdl/Lg9jP96NXenX4enugncn3oWPpvRisEJERGRDNglYVqxYgTlz5uCll15CSkoKBg8ejKSkJGRlZZksn5mZibFjx2Lw4MFISUnBiy++iNmzZ2PlypW2qF6DVOsEPt6agWn/3o9rxeW4I6QV1s0chMl9I5mvQkREZGMaIYRo7IP2798f8fHx+PTTT+Xb7rzzTkyYMAELFy40Kj9//nysW7cOJ0+elG978sknkZaWhn379ln0N4uKiuDv74/CwkL4+TVuHsm14jLMXZGKn8/kAQAm9W6H18d3h7cHe1WIiIhuh6Xtd6P3sFRUVODXX3/F6NGj9W4fPXo09u7da/Ix+/btMyqfmJiIQ4cOobKy0uRjysvLUVRUpPdlCz+fycXYj/fg5zN58HJ3xYeTY/HepFgGK0RERE2o0QOW3NxcVFdXIzQ0VO/20NBQ5OTkmHxMTk6OyfJVVVXIzc01+ZiFCxfC399f/oqMjGycE1C4VVGNZ75JRW5JObqG+eKHWYPwYHy7Rv87REREZJ7Nkm4N8zqEEGZzPUyVN3V7rRdeeAGFhYXyV3Z29m3W2JiXhys+mByLqf3aY82Mu3FHSKtG/xtERERUv0Yf12jTpg1cXV2NelOuXbtm1ItSKywszGR5Nzc3BAUFmXyMVquFVqttnEqbMTQmGENjgm3+d4iIiEhdo/eweHh4oHfv3tiyZYve7Vu2bMHAgQNNPiYhIcGo/ObNm9GnTx+4u3N5eyIiopbOJkNC8+bNw3/+8x98/vnnOHnyJObOnYusrCw8+eSTAKThnOnTp8vln3zySVy4cAHz5s3DyZMn8fnnn+Ozzz7Ds88+a4vqERERkZOxyVSXKVOmIC8vD3/5y19w5coV9OjRA8nJyYiKigIAXLlyRW9Nlo4dOyI5ORlz587FkiVLEBERgUWLFmHixIm2qB4RERE5GZusw2IPtlyHhYiIiGzDbuuwEBERETU2BixERETk8BiwEBERkcNjwEJEREQOjwELEREROTwGLEREROTwGLAQERGRw2PAQkRERA6PAQsRERE5PJsszW8PtQv2FhUV2bkmREREZKnadru+hfebTcBSXFwMAIiMjLRzTYiIiMhaxcXF8Pf3V72/2ewlpNPpcPnyZfj6+kKj0TTacYuKihAZGYns7Oxmu0dRcz9Hnp/za+7nyPNzfs39HG15fkIIFBcXIyIiAi4u6pkqzaaHxcXFBe3atbPZ8f38/Jrlm1CpuZ8jz8/5Nfdz5Pk5v+Z+jrY6P3M9K7WYdEtEREQOjwELEREROTwGLPXQarV49dVXodVq7V0Vm2nu58jzc37N/Rx5fs6vuZ+jI5xfs0m6JSIiouaLPSxERETk8BiwEBERkcNjwEJEREQOjwELEREROTwGLAD+/ve/o2PHjvD09ETv3r2xe/dus+V37tyJ3r17w9PTE506dcI//vGPJqqp9RYuXIi+ffvC19cXISEhmDBhAk6fPm32MTt27IBGozH6OnXqVBPV2nKvvfaaUT3DwsLMPsaZXr8OHTqYfC1mzJhhsrwzvHa7du3CuHHjEBERAY1GgzVr1ujdL4TAa6+9hoiICHh5eWHYsGE4fvx4vcdduXIlunXrBq1Wi27dumH16tU2OgPzzJ1fZWUl5s+fj549e8LHxwcRERGYPn06Ll++bPaYX3zxhcnXtayszMZnY1p9r+Hjjz9uVNcBAwbUe1xneA0BmHwtNBoN3nvvPdVjOtJraEm74Ij/hy0+YFmxYgXmzJmDl156CSkpKRg8eDCSkpKQlZVlsnxmZibGjh2LwYMHIyUlBS+++CJmz56NlStXNnHNLbNz507MmDED+/fvx5YtW1BVVYXRo0ejtLS03seePn0aV65ckb+io6OboMbW6969u149jx49qlrW2V6/gwcP6p3bli1bAACTJk0y+zhHfu1KS0sRGxuLxYsXm7z/3XffxYcffojFixfj4MGDCAsLw6hRo+T9wkzZt28fpkyZgkcffRRpaWl49NFHMXnyZBw4cMBWp6HK3PndvHkThw8fxiuvvILDhw9j1apVSE9Px/3331/vcf38/PRe0ytXrsDT09MWp1Cv+l5DABgzZoxeXZOTk80e01leQwBGr8Pnn38OjUaDiRMnmj2uo7yGlrQLDvl/KFq4fv36iSeffFLvtq5du4oFCxaYLP/888+Lrl276t32xBNPiAEDBtisjo3p2rVrAoDYuXOnapnt27cLAOLGjRtNV7EGevXVV0VsbKzF5Z399XvmmWdE586dhU6nM3m/M712QggBQKxevVr+XafTibCwMPH222/Lt5WVlQl/f3/xj3/8Q/U4kydPFmPGjNG7LTExUTz88MONXmdrGJ6fKb/88osAIC5cuKBaZunSpcLf379xK9dITJ3jY489JsaPH2/VcZz5NRw/frwYMWKE2TKO/BoatguO+n/YontYKioq8Ouvv2L06NF6t48ePRp79+41+Zh9+/YZlU9MTMShQ4dQWVlps7o2lsLCQgBAYGBgvWXj4uIQHh6OkSNHYvv27bauWoNlZGQgIiICHTt2xMMPP4xz586plnXm16+iogJfffUVfve739W7waezvHaGMjMzkZOTo/caabVaDB06VPV/ElB/Xc09xlEUFhZCo9GgdevWZsuVlJQgKioK7dq1w3333YeUlJSmqWAD7dixAyEhIYiJicEf//hHXLt2zWx5Z30Nr169ivXr1+P3v/99vWUd9TU0bBcc9f+wRQcsubm5qK6uRmhoqN7toaGhyMnJMfmYnJwck+WrqqqQm5trs7o2BiEE5s2bh0GDBqFHjx6q5cLDw/Gvf/0LK1euxKpVq9ClSxeMHDkSu3btasLaWqZ///748ssvsWnTJvz73/9GTk4OBg4ciLy8PJPlnfn1W7NmDQoKCvD444+rlnGm186U2v87a/4nax9n7WMcQVlZGRYsWIBp06aZ3VCua9eu+OKLL7Bu3TosX74cnp6euPvuu5GRkdGEtbVcUlISvv76a2zbtg0ffPABDh48iBEjRqC8vFz1Mc76Gv73v/+Fr68vHnzwQbPlHPU1NNUuOOr/YbPZrfl2GF6tCiHMXsGaKm/qdkczc+ZMHDlyBHv27DFbrkuXLujSpYv8e0JCArKzs/H+++9jyJAhtq6mVZKSkuSfe/bsiYSEBHTu3Bn//e9/MW/ePJOPcdbX77PPPkNSUhIiIiJUyzjTa2eOtf+TDX2MPVVWVuLhhx+GTqfD3//+d7NlBwwYoJe0evfddyM+Ph6ffPIJFi1aZOuqWm3KlCnyzz169ECfPn0QFRWF9evXm23Yne01BIDPP/8cjzzySL25KI76GpprFxzt/7BF97C0adMGrq6uRtHftWvXjKLEWmFhYSbLu7m5ISgoyGZ1vV2zZs3CunXrsH37drRr187qxw8YMMDuVwKW8PHxQc+ePVXr6qyv34ULF7B161b84Q9/sPqxzvLaAZBneFnzP1n7OGsfY0+VlZWYPHkyMjMzsWXLFrO9K6a4uLigb9++TvO6hoeHIyoqymx9ne01BIDdu3fj9OnTDfq/dITXUK1dcNT/wxYdsHh4eKB3797yzItaW7ZswcCBA00+JiEhwaj85s2b0adPH7i7u9usrg0lhMDMmTOxatUqbNu2DR07dmzQcVJSUhAeHt7ItWt85eXlOHnypGpdne31q7V06VKEhITg3nvvtfqxzvLaAUDHjh0RFham9xpVVFRg586dqv+TgPrrau4x9lIbrGRkZGDr1q0NCpSFEEhNTXWa1zUvLw/Z2dlm6+tMr2Gtzz77DL1790ZsbKzVj7Xna1hfu+Cw/4eNkrrrxL755hvh7u4uPvvsM3HixAkxZ84c4ePjI86fPy+EEGLBggXi0UcflcufO3dOeHt7i7lz54oTJ06Izz77TLi7u4vvv//eXqdg1lNPPSX8/f3Fjh07xJUrV+SvmzdvymUMz/Gjjz4Sq1evFunp6eLYsWNiwYIFAoBYuXKlPU7BrD//+c9ix44d4ty5c2L//v3ivvvuE76+vs3m9RNCiOrqatG+fXsxf/58o/uc8bUrLi4WKSkpIiUlRQAQH374oUhJSZFnybz99tvC399frFq1Shw9elRMnTpVhIeHi6KiIvkYjz76qN5Mvp9//lm4urqKt99+W5w8eVK8/fbbws3NTezfv9+hzq+yslLcf//9ol27diI1NVXvf7K8vFz1/F577TWxceNGcfbsWZGSkiJ++9vfCjc3N3HgwIEmPz8hzJ9jcXGx+POf/yz27t0rMjMzxfbt20VCQoJo27Zts3gNaxUWFgpvb2/x6aefmjyGI7+GlrQLjvh/2OIDFiGEWLJkiYiKihIeHh4iPj5eb8rvY489JoYOHapXfseOHSIuLk54eHiIDh06qL5hHQEAk19Lly6Vyxie4zvvvCM6d+4sPD09RUBAgBg0aJBYv35901feAlOmTBHh4eHC3d1dREREiAcffFAcP35cvt/ZXz8hhNi0aZMAIE6fPm10nzO+drVTrw2/HnvsMSGENKXy1VdfFWFhYUKr1YohQ4aIo0eP6h1j6NChcvla3333nejSpYtwd3cXXbt2tVuQZu78MjMzVf8nt2/fLh/D8PzmzJkj2rdvLzw8PERwcLAYPXq02Lt3b9OfXA1z53jz5k0xevRoERwcLNzd3UX79u3FY489JrKysvSO4ayvYa1//vOfwsvLSxQUFJg8hiO/hpa0C474f6ipqTwRERGRw2rROSxERETkHBiwEBERkcNjwEJEREQOjwELEREROTwGLEREROTwGLAQERGRw2PAQkRERA6PAQsRERE5PAYsRERE5PAYsBAREZHDY8BCREREDo8BCxERETm8/wcgOucviqhgWQAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.12129447943215599\n", "0.14153111901273285\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiwAAAGdCAYAAAAxCSikAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAABwSklEQVR4nO3deVxU5f4H8M8My7AIKMiqqGiguQPupbmkSGVqpZZL9rvdW6aZ5a3MllvdunKzui2aWt1uVphpKmpuqLnnkqKYuYALiguIgDAsss2c3x+HOZwDM8MMMs4An/frxQuYOXPmObOd7zzP9/k+KkEQBBARERE5MLW9G0BERERUGwYsRERE5PAYsBAREZHDY8BCREREDo8BCxERETk8BixERETk8BiwEBERkcNjwEJEREQOz9neDagver0e165dg5eXF1Qqlb2bQ0RERBYQBAEFBQUICQmBWm26H6XRBCzXrl1DaGiovZtBREREdXD58mW0bt3a5PWNJmDx8vICIB6wt7e3nVtDREREltBqtQgNDZXO46Y0moDFMAzk7e3NgIWIiKiBqS2dg0m3RERE5PAYsBAREZHDY8BCREREDo8BCxERETk8BixERETk8BiwEBERkcNjwEJEREQOjwELEREROTwGLEREROTwrApY4uLi0Lt3b3h5eSEgIABjxoxBSkqKYhtBEPDOO+8gJCQE7u7uGDx4ME6ePFnrvlevXo3OnTtDo9Ggc+fOSEhIsO5IiIiIqNGyKmDZvXs3ZsyYgYMHD2Lbtm2oqKjAiBEjUFRUJG0zf/58/Oc//8HChQtx+PBhBAUFYfjw4SgoKDC53wMHDmDChAmYMmUKjh8/jilTpmD8+PE4dOhQ3Y+MiIiIGg2VIAhCXW9848YNBAQEYPfu3Rg0aBAEQUBISAhefPFFzJkzBwBQWlqKwMBAfPDBB3j22WeN7mfChAnQarXYvHmzdNnIkSPRokULLF++3KK2aLVa+Pj4ID8/n2sJERERNRCWnr9vK4clPz8fAODr6wsASEtLQ2ZmJkaMGCFto9FocN9992H//v0m93PgwAHFbQAgJibG7G1KS0uh1WoVP0RERE2ZtqQc035Iwp7UG/ZuSr2rc8AiCAJmz56Ne++9F127dgUAZGZmAgACAwMV2wYGBkrXGZOZmWn1beLi4uDj4yP9hIaG1vVQiIiIGryUzAKMXvgbtpzMxCurjqOkXGfvJtWrOgcszz//PP744w+jQzbVl4gWBKHWZaOtvc3cuXORn58v/Vy+fNmK1hMRETUe649fw5gvfkNadhFCfNzw1ZRecHNxsnez6pVzXW40c+ZMrF+/Hnv27EHr1q2ly4OCggCIPSbBwcHS5VlZWTV6UOSCgoJq9KbUdhuNRgONRlOX5hMRETUK5To94jadwf9+SwMA3HOXHz5/PBJ+zRrf+dGqHhZBEPD8889jzZo12LFjB8LCwhTXh4WFISgoCNu2bZMuKysrw+7duzFgwACT++3fv7/iNgCwdetWs7chIiJqyrIKSjDp60NSsDJ9cAd8/5e+jTJYAazsYZkxYwZ+/PFHrFu3Dl5eXlKviI+PD9zd3aFSqfDiiy9i3rx5CA8PR3h4OObNmwcPDw9MnDhR2s+TTz6JVq1aIS4uDgAwa9YsDBo0CB988AFGjx6NdevWYfv27di3b189HioREVHjcPhiLmYsO4qsglJ4aZzx0fgeiOkSZO9m2ZRVAcvixYsBAIMHD1Zc/u233+Kpp54CALz66qu4desWpk+fjps3b6Jv377YunUrvLy8pO3T09OhVld17gwYMAA//fQT3nzzTbz11lvo0KEDVqxYgb59+9bxsIiIiBofQRCwdP9F/GvjaVToBUQENsOSydFo79/M3k2zuduqw+JIWIeFiIgas+KyCsxdcwLrkq8BAB7qHowPHu0OT02d0lEdhqXn74Z9lERERE1AWnYRpv2QhJTrBXBSq/D6A3fjL/e0q3UGbmPCgIWIiMiBbTt1HbNXJKOgtAItm2mwaFIU+oT52rtZdxwDFiIiIgek0wv4ZFsqFu48BwDo1bYFvpgUhUBvNzu3zD4YsBARETmY3KIyzPrpGPaezQYAPDWgHd548G64ON3WijoNGgMWIiIiB/LHlTw8F38UV/Nuwd3FCf9+tBtG92xl72bZHQMWIiIiB7HicDreWncSZRV6tPPzwJIp0egUxJmvAAMWIiIiuysp1+Gd9Sfx02FxXbz77w7Ax+N7wsfdxc4tcxwMWIiIiOzoys1iTF92FH9cyYdKBbw8oiOeu68D1OqmM2XZEgxYiIiI7GTv2Rt4Yfkx3CwuRwsPF3z2eCQGRfjbu1kOiQELERHRHabXC1i8+zw+2poCQQC6tfLB4slRaN3Cw95Nc1gMWIiIiO4gbUk5/r7yOLadug4AmNArFO+O7gI3Fyc7t8yxMWAhIiK6Q1IyC/DsD0dwMacYrk5q/HN0Fzzep429m9UgMGAhIiK6A9YlX8Vrq0/gVrkOrZq7Y9GkKPQIbW7vZjUYDFiIiIhsqFynx7xNp/HtbxcBAAPDW+KzxyPh6+lq34Y1MAxYiIiIbCRLW4Lpy47iyKWbAIAZQzpg9vCOcOKUZasxYCEiIrKB39NyMePHo7hRUAovjTM+Ht8DI7oE2btZDRYDFiIionokCAK+/e0i5m06jQq9gIjAZlgyORrt/ZvZu2kNGgMWIiKielJcVoHXVp/A+uPXAAAP9wjBvx/tBg9Xnm5vFx9BIiKiepCWXYRpPyQh5XoBnNUqvPHg3XhqQDuoVMxXqQ8MWIiIiG7T1pOZ+PvK4ygorYC/lwaLJkWhdztfezerUWHAQkREVEc6vYCPt6Zg0a7zAIDe7Vrgi4lRCPB2s3PLGh8GLERERHWQW1SGF5Yfw75z2QCA/7unHV5/4G64OKnt3LLGiQELERGRlY5fzsP0ZUdxNe8W3F2c8O9Hu2F0z1b2blajxoCFiIjICj/9no5/rDuJMp0eYS09sWRyNDoGedm7WY0eAxYiIiILlJTr8Pa6k1hx5DIAYHjnQHw8vge83Vzs3LKmgQELERFRLS7nFmP6sqM4cTUfahXw9xEd8dx9HaBmif07hgELERGRGXtSb+CFn44hr7gcLTxc8PkTkRgY7m/vZjU5DFiIiIiM0OsFLNp1Dh9vS4UgAN1b+2DRpCi0buFh76Y1SQxYiIiIqsm/VY6/rzyO7aevAwCe6BOKt0d1gZuLk51b1nQxYCEiIpI5k6nFtB+ScDGnGK7Oarw3ugsm9G5j72Y1eQxYiIiIKq1Lvoo5q/9ASbkerZq7Y/HkKHRv3dzezSIAVpfj27NnD0aNGoWQkBCoVCqsXbtWcb1KpTL68+GHH5rc59KlS43epqSkxOoDIiIislZZhR7vrD+JWT8lo6Rcj4HhLfHLzHsZrDgQq3tYioqK0KNHD/zf//0fHn300RrXZ2RkKP7fvHkznn76aaPbynl7eyMlJUVxmZsb12IgIiLbuq4twYxlR3Hk0k0AwPND7sJLwyPgxCnLDsXqgCU2NhaxsbEmrw8KClL8v27dOgwZMgTt27c3u1+VSlXjtkRERLb0e1ouZvx4FDcKSuGlccZ/JvTE8M6B9m4WGWHTHJbr169j48aN+O6772rdtrCwEG3btoVOp0PPnj3x3nvvITIy0uT2paWlKC0tlf7XarX10mYiImr8BEHA/367iHmbTkOnF9Ax0AtLpkQjrKWnvZtGJth0ScnvvvsOXl5eeOSRR8xu16lTJyxduhTr16/H8uXL4ebmhnvuuQdnz541eZu4uDj4+PhIP6GhofXdfCIiaoSKSiswc/kxvLfhFHR6AaN7hiBhxgAGKw5OJQiCUOcbq1RISEjAmDFjjF7fqVMnDB8+HAsWLLBqv3q9HlFRURg0aBA+//xzo9sY62EJDQ1Ffn4+vL29rbo/IiJqGi7cKMS0+CSkXi+Es1qFNx+8G1MHtINKxXwVe9FqtfDx8an1/G2zIaG9e/ciJSUFK1assPq2arUavXv3NtvDotFooNFobqeJRETUhCSezMTfVx5HYWkF/L00WDQpCr3b+dq7WWQhmwUs33zzDaKjo9GjRw+rbysIApKTk9GtWzcbtIyIiJoSnV7AR1tTsHjXeQBAn3a+WDgxEgHenInakFgdsBQWFuLcuXPS/2lpaUhOToavry/atBErAWq1Wvz888/4+OOPje7jySefRKtWrRAXFwcAePfdd9GvXz+Eh4dDq9Xi888/R3JyMr744ou6HBMREREAIKewFLN+Ssa+c9kAgKfvDcNrsZ3g4mTTFE6yAasDliNHjmDIkCHS/7NnzwYATJ06FUuXLgUA/PTTTxAEAU888YTRfaSnp0Otrnqx5OXl4ZlnnkFmZiZ8fHwQGRmJPXv2oE+fPtY2j4iICACQfDkP0+OTcC2/BO4uTvjgse54uEeIvZtFdXRbSbeOxNKkHSIiatwEQcDy3y/jnfUnUabTI6ylJ76cEo2IQC97N42MsHvSLRER0Z1WUq7DP9b9iZVHrgAARnQOxEfje8DbzcXOLaPbxYCFiIgahcu5xXhuWRL+vKqFWgW8HNMR0wZ1gJol9hsFBixERNTg7U69gVk/HUNecTl8PV3x+eORuDe8pb2bRfWIAQsRETVYer2AL3aew3+2p0IQgB6tfbBocjRaNXe3d9OonjFgISKiBin/Vjlmr0jGr2eyAABP9GmDt0d1hpuLk51bRrbAgIWIiBqc0xlaTItPwqWcYrg6q/H+6K4Y35tryjVmDFiIiKhBWXvsKl5b8wdKyvVo1dwdSyZHo1trH3s3i2yMAQsRETUIZRV6zNt0Gkv3XwQADIrwx2cTeqKFp6t9G0Z3BAMWIiJyeNe1JZi+7CiSLt0EALww9C7Muj8CTpyy3GQwYCEiIod28EIOnv/xGLILS+Hl5oxPxvfE/Z0D7d0susMYsBARkUMSBAHf7EtD3OYz0OkFdArywpLJ0WjX0tPeTSM7YMBCREQOp6i0Aq+u/gMb/8gAAIzuGYK4R7rBw5WnraaKzzwRETmU8zcKMe2HJJzNKoSzWoW3HuqMJ/u3hUrFfJWmjAELERE5jC1/ZuLln4+jsLQCAV4aLJ4chei2vvZuFjkABixERGR3FTo9PtqaiiW7zwMA+oT5YuHESAR4udm5ZeQoGLAQEZFd5RSWYubyY9h/PgcA8Nd7wzAnthNcnNR2bhk5EgYsRERkN8mX8/BcfBIy8kvg4eqEDx7tjlE9QuzdLHJADFiIiOiOEwQBy3+/jHfWn0SZTo/2LT2xZEo0IgK97N00clAMWIiI6I4qKdfhrbV/4uekKwCAmC6B+GhcD3i5udi5ZeTIGLAQEdEdczm3GNPik3DymhZqFfBKTCdMu689pyxTrRiwEBHRHbErJQuzfkpG/q1y+Hq6YsETkbjnrpb2bhY1EAxYiIjIpvR6AQt3nsMn21MhCECP1j5YNDkarZq727tp1IAwYCEiIpvJv1WO2SuS8euZLADAxL5t8PaoztA4O9m5ZdTQMGAhIiKbOJ2hxbT4JFzKKYarsxrvj+mK8b1C7d0saqAYsBARUb1LOHYFc9ecQEm5Hq1buGPJ5Gh0beVj72ZRA8aAhYiI6k1ZhR7vbzyF7w9cAgAMivDHZxN6ooWnq51bRg0dAxYiIqoXmfklmL4sCUfT8wAALwy9C7Puj4CTmlOW6fYxYCEiott28EIOnv/xKLILy+Dl5oxPJ/TEsLsD7d0sakQYsBARUZ0JgoBv9qUhbvMZ6PQCOgV5YcnkaLRr6WnvplEjw4CFiIjqpLC0AnNW/YGNJzIAAGMjW2He2G5wd+WUZap/DFiIiMhq57IKMS0+CeeyCuGsVuEfozpjSr+2LLFPNqO29gZ79uzBqFGjEBISApVKhbVr1yquf+qpp6BSqRQ//fr1q3W/q1evRufOnaHRaNC5c2ckJCRY2zQiIroDtvyZgTFf/IZzWYUI9NZgxbP98GT/dgxWyKasDliKiorQo0cPLFy40OQ2I0eOREZGhvSzadMms/s8cOAAJkyYgClTpuD48eOYMmUKxo8fj0OHDlnbPCIispEKnR5xm09jWvxRFJZWoE+YL36ZeS+i2/rau2nUBKgEQRDqfGOVCgkJCRgzZox02VNPPYW8vLwaPS/mTJgwAVqtFps3b5YuGzlyJFq0aIHly5dbtA+tVgsfHx/k5+fD29vb4vsmIqLaZReW4oXlx7D/fA4A4K/3hmFObCe4OFn9vZdIwdLzt01eabt27UJAQAAiIiLwt7/9DVlZWWa3P3DgAEaMGKG4LCYmBvv37zd5m9LSUmi1WsUPERHVv2PpNzFqwT7sP58DD1cnLJwYiTcf6sxghe6oen+1xcbGYtmyZdixYwc+/vhjHD58GEOHDkVpaanJ22RmZiIwUDlfPzAwEJmZmSZvExcXBx8fH+knNJTrUxAR1SdBEBB/8BImfHkQGfklaO/viXUz7sFD3UPs3TRqgup9ltCECROkv7t27YpevXqhbdu22LhxIx555BGTt6uerCUIgtkErrlz52L27NnS/1qtlkELEVE9KSnX4Y2EP7H66BUAwMguQfhwXHd4ubnYuWXUVNl8WnNwcDDatm2Ls2fPmtwmKCioRm9KVlZWjV4XOY1GA41GU2/tJCIi0eXcYjz7QxJOZWihVgGvjuyEZwe15ywgsiubD0Dm5OTg8uXLCA4ONrlN//79sW3bNsVlW7duxYABA2zdPCIiktmZkoWHFuzDqQwtfD1dEf90X0y7rwODFbI7q3tYCgsLce7cOen/tLQ0JCcnw9fXF76+vnjnnXfw6KOPIjg4GBcvXsTrr7+Oli1bYuzYsdJtnnzySbRq1QpxcXEAgFmzZmHQoEH44IMPMHr0aKxbtw7bt2/Hvn376uEQiYioNnq9gAU7zuHTX1MhCECP0OZYPCkKIc3d7d00IgB1CFiOHDmCIUOGSP8b8kimTp2KxYsX48SJE/j++++Rl5eH4OBgDBkyBCtWrICXl5d0m/T0dKjVVZ07AwYMwE8//YQ333wTb731Fjp06IAVK1agb9++t3NsRERkgfzicry0Mhk7zogzOif1bYN/jOoMjTNL7JPjuK06LI6EdViIiKx38lo+nos/ivTcYmic1Xh/TFeM68UJDHTnWHr+5lpCRERN1JqjVzB3zQmUVujRuoU7lkyORtdWPvZuFpFRDFiIiJqYsgo93ttwCj8cvAQAuC/CH5893hPNPVzt3DIi0xiwEBE1IZn5JXhuWRKOpecBAGYNC8cLw8LhpOYsIHJsDFiIiJqIA+dzMHP5UWQXlsHbzRmfPt4TQzuZrndF5EgYsBARNXKCIODrvRfwwZYU6PQC7g72xpLJUWjr52nvphFZjAELEVEjVlhagVdXHcemE2I18UciW+FfY7vB3ZVTlqlhYcBCRNRIncsqxLM/HMH5G0VwcVLhHw91xuR+bVm1lhokBixERI3Q5hMZePnn4ygq0yHQW4NFk6IR3baFvZtFVGcMWIiIGpEKnR4fJqbgyz0XAAB9w3yxcGIU/L24WCw1bAxYiIgaiezCUsz88RgOXMgBADwzqD1ejekIZyebr3NLZHMMWIiIGoGj6TcxPf4oMrUl8HR1wofjeuCBbsH2bhZRvWHAQkTUgAmCgPhD6fjnLydRrhPQ3t8TX02Jxl0BXrXfmKgBYcBCRNRAlZTr8EbCn1h99AoAILZrEOY/1h1ebi52bhlR/WPAQkTUAKXnFGNafBJOZWihVgFzRnbCM4Pac8oyNVoMWIiIGpidZ7Lw4opk5N8qh5+nKxZMjMSADi3t3Swim2LAQkTUQOj1Aj779Sw+33EWggD0DG2OxZOjEOzjbu+mEdkcAxYiogYgr7gML61Ixs6UGwCAyf3a4K2HOkPjzBL71DQwYCEicnAnr+VjWnwSLufegsZZjX+N7YbHolvbu1lEdxQDFiIiB7Y66QpeTziB0go9Qn3dsWRyNLqE+Ni7WUR3HAMWIiIHVFqhw3sbTiH+YDoAYEhHf3w6IRI+HpyyTE0TAxYiIgeTkX8Lz8UfRfLlPKhUwKxh4XhhaDjUak5ZpqaLAQsRkQPZfz4bM388hpyiMni7OeOzxyMxpFOAvZtFZHcMWIiIHIAgCPhqzwV8sOUM9AJwd7A3vpwcjTZ+HvZuGpFDYMBCRGRnhaUVeOXn49j8ZyYA4JGoVvjXmG5wd+WUZSIDBixERHZ0LqsAz/6QhPM3iuDipMI/RnXB5L5tWGKfqBoGLEREdrLxjwy8uuo4isp0CPJ2w6LJUYhq08LezSJySAxYiIjusAqdHvMTU/DVngsAgH7tfbFwYhRaNtPYuWVEjosBCxHRHXSjoBQzlx/FwQu5AIBnB7XHKzEd4eyktnPLiBwbAxYiojvkaPpNTI8/ikxtCTxdnfDhuB54oFuwvZtF1CAwYCEisjFBEBB/8BL+ueEUynUCOvh74ssp0bgrwMveTSNqMBiwEBHZ0K0yHd5YewJrjl4FADzQLQjzH+uBZhp+/BJZw+pB0z179mDUqFEICQmBSqXC2rVrpevKy8sxZ84cdOvWDZ6enggJCcGTTz6Ja9eumd3n0qVLoVKpavyUlJRYfUBERI7iUk4RHlm8H2uOXoVaBbz+QCd8MTGKwQpRHVgdsBQVFaFHjx5YuHBhjeuKi4tx9OhRvPXWWzh69CjWrFmD1NRUPPzww7Xu19vbGxkZGYofNzc3a5tHROQQdpy5jlEL9uF0hhZ+nq6I/2tfPDOoA+urENWR1WF+bGwsYmNjjV7n4+ODbdu2KS5bsGAB+vTpg/T0dLRp08bkflUqFYKCgqxtDhGRQ9HrBXz261l89utZAEBkm+ZYNCkKwT7udm4ZUcNm837J/Px8qFQqNG/e3Ox2hYWFaNu2LXQ6HXr27In33nsPkZGRJrcvLS1FaWmp9L9Wq62vJhMR1UlecRleXJGMXSk3AABT+rXFmw/dDY0zS+wT3S6bTvwvKSnBa6+9hokTJ8Lb29vkdp06dcLSpUuxfv16LF++HG5ubrjnnntw9uxZk7eJi4uDj4+P9BMaGmqLQyAissifV/MxauE+7Eq5AY2zGh+P64H3xnRlsEJUT1SCIAh1vrFKhYSEBIwZM6bGdeXl5Rg3bhzS09Oxa9cuswFLdXq9HlFRURg0aBA+//xzo9sY62EJDQ1Ffn6+VfdFRHS7ViVdwRsJJ1BaoUcbXw8snhyFLiE+9m4WUYOg1Wrh4+NT6/nbJkNC5eXlGD9+PNLS0rBjxw6rAwi1Wo3evXub7WHRaDTQaFjGmojsp7RCh3/+cgrLDqUDAIZ09MenEyLh4+Fi55YRNT71HrAYgpWzZ89i586d8PPzs3ofgiAgOTkZ3bp1q+/mERHVi4z8W3gu/iiSL+dBpQJmDQvHC0PDoVZzFhCRLVgdsBQWFuLcuXPS/2lpaUhOToavry9CQkLw2GOP4ejRo9iwYQN0Oh0yMzMBAL6+vnB1dQUAPPnkk2jVqhXi4uIAAO+++y769euH8PBwaLVafP7550hOTsYXX3xRH8dIRFSv9p/Lxszlx5BTVAYfdxd8+nhPDOkYYO9mETVqVgcsR44cwZAhQ6T/Z8+eDQCYOnUq3nnnHaxfvx4A0LNnT8Xtdu7cicGDBwMA0tPToVZX5fvm5eXhmWeeQWZmJnx8fBAZGYk9e/agT58+1jaPiMhmBEHAl3suYP6WM9ALQOdgbyyZHI02fh72bhpRo3dbSbeOxNKkHSKiuigoKccrP/+BLSfFXuNHo1rjX2O7ws2Fs4CIboddk26JiBqTs9cL8Gx8Ei7cKIKLkwpvj+qCSX3bsGot0R3EgIWIyIyNf2TglVXHUVymQ5C3GxZPjkJkmxb2bhZRk8OAhYjIiAqdHh9sOYOv96YBAPq398OCiZFo2YzlFIjsgQELEVE1NwpK8fyPR3EoLRcA8Ox97fHKiI5wdrJpcXAiMoMBCxGRTNKlm5i+LAnXtaXwdHXCR+N6ILZbsL2bRdTkMWAhIoI4ZfmHg5fw3oZTKNcJuCugGZZMjsZdAc3s3TQiAgMWIiLcKtPh9YQTSDh2FQDwYLdgfPBYdzTT8COSyFHw3UhETdqlnCI8+0MSzmQWwEmtwmsjO+GvA8M4ZZnIwTBgIaIm69fT1/HiimQUlFSgZTNXLHgiCv07WL/+GRHZHgMWImpydHoBn/16Fp//Kq4IH9WmORZNikaQj5udW0ZEpjBgIaImJa+4DLN+Ssbu1BsAgCf7t8WbD3aGqzOnLBM5MgYsRNRk/Hk1H9Pik3Dl5i24uagxb2w3PBLV2t7NIiILMGAhoibh5yOX8ebaP1FaoUcbXw8smRyNziFcKJWooWDAQkSNWmmFDu/+cgo/HkoHAAztFIBPxveEj4eLnVtGRNZgwEJEjda1vFt4btlRHL+cB5UKeOn+CDw/5C6o1ZyyTNTQMGAhokbpt3PZmLn8GHKLyuDj7oLPHu+JwR0D7N0sIqojBixE1KgIgoAluy/gw8Qz0AtAlxBvLJkcjVBfD3s3jYhuAwMWImo0CkrK8fLPx5F48joA4LHo1nh/TFe4uTjZuWVEdLsYsBBRo3D2egGe/SEJF7KL4OqkxtsPd8bEPm1YYp+okWDAQkQN3oY/ruHVVX+guEyHYB83LJ4cjZ6hze3dLCKqRwxYiKjBKtfp8cHmM/jvvjQAwIAOfljwRCT8mmns3DIiqm8MWIioQcoqKMHzPx7D72m5AIBp93XAyyMi4OzEEvtEjREDFiJqcJIu5WL6sqO4ri1FM40zPhrXHSO7Btu7WURkQwxYiKjBEAQB3x+4hPc2nEKFXsBdAc2wZHI07gpoZu+mEZGNMWAhogbhVpkOryecQMKxqwCAB7sHY/6j3eGp4ccYUVPAdzoRObyL2UWYFp+EM5kFcFKrMDe2E56+N4xTlomaEAYsROTQtp+6jpdWJqOgpAItm7li4cQo9GvvZ+9mEdEdxoCFiBySTi/g0+2pWLDjHAAgqk1zLJoUjSAfNzu3jIjsgQELETmcm0VlmLUiGXtSbwAApvZvizce7AxXZ05ZJmqqGLAQkUP582o+psUn4crNW3BzUSPukW4YG9na3s0iIjtjwEJEDmPlkct4c+2fKKvQo62fB5ZMjsbdwd72bhYROQCr+1f37NmDUaNGISQkBCqVCmvXrlVcLwgC3nnnHYSEhMDd3R2DBw/GyZMna93v6tWr0blzZ2g0GnTu3BkJCQnWNo2IGqjSCh3mrjmBV1f9gbIKPYZ1CsD65+9lsEJEEqsDlqKiIvTo0QMLFy40ev38+fPxn//8BwsXLsThw4cRFBSE4cOHo6CgwOQ+Dxw4gAkTJmDKlCk4fvw4pkyZgvHjx+PQoUPWNo+IGpirebcwfskBLP89HSoV8PfhEfj6yV7wcXexd9OIyIGoBEEQ6nxjlQoJCQkYM2YMALF3JSQkBC+++CLmzJkDACgtLUVgYCA++OADPPvss0b3M2HCBGi1WmzevFm6bOTIkWjRogWWL19uUVu0Wi18fHyQn58Pb29+KyNqCH47l42Zy48ht6gMPu4u+OzxnhjcMcDezSKiO8jS83e9ptynpaUhMzMTI0aMkC7TaDS47777sH//fpO3O3DggOI2ABATE2P2NqWlpdBqtYofImoYBEHAol3nMOWbQ8gtKkPXVt7YMPNeBitEZFK9BiyZmZkAgMDAQMXlgYGB0nWmbmftbeLi4uDj4yP9hIaG3kbLiehO0ZaUY1p8EuZvSYFeAMZFt8aqaQMQ6uth76YRkQOzSVGD6uWyBUGotYS2tbeZO3cu8vPzpZ/Lly/XvcFEdEekXi/AmIW/IfHkdbg6iVOW5z/WHW4uTvZuGhE5uHqd1hwUFARA7DEJDq5a6j0rK6tGD0r121XvTantNhqNBhqN5jZbTER3yi/Hr+HVVX/gVrkOIT5uWDQ5Gj1Dm9u7WUTUQNRrD0tYWBiCgoKwbds26bKysjLs3r0bAwYMMHm7/v37K24DAFu3bjV7GyJqGMp1ery34RRmLj+GW+U63HOXH36ZeS+DFSKyitU9LIWFhTh37pz0f1paGpKTk+Hr64s2bdrgxRdfxLx58xAeHo7w8HDMmzcPHh4emDhxonSbJ598Eq1atUJcXBwAYNasWRg0aBA++OADjB49GuvWrcP27duxb9++ejhEIrKXrIISPL/sGH6/mAsAeG5wB/x9eAScnVhin4isY3XAcuTIEQwZMkT6f/bs2QCAqVOnYunSpXj11Vdx69YtTJ8+HTdv3kTfvn2xdetWeHl5SbdJT0+HWl31gTVgwAD89NNPePPNN/HWW2+hQ4cOWLFiBfr27Xs7x0ZEdnTkYi6mLzuKrIJSNNM446NxPTCya5C9m0VEDdRt1WFxJKzDQuQYBEHAd/sv4v2Np1GhFxAe0AxfTolGe/9m9m4aETkgS8/fXEuIiOpNcVkF5q45gXXJ1wAAD3UPxgePdoenhh81RHR7+ClCRPXiYnYRpsUn4UxmAZzUKrz+wN34yz3tai1pQERkCQYsRHTbtp+6jpdWJqOgpAItm2nwxcRI9G3vZ+9mEVEjwoCFiOpMpxfw6fZULNghzhyMbtsCiyZFIdDbzc4tI6LGhgELEdXJzaIyvPDTMew9mw0AeGpAO7z+wN1wdeaUZSKqfwxYiMhqJ67kY1p8Eq7m3YKbixr/fqQ7xkS2sneziKgRY8BCRFZZcTgdb607ibIKPdr6eWDJ5GjcHcxSAkRkWwxYiBxcamoqzp8/j7vuugvh4eF2a0dJuQ7v/nISy38XFxq9/+4AfDy+J3zcXeq0P0c5LiJqGDjYTE1SamoqNm/ejLNnz9q7KSbl5uZi5AMj0bFjRzzwwAOIiIjAyAdG4ubNm3e8LVfzbmH8lwew/PfLUKmAl0dE4KspveoUrDjKcTWE1wARVWHAQk1KXU6W9jqxTZw8Edv3bAceAfASgEeA7Xu244lJT9zRduw7m42HPt+LP67ko7mHC777vz54fmg41Oq61Vex93E5SsBERNZhaX5qUkY+MBLb92yHLkYHtAVwCXBKdML9g+7Hlk1bFNvm5uZi4uSJSNycKF0WExuD5cuWo0WLFjZtZ2pqKjp27Cie1LvLrjgOIEG83tbDKHq9gMW7z+PjrSnQC0C3Vj5YNCkKob4edd6nIxyXNa8BIrI9S8/f7GGhJiM1NRWJmxPFE1V3AD4AugO6ETokbk6s0YNiz56A8+fPi3+0rXZFO/GXfMV0W9CWlOPZ+CR8mCgGK+N7tcbP0/rfVrAC2P+4rH0NEJHjYMBCTYY1J0t7n9g6dOgg/nGp2hUXxV933XWXze47JbMAoxf+hm2nrsPVSY24R7ph/mM94ObidNv7tudxAfYPmIio7hiwUJNhzclScWLLBnAWQA7u2IktIiICMbExcEp0EodL8gEcB5y2OiEmNsZmwybrj1/DmC9+Q1p2EUJ83PDztP54ok+betu/vY7LwN4BExHVHac1U5MREREBP38/5GzMAQSIwcdFAJsAP38/xclSOrEtB5Ap20mg+OtOnNiWL1uOJyY9gcSEqhya+2Pvx/Jly+v9vsp1esRtOoP//ZYGALj3rpb4/IlI+Hq6WrUfS6Yq38njqs4QMG1P3A6doJNeA05bnXB/7P0OO73amingnC5OjZbQSOTn5wsAhPz8fHs3hRxUSkqKAECAG8Tfhh+N+Ds1NVWxvZ+/n3jdcAgYAwEjxG39/P3uaLtTU1OFTZs21Whffbmef0t4bPFvQts5G4S2czYIH2w+LVTo9FbtIycnR4iJjVE8rjGxMUJubq7J21hzXCkpKfX2GOTm5lrdVnux5nGty3NA5AgsPX8zYKEmY9OmTQJUEOBeGXwYghB3CFBB2LRpk7StFNwEVQtuAo0HNw3V72k5Qq/3twlt52wQuv5ji7Dlz4w67ScmNkZw8nQS8AgEvAQBj0Bw8nQSYmJjbqt9tjwJJyYmCu+++66wdevW296XrVjzuNrqOSCyNUvP3xwSoiZDrVaLp7xYKKfUegJIAJydq94OUg7LjWo7Edf5w7lz5xp0d7sgCFi6/yL+tfE0KvQCIgKbYcnkaLT3b2b1vgwJyoqpyt0BnaBDYoKYoGzssbJk6EIxU6tyCvL2RHGmVl2nINtzuro1rHlc6/ocEDUkTLqlJkOv14t/mJghUlFRIV2kVpt/a8iDG7lvvvkGU6ZMwdKlS+vWyDuguKwCL65Ixru/nEKFXsBD3YORMP2eOgUrgPUzbywt3GarmVr2LlxnKWseV85+qhtWO25YGLCQw6uvDxVrZoikp6cDKgAuUJzY4AJABVy6pNxJUlISXN1c8de//hXx8fH4v//7P7i6uSI5Ofm22lzf0rKLMPaL/ViXfA3OahX+8VBnLHgiEp6aune2SsGdice1enA3euxoJCYmKi5LTEzE6LGjFZfZ4iRc1yDIHic2a16vnP1kHVY7bpgYsJDDqu8y+ooptYkQf7Yan1J7/fp1cfjoAShObIgFIFReL9P/nv4oRzkwAEB/APcA5ShHn359bvdhsIq54996MhMPL9iHlOsF8PfS4Me/9cNf7g2DSlW3EvsGUnC3GYqpytiCGsFdamoq9u3dJwZ+wwGMATACgAuwd89eRbttcRK2VW+QLVgzBdzW08UbW09EQ+llo2ruTEqN7THptvGxJonQ0uTMpKQkwUXjotjOReMiHDt2TLHdV199JV7/EgQ8DwGTIGBm5f+A8PXXX0vb/ve//zU7++jbb7+9rcdhy5YttSaHmjv+Cp1emL/ltDQL6NFFvwnX82/dVpvkpMfKRIKy/LF67733zG77/vvvK/YtvQbGVj72Y28vkVRKpn4EAt6R/Yw1nkxt70RWa2Y02WL2U2OceWTta4Bsj0m31KBZm0QofWMaDjGJtrjqG5M8OXPIsCEoryhX3Fd5RTkGDxmMvJt50mXSMIeJOizyYY5du3aJPQwCFMmh2AhABfz666946qmnrH4Mzp8/j779+yLnRo50mZ+/Hw4fOoywsDDFtqaSU8c9+X8IHjMXe8+K2cJPDWiHNx68Gy5O9de52qZNG/H4b6Lq8S8CsAeACmjbtqo7IzU1VfzDRDKzdH0lm9RsUQHYBGUtns2Vl8s4QiJrixYtsGXTFpw9exbnzp0zm6BszbYGtSU+1yXp2dHrwFjSy+aI7SYWjiMHZc2HinRiCQKwrWpTXWBVXkJ4eDgSExOhzdcCGgBDIQU22APk5+dj27ZtGD58OADg6tWrVSdhI0FIenq6dD8tW7YUT34PAggBkAWgFcThpAQgMDDQ6DHW9sHet39f5GhzFPefszEHvfv2RnZWtmI/xk6sTq5hONN8NM6dzYa7ixP+/Wg3jO7ZymhbboderxePvwKKxx9OAARlMrOvr29VbtDoquPCJgD6yutlDCfhrVu34uDBg+jfv7/0HNXF+fPnxbYGA0iQXREGIE35unKkE1t4eLjF92XJtpbMlLI2YGsos68UQ43y2YIXxV/M93FczGEhh1SnMvpmpiADwOLFi8WTVXOIJ9a1ALZCzE8RgEWLFkk3bdWqVVUQIs9heUDctk2bqnL1Op1O/OMYgIUAlgFYACBZvLi8XNmjY0leRGJiotizYuT+c27kYNu2qsjA2Im1WcVwBLWZD2efAPi7AwkzBtxWsGIuh0HqjfKvdkVL8VeNGVVmcoOqMzxWMTExePvttzFixIjbyiGRXleRACYDGAxgCoCe4sV3MpHVnnkhluRwWJvv01DyQuy9PATVHQMWckjWfKio1WqzM3oMJ8zMzMqxHROBjTyRNiMjQ/zDxIf11atXpYsCAgLE+8+AIukWGeL9BwQEKHahGL4aA2BEzQ/2Q4cOmb3/AwcOSBcpTqyCC3zLZsKvfBZUKlcUnz2Irx/rgE5BppdsN8eS4Eqv14vHnw/l468Vj1/ew3Lx4kWzx5WWlqa4uL5PghERERgybAiwHkA8gF0AfgDwCzD0/qF3JJG1vpPJrWXpTClrAjZ7LxZqreXLluP+QfeLvWyfAEgA7h90Z5aHoLpjwEIOy9IPlfT0dLPf2g2zVDp27FgV2FSboQKVeIIy2LVrl/iHiQ9r6XoAvXv3ruod2A/gAIDfIKUp9ulTNVNI+mD30il6eXTNlB/sffv2NXv//fv3ly4ynFhd9wchKG8+vHQxEAQ98g/8gMhbh9GzSyfU1bjx47B151ZFwLB151Y8Nv4xaRtFQT53iD1NngBGiscv72ERBMHscclnLNnqJKhSqaByVimOSeVsfKaULU5s1gRhtpilZGnPiTUBW0OrA2MYakxNTcWmTZuQmpqKLZu2ONTQFdXEHBZyWFYnEbaF2FtyE4AvpA9Lg/DwcOWQkEEggOtQ7FvqNdgMZXJm5VRd6cQL2bReE0m38mm958+fV/ZGGLatTPo05EWEhYWJ222sdv+bxO3atVMe3Kz3F+Psj0nQObtDV5yP7F8+wn13B9zWiTU1NRU7ft1RI4dBEATsSNgh5TBIBfm2QMwJMvAQf8l7WKTjMvG4ypOJbZFDkpqaih3baz8mg/pOZK1zMnk9Jr1ak8NhadJzQ80LsSY3iOyPAQs5vNo+VO677z7xDxMzeqTrAbPBglybNm3EE6oPlMmZgQBuKWe+nDx5UpnvgsrfgnjbkydPStteu3at5vIAsm0Nw1K7d+8WLyuvdv9qcdvdu3dXBgsCFu8+j48SUyA4u6M04yxurJ0HnfYGcHeMycfMErt37xb/MBEwGNogDcnpYDRgk/ewSAnKJh5XPz8/6SJbnATrGgTVVyJrnZLJ6znp1ZoVq+WBuTkNdRVsalg4JEQNXlpamnJa7RiIQz15AFRVeRPZ2dnKYMEwdFQ5dJGdXTXzRuo1yZPtczjEYKdar0ltJf+l6yHLfTGxrWH2kZRPE1Btu8rE1uvXr0NbUo5n45PwYWIKBACFfyYis+hV6J6+YXTops5MDN8YHD582PQsKQH4/fffpW13795t9nHds2ePtG1ERAT8/P3EwEdekG6TOL27LifBa9eumT2m6gUBrWHJUE+dksktHGaxZPjOwNKhLmuGr5gXQrbGHhZq8DZu3CieMFvA6FDPhg0bMHz48KoTp4kTgJToCog5AgKA0mr7rBz6yc3NlS568MEHsWDBApM9AQ899JB0kSI3xci2htwUaSq0iQRhVfNWeHjBPlzMKYaLkwqZGz5D4V1bgW6V25kZ5rDUfffdV1WzRAugGcT6KnsBqKp6rrKyssQbHAOwRraDytEd6XpUnmQN04q3Vds2DYq8lNTUVHGmVBBq9MbkXM+p03FJ09VNDEnJp6tbw6reEAvrwCiWPDDyWpH3XFk6fGdgyVCX4phkgahuhPEenroMn9mCo9eBobqr9x6Wdu3aiUlt1X5mzJhhdPtdu3YZ3f7MmTP13TRqpKRZOCZO7obrL1y4IF5g4tutfIZKSUmJ+Ef1d0jl/7du3ZIuiomJgbPG2WhPgLPGWVE3JCYmxmyvgWFbqRibkZlPHp0HYelVf1zMKUar5u6YHJSFwj+2mh26qYuIiAj069cPKAOwHWKC8DYAZUC//v2kk0GPHj2qZknJ21o5SyoyMrLq4TOchCMBzAQwqfJ3z2rXQ9bD8ASUU5AnihfXJZFTmq5eOQRn6AmAHjWmq8vVNkvH0t6QGnVgDPcfLN6//JikXr5NUL5WKoMbeS+fJcN3xoSHhyM2NtboiV06JhPT9U09/ub2aUtcH6jxq/celsOHD1fVpQDw559/Yvjw4Rg3bpzZ26WkpMDbu2rqpb9/9aIO5Ojs9c0mODjYbDGyVq3E+iOlpaVmewxKS0ulfdb2IZeXlyf9nZqaiorSCsANyp4ADVBRWlHjm+i2xG3o278vyhOq6rO4aFywfet26X/FzCfp260TWjz5NLxbPIwyPTAwvCU+ezwSiz6ZL97IxDfx2xnmSD2bKj6uD0KRmyKvSCsVjjPM0gIUeTnypFtBEKqSiR9AjWRi+fCZNHxiIjepLjksUjK1AHHY0ANiovBu1JiCDVieF2Jpvo2iDsxDAHIhJohfAZBm5JiM5TFVFuQzysT910WHDh2Ugaj8faVyvETauiQoU8NS7z0s/v7+CAoKkn42bNiADh06KBMfjQgICFDczsnJqb6bRjZi6282iYmJ+Oc//6kolia3fPlys9Oa4+PjAVQWeBMgVmSV9xhUiNvJA22tVmu2totWq5W2lb6JPgexB2Bw5e/p4sXVv4n+/ZW/o1xXbXkAXTn+/srfax5c5bdbp7UtEJg7D94tHgYA3NOiEEv/rw98PV3F3BvDMIf8m3jlMEdOTk7N/VogMTERudm5RovX5WbnSs+HlFRs4tv9qVOnpIt8fHyqhu/kPQzNAQiokRzq29K3qtqw4TnIA3xb+hoNimvrCZEWtXwQQATE6dcdIeXbVA/uLM3hsHQKsGK7KxBzlK6YqS8EiEG4vDdKfAkohoQUw3dGemNq+/w1ycz7ypE0pFW4qe5smnRbVlaG+Ph4/OUvf6l1RdjIyEgEBwdj2LBh2LlzZ637Li0thVarVfyQfdSluJclHxTnz59Hy4CWGDlypFTltGVAyxrFxa5cuSL+YeKEabjexcVF/FB3gvIE6ARABbi6uko3raioMPthLa9ee/ToUfGPSwA6QAxYOkD6dnv8+HHFce/csVPs25S3wRnY8esO6fHIysqSvt1qJnZB0IzP4Na6C/SlRcha8x66CWlwUovvKamHw8QwhzwQs4alxeukXhETQ23y+5dmnVR/uxZAuS+Ij5W5gEn+2rE0aJZyg0wMc8iXUbD2JGhp0qml2ykStOUBQjvxlzzfJiIiAkOHDRWDb/lroAIYOmxonXo8G1JtlYa0CjfVnU0DlrVr1yIvL8/swm/BwcH46quvsHr1aqxZswYdO3bEsGHDFLMFjImLi4OPj4/0ExoaWs+tJ0tY+6FuzQeFYi2dyhN7jlZcS0fu7rvvFv8wccLs0qULgMpcFsO3ayPl9uXDkNK3WxMfgPJci19//bXq2+0+iCe/3yB9u5X3DEnTlRVDPZACIUOuwc8//wwIgNfEhxEY+i84q3xRprqIjGsv4dbZQ1ixYoW0TymHRIBYYddQaReokUNiDUuL1z344INmv93Lk46lYTnDFGhDwKZDjWE5a/IyHhv/GBK3JSo2S9yWWGOGjJQbZCLfRj5d3dqToKXFyCzdTnr8l0MZXP0oXiwvHggAq1auQsxw5VT2mOExWLVyFerC1ksT1Cdr29pQlhEgJZvOEvrmm28QGxuLkJAQk9t07NhRrEBaqX///rh8+TI++ugjDBo0yOTt5s6di9mzZ0v/a7VaBi12YG1dC0vHmaW1dKrNeoAA5CTkKBYq9Pb2NltkzcvLC0C1b6xGCszJy+17eHiIJ08TOQEeHh7SRVKlVzXEoSZpJ2J75MGNNORgYkaN4fr84hK0HPUKPP3Frvwip13IcVkAoZV4Qpf3KEo9LC0gBkoGlbOkqudlWComJga+LX2RuzFXPKED4uOcJA7JGB7/sLAw8f7LYLRmjLzIXVlZmdmaNWVlZTUbUktehtRr5QpxuESWa2PotTK8BqUp2CbybX7//XfpuOpaB8bSYmS1bScV0TORTF69eKClNVMs1ZBqq1jTVkdYhVveFs5ospzNApZLly5h+/btWLNmTe0bV9OvXz8p78AUjUYDjUZT1+ZRPbHmQ92aDwpLhiMMJ5aUlJSq3BQjyYmGBFFp5o+JJE75zJ/i4mKz01+Li6tKukrDnSXV2lpS7Xq56rNnZf9fuFEI91H/gODiA0GowE3Xb1Dg9IvYnoviNgMHDlTeXgWxZ2M4qlahrkwmvh3tw9oj90iuuNyA7L7at28v/SvVVnEBcB+UiaxlVQXmAFkys4nnVT5d3NJp1VKvlYkgSH7/0hRrE/cvn4KtOAlqddL9O+2vnxN2bSer2mZ3yY8LqLZGVeVrwNBrUNekU0sr3ToCS9vqCKtwN5SVrR2NzQKWb7/9FgEBAWJ3sZWOHTsmzvwgh2fNNxvFB4WRHg75B4Wl9UoMtwMgJid6QExmDAVQCCChqrZHaGgoLqRdqErilH0Th0o5pVUamvCB0Yqs8qGLy5cvV52wB6EqYKg8YV++fFn5oJmZ0XSx3BujF/6GYhcfVBTmInvTv1Ha81SNXqNJkyZJu5N6eHxQsw7NLSOrJVsoNTUVR44cEXsuqs0SOnL4iBRgKhJZQyA+vqGVj0OCMpFVymcx8bzK810iIiIwcNBA7N27V9lzpQYGDhoovVYUSb9GXlfypF9rauYAwKKFi9CnXx/kbK9KXG7u3xyLv1hs/EGzgKUnq+vXr5t9rcgfV+nLQBAUrwFdYNXQbF1Owo5SW8USlrbVEZYR4IymurFJwKLX6/Htt99i6tSpNT4s586di6tXr+L7778HAHz66ado164dunTpIiXprl69GqtXr7ZF08gGrF5vxIJpqoZ6JTkbc2oM88jrlQCyb+3HAMjzcSt71A3f2q0ejlChqiKrJxTf7uVJkFIF3RYwWrhOXkEXgIkhCTWa50zGtpL2ACoQqC5E0tJZ0OluKo9JA6l6rOExUFSPNTL9dOfOnWbzyExZuXKl2cdr5cqVeOONN6puYGKYS04q429i+K767EAXFxeoXFUQHhCk41JtUokJ1JWkRF0Tryt5EGTtGk3Tn5+OvOI8xeOal5iH52Y8V+cTi6UnK+l1ZWL4Sv66ktaoyoPR18Dt9ho0pDV3amurvYe6HGlIyhqOMHxlk4Bl+/btSE9Px1/+8pca12VkZCiy28vKyvDyyy/j6tWrcHd3R5cuXbBx40Y88MADtmga2YCl32wMpdZzbubU6OEwVmr98KHD6N23N3ISqr7d+vn74fChwzUbIU+krPZhbVDbbCJ5T4hKpRJzAsqhDEIqh5nkwzzS8FF+tfuvTDotKiqStpWSkGVtUAveaHnXK3CPEJNj/3JPGLK2fYnfi26KCYHZAC5D7LVoCeAT5dDF2bNnzZ7Y6jqbw5rhE0sef6Cyt0eovFzec1UZiMkDFksXKnzwwQexYOECkz1n8l4TafioBWr2nF1XDrPY4sRizT6tWfJB6mUz8Rqoay9bY2XPoS5HGJKyhiMNX9nkVTxixAiTCWBLly5V/P/qq6/i1VdftUUz6A6r7ZuNVGrdRCJt9RNAWFgYsrOysW3bNhw4cAD9+/dX9KwYODk5QV+uN/lh7eRcrabPJQDuAK6iaujIFH8ov7W3BFCtDpuU9GpiQUP5iUUqOFfZHe2qD4d/2Vw4qwOgLytBuxu/4R+j/oNvsrpXbRcCcYpyc0jd1vKZP9I+TXwA1nWqZo8ePRRtlVRrgzU9AdLnwnMwGojJWfrBLiX9mugJkveaSMMo7tX26VHteivu3xrW7NOa4SvpS6CJ/cqr4lLVl6ytW7fi4MGDJj9bbMERhqSs4UjDVwy7qd7U1mVY1xOA/IRvjHQSNLHfGsHzWogBgIGRyf3SbZ4AcB7isEz7yp9PlPuUarK0BXAWVYFQu2rXA3j44Yex/pf1wEagmWsMfEOnQaV2QfnNq7iRMA//nP8OAFTNrFsHccqvQWXsJa8X4uPjI/5h4gOwefPmNQ8QtT9fISEhZodPDG34888/zR6/dD1kycqGtlZ+duO4+EveG6X4YDfkxhiqwqLqg92a15X0uJlIepY/rrY4sVh6TEC1WVrypOM9yllagCzQMtHW26l23BjZs9fA3kNS1nC04SsGLHTb6rt8ucH58+fFWiw3ag4JSVM+Ic4Yq6ioMHkSUMwmMyQxVksiRRmMV+9cjKrZPycgDl1UIwVU8m1Rta084Bo4cCCgdoHv0GnwaivWzChOPYDszZ9AKCnGPfeIBVTkdVaMWbVqFWJjYwEAo0aNwqHfD5lcUO/hhx9W3NbS50saZqheGr5yurJhmEEq5Gfi+Gus0WQmCJJmckH8YIcaxoM2NaQPSmteV6bWCjKQ12GxxSyhiIgIDBk2BDvX7xRntRk4A0Pvr1ngbfXPqzH0/qEQtle9OFVOKiSsTlBsJ1U7NvEaqJFH1cTZu9egocy+crThKwYsdNusevObOVlVF907GvnF+Yr95mzMQWR0JPJy86Tt3NzcxG/mJnoj3N1l/f9mhg5qMCTXGsmLqBHcWLjtuu37EDR5PjRB4RAEHfJ08dCqVokbqapyKDZs2FAVXA1F1cyjPQD0wPr166V9RkVFmV1zRhraqWTp83X4cGWu0BiIj+sFiD1MaihqluTm5po9fvlUZQBmp6DLXwfffPONeFn1WTKVAebSpUvx1FNPWfWNVVpQ0MTMm+pDJ7aYJaRSqaByVkF4WJlIbMzDox+GoFe+2AS9gIdGPQRtvpFaPCZeA7X1UjYljtBr0FBmXzna8JVNK91S42dNpVtppVoj5cOrr1SbmJiI/Jv5RqvS5t/MV1SPldb9MVLuHiogPz9f2WgT3xZqkAc3svs32hNj2FZevbbatntSb+C/6X7QBIVDp8tHluZtaL1+BroLUqVbQ9d9SUmJeNvmEJN+1wLYWtkOQVkzZuvWrVVtqN4mVFbiraR4vmRtNfZ8SQscHoMYDJ6o/J2svL6goMDsY1VQUCDtU0r+HA2xyFs32d9QJoeuX7/e7H4TEqrOzJaWuz958qTZJRekKdKV/vbM35BbkKt4XeUW5OKvz/wVdWFIJBYeEBT3L8QK2LF9h+LxT0xMFB87Vyhf167iYyp/D0jlI6qKNYtair+qT9duyhxpyQF7rWxtKUvXyLpT2MNCtTKX62BNl6FiMbdWUK5Um6A8WS1evNjsfr/44gtpDF/KETHRcyLPIQFg3Yq2lgY3gJlpvSos3HEWH29LhQBnlGak4oZfHHROshKmlfs1fFhK6x6ZmHkkX/fowIEDZoe69u3bJ20rPV8m2ip/viIiIszO/omIiAAgmzZs4rGSV9qVnostEHuMADEQ8qh2PWSVXk3sV/r2B8u/sVoz8yY1NRU7fq19lpI1rHm/zJ8/32yP4Pz586X3gJTvcjNXOQ3fSL5LU+dovQaOzpGGr9jDQiZZsu6P4s2fDTHpMgdG3/yKk4UfgPDK3+3Ei+UnNkUSoVzlfuVTaq1Z98fcqsZGmbj/GuQndsM34QxA5eYJ/0fexEdbUyEIgPu1o8hcNge6S9XqrVfu98yZMwBkK0vHQtlrMxKAoHysgoODzfbwtGrVStq2Q4cOVW0dgKp1hyrX0pE/X9J+TfRGGPYrPb4mHivF4294rEysJSTXrVu3qv0aeW11794d1dX2jVXqiTCxzxpToAGL1jKylDVr3kirbJu4/xs3lK+hI78fgZ+3X1WP3DbAz9sPR34/YnU7GzNH6zVwdJaufXUnsIeFTLIk18GaJEJrvtn07dsXBw8dNJlEKFXChWzGjon9KmYJCTBZvbYGM0mMRodfqk3rdXFpC3/vN+DiGwJXZzXeG90Fn77wPqAvN1ny33BylwISEz0h8oAlOjoaa9euNbltVFRUzbYCwH7ZZZqax6RYe0munfjLMJVWo9HgVsktk7lJNZbQsDCPSLp/E7lJ8npOloqJiRGfP2P7VMF4T4Q1PXK1sCbfZty4ceJK3ybu//HHH1fs28fHB7169VIkU/fq1cvkLLGmzJF6DRoKRygeyICFjLImMc3SJEJrPqynT5+Ozz77zGQS4fTp06WLBEEwm8xbY1pzlvLfGovLSTuGyQX9jJKd2D0q7oNf25lQq9xQkZ+F9W+MRffWzfF6VpbZoMnQsyStapwB5fpAe1BjVWNphoiJoRv5DBGpKq6JBFl54TRLl0fw8/MTi/KZmE3UsmVLs48VAKNDba1atarKTaqedKuvfcaPMYmJiaafPwGKRTUVaxkZCVoNaxlZy9KT5RtvvIE333rT5Ov6tddeU2w/5pEx2Htwr+J5TdyYiDFjx2D3Lut7gxqzhpL0SkoMWMgoS8faLa1GamDph7V8KqwxFy9eVH7AyJN5DQwzT+SsmdasgpjwOAhVC/rtAVBqZFtU7ivEGS30f4G318OACriVdhTZv3yE7ov/D4Bslko+lLkG+8T7M8xSkYbPmsNouX+9UJVr8fvvv5st3Pb7779L2+7bt89sD8e+ffvw17+KCaUxMTFi0GHshKmu6o1o1qyZuJ8xlcdjKAZXuZaTYbXsGo9VLb0W0swXE201tgp1bbVlNm7caHaW0IYNG6TjioiIwNBhQ7Fj1w7l68oZGDqs5hRkS1l6spSCKxOBoDy4Sk1Nxd7de40WZdyTsMdhy73bmyP0GpDlmMNCRlk61m5txr2pCsjVLVq0SPzDxKwH6XoDwzfxERBPnCMgzRJSNgDWzfx5AGKuR8/K37EmtgXgtN0XgTf/JQYrAPIO/ISsn9+B/lbV9NOKioqqHhZZrgG8ochNcXJyUibdGnI9tKix5o60pICJ50C+5EBtqyXL85MSExPFAnuGE+Ynlb/LAeghzVJRDB3JZ88auX8AVb0W+yDOOPoNVUNtMlKysIm2/vbbb9JFluRbAUZK2FfLy6meb7Nq5SrEDI9RXBYzPAarVq7C7aot30ZasXwWgGEQj3tY5f+oTLautHLlSvEPE4+VdD1RA8YeFjLK0uEbazPux40fh52/7VR0W2/dtBWPjX8Mv26rmn576dKlmj0RxZAWH6zRA2MIROQl9x+A8foqFgxHWLutJrQL/Ee/BifPFtALRcjO+Bi3Dv1ufGOg5jBUtbpe0swbE+X+5Qv6SdO2TTwH8mndo0ePxi+//GJy27Fjx0oXxcfHm+1lio+PV+Z8mCgcJ193CUDVUFu1FZirB4LJyclmj+vYsWPSRVK+ley1sn2PmUJgJp7X6m215dBBbb1BiiG5gZU/gFQVWL5ieUpKStW2Rh4raYo6UQPGgIVMsmT4RlrQ0MSqyvIPYsU0UdlsFiG25vCRh4eHsifCoDLXw8PDo2aD5VNlAWmqbA3WJFFegtHquQaCIMCr12i0GPIXqNROKFNdxA3NPFR0uGY6YDKTl1Gj96YtxGDGcP/tau6uoqLCbA6PfKrw008/jb/+7a8mt5Wv6izVV5EPNQFiQJBQWf8GYrJnQWGBybwYaekA+fFbMCynUqmqZnUZSVA2kPKtgqB4regCq2rL1FhQ0MRrQB4IytXn0IGllYZjYmLgonFB+cbyGs+Vi8ZFESx27NjRbL6NYQo6UUPGgIVMsmT4RlrQMAg1kkhzrisXNJSmgZqYzSJP+PTw8DBbh6RGwCKfKlvthKkIAsyc2I0O9ZiYoQIARaUVmLP6D/gO+5v4v24XcjwXQFBVJsS2M7I/wLpqu8uhXHwxsOYmGo1GLCRnItfBzc1NukjKi1BV27ZylpA8L6KwsHJVSBO9EYZ1f27dumX2mORF7gBYfPxhYWHiLBkTCcqG3r3z58+bfa3UWEvIzGsgODgYtmZppeHU1FSUl5YbfW+VXy9XvLfGjx+Pt956y2SS+vjx421+XES2xoCFTLLkg1XKYTGx+q38ZHH9+nWzs1nkC7SlpaVV1SExcmK7ePGi8v4MJ8HqdUiqBwFmkhhrMNMT4tw8BGMX/YbU64UQdBW4ueO/KGi3oX4L0qkg9qzUEoRJ6++4Qjkk4wKgVLk+z7Jly8Q/qmevVQZi8mEeKWAx0Rth6GGR9m/imGoELGa2lWvWrJl4rHlQJihXDgsakn2lvBQTrxV5QcLr16+Ll7dAzSDoOpCRkVGzIfXImtl30nvrCYgJ5YZCi84APqlZ5G/gfQOxd9/eGvc58L6BTCylRoEBCxll6QerlMNiYvVbeQ5Ldna22dks8um3tRXNqrE+DWCm0mw1AVD2WvgDMLaYrYmeAPc/+6Hlg7ORer0QAV4a/LH4FZReOw2cgmU1WwDLhqUs7IkoKysT/6hW0NdQF0e6HrIp4KZ6o2SkRRVN9EaMGTMGgBg4FBUVmTymus4S6tixY1W+i3xYsDLANAxz1Fa9Vj6bKCAgQPzDRBAgXW8j1lS6rZEf5le5bWUOS/X8sKX/WyqueyRfLNTXD999+119NZ/IrjhLiIyydPZPWlpaVU6CfDaLCwCVsifEmrLo0rd2E7OUiouLlZfLe24Mbais3lrDEwAmAxgMYAqAiUa2MZC3VVCjeYepCHjkTag1HujTzhcbXrgXpVdPiyfWYChn0wTDdM/NJiir7RqZJVPj/gGjPRHS0F31+6r8X/64tmzZ0uxMKX//qmlZ48aNU04XNxxX5dpPjz76KADZMgImKgi7uLjU6fjHjx9f9dqSz/6qfG0ZhjkUlXaNVK+V97D07t27alt5teXKbfv06QNbsqbSrbUVWac/Px15xXmK90BecR6em/GcTY6F6E5jDwsZZensn40bN5rtNZHXtZBWDTaRyBoZGSndjVQ4zUTCpbxwGgCzbajBgrwQSeXxqwVvtCx7Fe5OPQEA2sNrsexfX8LFSRbzRwJ4CMo1ktKM7NPQa2DJsJSlCcLmElllpF4sE8m88mE5aSqsC5R5PM7i/ytXrsQbb7xRNcxiItckM1P+YEMZ3BmEwfRjJe9lAqSkXwMpIDORbyTvYZHq4JhITq2+WnN9s6Z4ImB53SJHWIGYyNYYsJBRhqJZOzfthKAVgGYAigDVXhWG3D+k5oKGJnoC5PVCrDmxALCujL6ZNihYmBcibbsJcNVEwD/0NTirAqAvL0HO5s9RfHoPXJy+Vm67EWLQ1A61J/NW700x1rtiboaMbJ+urq5iAGdi+EjjVlUaf/DgweJ0ZRNB27Bhw6SLjhw5It6XCmLPhmFac2UOyeHDhwFUPq+GpFcjxfDkPTwSC4I7S4dP1Gq1+Xwj52ofcwLEgnxGcljuBGvKwls6rdqaoSaihooBC5lUUlwEoVRQ1MsQVAJKZcMxUtl1Ez0Bfn5+0kXyVYONkVdZldRSr0TBmryQ2pJzK7dt1ikGviHToFK5oDz3Km6s/RfKbxhZw0Y+dGJgrNIuYLbSqmJ7CwO2Fi1aiL0YJnpN5GvJPP300/jrM381HrSpldOapZ4TwwKMNyHWt6ns4TAsvufq6iom1vrA6BR0+crSarVarNK7EWJdkWYQn4fKJQfUKrViWwAme+QMgUh6errZfB95r4lUbj8PRhN561pu3xp1qe1S27RqrkBMTQEDFjIqNTUV+w8cEk+68t4QNfDb/oNSF3Nt00QDA6vGW1JSUsx+E76t4lYW9kYAsCg5V+XsCt/h09Cs+wgAQHHBAWRf/gSCtth0b4wzxEqkhp6I3TBeW8XS4SszJ1b5PqUp3iZ6TTw9PaWLUlNTxTaZOLnXqIUDmHy83N3FqWG+vr64eu2qGFDI21oZhMiDVk9PT7G+iwrKwnGV06o9m1W11eoeOQt62BTl9uXB1W2W26+L+qztYu1QE1FDxICFjFq5cqXZngBD/oI0pdRE74K8Oz4/P9/sN+G8vDxlIyztiUDl/9VP+kZWIDY3rdqw7eXcYgROmg9N0F0QBB3yXL6H1n+1OLvIHSZ7Y2rLtVCwZPhKgDjzR35iNdJr4+XlZXaoS1rrB7JaOCbuX14LZ+LEidixc4fJx2vy5MkAgPvvvx/fffddzbZW5uWMGDFCusjV1bVq+MvIPuUrO3fo0MFsgGvoNZB6RUz0LlTvNVm1cpU4JCMv3DY8psGv1MsViKmx4ywhMurIkSNm11w5cuQIANk6MsYCCFR211eyZs0baR8m7r8GQ8Ahn01iuNzYPuVDQrJ97k69gVEL90ETdBd0xfnIqvgHtC6rq/bTzsh9G1gShBiYmCVSg4m1lOTCwsLMzvwxOhxgwf0PHDjQ7HNwzz33AAAmTJggPj4aAHcDaF35WwNABTz22GNVh+Pvb3af8llKUi0eE8dlmIFmqEGCjVDOPNoEDLpvUI3eBcOQTGpqKjZt2oTU1FRs2bRFUWW2IWqsx0VkwB4WMsrb21v8w8RJ2HB9q1atzM5QadOmjXRTxVRlIzkJJguM1VKaHoB1PRxGhzhU8Ok/Hk99+zsEASi9looba+OgG37DujL+ls7oqaXarlqtFodETNQLkS/SJ5WTN/FcyUvzSzkcJmbJyHsjLE3k7NChQ1W+zWnZdpU5LEYDJguCO2nxPxPbHjhwQJqB5uLiIg4byZ9vZ8DZxfRHXGNdqbexHhcRAxYyatKkSfjhhx9MBheG4YCMjAyzwzxSDwxkC8uZyEmovlIuAOumIFvSw2FkSEi13RMtH/07PO7qA0EAnujTBv8ePxbQl1text+CIEQiQHxM5SfXatN6XVxcxJk/hiCoWtEweW0TaSaWiYBJPiynyOGodnKvnsNhaSJnREQEBg4aiL2/Vauyml2zyqqUAGxin/IEYcXif0a2NSz+l5qaih3bK9eoagXFzKPqa1QRUcPFgIXMMxFcGGRlZYl/mAgWpOsNzOQk1Fi7yJopyIDls4RkQ0IurdvB/+nX4eIaAqGiDB9O6IXxvUPxb11lr0QtgYViv5aW/AdqndZ79913I/l4ssmekC5dukjbhoaGmu01ad26teKuLc3hsCaR8+Spk0af15MnTyr2+dBDD+HgoYMm2/rwww9XtSkmxuzCmobeFUVPkA+qgrvKTzdO6SVqHBiwkFEbN240m/RqKAhX27d7eU+ANKvDRG+M0Tosli4SWIdZQp6dB8N35PNQu7ihIv86biTMw/iPzim3taBeiGQMxGGoyxCn/xbWbKtKpYIAQXwcY1HjhK2qTJaZPn06nnnmGZOL2T33XFX10gcffBALFiwwue1DDz2kaIMh12Hr1q04ePAg+vfvr1j5V86SRM7ExETkZufWKFoGAchNyFUsqBgVFWU8uKtsq1RcsNLhQ4fRu29v5CTIys37++HwocPS/5zSS9Q0MGAho6TZPyam3xqGb7Kzs80GC/LKqVJehoneGKNDQpYmshpyKOQnQWNF5lQArjujxbNPw7v5KADArYtJyF7/EfS3Cmpua00xOMM3/MrzJ/JrbtKvXz8cOHDAZOGyfv37AZDlkphIZpbnmsTExKCFXwvczLtZ4/5a+LWoEYzk5uZi4uSJyh6WWLGHpXqCpiU1Q6zJNZGCCxPVc6sHF2FhYcjOysa2bdtw4MABo8EVp/QSNQ0MWMgoacjBxEnIcH2nTp3MBgvyoYsWLVqIixqa+Cbs6+tbsyHWJLLmodaaJU6evmj5l9fg5t4ZAJDnvBz5ZcuBW0aqsVo4zOPs7Cz2DlnQy/T2229jZOxIkzVL3n33XQCVuSb3D8XOfTshhAlAAQAvQJWmwpB7h9Q4CScdThJ7IqotfCfviTCwZBXu6swlclqaa2I4rpjYGGzfsx26ATrxsVQBTsedcP9Q08HF8OHDTfYCAZzSS9QUMGAhoyytbREQEFCVa2LkBCxVwgXQs2dP/LrjV5PJqT179pS2dXd3x62SWyZzHdzd3JUNFiCuTyOvA1It30QT2hX+D8+Bk3sL6FGIbNf/4JbT7+anH1efFl39fwBBQUG4cvWKyeMKCgqSto2JiYGXlxcKCgtq1Czx8vJSnJSN5ZqMiB1h9CRsSU8EYJs1ZyzNNTGQgovN9Rdc1KV6LBE1LAxYyCjpG/6mnWIybDsAFwHVZuVaQgDEk5QTlCdgD9ToiRg8eDB+/fVXcduEmtsOHjxYcf/Hjx83OXTSqVMn6aLmzZuLRedM5Ju0aNEC/917AYGP/wsqtRPKStNww3seKtQZ4g4u1jx+aZ8myGezTJs2DW+++abJ3pjp06crbns8+Tj69O2NbFlvSEs/P/xerTekLifh2noibLXmjCW5Jga2DC44pZeo8WLhODJp1cpVGDFkhHgS/gRAAjBiyAisWrlK2kbqiRkJYAqAwZW/Y6pdD2D8+PFmt5WuR2WxMXnPzZjK33kAVMCjjz4qbTtq1KiqWTJXIFakvQJgM6BydUOHKf/C+xtPQ6V2QuHJncj8+mVUnMhQFBiDCujcubO0z5dffln8o/pIUeX/c+bMkS6KiooS/zCRb1I9kTQsLAw3srKxdetWvPvuu9i6dStuZGWLBeCMCA8PR2xsbL2ciBUJqnIXxV91TVA19PDIjynbzDEB9XtcRNQECPXs7bffFlBVKF0AIAQGBpq9za5du4SoqChBo9EIYWFhwuLFi62+3/z8fAGAkJ+fX9emkwmpqanCpk2bhNTUVKPXD71/qKByUwkYCwEvQcBYCCo3lTD0/qE1th103yABGii2hQbCoPsGKbZLSUkRXz9OyteS4X95W7Zs2SJeF6Tc1jm8lRD89BdC2zkbhA5zNwp/+zDe7D6//vprRRsACFBV27byf6Ntdau2raZmWx1BTGyM4OTppHgOnDydhJjYGHs3jYiaIEvP3zYJWLp06SJkZGRIP1lZWSa3v3DhguDh4SHMmjVLOHXqlPD1118LLi4uwqpVq6y6XwYs9pObmyvExMYoTtYxsTFCbm7ubW0rBTeRENCp8reR4EYQBKGFbwtx2+EQMAaC+7j+QuiLK4W2czYIvd/fJhy5mCMGFioY3SdUNQOL3bt3CyonlaKtKieVsHv37hr3LwUBAyCgPwQMcNwgwJrngIjI1uwasPTo0cPi7V999VWhU6dOisueffZZoV+/flbdLwMW+6utJ8baba05sV64cEHw8/cToFILze+bKrSds0FoO2eDMOrTHcJ17S1pu6H3DxXgXK0nxBlGe4MM4uLihCFDhghxcXH10lZHYc3zRURkK5aev1WCUL286O1555138OGHH8LHxwcajQZ9+/bFvHnz0L59e6PbDxo0CJGRkfjss8+kyxISEjB+/HgUFxcrpoTKlZaWiqXLK2m1WoSGhiI/P79qHRxqFCxNzswpLMWkL37FmZviS/qv94ZhTmwnuDhVpWrdvHmzZpVXEzVIbNlWIiISabVa+Pj41Hr+rvdZQn379sX333+PiIgIXL9+He+//z4GDBiAkydPws/Pr8b2mZmZCAxULhATGBiIiooKZGdnIzg42Oj9xMXFSTUrqHGzZOZH8uU8PBefhIx8AR6uTpj/WHc81D2kxna2nv7KWSpERLZR7wFLbGys9He3bt3Qv39/dOjQAd999x1mz55t9DbSoniVDJ0+1S+Xmzt3rmJ/hh4WaloEQcCPv6fj3fWnUKbTo31LT3w5JRrhgV5mb8fAgoioYbF5HRZPT09069YNZ8+eNXp9UFAQMjMzFZdlZWXB2dnZaI+MgUajgUajqde2UsNSUq7Dm2v/xKokcQnpmC6B+GhcD3i5GR9GJCKihsvmAUtpaSlOnz6NgQMHGr2+f//++OWXXxSXbd26Fb169TKZv0J0ObcY0+KTcPKaFmoV8EpMJ0y7r73ZXjkiImq46r1w3Msvv4zdu3cjLS0Nhw4dwmOPPQatVoupU6cCEIdynnzySWn7adOm4dKlS5g9ezZOnz6N//3vf/jmm2+qCncRVbMrJQsPLdiHk9e08PV0xQ9P98VzgzswWCEiasTqvYflypUreOKJJ5CdnQ1/f3/069cPBw8eRNu2Yi3wjIwMpKenS9uHhYVh06ZNeOmll/DFF18gJCQEn3/+uaKSKREA6PUCFu48h0+2p0IQgB6hzbF4UhRCmrvXfmMiImrQ6n1as71YOi2KGqb84nK8tDIZO85kAQAm9m2Dt0d1hsbZyc4tIyKi22G3ac1E9e3UNS2mxSchPbcYrs5qvD+mK8b34owwIqKmhAELObSEY1cwd80JlJTr0bqFO5ZMjkbXVj72bhYREd1hDFjIIZVV6PH+xlP4/oC4rPCgCH98NqEnWni62rllRERkDwxYyOFk5pdg+rIkHE3PAwC8MPQuzLo/Ak5qzgIiImqqGLCQQzl4IQfP/3gU2YVl8HJzxqcTemLY3YG135CIiBo1BizkEARBwH/3puHfW85ApxfQKcgLX06JRls/T3s3jYiIHAADFrK7wtIKzFn1BzaeyAAAjI1shXlju8HdlVOWiYhIxICF7OpcViGmxSfhXFYhnNUq/GNUZ0zp15ZVa4mISIEBC9nNlj8z8PLPf6CwtAKB3hosmhSF6La+9m4WERE5IAYsdMdV6PT4cGsKvtx9AQDQN8wXCyZGIsDLzc4tIyIiR8WAhe6o7MJSzPzxGA5cyAEA/G1gGOaM7ARnp3pfh5OIiBoRBix0xxxLv4npy44iI78EHq5O+PCxHniwe7C9m0VERA0AAxayOUEQsOxQOt795STKdQLa+3viy8nRCA/0snfTiIiogWDAQjZVUq7DGwl/YvXRKwCAkV2C8OG47vByc7Fzy4iIqCFhwEI2czm3GM/+kIRTGVqoVcCckZ3wzKD2nLJMRERWY8BCNrEzJQsv/pSM/Fvl8PN0xYInIjHgrpb2bhYRETVQDFioXun1Aj7fcRaf/XoWggD0CG2OxZOiENLc3d5NIyKiBowBC9Wb/OJyvLjiGHam3AAATOrbBv8Y1RkaZ5bYJyKi28OAherFyWv5eC7+KNJzi6FxVuP9MV0xrleovZtFRESNBAMWum1rjl7B3DUnUFqhR6ivOxZPikbXVj72bhYRETUiDFiozsoq9Hhvwyn8cPASAGBwR398OqEnmnu42rllRETU2DBgoTrJyL+F6cuO4lh6HgBg1rBwzBoWDrWaU5aJiKj+MWAhqx04n4OZy48iu7AM3m7O+PTxnhjaKdDezSIiokaMAQtZTBAEfL33Aj7YkgKdXsDdwd5YMjkKbf087d00IiJq5BiwkEUKSyvw6qrj2HQiEwDwSGQr/GtsN7i7csoyERHZHgMWqtW5rEI8+8MRnL9RBBcnFf7xUGdM7teWJfaJiOiOYcBCZm0+kYGXfz6OojIdAr01WDQpGtFtW9i7WURE1MQwYCGjKnR6fJiYgi/3XAAA9GvviwVPRMHfS2PnlhERUVPEgIVqyC4sxfM/HsXBC7kAgGcGtcerMR3h7KS2c8uIiKipYsBCCkfTb2J6/FFkakvg6eqED8f1wAPdgu3dLCIiauIYsBAAccpy/KF0/POXkyjXCejg74kvp0TjrgAvezeNiIgI9d7HHxcXh969e8PLywsBAQEYM2YMUlJSzN5m165dUKlUNX7OnDlT380jI26V6fD3n4/jrbV/olwnILZrENY9fy+DFSIichj13sOye/duzJgxA71790ZFRQXeeOMNjBgxAqdOnYKnp/kCYykpKfD29pb+9/f3r+/mUTXpOcV4Nj4JpzO0UKuA12I74W8D23PKMhEROZR6D1i2bNmi+P/bb79FQEAAkpKSMGjQILO3DQgIQPPmzeu7SWTCzjNZmPXTMWhLKuDn6YoFEyMxoENLezeLiIioBptP+8jPzwcA+Pr61rptZGQkgoODMWzYMOzcudPstqWlpdBqtYofsoxeL+CTban4y3eHoS2pQM/Q5tjwwr0MVoiIyGHZNGARBAGzZ8/Gvffei65du5rcLjg4GF999RVWr16NNWvWoGPHjhg2bBj27Nlj8jZxcXHw8fGRfkJDQ21xCI1OXnEZnv7uMD779SwEAZjSry1WPNsPwT7u9m4aERGRSSpBEARb7XzGjBnYuHEj9u3bh9atW1t121GjRkGlUmH9+vVGry8tLUVpaan0v1arRWhoKPLz8xV5MFTlz6v5eG5ZEi7n3oLGWY15Y7vh0WjrnhciIqL6pNVq4ePjU+v522bTmmfOnIn169djz549VgcrANCvXz/Ex8ebvF6j0UCjYdVVS61KuoI3Ek6gtEKPUF93LJkcjS4hPvZuFhERkUXqPWARBAEzZ85EQkICdu3ahbCwsDrt59ixYwgOZsGy21VaocN7G04h/mA6AGBIR398OiESPh4udm4ZERGR5eo9YJkxYwZ+/PFHrFu3Dl5eXsjMzAQA+Pj4wN1dzJOYO3curl69iu+//x4A8Omnn6Jdu3bo0qULysrKEB8fj9WrV2P16tX13bwmJSP/Fp6LP4rky3lQqYBZw8LxwtBwqNWcskxERA1LvQcsixcvBgAMHjxYcfm3336Lp556CgCQkZGB9PR06bqysjK8/PLLuHr1Ktzd3dGlSxds3LgRDzzwQH03r8nYfz4bM388hpyiMni7OeOzxyMxpFOAvZtFRERUJzZNur2TLE3aaewEQcBXey7ggy1noBeAu4O98eXkaLTx87B304iIiGqwe9It3XmFpRV45efj2PynOAz3SFQr/GtMN7i7Otm5ZURERLeHAUsjcS6rAM/+kITzN4rg4qTCP0Z1weS+bVhin4iIGgUGLI3Axj8y8Oqq4ygq0yHI2w2LJkchqk0LezeLiIio3jBgacAqdHrMT0zBV3suAAD6tffFwolRaNmM9WmIiKhxYcDSQN0oKMXM5Udx8EIuAODZQe3xSkxHODvZfHkoIiKiO44BSwOUdOkmZiw7ikxtCTxdnfDRuB6I7cYie0RE1HgxYGlABEFA/MFL+OeGUyjXCejg74kvp/TCXQHN7N00IiIim2LA0kDcKtPhjYQTWHPsKgDggW5BmP9YDzTT8CkkIqLGj2e7BuBSThGmxR/F6Qwt1CrgtdhO+NvA9pyyTERETQYDFge348x1vPhTMrQlFWjZzBWfPxGJAR1a2rtZREREdxQDFgel0wv47Nez+PzXswCAyDbNsWhSFIJ93O3cMiIiojuPAYsDyisuw6yfkrE79QYA4Mn+bfHmg53h6swpy0RE1DQxYHEwf17Nx7T4JFy5eQsaZzXmje2GR6Nb27tZREREdsWAxYGsSrqCNxJOoLRCjza+Hlg8OQpdQnzs3SwiIiK7Y8DiAEordPjnL6ew7FA6AGBopwB8Mr4nfDxc7NwyIiIix8CAxc4y8m/hufijSL6cB5UKeHFYBGYOvQtqNacsExERGTBgsaP957Ixc/kx5BSVwcfdBZ8+3hNDOgbYu1lEREQOhwGLHQiCgC/3XMD8LWegF4DOwd5YMjkabfw87N00IiIih8SA5Q4rKCnHKz//gS0nMwEAj0a1xr/GdoWbi5OdW0ZEROS4GLDcQWevF+DZ+CRcuFEEFycV3h7VBZP6tmGJfSIiolowYLlDNv6RgVdWHUdxmQ7BPm5YNCkKkW1a2LtZREREDQIDFhur0OnxwZYz+HpvGgCgf3s/LJgYiZbNNHZuGRERUcPBgMWGbhSU4vkfj+JQWi4A4Nn72uOVER3h7MQS+0RERNZgwGIjSZdyMX3ZUVzXlsLT1QkfjeuB2G7B9m4WERFRg8SApZ4JgoAfDl7CextOoVwn4K6AZlgyORp3BTSzd9OIiIgaLAYs9ehWmQ6vJ5xAwrGrAIAHuwXjg8e6o5mGDzMREdHt4Jm0nlzKKcKzPyThTGYBnNQqzI3thKfvDeOUZSIionrAgKUe/Hr6Ol5ckYyCkgq0bOaKhROj0K+9n72bRURE1GgwYLkNOr2Az7an4vMd5wAAUW2aY9GkaAT5uNm5ZURERI0LA5Y6yisuw6yfkrE79QYA4Mn+bfHmg53h6swpy0RERPWNAUsd/Hk1H9Pik3Dl5i24uagxb2w3PBLV2t7NIiIiarRs1h2waNEihIWFwc3NDdHR0di7d6/Z7Xfv3o3o6Gi4ubmhffv2WLJkia2adltWHrmMRxfvx5Wbt9DG1wNrnruHwQoREZGN2SRgWbFiBV588UW88cYbOHbsGAYOHIjY2Fikp6cb3T4tLQ0PPPAABg4ciGPHjuH111/HCy+8gNWrV9uieXVSWqHD3DUn8OqqP1BaocewTgH45fl70TnE295NIyIiavRUgiAI9b3Tvn37IioqCosXL5Yuu/vuuzFmzBjExcXV2H7OnDlYv349Tp8+LV02bdo0HD9+HAcOHLDoPrVaLXx8fJCfnw9v7/oNIq7l3cJz8Uk4fiUfKhXw0v0ReH7IXVCrOWWZiIjodlh6/q73HpaysjIkJSVhxIgRistHjBiB/fv3G73NgQMHamwfExODI0eOoLy83OhtSktLodVqFT+28Nu5bDy0YB+OX8mHj7sLvn2qN14YFs5ghYiI6A6q94AlOzsbOp0OgYGBissDAwORmZlp9DaZmZlGt6+oqEB2drbR28TFxcHHx0f6CQ0NrZ8DkCkuq8Csn44ht6gMXUK8sWHmvRjcMaDe74eIiIjMs1nSbfUKr4IgmK36amx7Y5cbzJ07F/n5+dLP5cuXb7PFNXm4OuOTCT0xvldrrH5uAEJ9Per9PoiIiKh29T6tuWXLlnBycqrRm5KVlVWjF8UgKCjI6PbOzs7w8zNeMVaj0UCj0dRPo80YGO6PgeH+Nr8fIiIiMq3ee1hcXV0RHR2Nbdu2KS7ftm0bBgwYYPQ2/fv3r7H91q1b0atXL7i4uNR3E4mIiKiBscmQ0OzZs/Hf//4X//vf/3D69Gm89NJLSE9Px7Rp0wCIwzlPPvmktP20adNw6dIlzJ49G6dPn8b//vc/fPPNN3j55Zdt0TwiIiJqYGxS6XbChAnIycnBP//5T2RkZKBr167YtGkT2rZtCwDIyMhQ1GQJCwvDpk2b8NJLL+GLL75ASEgIPv/8czz66KO2aB4RERE1MDapw2IPtqzDQkRERLZhtzosRERERPWNAQsRERE5PAYsRERE5PAYsBAREZHDY8BCREREDo8BCxERETk8BixERETk8BiwEBERkcNjwEJEREQOzyal+e3BULBXq9XauSVERERkKcN5u7bC+40mYCkoKAAAhIaG2rklREREZK2CggL4+PiYvL7RrCWk1+tx7do1eHl5QaVS1dt+tVotQkNDcfnyZa5R1ADw+Wo4+Fw1HHyuGpaG9nwJgoCCggKEhIRArTadqdJoeljUajVat25ts/17e3s3iCeeRHy+Gg4+Vw0Hn6uGpSE9X+Z6VgyYdEtEREQOjwELEREROTwGLLXQaDR4++23odFo7N0UsgCfr4aDz1XDweeqYWmsz1ejSbolIiKixos9LEREROTwGLAQERGRw2PAQkRERA6PAQsRERE5PAYstVi0aBHCwsLg5uaG6Oho7N27195NomreeecdqFQqxU9QUJC9m0WV9uzZg1GjRiEkJAQqlQpr165VXC8IAt555x2EhITA3d0dgwcPxsmTJ+3T2CautufqqaeeqvFe69evn30a28TFxcWhd+/e8PLyQkBAAMaMGYOUlBTFNo3tvcWAxYwVK1bgxRdfxBtvvIFjx45h4MCBiI2NRXp6ur2bRtV06dIFGRkZ0s+JEyfs3SSqVFRUhB49emDhwoVGr58/fz7+85//YOHChTh8+DCCgoIwfPhwaX0wunNqe64AYOTIkYr32qZNm+5gC8lg9+7dmDFjBg4ePIht27ahoqICI0aMQFFRkbRNo3tvCWRSnz59hGnTpiku69Spk/Daa6/ZqUVkzNtvvy306NHD3s0gCwAQEhISpP/1er0QFBQk/Pvf/5YuKykpEXx8fIQlS5bYoYVkUP25EgRBmDp1qjB69Gi7tIfMy8rKEgAIu3fvFgShcb632MNiQllZGZKSkjBixAjF5SNGjMD+/fvt1Coy5ezZswgJCUFYWBgef/xxXLhwwd5NIgukpaUhMzNT8T7TaDS47777+D5zULt27UJAQAAiIiLwt7/9DVlZWfZuEgHIz88HAPj6+gJonO8tBiwmZGdnQ6fTITAwUHF5YGAgMjMz7dQqMqZv3774/vvvkZiYiK+//hqZmZkYMGAAcnJy7N00qoXhvcT3WcMQGxuLZcuWYceOHfj4449x+PBhDB06FKWlpfZuWpMmCAJmz56Ne++9F127dgXQON9bjWa1ZltRqVSK/wVBqHEZ2VdsbKz0d7du3dC/f3906NAB3333HWbPnm3HlpGl+D5rGCZMmCD93bVrV/Tq1Qtt27bFxo0b8cgjj9ixZU3b888/jz/++AP79u2rcV1jem+xh8WEli1bwsnJqUYkmpWVVSNiJcfi6emJbt264ezZs/ZuCtXCMJuL77OGKTg4GG3btuV7zY5mzpyJ9evXY+fOnWjdurV0eWN8bzFgMcHV1RXR0dHYtm2b4vJt27ZhwIABdmoVWaK0tBSnT59GcHCwvZtCtQgLC0NQUJDifVZWVobdu3fzfdYA5OTk4PLly3yv2YEgCHj++eexZs0a7NixA2FhYYrrG+N7i0NCZsyePRtTpkxBr1690L9/f3z11VdIT0/HtGnT7N00knn55ZcxatQotGnTBllZWXj//feh1WoxdepUezeNABQWFuLcuXPS/2lpaUhOToavry/atGmDF198EfPmzUN4eDjCw8Mxb948eHh4YOLEiXZsddNk7rny9fXFO++8g0cffRTBwcG4ePEiXn/9dbRs2RJjx461Y6ubphkzZuDHH3/EunXr4OXlJfWk+Pj4wN3dHSqVqvG9t+w6R6kB+OKLL4S2bdsKrq6uQlRUlDRljBzHhAkThODgYMHFxUUICQkRHnnkEeHkyZP2bhZV2rlzpwCgxs/UqVMFQRCnX7799ttCUFCQoNFohEGDBgknTpywb6ObKHPPVXFxsTBixAjB399fcHFxEdq0aSNMnTpVSE9Pt3ezmyRjzxMA4dtvv5W2aWzvLZUgCMKdD5OIiIiILMccFiIiInJ4DFiIiIjI4TFgISIiIofHgIWIiIgcHgMWIiIicngMWIiIiMjhMWAhIiIih8eAhYiIiBweAxYiIiJyeAxYiIiIyOExYCEiIiKHx4CFiIiIHN7/A/J0lTBvVaL+AAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_train_predict = sample_predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_test_predict = sample_predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "f574ffdb", "metadata": {}, "source": [ "Train neural network for goalkeepers.\n", "\n", "For clean sheet probability prediction, a Bernoulli distribution is used." ] }, { "cell_type": "code", "execution_count": 57, "id": "41e7e1ee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/2000\n", "8/8 [==============================] - 4s 102ms/step - loss: 86.2533 - distribution_lambda_14_loss: 76.3453 - distribution_lambda_15_loss: 8.9897 - distribution_lambda_16_loss: 0.9182 - val_loss: 74.3172 - val_distribution_lambda_14_loss: 65.4215 - val_distribution_lambda_15_loss: 7.9738 - val_distribution_lambda_16_loss: 0.9220\n", "Epoch 2/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 68.8012 - distribution_lambda_14_loss: 60.2621 - distribution_lambda_15_loss: 7.6220 - distribution_lambda_16_loss: 0.9171 - val_loss: 59.5450 - val_distribution_lambda_14_loss: 51.7760 - val_distribution_lambda_15_loss: 6.8508 - val_distribution_lambda_16_loss: 0.9182\n", "Epoch 3/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 55.4490 - distribution_lambda_14_loss: 47.9629 - distribution_lambda_15_loss: 6.5739 - distribution_lambda_16_loss: 0.9123 - val_loss: 48.1461 - val_distribution_lambda_14_loss: 41.3038 - val_distribution_lambda_15_loss: 5.9274 - val_distribution_lambda_16_loss: 0.9148\n", "Epoch 4/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 45.1109 - distribution_lambda_14_loss: 38.4840 - distribution_lambda_15_loss: 5.7175 - distribution_lambda_16_loss: 0.9094 - val_loss: 39.7642 - val_distribution_lambda_14_loss: 33.6357 - val_distribution_lambda_15_loss: 5.2195 - val_distribution_lambda_16_loss: 0.9090\n", "Epoch 5/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 37.5347 - distribution_lambda_14_loss: 31.5482 - distribution_lambda_15_loss: 5.0838 - distribution_lambda_16_loss: 0.9027 - val_loss: 33.6112 - val_distribution_lambda_14_loss: 28.0225 - val_distribution_lambda_15_loss: 4.6863 - val_distribution_lambda_16_loss: 0.9024\n", "Epoch 6/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 32.0395 - distribution_lambda_14_loss: 26.5573 - distribution_lambda_15_loss: 4.5872 - distribution_lambda_16_loss: 0.8950 - val_loss: 28.9921 - val_distribution_lambda_14_loss: 23.8037 - val_distribution_lambda_15_loss: 4.2949 - val_distribution_lambda_16_loss: 0.8935\n", "Epoch 7/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 28.0116 - distribution_lambda_14_loss: 22.8873 - distribution_lambda_15_loss: 4.2382 - distribution_lambda_16_loss: 0.8861 - val_loss: 25.4246 - val_distribution_lambda_14_loss: 20.5564 - val_distribution_lambda_15_loss: 3.9849 - val_distribution_lambda_16_loss: 0.8833\n", "Epoch 8/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 24.5654 - distribution_lambda_14_loss: 19.7377 - distribution_lambda_15_loss: 3.9525 - distribution_lambda_16_loss: 0.8752 - val_loss: 22.6632 - val_distribution_lambda_14_loss: 18.0421 - val_distribution_lambda_15_loss: 3.7491 - val_distribution_lambda_16_loss: 0.8720\n", "Epoch 9/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 22.0522 - distribution_lambda_14_loss: 17.4524 - distribution_lambda_15_loss: 3.7348 - distribution_lambda_16_loss: 0.8650 - val_loss: 20.4611 - val_distribution_lambda_14_loss: 16.0396 - val_distribution_lambda_15_loss: 3.5610 - val_distribution_lambda_16_loss: 0.8605\n", "Epoch 10/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 19.9589 - distribution_lambda_14_loss: 15.5523 - distribution_lambda_15_loss: 3.5541 - distribution_lambda_16_loss: 0.8525 - val_loss: 18.6782 - val_distribution_lambda_14_loss: 14.4184 - val_distribution_lambda_15_loss: 3.4119 - val_distribution_lambda_16_loss: 0.8479\n", "Epoch 11/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 18.3356 - distribution_lambda_14_loss: 14.0772 - distribution_lambda_15_loss: 3.4192 - distribution_lambda_16_loss: 0.8392 - val_loss: 17.2069 - val_distribution_lambda_14_loss: 13.0805 - val_distribution_lambda_15_loss: 3.2908 - val_distribution_lambda_16_loss: 0.8356\n", "Epoch 12/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 16.9504 - distribution_lambda_14_loss: 12.8092 - distribution_lambda_15_loss: 3.3136 - distribution_lambda_16_loss: 0.8276 - val_loss: 15.9607 - val_distribution_lambda_14_loss: 11.9492 - val_distribution_lambda_15_loss: 3.1890 - val_distribution_lambda_16_loss: 0.8226\n", "Epoch 13/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 15.7589 - distribution_lambda_14_loss: 11.7293 - distribution_lambda_15_loss: 3.2153 - distribution_lambda_16_loss: 0.8143 - val_loss: 14.9022 - val_distribution_lambda_14_loss: 10.9912 - val_distribution_lambda_15_loss: 3.1003 - val_distribution_lambda_16_loss: 0.8107\n", "Epoch 14/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 14.7430 - distribution_lambda_14_loss: 10.8122 - distribution_lambda_15_loss: 3.1286 - distribution_lambda_16_loss: 0.8022 - val_loss: 13.9939 - val_distribution_lambda_14_loss: 10.1708 - val_distribution_lambda_15_loss: 3.0252 - val_distribution_lambda_16_loss: 0.7980\n", "Epoch 15/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 13.8760 - distribution_lambda_14_loss: 10.0294 - distribution_lambda_15_loss: 3.0561 - distribution_lambda_16_loss: 0.7904 - val_loss: 13.2096 - val_distribution_lambda_14_loss: 9.4642 - val_distribution_lambda_15_loss: 2.9613 - val_distribution_lambda_16_loss: 0.7840\n", "Epoch 16/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 13.1135 - distribution_lambda_14_loss: 9.3411 - distribution_lambda_15_loss: 2.9952 - distribution_lambda_16_loss: 0.7772 - val_loss: 12.5328 - val_distribution_lambda_14_loss: 8.8556 - val_distribution_lambda_15_loss: 2.9057 - val_distribution_lambda_16_loss: 0.7716\n", "Epoch 17/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 12.5135 - distribution_lambda_14_loss: 8.8023 - distribution_lambda_15_loss: 2.9471 - distribution_lambda_16_loss: 0.7641 - val_loss: 11.9401 - val_distribution_lambda_14_loss: 8.3237 - val_distribution_lambda_15_loss: 2.8566 - val_distribution_lambda_16_loss: 0.7598\n", "Epoch 18/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 11.9187 - distribution_lambda_14_loss: 8.2660 - distribution_lambda_15_loss: 2.9010 - distribution_lambda_16_loss: 0.7517 - val_loss: 11.4215 - val_distribution_lambda_14_loss: 7.8605 - val_distribution_lambda_15_loss: 2.8142 - val_distribution_lambda_16_loss: 0.7468\n", "Epoch 19/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 11.4098 - distribution_lambda_14_loss: 7.8053 - distribution_lambda_15_loss: 2.8645 - distribution_lambda_16_loss: 0.7400 - val_loss: 10.9618 - val_distribution_lambda_14_loss: 7.4499 - val_distribution_lambda_15_loss: 2.7772 - val_distribution_lambda_16_loss: 0.7347\n", "Epoch 20/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 10.9789 - distribution_lambda_14_loss: 7.4213 - distribution_lambda_15_loss: 2.8282 - distribution_lambda_16_loss: 0.7294 - val_loss: 10.5532 - val_distribution_lambda_14_loss: 7.0862 - val_distribution_lambda_15_loss: 2.7440 - val_distribution_lambda_16_loss: 0.7230\n", "Epoch 21/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 10.5841 - distribution_lambda_14_loss: 7.0725 - distribution_lambda_15_loss: 2.7939 - distribution_lambda_16_loss: 0.7177 - val_loss: 10.1882 - val_distribution_lambda_14_loss: 6.7630 - val_distribution_lambda_15_loss: 2.7132 - val_distribution_lambda_16_loss: 0.7120\n", "Epoch 22/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 10.2175 - distribution_lambda_14_loss: 6.7422 - distribution_lambda_15_loss: 2.7687 - distribution_lambda_16_loss: 0.7066 - val_loss: 9.8598 - val_distribution_lambda_14_loss: 6.4730 - val_distribution_lambda_15_loss: 2.6853 - val_distribution_lambda_16_loss: 0.7015\n", "Epoch 23/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.9116 - distribution_lambda_14_loss: 6.4748 - distribution_lambda_15_loss: 2.7400 - distribution_lambda_16_loss: 0.6968 - val_loss: 9.5644 - val_distribution_lambda_14_loss: 6.2131 - val_distribution_lambda_15_loss: 2.6602 - val_distribution_lambda_16_loss: 0.6911\n", "Epoch 24/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.6051 - distribution_lambda_14_loss: 6.1998 - distribution_lambda_15_loss: 2.7183 - distribution_lambda_16_loss: 0.6871 - val_loss: 9.2986 - val_distribution_lambda_14_loss: 5.9801 - val_distribution_lambda_15_loss: 2.6368 - val_distribution_lambda_16_loss: 0.6817\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 25/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 9.3625 - distribution_lambda_14_loss: 5.9934 - distribution_lambda_15_loss: 2.6906 - distribution_lambda_16_loss: 0.6786 - val_loss: 9.0576 - val_distribution_lambda_14_loss: 5.7695 - val_distribution_lambda_15_loss: 2.6150 - val_distribution_lambda_16_loss: 0.6731\n", "Epoch 26/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 9.1339 - distribution_lambda_14_loss: 5.7868 - distribution_lambda_15_loss: 2.6779 - distribution_lambda_16_loss: 0.6692 - val_loss: 8.8384 - val_distribution_lambda_14_loss: 5.5782 - val_distribution_lambda_15_loss: 2.5951 - val_distribution_lambda_16_loss: 0.6652\n", "Epoch 27/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.9139 - distribution_lambda_14_loss: 5.5956 - distribution_lambda_15_loss: 2.6553 - distribution_lambda_16_loss: 0.6629 - val_loss: 8.6370 - val_distribution_lambda_14_loss: 5.4037 - val_distribution_lambda_15_loss: 2.5761 - val_distribution_lambda_16_loss: 0.6572\n", "Epoch 28/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.7153 - distribution_lambda_14_loss: 5.4136 - distribution_lambda_15_loss: 2.6462 - distribution_lambda_16_loss: 0.6555 - val_loss: 8.4551 - val_distribution_lambda_14_loss: 5.2470 - val_distribution_lambda_15_loss: 2.5584 - val_distribution_lambda_16_loss: 0.6496\n", "Epoch 29/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.5409 - distribution_lambda_14_loss: 5.2691 - distribution_lambda_15_loss: 2.6236 - distribution_lambda_16_loss: 0.6482 - val_loss: 8.2898 - val_distribution_lambda_14_loss: 5.1039 - val_distribution_lambda_15_loss: 2.5411 - val_distribution_lambda_16_loss: 0.6448\n", "Epoch 30/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.3895 - distribution_lambda_14_loss: 5.1352 - distribution_lambda_15_loss: 2.6106 - distribution_lambda_16_loss: 0.6438 - val_loss: 8.1378 - val_distribution_lambda_14_loss: 4.9733 - val_distribution_lambda_15_loss: 2.5248 - val_distribution_lambda_16_loss: 0.6397\n", "Epoch 31/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.2238 - distribution_lambda_14_loss: 4.9901 - distribution_lambda_15_loss: 2.5946 - distribution_lambda_16_loss: 0.6391 - val_loss: 7.9970 - val_distribution_lambda_14_loss: 4.8536 - val_distribution_lambda_15_loss: 2.5093 - val_distribution_lambda_16_loss: 0.6341\n", "Epoch 32/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 8.0905 - distribution_lambda_14_loss: 4.8762 - distribution_lambda_15_loss: 2.5811 - distribution_lambda_16_loss: 0.6332 - val_loss: 7.8681 - val_distribution_lambda_14_loss: 4.7441 - val_distribution_lambda_15_loss: 2.4952 - val_distribution_lambda_16_loss: 0.6288\n", "Epoch 33/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.9675 - distribution_lambda_14_loss: 4.7743 - distribution_lambda_15_loss: 2.5643 - distribution_lambda_16_loss: 0.6288 - val_loss: 7.7489 - val_distribution_lambda_14_loss: 4.6430 - val_distribution_lambda_15_loss: 2.4812 - val_distribution_lambda_16_loss: 0.6247\n", "Epoch 34/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.8490 - distribution_lambda_14_loss: 4.6708 - distribution_lambda_15_loss: 2.5541 - distribution_lambda_16_loss: 0.6241 - val_loss: 7.6368 - val_distribution_lambda_14_loss: 4.5485 - val_distribution_lambda_15_loss: 2.4675 - val_distribution_lambda_16_loss: 0.6209\n", "Epoch 35/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.7417 - distribution_lambda_14_loss: 4.5756 - distribution_lambda_15_loss: 2.5451 - distribution_lambda_16_loss: 0.6210 - val_loss: 7.5342 - val_distribution_lambda_14_loss: 4.4624 - val_distribution_lambda_15_loss: 2.4545 - val_distribution_lambda_16_loss: 0.6173\n", "Epoch 36/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.6329 - distribution_lambda_14_loss: 4.4854 - distribution_lambda_15_loss: 2.5291 - distribution_lambda_16_loss: 0.6184 - val_loss: 7.4379 - val_distribution_lambda_14_loss: 4.3825 - val_distribution_lambda_15_loss: 2.4418 - val_distribution_lambda_16_loss: 0.6137\n", "Epoch 37/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.5324 - distribution_lambda_14_loss: 4.4050 - distribution_lambda_15_loss: 2.5131 - distribution_lambda_16_loss: 0.6142 - val_loss: 7.3487 - val_distribution_lambda_14_loss: 4.3089 - val_distribution_lambda_15_loss: 2.4295 - val_distribution_lambda_16_loss: 0.6103\n", "Epoch 38/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.4428 - distribution_lambda_14_loss: 4.3245 - distribution_lambda_15_loss: 2.5068 - distribution_lambda_16_loss: 0.6115 - val_loss: 7.2635 - val_distribution_lambda_14_loss: 4.2389 - val_distribution_lambda_15_loss: 2.4175 - val_distribution_lambda_16_loss: 0.6071\n", "Epoch 39/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.3695 - distribution_lambda_14_loss: 4.2605 - distribution_lambda_15_loss: 2.4999 - distribution_lambda_16_loss: 0.6091 - val_loss: 7.1847 - val_distribution_lambda_14_loss: 4.1747 - val_distribution_lambda_15_loss: 2.4057 - val_distribution_lambda_16_loss: 0.6043\n", "Epoch 40/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.2902 - distribution_lambda_14_loss: 4.2024 - distribution_lambda_15_loss: 2.4809 - distribution_lambda_16_loss: 0.6069 - val_loss: 7.1118 - val_distribution_lambda_14_loss: 4.1151 - val_distribution_lambda_15_loss: 2.3942 - val_distribution_lambda_16_loss: 0.6025\n", "Epoch 41/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.2169 - distribution_lambda_14_loss: 4.1360 - distribution_lambda_15_loss: 2.4756 - distribution_lambda_16_loss: 0.6052 - val_loss: 7.0433 - val_distribution_lambda_14_loss: 4.0594 - val_distribution_lambda_15_loss: 2.3830 - val_distribution_lambda_16_loss: 0.6008\n", "Epoch 42/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.1537 - distribution_lambda_14_loss: 4.0874 - distribution_lambda_15_loss: 2.4619 - distribution_lambda_16_loss: 0.6043 - val_loss: 6.9784 - val_distribution_lambda_14_loss: 4.0070 - val_distribution_lambda_15_loss: 2.3721 - val_distribution_lambda_16_loss: 0.5992\n", "Epoch 43/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.0880 - distribution_lambda_14_loss: 4.0300 - distribution_lambda_15_loss: 2.4552 - distribution_lambda_16_loss: 0.6028 - val_loss: 6.9174 - val_distribution_lambda_14_loss: 3.9580 - val_distribution_lambda_15_loss: 2.3616 - val_distribution_lambda_16_loss: 0.5979\n", "Epoch 44/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.0292 - distribution_lambda_14_loss: 3.9815 - distribution_lambda_15_loss: 2.4462 - distribution_lambda_16_loss: 0.6015 - val_loss: 6.8594 - val_distribution_lambda_14_loss: 3.9118 - val_distribution_lambda_15_loss: 2.3510 - val_distribution_lambda_16_loss: 0.5966\n", "Epoch 45/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.9626 - distribution_lambda_14_loss: 3.9296 - distribution_lambda_15_loss: 2.4333 - distribution_lambda_16_loss: 0.5997 - val_loss: 6.8054 - val_distribution_lambda_14_loss: 3.8684 - val_distribution_lambda_15_loss: 2.3407 - val_distribution_lambda_16_loss: 0.5963\n", "Epoch 46/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.9123 - distribution_lambda_14_loss: 3.8941 - distribution_lambda_15_loss: 2.4189 - distribution_lambda_16_loss: 0.5994 - val_loss: 6.7544 - val_distribution_lambda_14_loss: 3.8276 - val_distribution_lambda_15_loss: 2.3308 - val_distribution_lambda_16_loss: 0.5960\n", "Epoch 47/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.8667 - distribution_lambda_14_loss: 3.8541 - distribution_lambda_15_loss: 2.4135 - distribution_lambda_16_loss: 0.5991 - val_loss: 6.7093 - val_distribution_lambda_14_loss: 3.7896 - val_distribution_lambda_15_loss: 2.3244 - val_distribution_lambda_16_loss: 0.5952\n", "Epoch 48/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.8166 - distribution_lambda_14_loss: 3.8144 - distribution_lambda_15_loss: 2.4033 - distribution_lambda_16_loss: 0.5988 - val_loss: 6.6644 - val_distribution_lambda_14_loss: 3.7537 - val_distribution_lambda_15_loss: 2.3163 - val_distribution_lambda_16_loss: 0.5944\n", "Epoch 49/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 6.7670 - distribution_lambda_14_loss: 3.7761 - distribution_lambda_15_loss: 2.3934 - distribution_lambda_16_loss: 0.5976 - val_loss: 6.6202 - val_distribution_lambda_14_loss: 3.7194 - val_distribution_lambda_15_loss: 2.3071 - val_distribution_lambda_16_loss: 0.5937\n", "Epoch 50/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.7262 - distribution_lambda_14_loss: 3.7448 - distribution_lambda_15_loss: 2.3839 - distribution_lambda_16_loss: 0.5974 - val_loss: 6.5777 - val_distribution_lambda_14_loss: 3.6872 - val_distribution_lambda_15_loss: 2.2975 - val_distribution_lambda_16_loss: 0.5929\n", "Epoch 51/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.6809 - distribution_lambda_14_loss: 3.7106 - distribution_lambda_15_loss: 2.3731 - distribution_lambda_16_loss: 0.5972 - val_loss: 6.5368 - val_distribution_lambda_14_loss: 3.6569 - val_distribution_lambda_15_loss: 2.2878 - val_distribution_lambda_16_loss: 0.5920\n", "Epoch 52/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.6402 - distribution_lambda_14_loss: 3.6802 - distribution_lambda_15_loss: 2.3638 - distribution_lambda_16_loss: 0.5961 - val_loss: 6.4977 - val_distribution_lambda_14_loss: 3.6280 - val_distribution_lambda_15_loss: 2.2785 - val_distribution_lambda_16_loss: 0.5913\n", "Epoch 53/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.5999 - distribution_lambda_14_loss: 3.6481 - distribution_lambda_15_loss: 2.3564 - distribution_lambda_16_loss: 0.5955 - val_loss: 6.4608 - val_distribution_lambda_14_loss: 3.6005 - val_distribution_lambda_15_loss: 2.2697 - val_distribution_lambda_16_loss: 0.5906\n", "Epoch 54/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.5672 - distribution_lambda_14_loss: 3.6257 - distribution_lambda_15_loss: 2.3472 - distribution_lambda_16_loss: 0.5943 - val_loss: 6.4259 - val_distribution_lambda_14_loss: 3.5742 - val_distribution_lambda_15_loss: 2.2617 - val_distribution_lambda_16_loss: 0.5900\n", "Epoch 55/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.5260 - distribution_lambda_14_loss: 3.5933 - distribution_lambda_15_loss: 2.3382 - distribution_lambda_16_loss: 0.5945 - val_loss: 6.3927 - val_distribution_lambda_14_loss: 3.5497 - val_distribution_lambda_15_loss: 2.2534 - val_distribution_lambda_16_loss: 0.5896\n", "Epoch 56/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.5030 - distribution_lambda_14_loss: 3.5786 - distribution_lambda_15_loss: 2.3301 - distribution_lambda_16_loss: 0.5942 - val_loss: 6.3602 - val_distribution_lambda_14_loss: 3.5259 - val_distribution_lambda_15_loss: 2.2448 - val_distribution_lambda_16_loss: 0.5895\n", "Epoch 57/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4705 - distribution_lambda_14_loss: 3.5513 - distribution_lambda_15_loss: 2.3258 - distribution_lambda_16_loss: 0.5935 - val_loss: 6.3295 - val_distribution_lambda_14_loss: 3.5036 - val_distribution_lambda_15_loss: 2.2365 - val_distribution_lambda_16_loss: 0.5894\n", "Epoch 58/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4348 - distribution_lambda_14_loss: 3.5251 - distribution_lambda_15_loss: 2.3154 - distribution_lambda_16_loss: 0.5943 - val_loss: 6.3002 - val_distribution_lambda_14_loss: 3.4824 - val_distribution_lambda_15_loss: 2.2286 - val_distribution_lambda_16_loss: 0.5892\n", "Epoch 59/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4041 - distribution_lambda_14_loss: 3.5024 - distribution_lambda_15_loss: 2.3084 - distribution_lambda_16_loss: 0.5934 - val_loss: 6.2717 - val_distribution_lambda_14_loss: 3.4620 - val_distribution_lambda_15_loss: 2.2207 - val_distribution_lambda_16_loss: 0.5890\n", "Epoch 60/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3754 - distribution_lambda_14_loss: 3.4828 - distribution_lambda_15_loss: 2.2989 - distribution_lambda_16_loss: 0.5938 - val_loss: 6.2459 - val_distribution_lambda_14_loss: 3.4427 - val_distribution_lambda_15_loss: 2.2146 - val_distribution_lambda_16_loss: 0.5886\n", "Epoch 61/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3492 - distribution_lambda_14_loss: 3.4627 - distribution_lambda_15_loss: 2.2935 - distribution_lambda_16_loss: 0.5930 - val_loss: 6.2200 - val_distribution_lambda_14_loss: 3.4241 - val_distribution_lambda_15_loss: 2.2075 - val_distribution_lambda_16_loss: 0.5883\n", "Epoch 62/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3236 - distribution_lambda_14_loss: 3.4448 - distribution_lambda_15_loss: 2.2864 - distribution_lambda_16_loss: 0.5923 - val_loss: 6.1947 - val_distribution_lambda_14_loss: 3.4065 - val_distribution_lambda_15_loss: 2.2002 - val_distribution_lambda_16_loss: 0.5880\n", "Epoch 63/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2908 - distribution_lambda_14_loss: 3.4231 - distribution_lambda_15_loss: 2.2747 - distribution_lambda_16_loss: 0.5930 - val_loss: 6.1705 - val_distribution_lambda_14_loss: 3.3898 - val_distribution_lambda_15_loss: 2.1930 - val_distribution_lambda_16_loss: 0.5878\n", "Epoch 64/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2754 - distribution_lambda_14_loss: 3.4082 - distribution_lambda_15_loss: 2.2742 - distribution_lambda_16_loss: 0.5930 - val_loss: 6.1475 - val_distribution_lambda_14_loss: 3.3739 - val_distribution_lambda_15_loss: 2.1860 - val_distribution_lambda_16_loss: 0.5876\n", "Epoch 65/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2504 - distribution_lambda_14_loss: 3.3961 - distribution_lambda_15_loss: 2.2620 - distribution_lambda_16_loss: 0.5923 - val_loss: 6.1253 - val_distribution_lambda_14_loss: 3.3587 - val_distribution_lambda_15_loss: 2.1791 - val_distribution_lambda_16_loss: 0.5875\n", "Epoch 66/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2275 - distribution_lambda_14_loss: 3.3751 - distribution_lambda_15_loss: 2.2598 - distribution_lambda_16_loss: 0.5926 - val_loss: 6.1035 - val_distribution_lambda_14_loss: 3.3442 - val_distribution_lambda_15_loss: 2.1720 - val_distribution_lambda_16_loss: 0.5873\n", "Epoch 67/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2050 - distribution_lambda_14_loss: 3.3656 - distribution_lambda_15_loss: 2.2468 - distribution_lambda_16_loss: 0.5925 - val_loss: 6.0822 - val_distribution_lambda_14_loss: 3.3300 - val_distribution_lambda_15_loss: 2.1650 - val_distribution_lambda_16_loss: 0.5872\n", "Epoch 68/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.1882 - distribution_lambda_14_loss: 3.3519 - distribution_lambda_15_loss: 2.2445 - distribution_lambda_16_loss: 0.5918 - val_loss: 6.0619 - val_distribution_lambda_14_loss: 3.3165 - val_distribution_lambda_15_loss: 2.1583 - val_distribution_lambda_16_loss: 0.5872\n", "Epoch 69/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.1640 - distribution_lambda_14_loss: 3.3338 - distribution_lambda_15_loss: 2.2380 - distribution_lambda_16_loss: 0.5922 - val_loss: 6.0443 - val_distribution_lambda_14_loss: 3.3034 - val_distribution_lambda_15_loss: 2.1539 - val_distribution_lambda_16_loss: 0.5870\n", "Epoch 70/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.1422 - distribution_lambda_14_loss: 3.3182 - distribution_lambda_15_loss: 2.2324 - distribution_lambda_16_loss: 0.5917 - val_loss: 6.0263 - val_distribution_lambda_14_loss: 3.2909 - val_distribution_lambda_15_loss: 2.1484 - val_distribution_lambda_16_loss: 0.5869\n", "Epoch 71/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.1214 - distribution_lambda_14_loss: 3.3067 - distribution_lambda_15_loss: 2.2227 - distribution_lambda_16_loss: 0.5920 - val_loss: 6.0123 - val_distribution_lambda_14_loss: 3.2790 - val_distribution_lambda_15_loss: 2.1465 - val_distribution_lambda_16_loss: 0.5868\n", "Epoch 72/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.1124 - distribution_lambda_14_loss: 3.2989 - distribution_lambda_15_loss: 2.2213 - distribution_lambda_16_loss: 0.5921 - val_loss: 5.9966 - val_distribution_lambda_14_loss: 3.2674 - val_distribution_lambda_15_loss: 2.1426 - val_distribution_lambda_16_loss: 0.5867\n", "Epoch 73/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 6.0804 - distribution_lambda_14_loss: 3.2801 - distribution_lambda_15_loss: 2.2084 - distribution_lambda_16_loss: 0.5918 - val_loss: 5.9798 - val_distribution_lambda_14_loss: 3.2561 - val_distribution_lambda_15_loss: 2.1370 - val_distribution_lambda_16_loss: 0.5866\n", "Epoch 74/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0727 - distribution_lambda_14_loss: 3.2760 - distribution_lambda_15_loss: 2.2045 - distribution_lambda_16_loss: 0.5922 - val_loss: 5.9626 - val_distribution_lambda_14_loss: 3.2452 - val_distribution_lambda_15_loss: 2.1308 - val_distribution_lambda_16_loss: 0.5866\n", "Epoch 75/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0592 - distribution_lambda_14_loss: 3.2624 - distribution_lambda_15_loss: 2.2043 - distribution_lambda_16_loss: 0.5925 - val_loss: 5.9456 - val_distribution_lambda_14_loss: 3.2346 - val_distribution_lambda_15_loss: 2.1244 - val_distribution_lambda_16_loss: 0.5865\n", "Epoch 76/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0414 - distribution_lambda_14_loss: 3.2540 - distribution_lambda_15_loss: 2.1953 - distribution_lambda_16_loss: 0.5921 - val_loss: 5.9291 - val_distribution_lambda_14_loss: 3.2244 - val_distribution_lambda_15_loss: 2.1183 - val_distribution_lambda_16_loss: 0.5865\n", "Epoch 77/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0170 - distribution_lambda_14_loss: 3.2374 - distribution_lambda_15_loss: 2.1880 - distribution_lambda_16_loss: 0.5916 - val_loss: 5.9132 - val_distribution_lambda_14_loss: 3.2146 - val_distribution_lambda_15_loss: 2.1122 - val_distribution_lambda_16_loss: 0.5865\n", "Epoch 78/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0058 - distribution_lambda_14_loss: 3.2303 - distribution_lambda_15_loss: 2.1835 - distribution_lambda_16_loss: 0.5920 - val_loss: 5.8981 - val_distribution_lambda_14_loss: 3.2050 - val_distribution_lambda_15_loss: 2.1067 - val_distribution_lambda_16_loss: 0.5864\n", "Epoch 79/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9925 - distribution_lambda_14_loss: 3.2215 - distribution_lambda_15_loss: 2.1794 - distribution_lambda_16_loss: 0.5916 - val_loss: 5.8841 - val_distribution_lambda_14_loss: 3.1958 - val_distribution_lambda_15_loss: 2.1019 - val_distribution_lambda_16_loss: 0.5864\n", "Epoch 80/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9756 - distribution_lambda_14_loss: 3.2090 - distribution_lambda_15_loss: 2.1749 - distribution_lambda_16_loss: 0.5917 - val_loss: 5.8712 - val_distribution_lambda_14_loss: 3.1869 - val_distribution_lambda_15_loss: 2.0980 - val_distribution_lambda_16_loss: 0.5864\n", "Epoch 81/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9610 - distribution_lambda_14_loss: 3.2033 - distribution_lambda_15_loss: 2.1666 - distribution_lambda_16_loss: 0.5911 - val_loss: 5.8579 - val_distribution_lambda_14_loss: 3.1782 - val_distribution_lambda_15_loss: 2.0933 - val_distribution_lambda_16_loss: 0.5864\n", "Epoch 82/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9505 - distribution_lambda_14_loss: 3.1942 - distribution_lambda_15_loss: 2.1643 - distribution_lambda_16_loss: 0.5920 - val_loss: 5.8456 - val_distribution_lambda_14_loss: 3.1698 - val_distribution_lambda_15_loss: 2.0895 - val_distribution_lambda_16_loss: 0.5863\n", "Epoch 83/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9381 - distribution_lambda_14_loss: 3.1822 - distribution_lambda_15_loss: 2.1636 - distribution_lambda_16_loss: 0.5922 - val_loss: 5.8326 - val_distribution_lambda_14_loss: 3.1617 - val_distribution_lambda_15_loss: 2.0846 - val_distribution_lambda_16_loss: 0.5863\n", "Epoch 84/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9272 - distribution_lambda_14_loss: 3.1780 - distribution_lambda_15_loss: 2.1577 - distribution_lambda_16_loss: 0.5915 - val_loss: 5.8196 - val_distribution_lambda_14_loss: 3.1538 - val_distribution_lambda_15_loss: 2.0795 - val_distribution_lambda_16_loss: 0.5862\n", "Epoch 85/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9060 - distribution_lambda_14_loss: 3.1678 - distribution_lambda_15_loss: 2.1463 - distribution_lambda_16_loss: 0.5919 - val_loss: 5.8068 - val_distribution_lambda_14_loss: 3.1462 - val_distribution_lambda_15_loss: 2.0743 - val_distribution_lambda_16_loss: 0.5863\n", "Epoch 86/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.9028 - distribution_lambda_14_loss: 3.1628 - distribution_lambda_15_loss: 2.1485 - distribution_lambda_16_loss: 0.5915 - val_loss: 5.7941 - val_distribution_lambda_14_loss: 3.1387 - val_distribution_lambda_15_loss: 2.0692 - val_distribution_lambda_16_loss: 0.5863\n", "Epoch 87/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8864 - distribution_lambda_14_loss: 3.1529 - distribution_lambda_15_loss: 2.1417 - distribution_lambda_16_loss: 0.5918 - val_loss: 5.7818 - val_distribution_lambda_14_loss: 3.1313 - val_distribution_lambda_15_loss: 2.0643 - val_distribution_lambda_16_loss: 0.5862\n", "Epoch 88/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8737 - distribution_lambda_14_loss: 3.1457 - distribution_lambda_15_loss: 2.1359 - distribution_lambda_16_loss: 0.5921 - val_loss: 5.7699 - val_distribution_lambda_14_loss: 3.1242 - val_distribution_lambda_15_loss: 2.0595 - val_distribution_lambda_16_loss: 0.5861\n", "Epoch 89/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8602 - distribution_lambda_14_loss: 3.1376 - distribution_lambda_15_loss: 2.1309 - distribution_lambda_16_loss: 0.5918 - val_loss: 5.7581 - val_distribution_lambda_14_loss: 3.1172 - val_distribution_lambda_15_loss: 2.0548 - val_distribution_lambda_16_loss: 0.5861\n", "Epoch 90/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8458 - distribution_lambda_14_loss: 3.1313 - distribution_lambda_15_loss: 2.1228 - distribution_lambda_16_loss: 0.5918 - val_loss: 5.7467 - val_distribution_lambda_14_loss: 3.1104 - val_distribution_lambda_15_loss: 2.0503 - val_distribution_lambda_16_loss: 0.5860\n", "Epoch 91/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8362 - distribution_lambda_14_loss: 3.1258 - distribution_lambda_15_loss: 2.1190 - distribution_lambda_16_loss: 0.5914 - val_loss: 5.7354 - val_distribution_lambda_14_loss: 3.1037 - val_distribution_lambda_15_loss: 2.0458 - val_distribution_lambda_16_loss: 0.5860\n", "Epoch 92/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8212 - distribution_lambda_14_loss: 3.1142 - distribution_lambda_15_loss: 2.1153 - distribution_lambda_16_loss: 0.5917 - val_loss: 5.7248 - val_distribution_lambda_14_loss: 3.0973 - val_distribution_lambda_15_loss: 2.0416 - val_distribution_lambda_16_loss: 0.5859\n", "Epoch 93/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8197 - distribution_lambda_14_loss: 3.1137 - distribution_lambda_15_loss: 2.1141 - distribution_lambda_16_loss: 0.5919 - val_loss: 5.7151 - val_distribution_lambda_14_loss: 3.0909 - val_distribution_lambda_15_loss: 2.0383 - val_distribution_lambda_16_loss: 0.5859\n", "Epoch 94/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.8003 - distribution_lambda_14_loss: 3.1027 - distribution_lambda_15_loss: 2.1063 - distribution_lambda_16_loss: 0.5913 - val_loss: 5.7053 - val_distribution_lambda_14_loss: 3.0848 - val_distribution_lambda_15_loss: 2.0346 - val_distribution_lambda_16_loss: 0.5859\n", "Epoch 95/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7980 - distribution_lambda_14_loss: 3.0998 - distribution_lambda_15_loss: 2.1071 - distribution_lambda_16_loss: 0.5911 - val_loss: 5.6953 - val_distribution_lambda_14_loss: 3.0788 - val_distribution_lambda_15_loss: 2.0306 - val_distribution_lambda_16_loss: 0.5858\n", "Epoch 96/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7833 - distribution_lambda_14_loss: 3.0907 - distribution_lambda_15_loss: 2.1011 - distribution_lambda_16_loss: 0.5915 - val_loss: 5.6854 - val_distribution_lambda_14_loss: 3.0729 - val_distribution_lambda_15_loss: 2.0266 - val_distribution_lambda_16_loss: 0.5859\n", "Epoch 97/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.7688 - distribution_lambda_14_loss: 3.0824 - distribution_lambda_15_loss: 2.0951 - distribution_lambda_16_loss: 0.5913 - val_loss: 5.6755 - val_distribution_lambda_14_loss: 3.0671 - val_distribution_lambda_15_loss: 2.0226 - val_distribution_lambda_16_loss: 0.5858\n", "Epoch 98/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7705 - distribution_lambda_14_loss: 3.0829 - distribution_lambda_15_loss: 2.0966 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.6659 - val_distribution_lambda_14_loss: 3.0615 - val_distribution_lambda_15_loss: 2.0187 - val_distribution_lambda_16_loss: 0.5858\n", "Epoch 99/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7540 - distribution_lambda_14_loss: 3.0720 - distribution_lambda_15_loss: 2.0909 - distribution_lambda_16_loss: 0.5912 - val_loss: 5.6564 - val_distribution_lambda_14_loss: 3.0559 - val_distribution_lambda_15_loss: 2.0147 - val_distribution_lambda_16_loss: 0.5857\n", "Epoch 100/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7482 - distribution_lambda_14_loss: 3.0696 - distribution_lambda_15_loss: 2.0871 - distribution_lambda_16_loss: 0.5915 - val_loss: 5.6475 - val_distribution_lambda_14_loss: 3.0504 - val_distribution_lambda_15_loss: 2.0113 - val_distribution_lambda_16_loss: 0.5857\n", "Epoch 101/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7389 - distribution_lambda_14_loss: 3.0629 - distribution_lambda_15_loss: 2.0851 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.6383 - val_distribution_lambda_14_loss: 3.0450 - val_distribution_lambda_15_loss: 2.0076 - val_distribution_lambda_16_loss: 0.5857\n", "Epoch 102/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7269 - distribution_lambda_14_loss: 3.0565 - distribution_lambda_15_loss: 2.0785 - distribution_lambda_16_loss: 0.5919 - val_loss: 5.6299 - val_distribution_lambda_14_loss: 3.0397 - val_distribution_lambda_15_loss: 2.0046 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 103/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7168 - distribution_lambda_14_loss: 3.0516 - distribution_lambda_15_loss: 2.0739 - distribution_lambda_16_loss: 0.5912 - val_loss: 5.6212 - val_distribution_lambda_14_loss: 3.0345 - val_distribution_lambda_15_loss: 2.0012 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 104/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.7099 - distribution_lambda_14_loss: 3.0468 - distribution_lambda_15_loss: 2.0721 - distribution_lambda_16_loss: 0.5910 - val_loss: 5.6127 - val_distribution_lambda_14_loss: 3.0294 - val_distribution_lambda_15_loss: 1.9977 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 105/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7013 - distribution_lambda_14_loss: 3.0409 - distribution_lambda_15_loss: 2.0691 - distribution_lambda_16_loss: 0.5913 - val_loss: 5.6043 - val_distribution_lambda_14_loss: 3.0244 - val_distribution_lambda_15_loss: 1.9944 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 106/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6911 - distribution_lambda_14_loss: 3.0361 - distribution_lambda_15_loss: 2.0641 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.5966 - val_distribution_lambda_14_loss: 3.0194 - val_distribution_lambda_15_loss: 1.9916 - val_distribution_lambda_16_loss: 0.5855\n", "Epoch 107/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6838 - distribution_lambda_14_loss: 3.0308 - distribution_lambda_15_loss: 2.0618 - distribution_lambda_16_loss: 0.5912 - val_loss: 5.5885 - val_distribution_lambda_14_loss: 3.0145 - val_distribution_lambda_15_loss: 1.9884 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 108/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6737 - distribution_lambda_14_loss: 3.0246 - distribution_lambda_15_loss: 2.0579 - distribution_lambda_16_loss: 0.5913 - val_loss: 5.5808 - val_distribution_lambda_14_loss: 3.0098 - val_distribution_lambda_15_loss: 1.9854 - val_distribution_lambda_16_loss: 0.5856\n", "Epoch 109/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6693 - distribution_lambda_14_loss: 3.0195 - distribution_lambda_15_loss: 2.0590 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.5728 - val_distribution_lambda_14_loss: 3.0051 - val_distribution_lambda_15_loss: 1.9822 - val_distribution_lambda_16_loss: 0.5855\n", "Epoch 110/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6617 - distribution_lambda_14_loss: 3.0167 - distribution_lambda_15_loss: 2.0535 - distribution_lambda_16_loss: 0.5915 - val_loss: 5.5656 - val_distribution_lambda_14_loss: 3.0005 - val_distribution_lambda_15_loss: 1.9796 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 111/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6548 - distribution_lambda_14_loss: 3.0116 - distribution_lambda_15_loss: 2.0518 - distribution_lambda_16_loss: 0.5914 - val_loss: 5.5578 - val_distribution_lambda_14_loss: 2.9959 - val_distribution_lambda_15_loss: 1.9765 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 112/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6433 - distribution_lambda_14_loss: 3.0067 - distribution_lambda_15_loss: 2.0456 - distribution_lambda_16_loss: 0.5911 - val_loss: 5.5499 - val_distribution_lambda_14_loss: 2.9913 - val_distribution_lambda_15_loss: 1.9732 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 113/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6339 - distribution_lambda_14_loss: 2.9994 - distribution_lambda_15_loss: 2.0436 - distribution_lambda_16_loss: 0.5910 - val_loss: 5.5426 - val_distribution_lambda_14_loss: 2.9869 - val_distribution_lambda_15_loss: 1.9704 - val_distribution_lambda_16_loss: 0.5853\n", "Epoch 114/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6288 - distribution_lambda_14_loss: 2.9965 - distribution_lambda_15_loss: 2.0413 - distribution_lambda_16_loss: 0.5910 - val_loss: 5.5359 - val_distribution_lambda_14_loss: 2.9825 - val_distribution_lambda_15_loss: 1.9681 - val_distribution_lambda_16_loss: 0.5853\n", "Epoch 115/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.6204 - distribution_lambda_14_loss: 2.9940 - distribution_lambda_15_loss: 2.0358 - distribution_lambda_16_loss: 0.5906 - val_loss: 5.5292 - val_distribution_lambda_14_loss: 2.9782 - val_distribution_lambda_15_loss: 1.9658 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 116/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6105 - distribution_lambda_14_loss: 2.9884 - distribution_lambda_15_loss: 2.0310 - distribution_lambda_16_loss: 0.5911 - val_loss: 5.5221 - val_distribution_lambda_14_loss: 2.9738 - val_distribution_lambda_15_loss: 1.9630 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 117/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6015 - distribution_lambda_14_loss: 2.9835 - distribution_lambda_15_loss: 2.0276 - distribution_lambda_16_loss: 0.5904 - val_loss: 5.5149 - val_distribution_lambda_14_loss: 2.9696 - val_distribution_lambda_15_loss: 1.9602 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 118/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5985 - distribution_lambda_14_loss: 2.9795 - distribution_lambda_15_loss: 2.0279 - distribution_lambda_16_loss: 0.5910 - val_loss: 5.5076 - val_distribution_lambda_14_loss: 2.9654 - val_distribution_lambda_15_loss: 1.9571 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 119/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5926 - distribution_lambda_14_loss: 2.9754 - distribution_lambda_15_loss: 2.0267 - distribution_lambda_16_loss: 0.5906 - val_loss: 5.5011 - val_distribution_lambda_14_loss: 2.9612 - val_distribution_lambda_15_loss: 1.9548 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 120/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5876 - distribution_lambda_14_loss: 2.9713 - distribution_lambda_15_loss: 2.0255 - distribution_lambda_16_loss: 0.5908 - val_loss: 5.4939 - val_distribution_lambda_14_loss: 2.9570 - val_distribution_lambda_15_loss: 1.9517 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 121/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 5.5762 - distribution_lambda_14_loss: 2.9661 - distribution_lambda_15_loss: 2.0194 - distribution_lambda_16_loss: 0.5907 - val_loss: 5.4866 - val_distribution_lambda_14_loss: 2.9528 - val_distribution_lambda_15_loss: 1.9484 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 122/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5724 - distribution_lambda_14_loss: 2.9627 - distribution_lambda_15_loss: 2.0188 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.4792 - val_distribution_lambda_14_loss: 2.9487 - val_distribution_lambda_15_loss: 1.9451 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 123/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5625 - distribution_lambda_14_loss: 2.9582 - distribution_lambda_15_loss: 2.0135 - distribution_lambda_16_loss: 0.5908 - val_loss: 5.4718 - val_distribution_lambda_14_loss: 2.9446 - val_distribution_lambda_15_loss: 1.9418 - val_distribution_lambda_16_loss: 0.5854\n", "Epoch 124/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5542 - distribution_lambda_14_loss: 2.9554 - distribution_lambda_15_loss: 2.0076 - distribution_lambda_16_loss: 0.5912 - val_loss: 5.4645 - val_distribution_lambda_14_loss: 2.9405 - val_distribution_lambda_15_loss: 1.9387 - val_distribution_lambda_16_loss: 0.5852\n", "Epoch 125/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5506 - distribution_lambda_14_loss: 2.9500 - distribution_lambda_15_loss: 2.0098 - distribution_lambda_16_loss: 0.5907 - val_loss: 5.4572 - val_distribution_lambda_14_loss: 2.9365 - val_distribution_lambda_15_loss: 1.9356 - val_distribution_lambda_16_loss: 0.5851\n", "Epoch 126/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5412 - distribution_lambda_14_loss: 2.9463 - distribution_lambda_15_loss: 2.0043 - distribution_lambda_16_loss: 0.5906 - val_loss: 5.4502 - val_distribution_lambda_14_loss: 2.9325 - val_distribution_lambda_15_loss: 1.9326 - val_distribution_lambda_16_loss: 0.5851\n", "Epoch 127/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5374 - distribution_lambda_14_loss: 2.9438 - distribution_lambda_15_loss: 2.0032 - distribution_lambda_16_loss: 0.5904 - val_loss: 5.4432 - val_distribution_lambda_14_loss: 2.9286 - val_distribution_lambda_15_loss: 1.9296 - val_distribution_lambda_16_loss: 0.5851\n", "Epoch 128/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5284 - distribution_lambda_14_loss: 2.9378 - distribution_lambda_15_loss: 2.0004 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.4363 - val_distribution_lambda_14_loss: 2.9246 - val_distribution_lambda_15_loss: 1.9266 - val_distribution_lambda_16_loss: 0.5851\n", "Epoch 129/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5220 - distribution_lambda_14_loss: 2.9343 - distribution_lambda_15_loss: 1.9972 - distribution_lambda_16_loss: 0.5905 - val_loss: 5.4294 - val_distribution_lambda_14_loss: 2.9207 - val_distribution_lambda_15_loss: 1.9237 - val_distribution_lambda_16_loss: 0.5850\n", "Epoch 130/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5155 - distribution_lambda_14_loss: 2.9305 - distribution_lambda_15_loss: 1.9941 - distribution_lambda_16_loss: 0.5909 - val_loss: 5.4230 - val_distribution_lambda_14_loss: 2.9168 - val_distribution_lambda_15_loss: 1.9213 - val_distribution_lambda_16_loss: 0.5850\n", "Epoch 131/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5082 - distribution_lambda_14_loss: 2.9269 - distribution_lambda_15_loss: 1.9910 - distribution_lambda_16_loss: 0.5903 - val_loss: 5.4164 - val_distribution_lambda_14_loss: 2.9129 - val_distribution_lambda_15_loss: 1.9186 - val_distribution_lambda_16_loss: 0.5849\n", "Epoch 132/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5009 - distribution_lambda_14_loss: 2.9231 - distribution_lambda_15_loss: 1.9871 - distribution_lambda_16_loss: 0.5907 - val_loss: 5.4096 - val_distribution_lambda_14_loss: 2.9090 - val_distribution_lambda_15_loss: 1.9156 - val_distribution_lambda_16_loss: 0.5850\n", "Epoch 133/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4964 - distribution_lambda_14_loss: 2.9180 - distribution_lambda_15_loss: 1.9883 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.4030 - val_distribution_lambda_14_loss: 2.9052 - val_distribution_lambda_15_loss: 1.9129 - val_distribution_lambda_16_loss: 0.5849\n", "Epoch 134/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4904 - distribution_lambda_14_loss: 2.9148 - distribution_lambda_15_loss: 1.9848 - distribution_lambda_16_loss: 0.5908 - val_loss: 5.3963 - val_distribution_lambda_14_loss: 2.9013 - val_distribution_lambda_15_loss: 1.9100 - val_distribution_lambda_16_loss: 0.5849\n", "Epoch 135/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4826 - distribution_lambda_14_loss: 2.9125 - distribution_lambda_15_loss: 1.9797 - distribution_lambda_16_loss: 0.5904 - val_loss: 5.3908 - val_distribution_lambda_14_loss: 2.8975 - val_distribution_lambda_15_loss: 1.9084 - val_distribution_lambda_16_loss: 0.5849\n", "Epoch 136/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4747 - distribution_lambda_14_loss: 2.9069 - distribution_lambda_15_loss: 1.9772 - distribution_lambda_16_loss: 0.5906 - val_loss: 5.3846 - val_distribution_lambda_14_loss: 2.8937 - val_distribution_lambda_15_loss: 1.9061 - val_distribution_lambda_16_loss: 0.5848\n", "Epoch 137/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4661 - distribution_lambda_14_loss: 2.9026 - distribution_lambda_15_loss: 1.9736 - distribution_lambda_16_loss: 0.5899 - val_loss: 5.3780 - val_distribution_lambda_14_loss: 2.8899 - val_distribution_lambda_15_loss: 1.9034 - val_distribution_lambda_16_loss: 0.5847\n", "Epoch 138/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4602 - distribution_lambda_14_loss: 2.8985 - distribution_lambda_15_loss: 1.9713 - distribution_lambda_16_loss: 0.5904 - val_loss: 5.3720 - val_distribution_lambda_14_loss: 2.8861 - val_distribution_lambda_15_loss: 1.9012 - val_distribution_lambda_16_loss: 0.5847\n", "Epoch 139/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4558 - distribution_lambda_14_loss: 2.8953 - distribution_lambda_15_loss: 1.9701 - distribution_lambda_16_loss: 0.5904 - val_loss: 5.3667 - val_distribution_lambda_14_loss: 2.8823 - val_distribution_lambda_15_loss: 1.8997 - val_distribution_lambda_16_loss: 0.5847\n", "Epoch 140/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4461 - distribution_lambda_14_loss: 2.8906 - distribution_lambda_15_loss: 1.9653 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.3606 - val_distribution_lambda_14_loss: 2.8786 - val_distribution_lambda_15_loss: 1.8974 - val_distribution_lambda_16_loss: 0.5847\n", "Epoch 141/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4431 - distribution_lambda_14_loss: 2.8888 - distribution_lambda_15_loss: 1.9638 - distribution_lambda_16_loss: 0.5905 - val_loss: 5.3540 - val_distribution_lambda_14_loss: 2.8748 - val_distribution_lambda_15_loss: 1.8946 - val_distribution_lambda_16_loss: 0.5846\n", "Epoch 142/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4361 - distribution_lambda_14_loss: 2.8829 - distribution_lambda_15_loss: 1.9627 - distribution_lambda_16_loss: 0.5905 - val_loss: 5.3473 - val_distribution_lambda_14_loss: 2.8710 - val_distribution_lambda_15_loss: 1.8917 - val_distribution_lambda_16_loss: 0.5846\n", "Epoch 143/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4277 - distribution_lambda_14_loss: 2.8797 - distribution_lambda_15_loss: 1.9579 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.3406 - val_distribution_lambda_14_loss: 2.8672 - val_distribution_lambda_15_loss: 1.8888 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 144/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4237 - distribution_lambda_14_loss: 2.8754 - distribution_lambda_15_loss: 1.9578 - distribution_lambda_16_loss: 0.5905 - val_loss: 5.3340 - val_distribution_lambda_14_loss: 2.8635 - val_distribution_lambda_15_loss: 1.8860 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 145/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.4166 - distribution_lambda_14_loss: 2.8722 - distribution_lambda_15_loss: 1.9543 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.3273 - val_distribution_lambda_14_loss: 2.8597 - val_distribution_lambda_15_loss: 1.8831 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 146/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4087 - distribution_lambda_14_loss: 2.8668 - distribution_lambda_15_loss: 1.9521 - distribution_lambda_16_loss: 0.5898 - val_loss: 5.3207 - val_distribution_lambda_14_loss: 2.8559 - val_distribution_lambda_15_loss: 1.8802 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 147/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4028 - distribution_lambda_14_loss: 2.8641 - distribution_lambda_15_loss: 1.9485 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.3148 - val_distribution_lambda_14_loss: 2.8522 - val_distribution_lambda_15_loss: 1.8782 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 148/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3996 - distribution_lambda_14_loss: 2.8608 - distribution_lambda_15_loss: 1.9480 - distribution_lambda_16_loss: 0.5908 - val_loss: 5.3088 - val_distribution_lambda_14_loss: 2.8484 - val_distribution_lambda_15_loss: 1.8759 - val_distribution_lambda_16_loss: 0.5845\n", "Epoch 149/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3897 - distribution_lambda_14_loss: 2.8554 - distribution_lambda_15_loss: 1.9442 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.3021 - val_distribution_lambda_14_loss: 2.8447 - val_distribution_lambda_15_loss: 1.8730 - val_distribution_lambda_16_loss: 0.5844\n", "Epoch 150/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3880 - distribution_lambda_14_loss: 2.8527 - distribution_lambda_15_loss: 1.9452 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2959 - val_distribution_lambda_14_loss: 2.8409 - val_distribution_lambda_15_loss: 1.8705 - val_distribution_lambda_16_loss: 0.5844\n", "Epoch 151/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3768 - distribution_lambda_14_loss: 2.8493 - distribution_lambda_15_loss: 1.9374 - distribution_lambda_16_loss: 0.5900 - val_loss: 5.2895 - val_distribution_lambda_14_loss: 2.8372 - val_distribution_lambda_15_loss: 1.8680 - val_distribution_lambda_16_loss: 0.5844\n", "Epoch 152/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3758 - distribution_lambda_14_loss: 2.8463 - distribution_lambda_15_loss: 1.9398 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.2829 - val_distribution_lambda_14_loss: 2.8334 - val_distribution_lambda_15_loss: 1.8652 - val_distribution_lambda_16_loss: 0.5844\n", "Epoch 153/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3623 - distribution_lambda_14_loss: 2.8413 - distribution_lambda_15_loss: 1.9309 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2772 - val_distribution_lambda_14_loss: 2.8296 - val_distribution_lambda_15_loss: 1.8632 - val_distribution_lambda_16_loss: 0.5844\n", "Epoch 154/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3594 - distribution_lambda_14_loss: 2.8381 - distribution_lambda_15_loss: 1.9312 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2708 - val_distribution_lambda_14_loss: 2.8258 - val_distribution_lambda_15_loss: 1.8606 - val_distribution_lambda_16_loss: 0.5843\n", "Epoch 155/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3523 - distribution_lambda_14_loss: 2.8347 - distribution_lambda_15_loss: 1.9275 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2642 - val_distribution_lambda_14_loss: 2.8220 - val_distribution_lambda_15_loss: 1.8579 - val_distribution_lambda_16_loss: 0.5843\n", "Epoch 156/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3471 - distribution_lambda_14_loss: 2.8292 - distribution_lambda_15_loss: 1.9277 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2585 - val_distribution_lambda_14_loss: 2.8182 - val_distribution_lambda_15_loss: 1.8560 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 157/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3357 - distribution_lambda_14_loss: 2.8248 - distribution_lambda_15_loss: 1.9208 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2522 - val_distribution_lambda_14_loss: 2.8144 - val_distribution_lambda_15_loss: 1.8536 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 158/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3333 - distribution_lambda_14_loss: 2.8220 - distribution_lambda_15_loss: 1.9214 - distribution_lambda_16_loss: 0.5900 - val_loss: 5.2461 - val_distribution_lambda_14_loss: 2.8106 - val_distribution_lambda_15_loss: 1.8513 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 159/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3309 - distribution_lambda_14_loss: 2.8188 - distribution_lambda_15_loss: 1.9219 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.2396 - val_distribution_lambda_14_loss: 2.8068 - val_distribution_lambda_15_loss: 1.8486 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 160/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3255 - distribution_lambda_14_loss: 2.8160 - distribution_lambda_15_loss: 1.9194 - distribution_lambda_16_loss: 0.5901 - val_loss: 5.2329 - val_distribution_lambda_14_loss: 2.8030 - val_distribution_lambda_15_loss: 1.8457 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 161/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3138 - distribution_lambda_14_loss: 2.8092 - distribution_lambda_15_loss: 1.9153 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.2262 - val_distribution_lambda_14_loss: 2.7991 - val_distribution_lambda_15_loss: 1.8429 - val_distribution_lambda_16_loss: 0.5842\n", "Epoch 162/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3054 - distribution_lambda_14_loss: 2.8057 - distribution_lambda_15_loss: 1.9102 - distribution_lambda_16_loss: 0.5896 - val_loss: 5.2195 - val_distribution_lambda_14_loss: 2.7953 - val_distribution_lambda_15_loss: 1.8401 - val_distribution_lambda_16_loss: 0.5841\n", "Epoch 163/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.3050 - distribution_lambda_14_loss: 2.8031 - distribution_lambda_15_loss: 1.9117 - distribution_lambda_16_loss: 0.5902 - val_loss: 5.2130 - val_distribution_lambda_14_loss: 2.7914 - val_distribution_lambda_15_loss: 1.8375 - val_distribution_lambda_16_loss: 0.5841\n", "Epoch 164/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2970 - distribution_lambda_14_loss: 2.7994 - distribution_lambda_15_loss: 1.9079 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.2066 - val_distribution_lambda_14_loss: 2.7875 - val_distribution_lambda_15_loss: 1.8350 - val_distribution_lambda_16_loss: 0.5840\n", "Epoch 165/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2882 - distribution_lambda_14_loss: 2.7960 - distribution_lambda_15_loss: 1.9026 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.2102 - val_distribution_lambda_14_loss: 2.7836 - val_distribution_lambda_15_loss: 1.8426 - val_distribution_lambda_16_loss: 0.5840\n", "Epoch 166/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2887 - distribution_lambda_14_loss: 2.7917 - distribution_lambda_15_loss: 1.9073 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.2101 - val_distribution_lambda_14_loss: 2.7797 - val_distribution_lambda_15_loss: 1.8465 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 167/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2804 - distribution_lambda_14_loss: 2.7870 - distribution_lambda_15_loss: 1.9036 - distribution_lambda_16_loss: 0.5898 - val_loss: 5.2047 - val_distribution_lambda_14_loss: 2.7758 - val_distribution_lambda_15_loss: 1.8450 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 168/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2738 - distribution_lambda_14_loss: 2.7840 - distribution_lambda_15_loss: 1.9004 - distribution_lambda_16_loss: 0.5894 - val_loss: 5.1970 - val_distribution_lambda_14_loss: 2.7719 - val_distribution_lambda_15_loss: 1.8412 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 169/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.2706 - distribution_lambda_14_loss: 2.7801 - distribution_lambda_15_loss: 1.9009 - distribution_lambda_16_loss: 0.5896 - val_loss: 5.1887 - val_distribution_lambda_14_loss: 2.7679 - val_distribution_lambda_15_loss: 1.8369 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 170/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2595 - distribution_lambda_14_loss: 2.7750 - distribution_lambda_15_loss: 1.8946 - distribution_lambda_16_loss: 0.5899 - val_loss: 5.1803 - val_distribution_lambda_14_loss: 2.7640 - val_distribution_lambda_15_loss: 1.8325 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 171/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2501 - distribution_lambda_14_loss: 2.7712 - distribution_lambda_15_loss: 1.8896 - distribution_lambda_16_loss: 0.5893 - val_loss: 5.1722 - val_distribution_lambda_14_loss: 2.7600 - val_distribution_lambda_15_loss: 1.8284 - val_distribution_lambda_16_loss: 0.5838\n", "Epoch 172/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2445 - distribution_lambda_14_loss: 2.7661 - distribution_lambda_15_loss: 1.8888 - distribution_lambda_16_loss: 0.5895 - val_loss: 5.1645 - val_distribution_lambda_14_loss: 2.7560 - val_distribution_lambda_15_loss: 1.8247 - val_distribution_lambda_16_loss: 0.5839\n", "Epoch 173/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2394 - distribution_lambda_14_loss: 2.7633 - distribution_lambda_15_loss: 1.8862 - distribution_lambda_16_loss: 0.5899 - val_loss: 5.1580 - val_distribution_lambda_14_loss: 2.7520 - val_distribution_lambda_15_loss: 1.8221 - val_distribution_lambda_16_loss: 0.5838\n", "Epoch 174/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2317 - distribution_lambda_14_loss: 2.7586 - distribution_lambda_15_loss: 1.8839 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.1510 - val_distribution_lambda_14_loss: 2.7480 - val_distribution_lambda_15_loss: 1.8192 - val_distribution_lambda_16_loss: 0.5838\n", "Epoch 175/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.2267 - distribution_lambda_14_loss: 2.7550 - distribution_lambda_15_loss: 1.8821 - distribution_lambda_16_loss: 0.5896 - val_loss: 5.1437 - val_distribution_lambda_14_loss: 2.7440 - val_distribution_lambda_15_loss: 1.8160 - val_distribution_lambda_16_loss: 0.5837\n", "Epoch 176/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.2197 - distribution_lambda_14_loss: 2.7509 - distribution_lambda_15_loss: 1.8791 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.1364 - val_distribution_lambda_14_loss: 2.7400 - val_distribution_lambda_15_loss: 1.8127 - val_distribution_lambda_16_loss: 0.5837\n", "Epoch 177/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2119 - distribution_lambda_14_loss: 2.7471 - distribution_lambda_15_loss: 1.8753 - distribution_lambda_16_loss: 0.5895 - val_loss: 5.1292 - val_distribution_lambda_14_loss: 2.7359 - val_distribution_lambda_15_loss: 1.8096 - val_distribution_lambda_16_loss: 0.5837\n", "Epoch 178/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2075 - distribution_lambda_14_loss: 2.7423 - distribution_lambda_15_loss: 1.8755 - distribution_lambda_16_loss: 0.5896 - val_loss: 5.1238 - val_distribution_lambda_14_loss: 2.7318 - val_distribution_lambda_15_loss: 1.8084 - val_distribution_lambda_16_loss: 0.5836\n", "Epoch 179/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.2017 - distribution_lambda_14_loss: 2.7386 - distribution_lambda_15_loss: 1.8732 - distribution_lambda_16_loss: 0.5899 - val_loss: 5.1173 - val_distribution_lambda_14_loss: 2.7278 - val_distribution_lambda_15_loss: 1.8060 - val_distribution_lambda_16_loss: 0.5836\n", "Epoch 180/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1904 - distribution_lambda_14_loss: 2.7350 - distribution_lambda_15_loss: 1.8662 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.1101 - val_distribution_lambda_14_loss: 2.7237 - val_distribution_lambda_15_loss: 1.8029 - val_distribution_lambda_16_loss: 0.5836\n", "Epoch 181/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.1840 - distribution_lambda_14_loss: 2.7297 - distribution_lambda_15_loss: 1.8652 - distribution_lambda_16_loss: 0.5891 - val_loss: 5.1028 - val_distribution_lambda_14_loss: 2.7195 - val_distribution_lambda_15_loss: 1.7997 - val_distribution_lambda_16_loss: 0.5836\n", "Epoch 182/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.1757 - distribution_lambda_14_loss: 2.7255 - distribution_lambda_15_loss: 1.8612 - distribution_lambda_16_loss: 0.5890 - val_loss: 5.0955 - val_distribution_lambda_14_loss: 2.7154 - val_distribution_lambda_15_loss: 1.7966 - val_distribution_lambda_16_loss: 0.5836\n", "Epoch 183/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1698 - distribution_lambda_14_loss: 2.7220 - distribution_lambda_15_loss: 1.8588 - distribution_lambda_16_loss: 0.5890 - val_loss: 5.0886 - val_distribution_lambda_14_loss: 2.7112 - val_distribution_lambda_15_loss: 1.7939 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 184/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1672 - distribution_lambda_14_loss: 2.7191 - distribution_lambda_15_loss: 1.8591 - distribution_lambda_16_loss: 0.5890 - val_loss: 5.0816 - val_distribution_lambda_14_loss: 2.7070 - val_distribution_lambda_15_loss: 1.7911 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 185/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.1606 - distribution_lambda_14_loss: 2.7143 - distribution_lambda_15_loss: 1.8571 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.0745 - val_distribution_lambda_14_loss: 2.7028 - val_distribution_lambda_15_loss: 1.7883 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 186/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1556 - distribution_lambda_14_loss: 2.7094 - distribution_lambda_15_loss: 1.8570 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.0678 - val_distribution_lambda_14_loss: 2.6985 - val_distribution_lambda_15_loss: 1.7859 - val_distribution_lambda_16_loss: 0.5834\n", "Epoch 187/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1442 - distribution_lambda_14_loss: 2.7045 - distribution_lambda_15_loss: 1.8508 - distribution_lambda_16_loss: 0.5889 - val_loss: 5.0611 - val_distribution_lambda_14_loss: 2.6943 - val_distribution_lambda_15_loss: 1.7834 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 188/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.1409 - distribution_lambda_14_loss: 2.7009 - distribution_lambda_15_loss: 1.8503 - distribution_lambda_16_loss: 0.5897 - val_loss: 5.0541 - val_distribution_lambda_14_loss: 2.6900 - val_distribution_lambda_15_loss: 1.7806 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 189/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1297 - distribution_lambda_14_loss: 2.6958 - distribution_lambda_15_loss: 1.8444 - distribution_lambda_16_loss: 0.5895 - val_loss: 5.0473 - val_distribution_lambda_14_loss: 2.6857 - val_distribution_lambda_15_loss: 1.7781 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 190/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.1278 - distribution_lambda_14_loss: 2.6922 - distribution_lambda_15_loss: 1.8465 - distribution_lambda_16_loss: 0.5891 - val_loss: 5.0407 - val_distribution_lambda_14_loss: 2.6814 - val_distribution_lambda_15_loss: 1.7759 - val_distribution_lambda_16_loss: 0.5834\n", "Epoch 191/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1229 - distribution_lambda_14_loss: 2.6874 - distribution_lambda_15_loss: 1.8461 - distribution_lambda_16_loss: 0.5894 - val_loss: 5.0340 - val_distribution_lambda_14_loss: 2.6771 - val_distribution_lambda_15_loss: 1.7735 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 192/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1108 - distribution_lambda_14_loss: 2.6837 - distribution_lambda_15_loss: 1.8386 - distribution_lambda_16_loss: 0.5885 - val_loss: 5.0271 - val_distribution_lambda_14_loss: 2.6727 - val_distribution_lambda_15_loss: 1.7709 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 193/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.1095 - distribution_lambda_14_loss: 2.6797 - distribution_lambda_15_loss: 1.8409 - distribution_lambda_16_loss: 0.5889 - val_loss: 5.0201 - val_distribution_lambda_14_loss: 2.6683 - val_distribution_lambda_15_loss: 1.7684 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 194/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.1030 - distribution_lambda_14_loss: 2.6753 - distribution_lambda_15_loss: 1.8385 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.0131 - val_distribution_lambda_14_loss: 2.6639 - val_distribution_lambda_15_loss: 1.7657 - val_distribution_lambda_16_loss: 0.5835\n", "Epoch 195/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.0918 - distribution_lambda_14_loss: 2.6703 - distribution_lambda_15_loss: 1.8328 - distribution_lambda_16_loss: 0.5887 - val_loss: 5.0059 - val_distribution_lambda_14_loss: 2.6595 - val_distribution_lambda_15_loss: 1.7630 - val_distribution_lambda_16_loss: 0.5834\n", "Epoch 196/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.0891 - distribution_lambda_14_loss: 2.6662 - distribution_lambda_15_loss: 1.8337 - distribution_lambda_16_loss: 0.5892 - val_loss: 5.0006 - val_distribution_lambda_14_loss: 2.6550 - val_distribution_lambda_15_loss: 1.7623 - val_distribution_lambda_16_loss: 0.5833\n", "Epoch 197/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0804 - distribution_lambda_14_loss: 2.6612 - distribution_lambda_15_loss: 1.8301 - distribution_lambda_16_loss: 0.5892 - val_loss: 4.9944 - val_distribution_lambda_14_loss: 2.6505 - val_distribution_lambda_15_loss: 1.7607 - val_distribution_lambda_16_loss: 0.5833\n", "Epoch 198/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0741 - distribution_lambda_14_loss: 2.6572 - distribution_lambda_15_loss: 1.8285 - distribution_lambda_16_loss: 0.5884 - val_loss: 4.9874 - val_distribution_lambda_14_loss: 2.6459 - val_distribution_lambda_15_loss: 1.7583 - val_distribution_lambda_16_loss: 0.5832\n", "Epoch 199/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.0671 - distribution_lambda_14_loss: 2.6529 - distribution_lambda_15_loss: 1.8255 - distribution_lambda_16_loss: 0.5886 - val_loss: 4.9800 - val_distribution_lambda_14_loss: 2.6414 - val_distribution_lambda_15_loss: 1.7555 - val_distribution_lambda_16_loss: 0.5831\n", "Epoch 200/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0537 - distribution_lambda_14_loss: 2.6473 - distribution_lambda_15_loss: 1.8177 - distribution_lambda_16_loss: 0.5887 - val_loss: 4.9725 - val_distribution_lambda_14_loss: 2.6368 - val_distribution_lambda_15_loss: 1.7526 - val_distribution_lambda_16_loss: 0.5831\n", "Epoch 201/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0507 - distribution_lambda_14_loss: 2.6439 - distribution_lambda_15_loss: 1.8180 - distribution_lambda_16_loss: 0.5888 - val_loss: 4.9653 - val_distribution_lambda_14_loss: 2.6323 - val_distribution_lambda_15_loss: 1.7500 - val_distribution_lambda_16_loss: 0.5830\n", "Epoch 202/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0450 - distribution_lambda_14_loss: 2.6384 - distribution_lambda_15_loss: 1.8176 - distribution_lambda_16_loss: 0.5889 - val_loss: 4.9584 - val_distribution_lambda_14_loss: 2.6277 - val_distribution_lambda_15_loss: 1.7477 - val_distribution_lambda_16_loss: 0.5830\n", "Epoch 203/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0325 - distribution_lambda_14_loss: 2.6337 - distribution_lambda_15_loss: 1.8102 - distribution_lambda_16_loss: 0.5887 - val_loss: 4.9522 - val_distribution_lambda_14_loss: 2.6230 - val_distribution_lambda_15_loss: 1.7462 - val_distribution_lambda_16_loss: 0.5830\n", "Epoch 204/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0341 - distribution_lambda_14_loss: 2.6298 - distribution_lambda_15_loss: 1.8156 - distribution_lambda_16_loss: 0.5887 - val_loss: 4.9454 - val_distribution_lambda_14_loss: 2.6184 - val_distribution_lambda_15_loss: 1.7441 - val_distribution_lambda_16_loss: 0.5829\n", "Epoch 205/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.0254 - distribution_lambda_14_loss: 2.6240 - distribution_lambda_15_loss: 1.8124 - distribution_lambda_16_loss: 0.5891 - val_loss: 4.9381 - val_distribution_lambda_14_loss: 2.6137 - val_distribution_lambda_15_loss: 1.7415 - val_distribution_lambda_16_loss: 0.5829\n", "Epoch 206/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.0179 - distribution_lambda_14_loss: 2.6197 - distribution_lambda_15_loss: 1.8092 - distribution_lambda_16_loss: 0.5890 - val_loss: 4.9311 - val_distribution_lambda_14_loss: 2.6090 - val_distribution_lambda_15_loss: 1.7392 - val_distribution_lambda_16_loss: 0.5829\n", "Epoch 207/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.0100 - distribution_lambda_14_loss: 2.6154 - distribution_lambda_15_loss: 1.8056 - distribution_lambda_16_loss: 0.5890 - val_loss: 4.9238 - val_distribution_lambda_14_loss: 2.6043 - val_distribution_lambda_15_loss: 1.7367 - val_distribution_lambda_16_loss: 0.5828\n", "Epoch 208/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9963 - distribution_lambda_14_loss: 2.6094 - distribution_lambda_15_loss: 1.7979 - distribution_lambda_16_loss: 0.5889 - val_loss: 4.9159 - val_distribution_lambda_14_loss: 2.5995 - val_distribution_lambda_15_loss: 1.7335 - val_distribution_lambda_16_loss: 0.5828\n", "Epoch 209/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9903 - distribution_lambda_14_loss: 2.6051 - distribution_lambda_15_loss: 1.7964 - distribution_lambda_16_loss: 0.5888 - val_loss: 4.9084 - val_distribution_lambda_14_loss: 2.5947 - val_distribution_lambda_15_loss: 1.7309 - val_distribution_lambda_16_loss: 0.5828\n", "Epoch 210/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9914 - distribution_lambda_14_loss: 2.6012 - distribution_lambda_15_loss: 1.8009 - distribution_lambda_16_loss: 0.5893 - val_loss: 4.9009 - val_distribution_lambda_14_loss: 2.5899 - val_distribution_lambda_15_loss: 1.7282 - val_distribution_lambda_16_loss: 0.5828\n", "Epoch 211/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9821 - distribution_lambda_14_loss: 2.5961 - distribution_lambda_15_loss: 1.7969 - distribution_lambda_16_loss: 0.5890 - val_loss: 4.8934 - val_distribution_lambda_14_loss: 2.5850 - val_distribution_lambda_15_loss: 1.7256 - val_distribution_lambda_16_loss: 0.5827\n", "Epoch 212/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9706 - distribution_lambda_14_loss: 2.5910 - distribution_lambda_15_loss: 1.7906 - distribution_lambda_16_loss: 0.5890 - val_loss: 4.8859 - val_distribution_lambda_14_loss: 2.5802 - val_distribution_lambda_15_loss: 1.7230 - val_distribution_lambda_16_loss: 0.5827\n", "Epoch 213/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9616 - distribution_lambda_14_loss: 2.5861 - distribution_lambda_15_loss: 1.7874 - distribution_lambda_16_loss: 0.5882 - val_loss: 4.8786 - val_distribution_lambda_14_loss: 2.5753 - val_distribution_lambda_15_loss: 1.7207 - val_distribution_lambda_16_loss: 0.5827\n", "Epoch 214/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9520 - distribution_lambda_14_loss: 2.5808 - distribution_lambda_15_loss: 1.7827 - distribution_lambda_16_loss: 0.5885 - val_loss: 4.8722 - val_distribution_lambda_14_loss: 2.5704 - val_distribution_lambda_15_loss: 1.7192 - val_distribution_lambda_16_loss: 0.5826\n", "Epoch 215/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9532 - distribution_lambda_14_loss: 2.5755 - distribution_lambda_15_loss: 1.7886 - distribution_lambda_16_loss: 0.5891 - val_loss: 4.8650 - val_distribution_lambda_14_loss: 2.5654 - val_distribution_lambda_15_loss: 1.7170 - val_distribution_lambda_16_loss: 0.5825\n", "Epoch 216/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9397 - distribution_lambda_14_loss: 2.5710 - distribution_lambda_15_loss: 1.7801 - distribution_lambda_16_loss: 0.5886 - val_loss: 4.8576 - val_distribution_lambda_14_loss: 2.5604 - val_distribution_lambda_15_loss: 1.7146 - val_distribution_lambda_16_loss: 0.5825\n", "Epoch 217/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 4.9393 - distribution_lambda_14_loss: 2.5664 - distribution_lambda_15_loss: 1.7847 - distribution_lambda_16_loss: 0.5882 - val_loss: 4.8497 - val_distribution_lambda_14_loss: 2.5554 - val_distribution_lambda_15_loss: 1.7117 - val_distribution_lambda_16_loss: 0.5825\n", "Epoch 218/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9257 - distribution_lambda_14_loss: 2.5609 - distribution_lambda_15_loss: 1.7769 - distribution_lambda_16_loss: 0.5880 - val_loss: 4.8422 - val_distribution_lambda_14_loss: 2.5504 - val_distribution_lambda_15_loss: 1.7093 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 219/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9215 - distribution_lambda_14_loss: 2.5562 - distribution_lambda_15_loss: 1.7771 - distribution_lambda_16_loss: 0.5882 - val_loss: 4.8343 - val_distribution_lambda_14_loss: 2.5454 - val_distribution_lambda_15_loss: 1.7065 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 220/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9123 - distribution_lambda_14_loss: 2.5502 - distribution_lambda_15_loss: 1.7738 - distribution_lambda_16_loss: 0.5883 - val_loss: 4.8270 - val_distribution_lambda_14_loss: 2.5403 - val_distribution_lambda_15_loss: 1.7042 - val_distribution_lambda_16_loss: 0.5825\n", "Epoch 221/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9034 - distribution_lambda_14_loss: 2.5458 - distribution_lambda_15_loss: 1.7691 - distribution_lambda_16_loss: 0.5885 - val_loss: 4.8196 - val_distribution_lambda_14_loss: 2.5352 - val_distribution_lambda_15_loss: 1.7018 - val_distribution_lambda_16_loss: 0.5826\n", "Epoch 222/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9052 - distribution_lambda_14_loss: 2.5412 - distribution_lambda_15_loss: 1.7755 - distribution_lambda_16_loss: 0.5885 - val_loss: 4.8122 - val_distribution_lambda_14_loss: 2.5301 - val_distribution_lambda_15_loss: 1.6995 - val_distribution_lambda_16_loss: 0.5826\n", "Epoch 223/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8967 - distribution_lambda_14_loss: 2.5365 - distribution_lambda_15_loss: 1.7715 - distribution_lambda_16_loss: 0.5887 - val_loss: 4.8047 - val_distribution_lambda_14_loss: 2.5249 - val_distribution_lambda_15_loss: 1.6971 - val_distribution_lambda_16_loss: 0.5827\n", "Epoch 224/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8799 - distribution_lambda_14_loss: 2.5310 - distribution_lambda_15_loss: 1.7605 - distribution_lambda_16_loss: 0.5883 - val_loss: 4.7967 - val_distribution_lambda_14_loss: 2.5197 - val_distribution_lambda_15_loss: 1.6942 - val_distribution_lambda_16_loss: 0.5827\n", "Epoch 225/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8719 - distribution_lambda_14_loss: 2.5254 - distribution_lambda_15_loss: 1.7582 - distribution_lambda_16_loss: 0.5883 - val_loss: 4.7889 - val_distribution_lambda_14_loss: 2.5145 - val_distribution_lambda_15_loss: 1.6918 - val_distribution_lambda_16_loss: 0.5826\n", "Epoch 226/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8650 - distribution_lambda_14_loss: 2.5193 - distribution_lambda_15_loss: 1.7578 - distribution_lambda_16_loss: 0.5879 - val_loss: 4.7819 - val_distribution_lambda_14_loss: 2.5093 - val_distribution_lambda_15_loss: 1.6902 - val_distribution_lambda_16_loss: 0.5825\n", "Epoch 227/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8634 - distribution_lambda_14_loss: 2.5156 - distribution_lambda_15_loss: 1.7597 - distribution_lambda_16_loss: 0.5881 - val_loss: 4.7745 - val_distribution_lambda_14_loss: 2.5040 - val_distribution_lambda_15_loss: 1.6881 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 228/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8465 - distribution_lambda_14_loss: 2.5092 - distribution_lambda_15_loss: 1.7492 - distribution_lambda_16_loss: 0.5882 - val_loss: 4.7665 - val_distribution_lambda_14_loss: 2.4988 - val_distribution_lambda_15_loss: 1.6853 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 229/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8428 - distribution_lambda_14_loss: 2.5043 - distribution_lambda_15_loss: 1.7501 - distribution_lambda_16_loss: 0.5885 - val_loss: 4.7587 - val_distribution_lambda_14_loss: 2.4935 - val_distribution_lambda_15_loss: 1.6828 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 230/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8410 - distribution_lambda_14_loss: 2.4987 - distribution_lambda_15_loss: 1.7540 - distribution_lambda_16_loss: 0.5883 - val_loss: 4.7511 - val_distribution_lambda_14_loss: 2.4882 - val_distribution_lambda_15_loss: 1.6805 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 231/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8257 - distribution_lambda_14_loss: 2.4935 - distribution_lambda_15_loss: 1.7441 - distribution_lambda_16_loss: 0.5881 - val_loss: 4.7434 - val_distribution_lambda_14_loss: 2.4829 - val_distribution_lambda_15_loss: 1.6781 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 232/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8201 - distribution_lambda_14_loss: 2.4880 - distribution_lambda_15_loss: 1.7441 - distribution_lambda_16_loss: 0.5880 - val_loss: 4.7354 - val_distribution_lambda_14_loss: 2.4775 - val_distribution_lambda_15_loss: 1.6755 - val_distribution_lambda_16_loss: 0.5824\n", "Epoch 233/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8092 - distribution_lambda_14_loss: 2.4830 - distribution_lambda_15_loss: 1.7384 - distribution_lambda_16_loss: 0.5878 - val_loss: 4.7272 - val_distribution_lambda_14_loss: 2.4721 - val_distribution_lambda_15_loss: 1.6728 - val_distribution_lambda_16_loss: 0.5822\n", "Epoch 234/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8064 - distribution_lambda_14_loss: 2.4785 - distribution_lambda_15_loss: 1.7399 - distribution_lambda_16_loss: 0.5880 - val_loss: 4.7192 - val_distribution_lambda_14_loss: 2.4667 - val_distribution_lambda_15_loss: 1.6703 - val_distribution_lambda_16_loss: 0.5822\n", "Epoch 235/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7927 - distribution_lambda_14_loss: 2.4723 - distribution_lambda_15_loss: 1.7324 - distribution_lambda_16_loss: 0.5880 - val_loss: 4.7110 - val_distribution_lambda_14_loss: 2.4613 - val_distribution_lambda_15_loss: 1.6677 - val_distribution_lambda_16_loss: 0.5820\n", "Epoch 236/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7835 - distribution_lambda_14_loss: 2.4666 - distribution_lambda_15_loss: 1.7293 - distribution_lambda_16_loss: 0.5876 - val_loss: 4.7028 - val_distribution_lambda_14_loss: 2.4559 - val_distribution_lambda_15_loss: 1.6650 - val_distribution_lambda_16_loss: 0.5819\n", "Epoch 237/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7813 - distribution_lambda_14_loss: 2.4611 - distribution_lambda_15_loss: 1.7329 - distribution_lambda_16_loss: 0.5873 - val_loss: 4.6945 - val_distribution_lambda_14_loss: 2.4505 - val_distribution_lambda_15_loss: 1.6621 - val_distribution_lambda_16_loss: 0.5819\n", "Epoch 238/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7745 - distribution_lambda_14_loss: 2.4564 - distribution_lambda_15_loss: 1.7304 - distribution_lambda_16_loss: 0.5877 - val_loss: 4.6861 - val_distribution_lambda_14_loss: 2.4450 - val_distribution_lambda_15_loss: 1.6594 - val_distribution_lambda_16_loss: 0.5818\n", "Epoch 239/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7591 - distribution_lambda_14_loss: 2.4495 - distribution_lambda_15_loss: 1.7219 - distribution_lambda_16_loss: 0.5876 - val_loss: 4.6781 - val_distribution_lambda_14_loss: 2.4395 - val_distribution_lambda_15_loss: 1.6569 - val_distribution_lambda_16_loss: 0.5817\n", "Epoch 240/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7558 - distribution_lambda_14_loss: 2.4451 - distribution_lambda_15_loss: 1.7237 - distribution_lambda_16_loss: 0.5870 - val_loss: 4.6702 - val_distribution_lambda_14_loss: 2.4340 - val_distribution_lambda_15_loss: 1.6546 - val_distribution_lambda_16_loss: 0.5816\n", "Epoch 241/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.7494 - distribution_lambda_14_loss: 2.4393 - distribution_lambda_15_loss: 1.7225 - distribution_lambda_16_loss: 0.5876 - val_loss: 4.6623 - val_distribution_lambda_14_loss: 2.4285 - val_distribution_lambda_15_loss: 1.6523 - val_distribution_lambda_16_loss: 0.5815\n", "Epoch 242/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7361 - distribution_lambda_14_loss: 2.4340 - distribution_lambda_15_loss: 1.7142 - distribution_lambda_16_loss: 0.5880 - val_loss: 4.6539 - val_distribution_lambda_14_loss: 2.4230 - val_distribution_lambda_15_loss: 1.6494 - val_distribution_lambda_16_loss: 0.5815\n", "Epoch 243/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7268 - distribution_lambda_14_loss: 2.4282 - distribution_lambda_15_loss: 1.7111 - distribution_lambda_16_loss: 0.5875 - val_loss: 4.6457 - val_distribution_lambda_14_loss: 2.4175 - val_distribution_lambda_15_loss: 1.6468 - val_distribution_lambda_16_loss: 0.5815\n", "Epoch 244/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7214 - distribution_lambda_14_loss: 2.4222 - distribution_lambda_15_loss: 1.7116 - distribution_lambda_16_loss: 0.5875 - val_loss: 4.6378 - val_distribution_lambda_14_loss: 2.4119 - val_distribution_lambda_15_loss: 1.6444 - val_distribution_lambda_16_loss: 0.5815\n", "Epoch 245/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7160 - distribution_lambda_14_loss: 2.4172 - distribution_lambda_15_loss: 1.7111 - distribution_lambda_16_loss: 0.5877 - val_loss: 4.6299 - val_distribution_lambda_14_loss: 2.4063 - val_distribution_lambda_15_loss: 1.6421 - val_distribution_lambda_16_loss: 0.5815\n", "Epoch 246/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7082 - distribution_lambda_14_loss: 2.4112 - distribution_lambda_15_loss: 1.7098 - distribution_lambda_16_loss: 0.5871 - val_loss: 4.6218 - val_distribution_lambda_14_loss: 2.4008 - val_distribution_lambda_15_loss: 1.6396 - val_distribution_lambda_16_loss: 0.5814\n", "Epoch 247/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6969 - distribution_lambda_14_loss: 2.4056 - distribution_lambda_15_loss: 1.7034 - distribution_lambda_16_loss: 0.5879 - val_loss: 4.6137 - val_distribution_lambda_14_loss: 2.3952 - val_distribution_lambda_15_loss: 1.6370 - val_distribution_lambda_16_loss: 0.5814\n", "Epoch 248/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6880 - distribution_lambda_14_loss: 2.4008 - distribution_lambda_15_loss: 1.7001 - distribution_lambda_16_loss: 0.5871 - val_loss: 4.6072 - val_distribution_lambda_14_loss: 2.3896 - val_distribution_lambda_15_loss: 1.6363 - val_distribution_lambda_16_loss: 0.5814\n", "Epoch 249/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6880 - distribution_lambda_14_loss: 2.3952 - distribution_lambda_15_loss: 1.7066 - distribution_lambda_16_loss: 0.5862 - val_loss: 4.6009 - val_distribution_lambda_14_loss: 2.3840 - val_distribution_lambda_15_loss: 1.6356 - val_distribution_lambda_16_loss: 0.5814\n", "Epoch 250/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6688 - distribution_lambda_14_loss: 2.3895 - distribution_lambda_15_loss: 1.6922 - distribution_lambda_16_loss: 0.5871 - val_loss: 4.5941 - val_distribution_lambda_14_loss: 2.3784 - val_distribution_lambda_15_loss: 1.6345 - val_distribution_lambda_16_loss: 0.5812\n", "Epoch 251/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6621 - distribution_lambda_14_loss: 2.3833 - distribution_lambda_15_loss: 1.6918 - distribution_lambda_16_loss: 0.5871 - val_loss: 4.5853 - val_distribution_lambda_14_loss: 2.3727 - val_distribution_lambda_15_loss: 1.6314 - val_distribution_lambda_16_loss: 0.5812\n", "Epoch 252/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6586 - distribution_lambda_14_loss: 2.3767 - distribution_lambda_15_loss: 1.6947 - distribution_lambda_16_loss: 0.5873 - val_loss: 4.5768 - val_distribution_lambda_14_loss: 2.3671 - val_distribution_lambda_15_loss: 1.6285 - val_distribution_lambda_16_loss: 0.5811\n", "Epoch 253/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6432 - distribution_lambda_14_loss: 2.3722 - distribution_lambda_15_loss: 1.6844 - distribution_lambda_16_loss: 0.5867 - val_loss: 4.5697 - val_distribution_lambda_14_loss: 2.3615 - val_distribution_lambda_15_loss: 1.6272 - val_distribution_lambda_16_loss: 0.5810\n", "Epoch 254/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6367 - distribution_lambda_14_loss: 2.3664 - distribution_lambda_15_loss: 1.6830 - distribution_lambda_16_loss: 0.5873 - val_loss: 4.5617 - val_distribution_lambda_14_loss: 2.3559 - val_distribution_lambda_15_loss: 1.6249 - val_distribution_lambda_16_loss: 0.5809\n", "Epoch 255/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.6348 - distribution_lambda_14_loss: 2.3610 - distribution_lambda_15_loss: 1.6869 - distribution_lambda_16_loss: 0.5869 - val_loss: 4.5532 - val_distribution_lambda_14_loss: 2.3502 - val_distribution_lambda_15_loss: 1.6221 - val_distribution_lambda_16_loss: 0.5809\n", "Epoch 256/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6194 - distribution_lambda_14_loss: 2.3552 - distribution_lambda_15_loss: 1.6769 - distribution_lambda_16_loss: 0.5872 - val_loss: 4.5449 - val_distribution_lambda_14_loss: 2.3446 - val_distribution_lambda_15_loss: 1.6195 - val_distribution_lambda_16_loss: 0.5808\n", "Epoch 257/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6215 - distribution_lambda_14_loss: 2.3499 - distribution_lambda_15_loss: 1.6844 - distribution_lambda_16_loss: 0.5872 - val_loss: 4.5368 - val_distribution_lambda_14_loss: 2.3389 - val_distribution_lambda_15_loss: 1.6171 - val_distribution_lambda_16_loss: 0.5807\n", "Epoch 258/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6074 - distribution_lambda_14_loss: 2.3439 - distribution_lambda_15_loss: 1.6766 - distribution_lambda_16_loss: 0.5869 - val_loss: 4.5282 - val_distribution_lambda_14_loss: 2.3333 - val_distribution_lambda_15_loss: 1.6143 - val_distribution_lambda_16_loss: 0.5807\n", "Epoch 259/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6021 - distribution_lambda_14_loss: 2.3388 - distribution_lambda_15_loss: 1.6769 - distribution_lambda_16_loss: 0.5864 - val_loss: 4.5204 - val_distribution_lambda_14_loss: 2.3276 - val_distribution_lambda_15_loss: 1.6121 - val_distribution_lambda_16_loss: 0.5807\n", "Epoch 260/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5937 - distribution_lambda_14_loss: 2.3329 - distribution_lambda_15_loss: 1.6737 - distribution_lambda_16_loss: 0.5871 - val_loss: 4.5128 - val_distribution_lambda_14_loss: 2.3220 - val_distribution_lambda_15_loss: 1.6102 - val_distribution_lambda_16_loss: 0.5806\n", "Epoch 261/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5796 - distribution_lambda_14_loss: 2.3271 - distribution_lambda_15_loss: 1.6660 - distribution_lambda_16_loss: 0.5865 - val_loss: 4.5052 - val_distribution_lambda_14_loss: 2.3163 - val_distribution_lambda_15_loss: 1.6084 - val_distribution_lambda_16_loss: 0.5805\n", "Epoch 262/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.5777 - distribution_lambda_14_loss: 2.3213 - distribution_lambda_15_loss: 1.6697 - distribution_lambda_16_loss: 0.5867 - val_loss: 4.4973 - val_distribution_lambda_14_loss: 2.3106 - val_distribution_lambda_15_loss: 1.6062 - val_distribution_lambda_16_loss: 0.5805\n", "Epoch 263/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5648 - distribution_lambda_14_loss: 2.3152 - distribution_lambda_15_loss: 1.6628 - distribution_lambda_16_loss: 0.5867 - val_loss: 4.4890 - val_distribution_lambda_14_loss: 2.3050 - val_distribution_lambda_15_loss: 1.6036 - val_distribution_lambda_16_loss: 0.5804\n", "Epoch 264/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5568 - distribution_lambda_14_loss: 2.3098 - distribution_lambda_15_loss: 1.6609 - distribution_lambda_16_loss: 0.5861 - val_loss: 4.4812 - val_distribution_lambda_14_loss: 2.2993 - val_distribution_lambda_15_loss: 1.6016 - val_distribution_lambda_16_loss: 0.5803\n", "Epoch 265/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.5423 - distribution_lambda_14_loss: 2.3038 - distribution_lambda_15_loss: 1.6524 - distribution_lambda_16_loss: 0.5862 - val_loss: 4.4731 - val_distribution_lambda_14_loss: 2.2936 - val_distribution_lambda_15_loss: 1.5993 - val_distribution_lambda_16_loss: 0.5802\n", "Epoch 266/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5440 - distribution_lambda_14_loss: 2.2988 - distribution_lambda_15_loss: 1.6584 - distribution_lambda_16_loss: 0.5868 - val_loss: 4.4649 - val_distribution_lambda_14_loss: 2.2879 - val_distribution_lambda_15_loss: 1.5968 - val_distribution_lambda_16_loss: 0.5802\n", "Epoch 267/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5284 - distribution_lambda_14_loss: 2.2920 - distribution_lambda_15_loss: 1.6502 - distribution_lambda_16_loss: 0.5863 - val_loss: 4.4565 - val_distribution_lambda_14_loss: 2.2822 - val_distribution_lambda_15_loss: 1.5942 - val_distribution_lambda_16_loss: 0.5802\n", "Epoch 268/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5244 - distribution_lambda_14_loss: 2.2867 - distribution_lambda_15_loss: 1.6513 - distribution_lambda_16_loss: 0.5864 - val_loss: 4.4484 - val_distribution_lambda_14_loss: 2.2765 - val_distribution_lambda_15_loss: 1.5918 - val_distribution_lambda_16_loss: 0.5801\n", "Epoch 269/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.5150 - distribution_lambda_14_loss: 2.2814 - distribution_lambda_15_loss: 1.6472 - distribution_lambda_16_loss: 0.5863 - val_loss: 4.4410 - val_distribution_lambda_14_loss: 2.2708 - val_distribution_lambda_15_loss: 1.5901 - val_distribution_lambda_16_loss: 0.5801\n", "Epoch 270/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5064 - distribution_lambda_14_loss: 2.2751 - distribution_lambda_15_loss: 1.6454 - distribution_lambda_16_loss: 0.5860 - val_loss: 4.4339 - val_distribution_lambda_14_loss: 2.2651 - val_distribution_lambda_15_loss: 1.5889 - val_distribution_lambda_16_loss: 0.5800\n", "Epoch 271/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4991 - distribution_lambda_14_loss: 2.2697 - distribution_lambda_15_loss: 1.6427 - distribution_lambda_16_loss: 0.5866 - val_loss: 4.4262 - val_distribution_lambda_14_loss: 2.2593 - val_distribution_lambda_15_loss: 1.5870 - val_distribution_lambda_16_loss: 0.5799\n", "Epoch 272/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4903 - distribution_lambda_14_loss: 2.2638 - distribution_lambda_15_loss: 1.6401 - distribution_lambda_16_loss: 0.5864 - val_loss: 4.4232 - val_distribution_lambda_14_loss: 2.2537 - val_distribution_lambda_15_loss: 1.5898 - val_distribution_lambda_16_loss: 0.5797\n", "Epoch 273/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4928 - distribution_lambda_14_loss: 2.2590 - distribution_lambda_15_loss: 1.6480 - distribution_lambda_16_loss: 0.5859 - val_loss: 4.4175 - val_distribution_lambda_14_loss: 2.2480 - val_distribution_lambda_15_loss: 1.5899 - val_distribution_lambda_16_loss: 0.5796\n", "Epoch 274/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4783 - distribution_lambda_14_loss: 2.2523 - distribution_lambda_15_loss: 1.6402 - distribution_lambda_16_loss: 0.5858 - val_loss: 4.4102 - val_distribution_lambda_14_loss: 2.2422 - val_distribution_lambda_15_loss: 1.5884 - val_distribution_lambda_16_loss: 0.5795\n", "Epoch 275/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4675 - distribution_lambda_14_loss: 2.2469 - distribution_lambda_15_loss: 1.6347 - distribution_lambda_16_loss: 0.5859 - val_loss: 4.4001 - val_distribution_lambda_14_loss: 2.2365 - val_distribution_lambda_15_loss: 1.5841 - val_distribution_lambda_16_loss: 0.5795\n", "Epoch 276/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4653 - distribution_lambda_14_loss: 2.2411 - distribution_lambda_15_loss: 1.6392 - distribution_lambda_16_loss: 0.5850 - val_loss: 4.3895 - val_distribution_lambda_14_loss: 2.2308 - val_distribution_lambda_15_loss: 1.5793 - val_distribution_lambda_16_loss: 0.5794\n", "Epoch 277/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4525 - distribution_lambda_14_loss: 2.2356 - distribution_lambda_15_loss: 1.6309 - distribution_lambda_16_loss: 0.5860 - val_loss: 4.3819 - val_distribution_lambda_14_loss: 2.2250 - val_distribution_lambda_15_loss: 1.5775 - val_distribution_lambda_16_loss: 0.5794\n", "Epoch 278/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4463 - distribution_lambda_14_loss: 2.2292 - distribution_lambda_15_loss: 1.6316 - distribution_lambda_16_loss: 0.5855 - val_loss: 4.3737 - val_distribution_lambda_14_loss: 2.2192 - val_distribution_lambda_15_loss: 1.5751 - val_distribution_lambda_16_loss: 0.5794\n", "Epoch 279/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4362 - distribution_lambda_14_loss: 2.2236 - distribution_lambda_15_loss: 1.6268 - distribution_lambda_16_loss: 0.5858 - val_loss: 4.3658 - val_distribution_lambda_14_loss: 2.2134 - val_distribution_lambda_15_loss: 1.5730 - val_distribution_lambda_16_loss: 0.5794\n", "Epoch 280/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4303 - distribution_lambda_14_loss: 2.2182 - distribution_lambda_15_loss: 1.6265 - distribution_lambda_16_loss: 0.5856 - val_loss: 4.3581 - val_distribution_lambda_14_loss: 2.2076 - val_distribution_lambda_15_loss: 1.5712 - val_distribution_lambda_16_loss: 0.5793\n", "Epoch 281/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4191 - distribution_lambda_14_loss: 2.2118 - distribution_lambda_15_loss: 1.6218 - distribution_lambda_16_loss: 0.5855 - val_loss: 4.3504 - val_distribution_lambda_14_loss: 2.2018 - val_distribution_lambda_15_loss: 1.5693 - val_distribution_lambda_16_loss: 0.5793\n", "Epoch 282/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4069 - distribution_lambda_14_loss: 2.2060 - distribution_lambda_15_loss: 1.6159 - distribution_lambda_16_loss: 0.5851 - val_loss: 4.3436 - val_distribution_lambda_14_loss: 2.1960 - val_distribution_lambda_15_loss: 1.5684 - val_distribution_lambda_16_loss: 0.5792\n", "Epoch 283/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.4036 - distribution_lambda_14_loss: 2.2010 - distribution_lambda_15_loss: 1.6172 - distribution_lambda_16_loss: 0.5853 - val_loss: 4.3363 - val_distribution_lambda_14_loss: 2.1902 - val_distribution_lambda_15_loss: 1.5670 - val_distribution_lambda_16_loss: 0.5791\n", "Epoch 284/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3920 - distribution_lambda_14_loss: 2.1944 - distribution_lambda_15_loss: 1.6131 - distribution_lambda_16_loss: 0.5846 - val_loss: 4.3294 - val_distribution_lambda_14_loss: 2.1844 - val_distribution_lambda_15_loss: 1.5660 - val_distribution_lambda_16_loss: 0.5790\n", "Epoch 285/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3926 - distribution_lambda_14_loss: 2.1889 - distribution_lambda_15_loss: 1.6182 - distribution_lambda_16_loss: 0.5855 - val_loss: 4.3218 - val_distribution_lambda_14_loss: 2.1785 - val_distribution_lambda_15_loss: 1.5644 - val_distribution_lambda_16_loss: 0.5789\n", "Epoch 286/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3818 - distribution_lambda_14_loss: 2.1827 - distribution_lambda_15_loss: 1.6139 - distribution_lambda_16_loss: 0.5851 - val_loss: 4.3132 - val_distribution_lambda_14_loss: 2.1727 - val_distribution_lambda_15_loss: 1.5616 - val_distribution_lambda_16_loss: 0.5789\n", "Epoch 287/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3742 - distribution_lambda_14_loss: 2.1775 - distribution_lambda_15_loss: 1.6114 - distribution_lambda_16_loss: 0.5853 - val_loss: 4.3055 - val_distribution_lambda_14_loss: 2.1668 - val_distribution_lambda_15_loss: 1.5597 - val_distribution_lambda_16_loss: 0.5790\n", "Epoch 288/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.3639 - distribution_lambda_14_loss: 2.1704 - distribution_lambda_15_loss: 1.6083 - distribution_lambda_16_loss: 0.5851 - val_loss: 4.2982 - val_distribution_lambda_14_loss: 2.1609 - val_distribution_lambda_15_loss: 1.5580 - val_distribution_lambda_16_loss: 0.5792\n", "Epoch 289/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 4.3608 - distribution_lambda_14_loss: 2.1648 - distribution_lambda_15_loss: 1.6114 - distribution_lambda_16_loss: 0.5846 - val_loss: 4.2916 - val_distribution_lambda_14_loss: 2.1550 - val_distribution_lambda_15_loss: 1.5574 - val_distribution_lambda_16_loss: 0.5791\n", "Epoch 290/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3441 - distribution_lambda_14_loss: 2.1600 - distribution_lambda_15_loss: 1.5998 - distribution_lambda_16_loss: 0.5843 - val_loss: 4.2848 - val_distribution_lambda_14_loss: 2.1491 - val_distribution_lambda_15_loss: 1.5566 - val_distribution_lambda_16_loss: 0.5792\n", "Epoch 291/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.3474 - distribution_lambda_14_loss: 2.1532 - distribution_lambda_15_loss: 1.6090 - distribution_lambda_16_loss: 0.5852 - val_loss: 4.2775 - val_distribution_lambda_14_loss: 2.1431 - val_distribution_lambda_15_loss: 1.5553 - val_distribution_lambda_16_loss: 0.5791\n", "Epoch 292/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3336 - distribution_lambda_14_loss: 2.1475 - distribution_lambda_15_loss: 1.6003 - distribution_lambda_16_loss: 0.5858 - val_loss: 4.2696 - val_distribution_lambda_14_loss: 2.1371 - val_distribution_lambda_15_loss: 1.5536 - val_distribution_lambda_16_loss: 0.5789\n", "Epoch 293/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3271 - distribution_lambda_14_loss: 2.1412 - distribution_lambda_15_loss: 1.6007 - distribution_lambda_16_loss: 0.5851 - val_loss: 4.2615 - val_distribution_lambda_14_loss: 2.1311 - val_distribution_lambda_15_loss: 1.5517 - val_distribution_lambda_16_loss: 0.5787\n", "Epoch 294/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3175 - distribution_lambda_14_loss: 2.1353 - distribution_lambda_15_loss: 1.5974 - distribution_lambda_16_loss: 0.5849 - val_loss: 4.2531 - val_distribution_lambda_14_loss: 2.1251 - val_distribution_lambda_15_loss: 1.5497 - val_distribution_lambda_16_loss: 0.5783\n", "Epoch 295/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3067 - distribution_lambda_14_loss: 2.1291 - distribution_lambda_15_loss: 1.5927 - distribution_lambda_16_loss: 0.5848 - val_loss: 4.2452 - val_distribution_lambda_14_loss: 2.1191 - val_distribution_lambda_15_loss: 1.5479 - val_distribution_lambda_16_loss: 0.5782\n", "Epoch 296/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.2988 - distribution_lambda_14_loss: 2.1238 - distribution_lambda_15_loss: 1.5909 - distribution_lambda_16_loss: 0.5840 - val_loss: 4.2370 - val_distribution_lambda_14_loss: 2.1130 - val_distribution_lambda_15_loss: 1.5460 - val_distribution_lambda_16_loss: 0.5780\n", "Epoch 297/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2983 - distribution_lambda_14_loss: 2.1175 - distribution_lambda_15_loss: 1.5966 - distribution_lambda_16_loss: 0.5842 - val_loss: 4.2287 - val_distribution_lambda_14_loss: 2.1069 - val_distribution_lambda_15_loss: 1.5441 - val_distribution_lambda_16_loss: 0.5777\n", "Epoch 298/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2913 - distribution_lambda_14_loss: 2.1114 - distribution_lambda_15_loss: 1.5959 - distribution_lambda_16_loss: 0.5840 - val_loss: 4.2220 - val_distribution_lambda_14_loss: 2.1008 - val_distribution_lambda_15_loss: 1.5437 - val_distribution_lambda_16_loss: 0.5775\n", "Epoch 299/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2802 - distribution_lambda_14_loss: 2.1050 - distribution_lambda_15_loss: 1.5914 - distribution_lambda_16_loss: 0.5838 - val_loss: 4.2148 - val_distribution_lambda_14_loss: 2.0947 - val_distribution_lambda_15_loss: 1.5427 - val_distribution_lambda_16_loss: 0.5774\n", "Epoch 300/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.2779 - distribution_lambda_14_loss: 2.0992 - distribution_lambda_15_loss: 1.5944 - distribution_lambda_16_loss: 0.5843 - val_loss: 4.2082 - val_distribution_lambda_14_loss: 2.0886 - val_distribution_lambda_15_loss: 1.5423 - val_distribution_lambda_16_loss: 0.5774\n", "Epoch 301/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.2578 - distribution_lambda_14_loss: 2.0927 - distribution_lambda_15_loss: 1.5820 - distribution_lambda_16_loss: 0.5831 - val_loss: 4.2013 - val_distribution_lambda_14_loss: 2.0824 - val_distribution_lambda_15_loss: 1.5416 - val_distribution_lambda_16_loss: 0.5773\n", "Epoch 302/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.2582 - distribution_lambda_14_loss: 2.0866 - distribution_lambda_15_loss: 1.5878 - distribution_lambda_16_loss: 0.5838 - val_loss: 4.1940 - val_distribution_lambda_14_loss: 2.0762 - val_distribution_lambda_15_loss: 1.5406 - val_distribution_lambda_16_loss: 0.5772\n", "Epoch 303/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.2523 - distribution_lambda_14_loss: 2.0806 - distribution_lambda_15_loss: 1.5882 - distribution_lambda_16_loss: 0.5835 - val_loss: 4.1866 - val_distribution_lambda_14_loss: 2.0699 - val_distribution_lambda_15_loss: 1.5395 - val_distribution_lambda_16_loss: 0.5771\n", "Epoch 304/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2454 - distribution_lambda_14_loss: 2.0741 - distribution_lambda_15_loss: 1.5877 - distribution_lambda_16_loss: 0.5836 - val_loss: 4.1787 - val_distribution_lambda_14_loss: 2.0637 - val_distribution_lambda_15_loss: 1.5380 - val_distribution_lambda_16_loss: 0.5770\n", "Epoch 305/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2409 - distribution_lambda_14_loss: 2.0681 - distribution_lambda_15_loss: 1.5899 - distribution_lambda_16_loss: 0.5828 - val_loss: 4.1756 - val_distribution_lambda_14_loss: 2.0573 - val_distribution_lambda_15_loss: 1.5410 - val_distribution_lambda_16_loss: 0.5773\n", "Epoch 306/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2275 - distribution_lambda_14_loss: 2.0617 - distribution_lambda_15_loss: 1.5826 - distribution_lambda_16_loss: 0.5833 - val_loss: 4.1713 - val_distribution_lambda_14_loss: 2.0509 - val_distribution_lambda_15_loss: 1.5429 - val_distribution_lambda_16_loss: 0.5774\n", "Epoch 307/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2263 - distribution_lambda_14_loss: 2.0554 - distribution_lambda_15_loss: 1.5873 - distribution_lambda_16_loss: 0.5835 - val_loss: 4.1629 - val_distribution_lambda_14_loss: 2.0445 - val_distribution_lambda_15_loss: 1.5411 - val_distribution_lambda_16_loss: 0.5773\n", "Epoch 308/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2132 - distribution_lambda_14_loss: 2.0489 - distribution_lambda_15_loss: 1.5816 - distribution_lambda_16_loss: 0.5828 - val_loss: 4.1530 - val_distribution_lambda_14_loss: 2.0381 - val_distribution_lambda_15_loss: 1.5379 - val_distribution_lambda_16_loss: 0.5770\n", "Epoch 309/2000\n", "8/8 [==============================] - 0s 10ms/step - loss: 4.2058 - distribution_lambda_14_loss: 2.0423 - distribution_lambda_15_loss: 1.5799 - distribution_lambda_16_loss: 0.5836 - val_loss: 4.1444 - val_distribution_lambda_14_loss: 2.0316 - val_distribution_lambda_15_loss: 1.5360 - val_distribution_lambda_16_loss: 0.5767\n", "Epoch 310/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1975 - distribution_lambda_14_loss: 2.0365 - distribution_lambda_15_loss: 1.5782 - distribution_lambda_16_loss: 0.5828 - val_loss: 4.1362 - val_distribution_lambda_14_loss: 2.0251 - val_distribution_lambda_15_loss: 1.5344 - val_distribution_lambda_16_loss: 0.5766\n", "Epoch 311/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.1857 - distribution_lambda_14_loss: 2.0288 - distribution_lambda_15_loss: 1.5741 - distribution_lambda_16_loss: 0.5827 - val_loss: 4.1279 - val_distribution_lambda_14_loss: 2.0186 - val_distribution_lambda_15_loss: 1.5328 - val_distribution_lambda_16_loss: 0.5765\n", "Epoch 312/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.1890 - distribution_lambda_14_loss: 2.0226 - distribution_lambda_15_loss: 1.5833 - distribution_lambda_16_loss: 0.5831 - val_loss: 4.1197 - val_distribution_lambda_14_loss: 2.0120 - val_distribution_lambda_15_loss: 1.5315 - val_distribution_lambda_16_loss: 0.5762\n", "Epoch 313/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 4.1738 - distribution_lambda_14_loss: 2.0163 - distribution_lambda_15_loss: 1.5749 - distribution_lambda_16_loss: 0.5826 - val_loss: 4.1116 - val_distribution_lambda_14_loss: 2.0054 - val_distribution_lambda_15_loss: 1.5303 - val_distribution_lambda_16_loss: 0.5760\n", "Epoch 314/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1728 - distribution_lambda_14_loss: 2.0102 - distribution_lambda_15_loss: 1.5801 - distribution_lambda_16_loss: 0.5825 - val_loss: 4.1037 - val_distribution_lambda_14_loss: 1.9987 - val_distribution_lambda_15_loss: 1.5292 - val_distribution_lambda_16_loss: 0.5758\n", "Epoch 315/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1587 - distribution_lambda_14_loss: 2.0030 - distribution_lambda_15_loss: 1.5738 - distribution_lambda_16_loss: 0.5820 - val_loss: 4.0956 - val_distribution_lambda_14_loss: 1.9920 - val_distribution_lambda_15_loss: 1.5279 - val_distribution_lambda_16_loss: 0.5757\n", "Epoch 316/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1504 - distribution_lambda_14_loss: 1.9962 - distribution_lambda_15_loss: 1.5721 - distribution_lambda_16_loss: 0.5821 - val_loss: 4.0879 - val_distribution_lambda_14_loss: 1.9853 - val_distribution_lambda_15_loss: 1.5270 - val_distribution_lambda_16_loss: 0.5756\n", "Epoch 317/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1418 - distribution_lambda_14_loss: 1.9903 - distribution_lambda_15_loss: 1.5696 - distribution_lambda_16_loss: 0.5819 - val_loss: 4.0795 - val_distribution_lambda_14_loss: 1.9785 - val_distribution_lambda_15_loss: 1.5257 - val_distribution_lambda_16_loss: 0.5754\n", "Epoch 318/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.1373 - distribution_lambda_14_loss: 1.9830 - distribution_lambda_15_loss: 1.5725 - distribution_lambda_16_loss: 0.5818 - val_loss: 4.0739 - val_distribution_lambda_14_loss: 1.9716 - val_distribution_lambda_15_loss: 1.5269 - val_distribution_lambda_16_loss: 0.5755\n", "Epoch 319/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1317 - distribution_lambda_14_loss: 1.9764 - distribution_lambda_15_loss: 1.5726 - distribution_lambda_16_loss: 0.5827 - val_loss: 4.0676 - val_distribution_lambda_14_loss: 1.9649 - val_distribution_lambda_15_loss: 1.5272 - val_distribution_lambda_16_loss: 0.5755\n", "Epoch 320/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1228 - distribution_lambda_14_loss: 1.9696 - distribution_lambda_15_loss: 1.5718 - distribution_lambda_16_loss: 0.5815 - val_loss: 4.0614 - val_distribution_lambda_14_loss: 1.9581 - val_distribution_lambda_15_loss: 1.5275 - val_distribution_lambda_16_loss: 0.5758\n", "Epoch 321/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1183 - distribution_lambda_14_loss: 1.9630 - distribution_lambda_15_loss: 1.5736 - distribution_lambda_16_loss: 0.5817 - val_loss: 4.0573 - val_distribution_lambda_14_loss: 1.9511 - val_distribution_lambda_15_loss: 1.5299 - val_distribution_lambda_16_loss: 0.5763\n", "Epoch 322/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.1093 - distribution_lambda_14_loss: 1.9560 - distribution_lambda_15_loss: 1.5710 - distribution_lambda_16_loss: 0.5823 - val_loss: 4.0499 - val_distribution_lambda_14_loss: 1.9441 - val_distribution_lambda_15_loss: 1.5295 - val_distribution_lambda_16_loss: 0.5763\n", "Epoch 323/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0996 - distribution_lambda_14_loss: 1.9492 - distribution_lambda_15_loss: 1.5688 - distribution_lambda_16_loss: 0.5816 - val_loss: 4.0397 - val_distribution_lambda_14_loss: 1.9370 - val_distribution_lambda_15_loss: 1.5270 - val_distribution_lambda_16_loss: 0.5756\n", "Epoch 324/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0959 - distribution_lambda_14_loss: 1.9420 - distribution_lambda_15_loss: 1.5722 - distribution_lambda_16_loss: 0.5817 - val_loss: 4.0306 - val_distribution_lambda_14_loss: 1.9299 - val_distribution_lambda_15_loss: 1.5257 - val_distribution_lambda_16_loss: 0.5749\n", "Epoch 325/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0885 - distribution_lambda_14_loss: 1.9350 - distribution_lambda_15_loss: 1.5716 - distribution_lambda_16_loss: 0.5818 - val_loss: 4.0233 - val_distribution_lambda_14_loss: 1.9227 - val_distribution_lambda_15_loss: 1.5261 - val_distribution_lambda_16_loss: 0.5745\n", "Epoch 326/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0744 - distribution_lambda_14_loss: 1.9270 - distribution_lambda_15_loss: 1.5670 - distribution_lambda_16_loss: 0.5804 - val_loss: 4.0144 - val_distribution_lambda_14_loss: 1.9154 - val_distribution_lambda_15_loss: 1.5248 - val_distribution_lambda_16_loss: 0.5742\n", "Epoch 327/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0629 - distribution_lambda_14_loss: 1.9202 - distribution_lambda_15_loss: 1.5626 - distribution_lambda_16_loss: 0.5800 - val_loss: 4.0050 - val_distribution_lambda_14_loss: 1.9081 - val_distribution_lambda_15_loss: 1.5229 - val_distribution_lambda_16_loss: 0.5740\n", "Epoch 328/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0537 - distribution_lambda_14_loss: 1.9134 - distribution_lambda_15_loss: 1.5591 - distribution_lambda_16_loss: 0.5813 - val_loss: 3.9963 - val_distribution_lambda_14_loss: 1.9008 - val_distribution_lambda_15_loss: 1.5218 - val_distribution_lambda_16_loss: 0.5738\n", "Epoch 329/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0563 - distribution_lambda_14_loss: 1.9056 - distribution_lambda_15_loss: 1.5708 - distribution_lambda_16_loss: 0.5799 - val_loss: 3.9894 - val_distribution_lambda_14_loss: 1.8933 - val_distribution_lambda_15_loss: 1.5223 - val_distribution_lambda_16_loss: 0.5738\n", "Epoch 330/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0377 - distribution_lambda_14_loss: 1.8985 - distribution_lambda_15_loss: 1.5597 - distribution_lambda_16_loss: 0.5795 - val_loss: 3.9821 - val_distribution_lambda_14_loss: 1.8858 - val_distribution_lambda_15_loss: 1.5226 - val_distribution_lambda_16_loss: 0.5737\n", "Epoch 331/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0316 - distribution_lambda_14_loss: 1.8911 - distribution_lambda_15_loss: 1.5607 - distribution_lambda_16_loss: 0.5798 - val_loss: 3.9726 - val_distribution_lambda_14_loss: 1.8782 - val_distribution_lambda_15_loss: 1.5209 - val_distribution_lambda_16_loss: 0.5735\n", "Epoch 332/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0280 - distribution_lambda_14_loss: 1.8840 - distribution_lambda_15_loss: 1.5646 - distribution_lambda_16_loss: 0.5794 - val_loss: 3.9656 - val_distribution_lambda_14_loss: 1.8706 - val_distribution_lambda_15_loss: 1.5216 - val_distribution_lambda_16_loss: 0.5734\n", "Epoch 333/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.0140 - distribution_lambda_14_loss: 1.8748 - distribution_lambda_15_loss: 1.5597 - distribution_lambda_16_loss: 0.5795 - val_loss: 3.9582 - val_distribution_lambda_14_loss: 1.8629 - val_distribution_lambda_15_loss: 1.5220 - val_distribution_lambda_16_loss: 0.5734\n", "Epoch 334/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0008 - distribution_lambda_14_loss: 1.8683 - distribution_lambda_15_loss: 1.5535 - distribution_lambda_16_loss: 0.5790 - val_loss: 3.9485 - val_distribution_lambda_14_loss: 1.8551 - val_distribution_lambda_15_loss: 1.5203 - val_distribution_lambda_16_loss: 0.5731\n", "Epoch 335/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9938 - distribution_lambda_14_loss: 1.8601 - distribution_lambda_15_loss: 1.5543 - distribution_lambda_16_loss: 0.5794 - val_loss: 3.9389 - val_distribution_lambda_14_loss: 1.8472 - val_distribution_lambda_15_loss: 1.5190 - val_distribution_lambda_16_loss: 0.5727\n", "Epoch 336/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9807 - distribution_lambda_14_loss: 1.8523 - distribution_lambda_15_loss: 1.5496 - distribution_lambda_16_loss: 0.5788 - val_loss: 3.9296 - val_distribution_lambda_14_loss: 1.8393 - val_distribution_lambda_15_loss: 1.5180 - val_distribution_lambda_16_loss: 0.5724\n", "Epoch 337/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 3.9804 - distribution_lambda_14_loss: 1.8451 - distribution_lambda_15_loss: 1.5571 - distribution_lambda_16_loss: 0.5782 - val_loss: 3.9196 - val_distribution_lambda_14_loss: 1.8313 - val_distribution_lambda_15_loss: 1.5162 - val_distribution_lambda_16_loss: 0.5721\n", "Epoch 338/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9687 - distribution_lambda_14_loss: 1.8367 - distribution_lambda_15_loss: 1.5537 - distribution_lambda_16_loss: 0.5784 - val_loss: 3.9105 - val_distribution_lambda_14_loss: 1.8232 - val_distribution_lambda_15_loss: 1.5154 - val_distribution_lambda_16_loss: 0.5719\n", "Epoch 339/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9629 - distribution_lambda_14_loss: 1.8285 - distribution_lambda_15_loss: 1.5555 - distribution_lambda_16_loss: 0.5788 - val_loss: 3.9013 - val_distribution_lambda_14_loss: 1.8150 - val_distribution_lambda_15_loss: 1.5146 - val_distribution_lambda_16_loss: 0.5716\n", "Epoch 340/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.9567 - distribution_lambda_14_loss: 1.8208 - distribution_lambda_15_loss: 1.5581 - distribution_lambda_16_loss: 0.5778 - val_loss: 3.8936 - val_distribution_lambda_14_loss: 1.8068 - val_distribution_lambda_15_loss: 1.5153 - val_distribution_lambda_16_loss: 0.5715\n", "Epoch 341/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.9462 - distribution_lambda_14_loss: 1.8133 - distribution_lambda_15_loss: 1.5551 - distribution_lambda_16_loss: 0.5778 - val_loss: 3.8847 - val_distribution_lambda_14_loss: 1.7984 - val_distribution_lambda_15_loss: 1.5149 - val_distribution_lambda_16_loss: 0.5713\n", "Epoch 342/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9275 - distribution_lambda_14_loss: 1.8045 - distribution_lambda_15_loss: 1.5458 - distribution_lambda_16_loss: 0.5772 - val_loss: 3.8751 - val_distribution_lambda_14_loss: 1.7900 - val_distribution_lambda_15_loss: 1.5141 - val_distribution_lambda_16_loss: 0.5711\n", "Epoch 343/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9189 - distribution_lambda_14_loss: 1.7967 - distribution_lambda_15_loss: 1.5456 - distribution_lambda_16_loss: 0.5766 - val_loss: 3.8664 - val_distribution_lambda_14_loss: 1.7815 - val_distribution_lambda_15_loss: 1.5140 - val_distribution_lambda_16_loss: 0.5708\n", "Epoch 344/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9232 - distribution_lambda_14_loss: 1.7879 - distribution_lambda_15_loss: 1.5576 - distribution_lambda_16_loss: 0.5777 - val_loss: 3.8577 - val_distribution_lambda_14_loss: 1.7729 - val_distribution_lambda_15_loss: 1.5141 - val_distribution_lambda_16_loss: 0.5707\n", "Epoch 345/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9160 - distribution_lambda_14_loss: 1.7793 - distribution_lambda_15_loss: 1.5592 - distribution_lambda_16_loss: 0.5775 - val_loss: 3.8489 - val_distribution_lambda_14_loss: 1.7642 - val_distribution_lambda_15_loss: 1.5142 - val_distribution_lambda_16_loss: 0.5706\n", "Epoch 346/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8973 - distribution_lambda_14_loss: 1.7713 - distribution_lambda_15_loss: 1.5489 - distribution_lambda_16_loss: 0.5771 - val_loss: 3.8404 - val_distribution_lambda_14_loss: 1.7553 - val_distribution_lambda_15_loss: 1.5146 - val_distribution_lambda_16_loss: 0.5705\n", "Epoch 347/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.8824 - distribution_lambda_14_loss: 1.7623 - distribution_lambda_15_loss: 1.5440 - distribution_lambda_16_loss: 0.5761 - val_loss: 3.8312 - val_distribution_lambda_14_loss: 1.7464 - val_distribution_lambda_15_loss: 1.5146 - val_distribution_lambda_16_loss: 0.5702\n", "Epoch 348/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.8743 - distribution_lambda_14_loss: 1.7536 - distribution_lambda_15_loss: 1.5443 - distribution_lambda_16_loss: 0.5764 - val_loss: 3.8233 - val_distribution_lambda_14_loss: 1.7375 - val_distribution_lambda_15_loss: 1.5157 - val_distribution_lambda_16_loss: 0.5701\n", "Epoch 349/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8703 - distribution_lambda_14_loss: 1.7441 - distribution_lambda_15_loss: 1.5499 - distribution_lambda_16_loss: 0.5762 - val_loss: 3.8146 - val_distribution_lambda_14_loss: 1.7284 - val_distribution_lambda_15_loss: 1.5163 - val_distribution_lambda_16_loss: 0.5699\n", "Epoch 350/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8610 - distribution_lambda_14_loss: 1.7348 - distribution_lambda_15_loss: 1.5503 - distribution_lambda_16_loss: 0.5759 - val_loss: 3.8038 - val_distribution_lambda_14_loss: 1.7191 - val_distribution_lambda_15_loss: 1.5147 - val_distribution_lambda_16_loss: 0.5699\n", "Epoch 351/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8507 - distribution_lambda_14_loss: 1.7271 - distribution_lambda_15_loss: 1.5473 - distribution_lambda_16_loss: 0.5764 - val_loss: 3.7948 - val_distribution_lambda_14_loss: 1.7098 - val_distribution_lambda_15_loss: 1.5149 - val_distribution_lambda_16_loss: 0.5701\n", "Epoch 352/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8413 - distribution_lambda_14_loss: 1.7171 - distribution_lambda_15_loss: 1.5479 - distribution_lambda_16_loss: 0.5763 - val_loss: 3.7859 - val_distribution_lambda_14_loss: 1.7002 - val_distribution_lambda_15_loss: 1.5154 - val_distribution_lambda_16_loss: 0.5703\n", "Epoch 353/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8292 - distribution_lambda_14_loss: 1.7086 - distribution_lambda_15_loss: 1.5455 - distribution_lambda_16_loss: 0.5751 - val_loss: 3.7764 - val_distribution_lambda_14_loss: 1.6907 - val_distribution_lambda_15_loss: 1.5154 - val_distribution_lambda_16_loss: 0.5703\n", "Epoch 354/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8271 - distribution_lambda_14_loss: 1.6994 - distribution_lambda_15_loss: 1.5515 - distribution_lambda_16_loss: 0.5761 - val_loss: 3.7694 - val_distribution_lambda_14_loss: 1.6824 - val_distribution_lambda_15_loss: 1.5169 - val_distribution_lambda_16_loss: 0.5701\n", "Epoch 355/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8169 - distribution_lambda_14_loss: 1.6899 - distribution_lambda_15_loss: 1.5504 - distribution_lambda_16_loss: 0.5766 - val_loss: 3.7608 - val_distribution_lambda_14_loss: 1.6735 - val_distribution_lambda_15_loss: 1.5175 - val_distribution_lambda_16_loss: 0.5697\n", "Epoch 356/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.8048 - distribution_lambda_14_loss: 1.6818 - distribution_lambda_15_loss: 1.5478 - distribution_lambda_16_loss: 0.5752 - val_loss: 3.7505 - val_distribution_lambda_14_loss: 1.6639 - val_distribution_lambda_15_loss: 1.5172 - val_distribution_lambda_16_loss: 0.5693\n", "Epoch 357/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.7865 - distribution_lambda_14_loss: 1.6731 - distribution_lambda_15_loss: 1.5390 - distribution_lambda_16_loss: 0.5744 - val_loss: 3.7382 - val_distribution_lambda_14_loss: 1.6540 - val_distribution_lambda_15_loss: 1.5152 - val_distribution_lambda_16_loss: 0.5690\n", "Epoch 358/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7888 - distribution_lambda_14_loss: 1.6632 - distribution_lambda_15_loss: 1.5501 - distribution_lambda_16_loss: 0.5755 - val_loss: 3.7257 - val_distribution_lambda_14_loss: 1.6438 - val_distribution_lambda_15_loss: 1.5134 - val_distribution_lambda_16_loss: 0.5685\n", "Epoch 359/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.7822 - distribution_lambda_14_loss: 1.6545 - distribution_lambda_15_loss: 1.5529 - distribution_lambda_16_loss: 0.5748 - val_loss: 3.7133 - val_distribution_lambda_14_loss: 1.6335 - val_distribution_lambda_15_loss: 1.5117 - val_distribution_lambda_16_loss: 0.5681\n", "Epoch 360/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7685 - distribution_lambda_14_loss: 1.6441 - distribution_lambda_15_loss: 1.5499 - distribution_lambda_16_loss: 0.5745 - val_loss: 3.7015 - val_distribution_lambda_14_loss: 1.6230 - val_distribution_lambda_15_loss: 1.5107 - val_distribution_lambda_16_loss: 0.5679\n", "Epoch 361/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 3.7517 - distribution_lambda_14_loss: 1.6328 - distribution_lambda_15_loss: 1.5448 - distribution_lambda_16_loss: 0.5742 - val_loss: 3.6901 - val_distribution_lambda_14_loss: 1.6124 - val_distribution_lambda_15_loss: 1.5100 - val_distribution_lambda_16_loss: 0.5677\n", "Epoch 362/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7334 - distribution_lambda_14_loss: 1.6227 - distribution_lambda_15_loss: 1.5372 - distribution_lambda_16_loss: 0.5735 - val_loss: 3.6798 - val_distribution_lambda_14_loss: 1.6016 - val_distribution_lambda_15_loss: 1.5104 - val_distribution_lambda_16_loss: 0.5678\n", "Epoch 363/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7251 - distribution_lambda_14_loss: 1.6121 - distribution_lambda_15_loss: 1.5394 - distribution_lambda_16_loss: 0.5737 - val_loss: 3.6692 - val_distribution_lambda_14_loss: 1.5907 - val_distribution_lambda_15_loss: 1.5111 - val_distribution_lambda_16_loss: 0.5675\n", "Epoch 364/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7200 - distribution_lambda_14_loss: 1.6020 - distribution_lambda_15_loss: 1.5449 - distribution_lambda_16_loss: 0.5731 - val_loss: 3.6605 - val_distribution_lambda_14_loss: 1.5801 - val_distribution_lambda_15_loss: 1.5130 - val_distribution_lambda_16_loss: 0.5674\n", "Epoch 365/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.7054 - distribution_lambda_14_loss: 1.5897 - distribution_lambda_15_loss: 1.5425 - distribution_lambda_16_loss: 0.5731 - val_loss: 3.6496 - val_distribution_lambda_14_loss: 1.5691 - val_distribution_lambda_15_loss: 1.5134 - val_distribution_lambda_16_loss: 0.5671\n", "Epoch 366/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.6984 - distribution_lambda_14_loss: 1.5812 - distribution_lambda_15_loss: 1.5450 - distribution_lambda_16_loss: 0.5723 - val_loss: 3.6381 - val_distribution_lambda_14_loss: 1.5579 - val_distribution_lambda_15_loss: 1.5132 - val_distribution_lambda_16_loss: 0.5669\n", "Epoch 367/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6906 - distribution_lambda_14_loss: 1.5704 - distribution_lambda_15_loss: 1.5473 - distribution_lambda_16_loss: 0.5730 - val_loss: 3.6250 - val_distribution_lambda_14_loss: 1.5465 - val_distribution_lambda_15_loss: 1.5121 - val_distribution_lambda_16_loss: 0.5663\n", "Epoch 368/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6776 - distribution_lambda_14_loss: 1.5580 - distribution_lambda_15_loss: 1.5465 - distribution_lambda_16_loss: 0.5731 - val_loss: 3.6116 - val_distribution_lambda_14_loss: 1.5350 - val_distribution_lambda_15_loss: 1.5107 - val_distribution_lambda_16_loss: 0.5659\n", "Epoch 369/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6600 - distribution_lambda_14_loss: 1.5471 - distribution_lambda_15_loss: 1.5410 - distribution_lambda_16_loss: 0.5720 - val_loss: 3.5982 - val_distribution_lambda_14_loss: 1.5234 - val_distribution_lambda_15_loss: 1.5093 - val_distribution_lambda_16_loss: 0.5655\n", "Epoch 370/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.6465 - distribution_lambda_14_loss: 1.5357 - distribution_lambda_15_loss: 1.5395 - distribution_lambda_16_loss: 0.5713 - val_loss: 3.5847 - val_distribution_lambda_14_loss: 1.5115 - val_distribution_lambda_15_loss: 1.5081 - val_distribution_lambda_16_loss: 0.5651\n", "Epoch 371/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6494 - distribution_lambda_14_loss: 1.5249 - distribution_lambda_15_loss: 1.5525 - distribution_lambda_16_loss: 0.5720 - val_loss: 3.5707 - val_distribution_lambda_14_loss: 1.4996 - val_distribution_lambda_15_loss: 1.5065 - val_distribution_lambda_16_loss: 0.5646\n", "Epoch 372/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.6197 - distribution_lambda_14_loss: 1.5137 - distribution_lambda_15_loss: 1.5355 - distribution_lambda_16_loss: 0.5705 - val_loss: 3.5614 - val_distribution_lambda_14_loss: 1.4875 - val_distribution_lambda_15_loss: 1.5093 - val_distribution_lambda_16_loss: 0.5646\n", "Epoch 373/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.6130 - distribution_lambda_14_loss: 1.5051 - distribution_lambda_15_loss: 1.5374 - distribution_lambda_16_loss: 0.5704 - val_loss: 3.5515 - val_distribution_lambda_14_loss: 1.4754 - val_distribution_lambda_15_loss: 1.5114 - val_distribution_lambda_16_loss: 0.5646\n", "Epoch 374/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.5935 - distribution_lambda_14_loss: 1.4920 - distribution_lambda_15_loss: 1.5324 - distribution_lambda_16_loss: 0.5692 - val_loss: 3.5372 - val_distribution_lambda_14_loss: 1.4630 - val_distribution_lambda_15_loss: 1.5097 - val_distribution_lambda_16_loss: 0.5645\n", "Epoch 375/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.5921 - distribution_lambda_14_loss: 1.4816 - distribution_lambda_15_loss: 1.5400 - distribution_lambda_16_loss: 0.5705 - val_loss: 3.5236 - val_distribution_lambda_14_loss: 1.4505 - val_distribution_lambda_15_loss: 1.5086 - val_distribution_lambda_16_loss: 0.5645\n", "Epoch 376/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5685 - distribution_lambda_14_loss: 1.4653 - distribution_lambda_15_loss: 1.5338 - distribution_lambda_16_loss: 0.5694 - val_loss: 3.5092 - val_distribution_lambda_14_loss: 1.4377 - val_distribution_lambda_15_loss: 1.5074 - val_distribution_lambda_16_loss: 0.5641\n", "Epoch 377/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5651 - distribution_lambda_14_loss: 1.4532 - distribution_lambda_15_loss: 1.5413 - distribution_lambda_16_loss: 0.5706 - val_loss: 3.4959 - val_distribution_lambda_14_loss: 1.4249 - val_distribution_lambda_15_loss: 1.5075 - val_distribution_lambda_16_loss: 0.5636\n", "Epoch 378/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5592 - distribution_lambda_14_loss: 1.4444 - distribution_lambda_15_loss: 1.5444 - distribution_lambda_16_loss: 0.5705 - val_loss: 3.4829 - val_distribution_lambda_14_loss: 1.4121 - val_distribution_lambda_15_loss: 1.5078 - val_distribution_lambda_16_loss: 0.5630\n", "Epoch 379/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.5271 - distribution_lambda_14_loss: 1.4284 - distribution_lambda_15_loss: 1.5304 - distribution_lambda_16_loss: 0.5683 - val_loss: 3.4685 - val_distribution_lambda_14_loss: 1.3990 - val_distribution_lambda_15_loss: 1.5073 - val_distribution_lambda_16_loss: 0.5622\n", "Epoch 380/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.5238 - distribution_lambda_14_loss: 1.4151 - distribution_lambda_15_loss: 1.5392 - distribution_lambda_16_loss: 0.5695 - val_loss: 3.4532 - val_distribution_lambda_14_loss: 1.3858 - val_distribution_lambda_15_loss: 1.5059 - val_distribution_lambda_16_loss: 0.5615\n", "Epoch 381/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4936 - distribution_lambda_14_loss: 1.4033 - distribution_lambda_15_loss: 1.5228 - distribution_lambda_16_loss: 0.5675 - val_loss: 3.4385 - val_distribution_lambda_14_loss: 1.3726 - val_distribution_lambda_15_loss: 1.5049 - val_distribution_lambda_16_loss: 0.5610\n", "Epoch 382/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.4925 - distribution_lambda_14_loss: 1.3959 - distribution_lambda_15_loss: 1.5302 - distribution_lambda_16_loss: 0.5665 - val_loss: 3.4243 - val_distribution_lambda_14_loss: 1.3596 - val_distribution_lambda_15_loss: 1.5038 - val_distribution_lambda_16_loss: 0.5609\n", "Epoch 383/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4836 - distribution_lambda_14_loss: 1.3834 - distribution_lambda_15_loss: 1.5337 - distribution_lambda_16_loss: 0.5666 - val_loss: 3.4127 - val_distribution_lambda_14_loss: 1.3464 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5608\n", "Epoch 384/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4739 - distribution_lambda_14_loss: 1.3677 - distribution_lambda_15_loss: 1.5382 - distribution_lambda_16_loss: 0.5679 - val_loss: 3.3991 - val_distribution_lambda_14_loss: 1.3326 - val_distribution_lambda_15_loss: 1.5059 - val_distribution_lambda_16_loss: 0.5606\n", "Epoch 385/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 11ms/step - loss: 3.4604 - distribution_lambda_14_loss: 1.3543 - distribution_lambda_15_loss: 1.5391 - distribution_lambda_16_loss: 0.5670 - val_loss: 3.3855 - val_distribution_lambda_14_loss: 1.3191 - val_distribution_lambda_15_loss: 1.5061 - val_distribution_lambda_16_loss: 0.5603\n", "Epoch 386/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.4368 - distribution_lambda_14_loss: 1.3417 - distribution_lambda_15_loss: 1.5288 - distribution_lambda_16_loss: 0.5663 - val_loss: 3.3709 - val_distribution_lambda_14_loss: 1.3055 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5599\n", "Epoch 387/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.4371 - distribution_lambda_14_loss: 1.3325 - distribution_lambda_15_loss: 1.5366 - distribution_lambda_16_loss: 0.5680 - val_loss: 3.3585 - val_distribution_lambda_14_loss: 1.2920 - val_distribution_lambda_15_loss: 1.5067 - val_distribution_lambda_16_loss: 0.5598\n", "Epoch 388/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.4288 - distribution_lambda_14_loss: 1.3232 - distribution_lambda_15_loss: 1.5392 - distribution_lambda_16_loss: 0.5664 - val_loss: 3.3454 - val_distribution_lambda_14_loss: 1.2785 - val_distribution_lambda_15_loss: 1.5073 - val_distribution_lambda_16_loss: 0.5596\n", "Epoch 389/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.3977 - distribution_lambda_14_loss: 1.3031 - distribution_lambda_15_loss: 1.5285 - distribution_lambda_16_loss: 0.5661 - val_loss: 3.3342 - val_distribution_lambda_14_loss: 1.2647 - val_distribution_lambda_15_loss: 1.5101 - val_distribution_lambda_16_loss: 0.5593\n", "Epoch 390/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.4023 - distribution_lambda_14_loss: 1.2904 - distribution_lambda_15_loss: 1.5451 - distribution_lambda_16_loss: 0.5669 - val_loss: 3.3216 - val_distribution_lambda_14_loss: 1.2509 - val_distribution_lambda_15_loss: 1.5116 - val_distribution_lambda_16_loss: 0.5591\n", "Epoch 391/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3752 - distribution_lambda_14_loss: 1.2832 - distribution_lambda_15_loss: 1.5275 - distribution_lambda_16_loss: 0.5645 - val_loss: 3.3071 - val_distribution_lambda_14_loss: 1.2373 - val_distribution_lambda_15_loss: 1.5109 - val_distribution_lambda_16_loss: 0.5589\n", "Epoch 392/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.3725 - distribution_lambda_14_loss: 1.2681 - distribution_lambda_15_loss: 1.5388 - distribution_lambda_16_loss: 0.5656 - val_loss: 3.2917 - val_distribution_lambda_14_loss: 1.2237 - val_distribution_lambda_15_loss: 1.5096 - val_distribution_lambda_16_loss: 0.5585\n", "Epoch 393/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3516 - distribution_lambda_14_loss: 1.2574 - distribution_lambda_15_loss: 1.5297 - distribution_lambda_16_loss: 0.5645 - val_loss: 3.2758 - val_distribution_lambda_14_loss: 1.2100 - val_distribution_lambda_15_loss: 1.5078 - val_distribution_lambda_16_loss: 0.5579\n", "Epoch 394/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.3375 - distribution_lambda_14_loss: 1.2421 - distribution_lambda_15_loss: 1.5313 - distribution_lambda_16_loss: 0.5641 - val_loss: 3.2602 - val_distribution_lambda_14_loss: 1.1966 - val_distribution_lambda_15_loss: 1.5060 - val_distribution_lambda_16_loss: 0.5576\n", "Epoch 395/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.3183 - distribution_lambda_14_loss: 1.2300 - distribution_lambda_15_loss: 1.5246 - distribution_lambda_16_loss: 0.5637 - val_loss: 3.2454 - val_distribution_lambda_14_loss: 1.1832 - val_distribution_lambda_15_loss: 1.5049 - val_distribution_lambda_16_loss: 0.5573\n", "Epoch 396/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3059 - distribution_lambda_14_loss: 1.2196 - distribution_lambda_15_loss: 1.5229 - distribution_lambda_16_loss: 0.5634 - val_loss: 3.2311 - val_distribution_lambda_14_loss: 1.1699 - val_distribution_lambda_15_loss: 1.5041 - val_distribution_lambda_16_loss: 0.5570\n", "Epoch 397/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3000 - distribution_lambda_14_loss: 1.2053 - distribution_lambda_15_loss: 1.5313 - distribution_lambda_16_loss: 0.5634 - val_loss: 3.2179 - val_distribution_lambda_14_loss: 1.1564 - val_distribution_lambda_15_loss: 1.5046 - val_distribution_lambda_16_loss: 0.5569\n", "Epoch 398/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.2760 - distribution_lambda_14_loss: 1.1924 - distribution_lambda_15_loss: 1.5204 - distribution_lambda_16_loss: 0.5632 - val_loss: 3.2060 - val_distribution_lambda_14_loss: 1.1429 - val_distribution_lambda_15_loss: 1.5065 - val_distribution_lambda_16_loss: 0.5566\n", "Epoch 399/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2792 - distribution_lambda_14_loss: 1.1854 - distribution_lambda_15_loss: 1.5306 - distribution_lambda_16_loss: 0.5631 - val_loss: 3.1942 - val_distribution_lambda_14_loss: 1.1299 - val_distribution_lambda_15_loss: 1.5083 - val_distribution_lambda_16_loss: 0.5561\n", "Epoch 400/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2526 - distribution_lambda_14_loss: 1.1586 - distribution_lambda_15_loss: 1.5310 - distribution_lambda_16_loss: 0.5630 - val_loss: 3.1803 - val_distribution_lambda_14_loss: 1.1166 - val_distribution_lambda_15_loss: 1.5079 - val_distribution_lambda_16_loss: 0.5558\n", "Epoch 401/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2617 - distribution_lambda_14_loss: 1.1648 - distribution_lambda_15_loss: 1.5347 - distribution_lambda_16_loss: 0.5622 - val_loss: 3.1646 - val_distribution_lambda_14_loss: 1.1037 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5553\n", "Epoch 402/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.2417 - distribution_lambda_14_loss: 1.1453 - distribution_lambda_15_loss: 1.5345 - distribution_lambda_16_loss: 0.5619 - val_loss: 3.1485 - val_distribution_lambda_14_loss: 1.0910 - val_distribution_lambda_15_loss: 1.5026 - val_distribution_lambda_16_loss: 0.5549\n", "Epoch 403/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 3.2348 - distribution_lambda_14_loss: 1.1384 - distribution_lambda_15_loss: 1.5336 - distribution_lambda_16_loss: 0.5628 - val_loss: 3.1373 - val_distribution_lambda_14_loss: 1.0797 - val_distribution_lambda_15_loss: 1.5031 - val_distribution_lambda_16_loss: 0.5546\n", "Epoch 404/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.2156 - distribution_lambda_14_loss: 1.1210 - distribution_lambda_15_loss: 1.5324 - distribution_lambda_16_loss: 0.5622 - val_loss: 3.1262 - val_distribution_lambda_14_loss: 1.0679 - val_distribution_lambda_15_loss: 1.5040 - val_distribution_lambda_16_loss: 0.5543\n", "Epoch 405/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1953 - distribution_lambda_14_loss: 1.1098 - distribution_lambda_15_loss: 1.5239 - distribution_lambda_16_loss: 0.5616 - val_loss: 3.1150 - val_distribution_lambda_14_loss: 1.0556 - val_distribution_lambda_15_loss: 1.5053 - val_distribution_lambda_16_loss: 0.5541\n", "Epoch 406/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2038 - distribution_lambda_14_loss: 1.1067 - distribution_lambda_15_loss: 1.5348 - distribution_lambda_16_loss: 0.5623 - val_loss: 3.1034 - val_distribution_lambda_14_loss: 1.0433 - val_distribution_lambda_15_loss: 1.5061 - val_distribution_lambda_16_loss: 0.5540\n", "Epoch 407/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1738 - distribution_lambda_14_loss: 1.0883 - distribution_lambda_15_loss: 1.5238 - distribution_lambda_16_loss: 0.5618 - val_loss: 3.0908 - val_distribution_lambda_14_loss: 1.0307 - val_distribution_lambda_15_loss: 1.5064 - val_distribution_lambda_16_loss: 0.5536\n", "Epoch 408/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1649 - distribution_lambda_14_loss: 1.0747 - distribution_lambda_15_loss: 1.5293 - distribution_lambda_16_loss: 0.5609 - val_loss: 3.0775 - val_distribution_lambda_14_loss: 1.0186 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5534\n", "Epoch 409/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.1347 - distribution_lambda_14_loss: 1.0531 - distribution_lambda_15_loss: 1.5218 - distribution_lambda_16_loss: 0.5597 - val_loss: 3.0642 - val_distribution_lambda_14_loss: 1.0061 - val_distribution_lambda_15_loss: 1.5048 - val_distribution_lambda_16_loss: 0.5533\n", "Epoch 410/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1600 - distribution_lambda_14_loss: 1.0656 - distribution_lambda_15_loss: 1.5326 - distribution_lambda_16_loss: 0.5618 - val_loss: 3.0517 - val_distribution_lambda_14_loss: 0.9943 - val_distribution_lambda_15_loss: 1.5042 - val_distribution_lambda_16_loss: 0.5531\n", "Epoch 411/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1432 - distribution_lambda_14_loss: 1.0413 - distribution_lambda_15_loss: 1.5410 - distribution_lambda_16_loss: 0.5609 - val_loss: 3.0419 - val_distribution_lambda_14_loss: 0.9836 - val_distribution_lambda_15_loss: 1.5052 - val_distribution_lambda_16_loss: 0.5531\n", "Epoch 412/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1230 - distribution_lambda_14_loss: 1.0358 - distribution_lambda_15_loss: 1.5267 - distribution_lambda_16_loss: 0.5605 - val_loss: 3.0348 - val_distribution_lambda_14_loss: 0.9726 - val_distribution_lambda_15_loss: 1.5091 - val_distribution_lambda_16_loss: 0.5531\n", "Epoch 413/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.1249 - distribution_lambda_14_loss: 1.0337 - distribution_lambda_15_loss: 1.5305 - distribution_lambda_16_loss: 0.5606 - val_loss: 3.0239 - val_distribution_lambda_14_loss: 0.9627 - val_distribution_lambda_15_loss: 1.5085 - val_distribution_lambda_16_loss: 0.5527\n", "Epoch 414/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1224 - distribution_lambda_14_loss: 1.0245 - distribution_lambda_15_loss: 1.5352 - distribution_lambda_16_loss: 0.5627 - val_loss: 3.0112 - val_distribution_lambda_14_loss: 0.9526 - val_distribution_lambda_15_loss: 1.5063 - val_distribution_lambda_16_loss: 0.5523\n", "Epoch 415/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.1075 - distribution_lambda_14_loss: 1.0161 - distribution_lambda_15_loss: 1.5316 - distribution_lambda_16_loss: 0.5598 - val_loss: 3.0010 - val_distribution_lambda_14_loss: 0.9428 - val_distribution_lambda_15_loss: 1.5062 - val_distribution_lambda_16_loss: 0.5521\n", "Epoch 416/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0699 - distribution_lambda_14_loss: 0.9939 - distribution_lambda_15_loss: 1.5169 - distribution_lambda_16_loss: 0.5591 - val_loss: 2.9938 - val_distribution_lambda_14_loss: 0.9363 - val_distribution_lambda_15_loss: 1.5059 - val_distribution_lambda_16_loss: 0.5517\n", "Epoch 417/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0979 - distribution_lambda_14_loss: 0.9984 - distribution_lambda_15_loss: 1.5396 - distribution_lambda_16_loss: 0.5599 - val_loss: 2.9865 - val_distribution_lambda_14_loss: 0.9293 - val_distribution_lambda_15_loss: 1.5060 - val_distribution_lambda_16_loss: 0.5512\n", "Epoch 418/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0817 - distribution_lambda_14_loss: 0.9851 - distribution_lambda_15_loss: 1.5363 - distribution_lambda_16_loss: 0.5602 - val_loss: 2.9825 - val_distribution_lambda_14_loss: 0.9231 - val_distribution_lambda_15_loss: 1.5081 - val_distribution_lambda_16_loss: 0.5513\n", "Epoch 419/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0808 - distribution_lambda_14_loss: 0.9878 - distribution_lambda_15_loss: 1.5340 - distribution_lambda_16_loss: 0.5589 - val_loss: 2.9770 - val_distribution_lambda_14_loss: 0.9157 - val_distribution_lambda_15_loss: 1.5098 - val_distribution_lambda_16_loss: 0.5515\n", "Epoch 420/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0494 - distribution_lambda_14_loss: 0.9651 - distribution_lambda_15_loss: 1.5251 - distribution_lambda_16_loss: 0.5592 - val_loss: 2.9666 - val_distribution_lambda_14_loss: 0.9057 - val_distribution_lambda_15_loss: 1.5097 - val_distribution_lambda_16_loss: 0.5512\n", "Epoch 421/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0369 - distribution_lambda_14_loss: 0.9524 - distribution_lambda_15_loss: 1.5259 - distribution_lambda_16_loss: 0.5586 - val_loss: 2.9554 - val_distribution_lambda_14_loss: 0.8964 - val_distribution_lambda_15_loss: 1.5083 - val_distribution_lambda_16_loss: 0.5507\n", "Epoch 422/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0180 - distribution_lambda_14_loss: 0.9362 - distribution_lambda_15_loss: 1.5248 - distribution_lambda_16_loss: 0.5570 - val_loss: 2.9450 - val_distribution_lambda_14_loss: 0.8878 - val_distribution_lambda_15_loss: 1.5069 - val_distribution_lambda_16_loss: 0.5502\n", "Epoch 423/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0246 - distribution_lambda_14_loss: 0.9370 - distribution_lambda_15_loss: 1.5310 - distribution_lambda_16_loss: 0.5566 - val_loss: 2.9365 - val_distribution_lambda_14_loss: 0.8804 - val_distribution_lambda_15_loss: 1.5062 - val_distribution_lambda_16_loss: 0.5499\n", "Epoch 424/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9997 - distribution_lambda_14_loss: 0.9234 - distribution_lambda_15_loss: 1.5199 - distribution_lambda_16_loss: 0.5564 - val_loss: 2.9298 - val_distribution_lambda_14_loss: 0.8730 - val_distribution_lambda_15_loss: 1.5071 - val_distribution_lambda_16_loss: 0.5497\n", "Epoch 425/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9979 - distribution_lambda_14_loss: 0.9225 - distribution_lambda_15_loss: 1.5193 - distribution_lambda_16_loss: 0.5561 - val_loss: 2.9202 - val_distribution_lambda_14_loss: 0.8657 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5489\n", "Epoch 426/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0000 - distribution_lambda_14_loss: 0.9161 - distribution_lambda_15_loss: 1.5260 - distribution_lambda_16_loss: 0.5579 - val_loss: 2.9118 - val_distribution_lambda_14_loss: 0.8573 - val_distribution_lambda_15_loss: 1.5062 - val_distribution_lambda_16_loss: 0.5483\n", "Epoch 427/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0024 - distribution_lambda_14_loss: 0.9094 - distribution_lambda_15_loss: 1.5369 - distribution_lambda_16_loss: 0.5561 - val_loss: 2.9063 - val_distribution_lambda_14_loss: 0.8517 - val_distribution_lambda_15_loss: 1.5067 - val_distribution_lambda_16_loss: 0.5478\n", "Epoch 428/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9852 - distribution_lambda_14_loss: 0.8988 - distribution_lambda_15_loss: 1.5299 - distribution_lambda_16_loss: 0.5565 - val_loss: 2.9038 - val_distribution_lambda_14_loss: 0.8477 - val_distribution_lambda_15_loss: 1.5085 - val_distribution_lambda_16_loss: 0.5476\n", "Epoch 429/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9807 - distribution_lambda_14_loss: 0.8933 - distribution_lambda_15_loss: 1.5323 - distribution_lambda_16_loss: 0.5550 - val_loss: 2.8970 - val_distribution_lambda_14_loss: 0.8411 - val_distribution_lambda_15_loss: 1.5084 - val_distribution_lambda_16_loss: 0.5475\n", "Epoch 430/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9677 - distribution_lambda_14_loss: 0.8838 - distribution_lambda_15_loss: 1.5287 - distribution_lambda_16_loss: 0.5552 - val_loss: 2.8899 - val_distribution_lambda_14_loss: 0.8344 - val_distribution_lambda_15_loss: 1.5083 - val_distribution_lambda_16_loss: 0.5472\n", "Epoch 431/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.9556 - distribution_lambda_14_loss: 0.8747 - distribution_lambda_15_loss: 1.5265 - distribution_lambda_16_loss: 0.5544 - val_loss: 2.8808 - val_distribution_lambda_14_loss: 0.8287 - val_distribution_lambda_15_loss: 1.5053 - val_distribution_lambda_16_loss: 0.5468\n", "Epoch 432/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9424 - distribution_lambda_14_loss: 0.8633 - distribution_lambda_15_loss: 1.5244 - distribution_lambda_16_loss: 0.5548 - val_loss: 2.8771 - val_distribution_lambda_14_loss: 0.8250 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5466\n", "Epoch 433/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.9672 - distribution_lambda_14_loss: 0.8782 - distribution_lambda_15_loss: 1.5337 - distribution_lambda_16_loss: 0.5552 - val_loss: 2.8735 - val_distribution_lambda_14_loss: 0.8210 - val_distribution_lambda_15_loss: 1.5061 - val_distribution_lambda_16_loss: 0.5464\n", "Epoch 434/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9333 - distribution_lambda_14_loss: 0.8650 - distribution_lambda_15_loss: 1.5171 - distribution_lambda_16_loss: 0.5512 - val_loss: 2.8675 - val_distribution_lambda_14_loss: 0.8160 - val_distribution_lambda_15_loss: 1.5057 - val_distribution_lambda_16_loss: 0.5459\n", "Epoch 435/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.9583 - distribution_lambda_14_loss: 0.8740 - distribution_lambda_15_loss: 1.5301 - distribution_lambda_16_loss: 0.5541 - val_loss: 2.8631 - val_distribution_lambda_14_loss: 0.8091 - val_distribution_lambda_15_loss: 1.5084 - val_distribution_lambda_16_loss: 0.5456\n", "Epoch 436/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9436 - distribution_lambda_14_loss: 0.8650 - distribution_lambda_15_loss: 1.5249 - distribution_lambda_16_loss: 0.5537 - val_loss: 2.8660 - val_distribution_lambda_14_loss: 0.8062 - val_distribution_lambda_15_loss: 1.5142 - val_distribution_lambda_16_loss: 0.5456\n", "Epoch 437/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.9232 - distribution_lambda_14_loss: 0.8413 - distribution_lambda_15_loss: 1.5285 - distribution_lambda_16_loss: 0.5534 - val_loss: 2.8628 - val_distribution_lambda_14_loss: 0.8023 - val_distribution_lambda_15_loss: 1.5153 - val_distribution_lambda_16_loss: 0.5452\n", "Epoch 438/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9384 - distribution_lambda_14_loss: 0.8536 - distribution_lambda_15_loss: 1.5316 - distribution_lambda_16_loss: 0.5532 - val_loss: 2.8566 - val_distribution_lambda_14_loss: 0.7984 - val_distribution_lambda_15_loss: 1.5137 - val_distribution_lambda_16_loss: 0.5445\n", "Epoch 439/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.9015 - distribution_lambda_14_loss: 0.8292 - distribution_lambda_15_loss: 1.5199 - distribution_lambda_16_loss: 0.5525 - val_loss: 2.8509 - val_distribution_lambda_14_loss: 0.7945 - val_distribution_lambda_15_loss: 1.5125 - val_distribution_lambda_16_loss: 0.5440\n", "Epoch 440/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9154 - distribution_lambda_14_loss: 0.8392 - distribution_lambda_15_loss: 1.5251 - distribution_lambda_16_loss: 0.5510 - val_loss: 2.8436 - val_distribution_lambda_14_loss: 0.7912 - val_distribution_lambda_15_loss: 1.5092 - val_distribution_lambda_16_loss: 0.5433\n", "Epoch 441/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.9070 - distribution_lambda_14_loss: 0.8299 - distribution_lambda_15_loss: 1.5272 - distribution_lambda_16_loss: 0.5499 - val_loss: 2.8356 - val_distribution_lambda_14_loss: 0.7876 - val_distribution_lambda_15_loss: 1.5051 - val_distribution_lambda_16_loss: 0.5429\n", "Epoch 442/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9004 - distribution_lambda_14_loss: 0.8298 - distribution_lambda_15_loss: 1.5198 - distribution_lambda_16_loss: 0.5509 - val_loss: 2.8313 - val_distribution_lambda_14_loss: 0.7843 - val_distribution_lambda_15_loss: 1.5043 - val_distribution_lambda_16_loss: 0.5427\n", "Epoch 443/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9034 - distribution_lambda_14_loss: 0.8331 - distribution_lambda_15_loss: 1.5211 - distribution_lambda_16_loss: 0.5492 - val_loss: 2.8371 - val_distribution_lambda_14_loss: 0.7877 - val_distribution_lambda_15_loss: 1.5068 - val_distribution_lambda_16_loss: 0.5426\n", "Epoch 444/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8940 - distribution_lambda_14_loss: 0.8344 - distribution_lambda_15_loss: 1.5105 - distribution_lambda_16_loss: 0.5491 - val_loss: 2.8365 - val_distribution_lambda_14_loss: 0.7879 - val_distribution_lambda_15_loss: 1.5063 - val_distribution_lambda_16_loss: 0.5423\n", "Epoch 445/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8996 - distribution_lambda_14_loss: 0.8317 - distribution_lambda_15_loss: 1.5169 - distribution_lambda_16_loss: 0.5510 - val_loss: 2.8597 - val_distribution_lambda_14_loss: 0.8121 - val_distribution_lambda_15_loss: 1.5055 - val_distribution_lambda_16_loss: 0.5421\n", "Epoch 446/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9386 - distribution_lambda_14_loss: 0.8696 - distribution_lambda_15_loss: 1.5203 - distribution_lambda_16_loss: 0.5487 - val_loss: 2.8727 - val_distribution_lambda_14_loss: 0.8272 - val_distribution_lambda_15_loss: 1.5037 - val_distribution_lambda_16_loss: 0.5417\n", "Epoch 447/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9495 - distribution_lambda_14_loss: 0.8674 - distribution_lambda_15_loss: 1.5300 - distribution_lambda_16_loss: 0.5521 - val_loss: 2.8603 - val_distribution_lambda_14_loss: 0.8174 - val_distribution_lambda_15_loss: 1.5018 - val_distribution_lambda_16_loss: 0.5412\n", "Epoch 448/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9141 - distribution_lambda_14_loss: 0.8432 - distribution_lambda_15_loss: 1.5227 - distribution_lambda_16_loss: 0.5482 - val_loss: 2.8459 - val_distribution_lambda_14_loss: 0.8036 - val_distribution_lambda_15_loss: 1.5012 - val_distribution_lambda_16_loss: 0.5411\n", "Epoch 449/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8916 - distribution_lambda_14_loss: 0.8297 - distribution_lambda_15_loss: 1.5137 - distribution_lambda_16_loss: 0.5482 - val_loss: 2.8355 - val_distribution_lambda_14_loss: 0.7936 - val_distribution_lambda_15_loss: 1.5009 - val_distribution_lambda_16_loss: 0.5410\n", "Epoch 450/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8898 - distribution_lambda_14_loss: 0.8134 - distribution_lambda_15_loss: 1.5277 - distribution_lambda_16_loss: 0.5487 - val_loss: 2.8272 - val_distribution_lambda_14_loss: 0.7876 - val_distribution_lambda_15_loss: 1.4990 - val_distribution_lambda_16_loss: 0.5406\n", "Epoch 451/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8777 - distribution_lambda_14_loss: 0.8123 - distribution_lambda_15_loss: 1.5188 - distribution_lambda_16_loss: 0.5466 - val_loss: 2.8206 - val_distribution_lambda_14_loss: 0.7841 - val_distribution_lambda_15_loss: 1.4966 - val_distribution_lambda_16_loss: 0.5399\n", "Epoch 452/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8774 - distribution_lambda_14_loss: 0.8049 - distribution_lambda_15_loss: 1.5239 - distribution_lambda_16_loss: 0.5486 - val_loss: 2.8155 - val_distribution_lambda_14_loss: 0.7803 - val_distribution_lambda_15_loss: 1.4958 - val_distribution_lambda_16_loss: 0.5394\n", "Epoch 453/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8631 - distribution_lambda_14_loss: 0.7958 - distribution_lambda_15_loss: 1.5197 - distribution_lambda_16_loss: 0.5477 - val_loss: 2.8100 - val_distribution_lambda_14_loss: 0.7765 - val_distribution_lambda_15_loss: 1.4947 - val_distribution_lambda_16_loss: 0.5388\n", "Epoch 454/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8517 - distribution_lambda_14_loss: 0.7984 - distribution_lambda_15_loss: 1.5092 - distribution_lambda_16_loss: 0.5441 - val_loss: 2.8142 - val_distribution_lambda_14_loss: 0.7765 - val_distribution_lambda_15_loss: 1.4987 - val_distribution_lambda_16_loss: 0.5390\n", "Epoch 455/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8608 - distribution_lambda_14_loss: 0.7889 - distribution_lambda_15_loss: 1.5253 - distribution_lambda_16_loss: 0.5465 - val_loss: 2.8130 - val_distribution_lambda_14_loss: 0.7735 - val_distribution_lambda_15_loss: 1.5008 - val_distribution_lambda_16_loss: 0.5387\n", "Epoch 456/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8471 - distribution_lambda_14_loss: 0.7864 - distribution_lambda_15_loss: 1.5161 - distribution_lambda_16_loss: 0.5446 - val_loss: 2.8064 - val_distribution_lambda_14_loss: 0.7689 - val_distribution_lambda_15_loss: 1.4994 - val_distribution_lambda_16_loss: 0.5380\n", "Epoch 457/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.8483 - distribution_lambda_14_loss: 0.7936 - distribution_lambda_15_loss: 1.5096 - distribution_lambda_16_loss: 0.5452 - val_loss: 2.8018 - val_distribution_lambda_14_loss: 0.7654 - val_distribution_lambda_15_loss: 1.4990 - val_distribution_lambda_16_loss: 0.5373\n", "Epoch 458/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8437 - distribution_lambda_14_loss: 0.7862 - distribution_lambda_15_loss: 1.5164 - distribution_lambda_16_loss: 0.5412 - val_loss: 2.7981 - val_distribution_lambda_14_loss: 0.7630 - val_distribution_lambda_15_loss: 1.4985 - val_distribution_lambda_16_loss: 0.5366\n", "Epoch 459/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8469 - distribution_lambda_14_loss: 0.7877 - distribution_lambda_15_loss: 1.5172 - distribution_lambda_16_loss: 0.5421 - val_loss: 2.7947 - val_distribution_lambda_14_loss: 0.7610 - val_distribution_lambda_15_loss: 1.4978 - val_distribution_lambda_16_loss: 0.5359\n", "Epoch 460/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8729 - distribution_lambda_14_loss: 0.7949 - distribution_lambda_15_loss: 1.5340 - distribution_lambda_16_loss: 0.5441 - val_loss: 2.7904 - val_distribution_lambda_14_loss: 0.7608 - val_distribution_lambda_15_loss: 1.4940 - val_distribution_lambda_16_loss: 0.5356\n", "Epoch 461/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8250 - distribution_lambda_14_loss: 0.7701 - distribution_lambda_15_loss: 1.5131 - distribution_lambda_16_loss: 0.5418 - val_loss: 2.7928 - val_distribution_lambda_14_loss: 0.7616 - val_distribution_lambda_15_loss: 1.4957 - val_distribution_lambda_16_loss: 0.5355\n", "Epoch 462/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8548 - distribution_lambda_14_loss: 0.7765 - distribution_lambda_15_loss: 1.5344 - distribution_lambda_16_loss: 0.5438 - val_loss: 2.7888 - val_distribution_lambda_14_loss: 0.7590 - val_distribution_lambda_15_loss: 1.4947 - val_distribution_lambda_16_loss: 0.5351\n", "Epoch 463/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8343 - distribution_lambda_14_loss: 0.7747 - distribution_lambda_15_loss: 1.5167 - distribution_lambda_16_loss: 0.5429 - val_loss: 2.7869 - val_distribution_lambda_14_loss: 0.7576 - val_distribution_lambda_15_loss: 1.4946 - val_distribution_lambda_16_loss: 0.5347\n", "Epoch 464/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8186 - distribution_lambda_14_loss: 0.7612 - distribution_lambda_15_loss: 1.5164 - distribution_lambda_16_loss: 0.5410 - val_loss: 2.7862 - val_distribution_lambda_14_loss: 0.7568 - val_distribution_lambda_15_loss: 1.4949 - val_distribution_lambda_16_loss: 0.5345\n", "Epoch 465/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8330 - distribution_lambda_14_loss: 0.7707 - distribution_lambda_15_loss: 1.5199 - distribution_lambda_16_loss: 0.5423 - val_loss: 2.7789 - val_distribution_lambda_14_loss: 0.7516 - val_distribution_lambda_15_loss: 1.4934 - val_distribution_lambda_16_loss: 0.5340\n", "Epoch 466/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8332 - distribution_lambda_14_loss: 0.7585 - distribution_lambda_15_loss: 1.5297 - distribution_lambda_16_loss: 0.5450 - val_loss: 2.7738 - val_distribution_lambda_14_loss: 0.7482 - val_distribution_lambda_15_loss: 1.4923 - val_distribution_lambda_16_loss: 0.5333\n", "Epoch 467/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8290 - distribution_lambda_14_loss: 0.7623 - distribution_lambda_15_loss: 1.5231 - distribution_lambda_16_loss: 0.5436 - val_loss: 2.7701 - val_distribution_lambda_14_loss: 0.7456 - val_distribution_lambda_15_loss: 1.4918 - val_distribution_lambda_16_loss: 0.5327\n", "Epoch 468/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8173 - distribution_lambda_14_loss: 0.7619 - distribution_lambda_15_loss: 1.5156 - distribution_lambda_16_loss: 0.5398 - val_loss: 2.7667 - val_distribution_lambda_14_loss: 0.7428 - val_distribution_lambda_15_loss: 1.4916 - val_distribution_lambda_16_loss: 0.5322\n", "Epoch 469/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8116 - distribution_lambda_14_loss: 0.7603 - distribution_lambda_15_loss: 1.5110 - distribution_lambda_16_loss: 0.5404 - val_loss: 2.7630 - val_distribution_lambda_14_loss: 0.7402 - val_distribution_lambda_15_loss: 1.4913 - val_distribution_lambda_16_loss: 0.5314\n", "Epoch 470/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8178 - distribution_lambda_14_loss: 0.7518 - distribution_lambda_15_loss: 1.5249 - distribution_lambda_16_loss: 0.5412 - val_loss: 2.7597 - val_distribution_lambda_14_loss: 0.7379 - val_distribution_lambda_15_loss: 1.4910 - val_distribution_lambda_16_loss: 0.5308\n", "Epoch 471/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8144 - distribution_lambda_14_loss: 0.7497 - distribution_lambda_15_loss: 1.5218 - distribution_lambda_16_loss: 0.5429 - val_loss: 2.7631 - val_distribution_lambda_14_loss: 0.7401 - val_distribution_lambda_15_loss: 1.4921 - val_distribution_lambda_16_loss: 0.5309\n", "Epoch 472/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.8108 - distribution_lambda_14_loss: 0.7598 - distribution_lambda_15_loss: 1.5153 - distribution_lambda_16_loss: 0.5358 - val_loss: 2.7600 - val_distribution_lambda_14_loss: 0.7372 - val_distribution_lambda_15_loss: 1.4926 - val_distribution_lambda_16_loss: 0.5302\n", "Epoch 473/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7942 - distribution_lambda_14_loss: 0.7434 - distribution_lambda_15_loss: 1.5140 - distribution_lambda_16_loss: 0.5368 - val_loss: 2.7576 - val_distribution_lambda_14_loss: 0.7362 - val_distribution_lambda_15_loss: 1.4921 - val_distribution_lambda_16_loss: 0.5293\n", "Epoch 474/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8060 - distribution_lambda_14_loss: 0.7568 - distribution_lambda_15_loss: 1.5125 - distribution_lambda_16_loss: 0.5367 - val_loss: 2.7551 - val_distribution_lambda_14_loss: 0.7352 - val_distribution_lambda_15_loss: 1.4910 - val_distribution_lambda_16_loss: 0.5289\n", "Epoch 475/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7941 - distribution_lambda_14_loss: 0.7463 - distribution_lambda_15_loss: 1.5118 - distribution_lambda_16_loss: 0.5360 - val_loss: 2.7541 - val_distribution_lambda_14_loss: 0.7346 - val_distribution_lambda_15_loss: 1.4910 - val_distribution_lambda_16_loss: 0.5285\n", "Epoch 476/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8157 - distribution_lambda_14_loss: 0.7478 - distribution_lambda_15_loss: 1.5289 - distribution_lambda_16_loss: 0.5390 - val_loss: 2.7455 - val_distribution_lambda_14_loss: 0.7259 - val_distribution_lambda_15_loss: 1.4918 - val_distribution_lambda_16_loss: 0.5278\n", "Epoch 477/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8168 - distribution_lambda_14_loss: 0.7576 - distribution_lambda_15_loss: 1.5197 - distribution_lambda_16_loss: 0.5395 - val_loss: 2.7437 - val_distribution_lambda_14_loss: 0.7235 - val_distribution_lambda_15_loss: 1.4933 - val_distribution_lambda_16_loss: 0.5269\n", "Epoch 478/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7765 - distribution_lambda_14_loss: 0.7348 - distribution_lambda_15_loss: 1.5059 - distribution_lambda_16_loss: 0.5359 - val_loss: 2.7422 - val_distribution_lambda_14_loss: 0.7222 - val_distribution_lambda_15_loss: 1.4939 - val_distribution_lambda_16_loss: 0.5262\n", "Epoch 479/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7889 - distribution_lambda_14_loss: 0.7429 - distribution_lambda_15_loss: 1.5099 - distribution_lambda_16_loss: 0.5360 - val_loss: 2.7400 - val_distribution_lambda_14_loss: 0.7218 - val_distribution_lambda_15_loss: 1.4918 - val_distribution_lambda_16_loss: 0.5263\n", "Epoch 480/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7780 - distribution_lambda_14_loss: 0.7338 - distribution_lambda_15_loss: 1.5091 - distribution_lambda_16_loss: 0.5351 - val_loss: 2.7399 - val_distribution_lambda_14_loss: 0.7216 - val_distribution_lambda_15_loss: 1.4920 - val_distribution_lambda_16_loss: 0.5262\n", "Epoch 481/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.7879 - distribution_lambda_14_loss: 0.7437 - distribution_lambda_15_loss: 1.5100 - distribution_lambda_16_loss: 0.5342 - val_loss: 2.7316 - val_distribution_lambda_14_loss: 0.7149 - val_distribution_lambda_15_loss: 1.4913 - val_distribution_lambda_16_loss: 0.5254\n", "Epoch 482/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7991 - distribution_lambda_14_loss: 0.7499 - distribution_lambda_15_loss: 1.5148 - distribution_lambda_16_loss: 0.5344 - val_loss: 2.7295 - val_distribution_lambda_14_loss: 0.7121 - val_distribution_lambda_15_loss: 1.4927 - val_distribution_lambda_16_loss: 0.5247\n", "Epoch 483/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7808 - distribution_lambda_14_loss: 0.7350 - distribution_lambda_15_loss: 1.5104 - distribution_lambda_16_loss: 0.5355 - val_loss: 2.7281 - val_distribution_lambda_14_loss: 0.7094 - val_distribution_lambda_15_loss: 1.4940 - val_distribution_lambda_16_loss: 0.5247\n", "Epoch 484/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7967 - distribution_lambda_14_loss: 0.7503 - distribution_lambda_15_loss: 1.5141 - distribution_lambda_16_loss: 0.5323 - val_loss: 2.7282 - val_distribution_lambda_14_loss: 0.7087 - val_distribution_lambda_15_loss: 1.4946 - val_distribution_lambda_16_loss: 0.5249\n", "Epoch 485/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7833 - distribution_lambda_14_loss: 0.7348 - distribution_lambda_15_loss: 1.5139 - distribution_lambda_16_loss: 0.5345 - val_loss: 2.7302 - val_distribution_lambda_14_loss: 0.7082 - val_distribution_lambda_15_loss: 1.4967 - val_distribution_lambda_16_loss: 0.5253\n", "Epoch 486/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7878 - distribution_lambda_14_loss: 0.7364 - distribution_lambda_15_loss: 1.5171 - distribution_lambda_16_loss: 0.5343 - val_loss: 2.7361 - val_distribution_lambda_14_loss: 0.7093 - val_distribution_lambda_15_loss: 1.5008 - val_distribution_lambda_16_loss: 0.5259\n", "Epoch 487/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7770 - distribution_lambda_14_loss: 0.7257 - distribution_lambda_15_loss: 1.5161 - distribution_lambda_16_loss: 0.5352 - val_loss: 2.7343 - val_distribution_lambda_14_loss: 0.7079 - val_distribution_lambda_15_loss: 1.5006 - val_distribution_lambda_16_loss: 0.5258\n", "Epoch 488/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7547 - distribution_lambda_14_loss: 0.7106 - distribution_lambda_15_loss: 1.5115 - distribution_lambda_16_loss: 0.5326 - val_loss: 2.7269 - val_distribution_lambda_14_loss: 0.7068 - val_distribution_lambda_15_loss: 1.4956 - val_distribution_lambda_16_loss: 0.5245\n", "Epoch 489/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7608 - distribution_lambda_14_loss: 0.7155 - distribution_lambda_15_loss: 1.5123 - distribution_lambda_16_loss: 0.5330 - val_loss: 2.7197 - val_distribution_lambda_14_loss: 0.7047 - val_distribution_lambda_15_loss: 1.4920 - val_distribution_lambda_16_loss: 0.5230\n", "Epoch 490/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7490 - distribution_lambda_14_loss: 0.7114 - distribution_lambda_15_loss: 1.5073 - distribution_lambda_16_loss: 0.5304 - val_loss: 2.7158 - val_distribution_lambda_14_loss: 0.7031 - val_distribution_lambda_15_loss: 1.4905 - val_distribution_lambda_16_loss: 0.5222\n", "Epoch 491/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7554 - distribution_lambda_14_loss: 0.7164 - distribution_lambda_15_loss: 1.5067 - distribution_lambda_16_loss: 0.5322 - val_loss: 2.7151 - val_distribution_lambda_14_loss: 0.7029 - val_distribution_lambda_15_loss: 1.4902 - val_distribution_lambda_16_loss: 0.5219\n", "Epoch 492/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7356 - distribution_lambda_14_loss: 0.7060 - distribution_lambda_15_loss: 1.4975 - distribution_lambda_16_loss: 0.5321 - val_loss: 2.7146 - val_distribution_lambda_14_loss: 0.7023 - val_distribution_lambda_15_loss: 1.4909 - val_distribution_lambda_16_loss: 0.5214\n", "Epoch 493/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7702 - distribution_lambda_14_loss: 0.7263 - distribution_lambda_15_loss: 1.5101 - distribution_lambda_16_loss: 0.5338 - val_loss: 2.7140 - val_distribution_lambda_14_loss: 0.7012 - val_distribution_lambda_15_loss: 1.4916 - val_distribution_lambda_16_loss: 0.5212\n", "Epoch 494/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7500 - distribution_lambda_14_loss: 0.7209 - distribution_lambda_15_loss: 1.5017 - distribution_lambda_16_loss: 0.5274 - val_loss: 2.7115 - val_distribution_lambda_14_loss: 0.6992 - val_distribution_lambda_15_loss: 1.4916 - val_distribution_lambda_16_loss: 0.5207\n", "Epoch 495/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7322 - distribution_lambda_14_loss: 0.7022 - distribution_lambda_15_loss: 1.5021 - distribution_lambda_16_loss: 0.5279 - val_loss: 2.7083 - val_distribution_lambda_14_loss: 0.6982 - val_distribution_lambda_15_loss: 1.4899 - val_distribution_lambda_16_loss: 0.5202\n", "Epoch 496/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7453 - distribution_lambda_14_loss: 0.7047 - distribution_lambda_15_loss: 1.5110 - distribution_lambda_16_loss: 0.5296 - val_loss: 2.7090 - val_distribution_lambda_14_loss: 0.7002 - val_distribution_lambda_15_loss: 1.4890 - val_distribution_lambda_16_loss: 0.5198\n", "Epoch 497/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7603 - distribution_lambda_14_loss: 0.7132 - distribution_lambda_15_loss: 1.5147 - distribution_lambda_16_loss: 0.5324 - val_loss: 2.7107 - val_distribution_lambda_14_loss: 0.7038 - val_distribution_lambda_15_loss: 1.4877 - val_distribution_lambda_16_loss: 0.5192\n", "Epoch 498/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7782 - distribution_lambda_14_loss: 0.7252 - distribution_lambda_15_loss: 1.5206 - distribution_lambda_16_loss: 0.5324 - val_loss: 2.7116 - val_distribution_lambda_14_loss: 0.7061 - val_distribution_lambda_15_loss: 1.4868 - val_distribution_lambda_16_loss: 0.5186\n", "Epoch 499/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7409 - distribution_lambda_14_loss: 0.6985 - distribution_lambda_15_loss: 1.5129 - distribution_lambda_16_loss: 0.5294 - val_loss: 2.7099 - val_distribution_lambda_14_loss: 0.7065 - val_distribution_lambda_15_loss: 1.4855 - val_distribution_lambda_16_loss: 0.5179\n", "Epoch 500/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7582 - distribution_lambda_14_loss: 0.7121 - distribution_lambda_15_loss: 1.5181 - distribution_lambda_16_loss: 0.5280 - val_loss: 2.7060 - val_distribution_lambda_14_loss: 0.7043 - val_distribution_lambda_15_loss: 1.4846 - val_distribution_lambda_16_loss: 0.5172\n", "Epoch 501/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7225 - distribution_lambda_14_loss: 0.6874 - distribution_lambda_15_loss: 1.5061 - distribution_lambda_16_loss: 0.5289 - val_loss: 2.7012 - val_distribution_lambda_14_loss: 0.7001 - val_distribution_lambda_15_loss: 1.4845 - val_distribution_lambda_16_loss: 0.5165\n", "Epoch 502/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7423 - distribution_lambda_14_loss: 0.6985 - distribution_lambda_15_loss: 1.5138 - distribution_lambda_16_loss: 0.5300 - val_loss: 2.6969 - val_distribution_lambda_14_loss: 0.6948 - val_distribution_lambda_15_loss: 1.4862 - val_distribution_lambda_16_loss: 0.5159\n", "Epoch 503/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7325 - distribution_lambda_14_loss: 0.6976 - distribution_lambda_15_loss: 1.5080 - distribution_lambda_16_loss: 0.5270 - val_loss: 2.6919 - val_distribution_lambda_14_loss: 0.6913 - val_distribution_lambda_15_loss: 1.4852 - val_distribution_lambda_16_loss: 0.5154\n", "Epoch 504/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7457 - distribution_lambda_14_loss: 0.7126 - distribution_lambda_15_loss: 1.5106 - distribution_lambda_16_loss: 0.5226 - val_loss: 2.6866 - val_distribution_lambda_14_loss: 0.6889 - val_distribution_lambda_15_loss: 1.4829 - val_distribution_lambda_16_loss: 0.5148\n", "Epoch 505/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.7375 - distribution_lambda_14_loss: 0.6950 - distribution_lambda_15_loss: 1.5147 - distribution_lambda_16_loss: 0.5278 - val_loss: 2.6823 - val_distribution_lambda_14_loss: 0.6850 - val_distribution_lambda_15_loss: 1.4830 - val_distribution_lambda_16_loss: 0.5144\n", "Epoch 506/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7221 - distribution_lambda_14_loss: 0.6986 - distribution_lambda_15_loss: 1.5024 - distribution_lambda_16_loss: 0.5212 - val_loss: 2.6848 - val_distribution_lambda_14_loss: 0.6877 - val_distribution_lambda_15_loss: 1.4829 - val_distribution_lambda_16_loss: 0.5141\n", "Epoch 507/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7155 - distribution_lambda_14_loss: 0.6918 - distribution_lambda_15_loss: 1.4976 - distribution_lambda_16_loss: 0.5261 - val_loss: 2.6839 - val_distribution_lambda_14_loss: 0.6873 - val_distribution_lambda_15_loss: 1.4827 - val_distribution_lambda_16_loss: 0.5139\n", "Epoch 508/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7361 - distribution_lambda_14_loss: 0.6958 - distribution_lambda_15_loss: 1.5156 - distribution_lambda_16_loss: 0.5247 - val_loss: 2.6850 - val_distribution_lambda_14_loss: 0.6888 - val_distribution_lambda_15_loss: 1.4821 - val_distribution_lambda_16_loss: 0.5141\n", "Epoch 509/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7363 - distribution_lambda_14_loss: 0.7032 - distribution_lambda_15_loss: 1.5091 - distribution_lambda_16_loss: 0.5240 - val_loss: 2.6890 - val_distribution_lambda_14_loss: 0.6910 - val_distribution_lambda_15_loss: 1.4838 - val_distribution_lambda_16_loss: 0.5143\n", "Epoch 510/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7294 - distribution_lambda_14_loss: 0.6989 - distribution_lambda_15_loss: 1.5057 - distribution_lambda_16_loss: 0.5249 - val_loss: 2.6903 - val_distribution_lambda_14_loss: 0.6908 - val_distribution_lambda_15_loss: 1.4855 - val_distribution_lambda_16_loss: 0.5141\n", "Epoch 511/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7202 - distribution_lambda_14_loss: 0.6921 - distribution_lambda_15_loss: 1.5062 - distribution_lambda_16_loss: 0.5219 - val_loss: 2.6859 - val_distribution_lambda_14_loss: 0.6892 - val_distribution_lambda_15_loss: 1.4835 - val_distribution_lambda_16_loss: 0.5132\n", "Epoch 512/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7023 - distribution_lambda_14_loss: 0.6885 - distribution_lambda_15_loss: 1.4945 - distribution_lambda_16_loss: 0.5192 - val_loss: 2.6786 - val_distribution_lambda_14_loss: 0.6858 - val_distribution_lambda_15_loss: 1.4809 - val_distribution_lambda_16_loss: 0.5119\n", "Epoch 513/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7061 - distribution_lambda_14_loss: 0.6869 - distribution_lambda_15_loss: 1.5001 - distribution_lambda_16_loss: 0.5191 - val_loss: 2.6731 - val_distribution_lambda_14_loss: 0.6830 - val_distribution_lambda_15_loss: 1.4794 - val_distribution_lambda_16_loss: 0.5107\n", "Epoch 514/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7160 - distribution_lambda_14_loss: 0.6883 - distribution_lambda_15_loss: 1.5084 - distribution_lambda_16_loss: 0.5193 - val_loss: 2.6689 - val_distribution_lambda_14_loss: 0.6806 - val_distribution_lambda_15_loss: 1.4785 - val_distribution_lambda_16_loss: 0.5098\n", "Epoch 515/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6967 - distribution_lambda_14_loss: 0.6714 - distribution_lambda_15_loss: 1.5044 - distribution_lambda_16_loss: 0.5209 - val_loss: 2.6660 - val_distribution_lambda_14_loss: 0.6789 - val_distribution_lambda_15_loss: 1.4780 - val_distribution_lambda_16_loss: 0.5092\n", "Epoch 516/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7126 - distribution_lambda_14_loss: 0.6959 - distribution_lambda_15_loss: 1.5011 - distribution_lambda_16_loss: 0.5156 - val_loss: 2.6671 - val_distribution_lambda_14_loss: 0.6789 - val_distribution_lambda_15_loss: 1.4791 - val_distribution_lambda_16_loss: 0.5090\n", "Epoch 517/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6949 - distribution_lambda_14_loss: 0.6802 - distribution_lambda_15_loss: 1.4965 - distribution_lambda_16_loss: 0.5182 - val_loss: 2.6667 - val_distribution_lambda_14_loss: 0.6785 - val_distribution_lambda_15_loss: 1.4794 - val_distribution_lambda_16_loss: 0.5088\n", "Epoch 518/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6847 - distribution_lambda_14_loss: 0.6843 - distribution_lambda_15_loss: 1.4880 - distribution_lambda_16_loss: 0.5123 - val_loss: 2.6629 - val_distribution_lambda_14_loss: 0.6758 - val_distribution_lambda_15_loss: 1.4792 - val_distribution_lambda_16_loss: 0.5079\n", "Epoch 519/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7083 - distribution_lambda_14_loss: 0.6875 - distribution_lambda_15_loss: 1.5040 - distribution_lambda_16_loss: 0.5168 - val_loss: 2.6613 - val_distribution_lambda_14_loss: 0.6760 - val_distribution_lambda_15_loss: 1.4779 - val_distribution_lambda_16_loss: 0.5074\n", "Epoch 520/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7016 - distribution_lambda_14_loss: 0.6896 - distribution_lambda_15_loss: 1.4945 - distribution_lambda_16_loss: 0.5176 - val_loss: 2.6558 - val_distribution_lambda_14_loss: 0.6717 - val_distribution_lambda_15_loss: 1.4773 - val_distribution_lambda_16_loss: 0.5069\n", "Epoch 521/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7433 - distribution_lambda_14_loss: 0.7002 - distribution_lambda_15_loss: 1.5191 - distribution_lambda_16_loss: 0.5240 - val_loss: 2.6566 - val_distribution_lambda_14_loss: 0.6717 - val_distribution_lambda_15_loss: 1.4780 - val_distribution_lambda_16_loss: 0.5068\n", "Epoch 522/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6954 - distribution_lambda_14_loss: 0.6785 - distribution_lambda_15_loss: 1.4982 - distribution_lambda_16_loss: 0.5187 - val_loss: 2.6587 - val_distribution_lambda_14_loss: 0.6720 - val_distribution_lambda_15_loss: 1.4800 - val_distribution_lambda_16_loss: 0.5067\n", "Epoch 523/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6949 - distribution_lambda_14_loss: 0.6740 - distribution_lambda_15_loss: 1.5036 - distribution_lambda_16_loss: 0.5174 - val_loss: 2.6595 - val_distribution_lambda_14_loss: 0.6724 - val_distribution_lambda_15_loss: 1.4808 - val_distribution_lambda_16_loss: 0.5062\n", "Epoch 524/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7007 - distribution_lambda_14_loss: 0.6812 - distribution_lambda_15_loss: 1.5024 - distribution_lambda_16_loss: 0.5171 - val_loss: 2.6654 - val_distribution_lambda_14_loss: 0.6750 - val_distribution_lambda_15_loss: 1.4839 - val_distribution_lambda_16_loss: 0.5065\n", "Epoch 525/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6882 - distribution_lambda_14_loss: 0.6645 - distribution_lambda_15_loss: 1.5052 - distribution_lambda_16_loss: 0.5184 - val_loss: 2.6706 - val_distribution_lambda_14_loss: 0.6783 - val_distribution_lambda_15_loss: 1.4857 - val_distribution_lambda_16_loss: 0.5066\n", "Epoch 526/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6997 - distribution_lambda_14_loss: 0.6832 - distribution_lambda_15_loss: 1.5023 - distribution_lambda_16_loss: 0.5141 - val_loss: 2.6674 - val_distribution_lambda_14_loss: 0.6776 - val_distribution_lambda_15_loss: 1.4838 - val_distribution_lambda_16_loss: 0.5061\n", "Epoch 527/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6959 - distribution_lambda_14_loss: 0.6838 - distribution_lambda_15_loss: 1.4966 - distribution_lambda_16_loss: 0.5155 - val_loss: 2.6624 - val_distribution_lambda_14_loss: 0.6765 - val_distribution_lambda_15_loss: 1.4807 - val_distribution_lambda_16_loss: 0.5052\n", "Epoch 528/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6929 - distribution_lambda_14_loss: 0.6700 - distribution_lambda_15_loss: 1.5042 - distribution_lambda_16_loss: 0.5188 - val_loss: 2.6592 - val_distribution_lambda_14_loss: 0.6758 - val_distribution_lambda_15_loss: 1.4791 - val_distribution_lambda_16_loss: 0.5043\n", "Epoch 529/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.6608 - distribution_lambda_14_loss: 0.6590 - distribution_lambda_15_loss: 1.4894 - distribution_lambda_16_loss: 0.5124 - val_loss: 2.6570 - val_distribution_lambda_14_loss: 0.6748 - val_distribution_lambda_15_loss: 1.4788 - val_distribution_lambda_16_loss: 0.5035\n", "Epoch 530/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6891 - distribution_lambda_14_loss: 0.6688 - distribution_lambda_15_loss: 1.5031 - distribution_lambda_16_loss: 0.5172 - val_loss: 2.6553 - val_distribution_lambda_14_loss: 0.6730 - val_distribution_lambda_15_loss: 1.4793 - val_distribution_lambda_16_loss: 0.5031\n", "Epoch 531/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7051 - distribution_lambda_14_loss: 0.6842 - distribution_lambda_15_loss: 1.5105 - distribution_lambda_16_loss: 0.5104 - val_loss: 2.6549 - val_distribution_lambda_14_loss: 0.6706 - val_distribution_lambda_15_loss: 1.4815 - val_distribution_lambda_16_loss: 0.5029\n", "Epoch 532/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7040 - distribution_lambda_14_loss: 0.6769 - distribution_lambda_15_loss: 1.5102 - distribution_lambda_16_loss: 0.5169 - val_loss: 2.6533 - val_distribution_lambda_14_loss: 0.6689 - val_distribution_lambda_15_loss: 1.4821 - val_distribution_lambda_16_loss: 0.5023\n", "Epoch 533/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6714 - distribution_lambda_14_loss: 0.6648 - distribution_lambda_15_loss: 1.4966 - distribution_lambda_16_loss: 0.5099 - val_loss: 2.6516 - val_distribution_lambda_14_loss: 0.6683 - val_distribution_lambda_15_loss: 1.4820 - val_distribution_lambda_16_loss: 0.5014\n", "Epoch 534/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6751 - distribution_lambda_14_loss: 0.6651 - distribution_lambda_15_loss: 1.4972 - distribution_lambda_16_loss: 0.5128 - val_loss: 2.6488 - val_distribution_lambda_14_loss: 0.6676 - val_distribution_lambda_15_loss: 1.4800 - val_distribution_lambda_16_loss: 0.5012\n", "Epoch 535/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6844 - distribution_lambda_14_loss: 0.6724 - distribution_lambda_15_loss: 1.4994 - distribution_lambda_16_loss: 0.5126 - val_loss: 2.6436 - val_distribution_lambda_14_loss: 0.6622 - val_distribution_lambda_15_loss: 1.4804 - val_distribution_lambda_16_loss: 0.5010\n", "Epoch 536/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6427 - distribution_lambda_14_loss: 0.6549 - distribution_lambda_15_loss: 1.4822 - distribution_lambda_16_loss: 0.5056 - val_loss: 2.6377 - val_distribution_lambda_14_loss: 0.6585 - val_distribution_lambda_15_loss: 1.4791 - val_distribution_lambda_16_loss: 0.5001\n", "Epoch 537/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6803 - distribution_lambda_14_loss: 0.6698 - distribution_lambda_15_loss: 1.4974 - distribution_lambda_16_loss: 0.5130 - val_loss: 2.6358 - val_distribution_lambda_14_loss: 0.6582 - val_distribution_lambda_15_loss: 1.4784 - val_distribution_lambda_16_loss: 0.4993\n", "Epoch 538/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6740 - distribution_lambda_14_loss: 0.6682 - distribution_lambda_15_loss: 1.4970 - distribution_lambda_16_loss: 0.5087 - val_loss: 2.6352 - val_distribution_lambda_14_loss: 0.6592 - val_distribution_lambda_15_loss: 1.4776 - val_distribution_lambda_16_loss: 0.4984\n", "Epoch 539/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6750 - distribution_lambda_14_loss: 0.6681 - distribution_lambda_15_loss: 1.4978 - distribution_lambda_16_loss: 0.5091 - val_loss: 2.6351 - val_distribution_lambda_14_loss: 0.6611 - val_distribution_lambda_15_loss: 1.4765 - val_distribution_lambda_16_loss: 0.4976\n", "Epoch 540/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6655 - distribution_lambda_14_loss: 0.6603 - distribution_lambda_15_loss: 1.5002 - distribution_lambda_16_loss: 0.5050 - val_loss: 2.6295 - val_distribution_lambda_14_loss: 0.6525 - val_distribution_lambda_15_loss: 1.4800 - val_distribution_lambda_16_loss: 0.4970\n", "Epoch 541/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6897 - distribution_lambda_14_loss: 0.6777 - distribution_lambda_15_loss: 1.5049 - distribution_lambda_16_loss: 0.5071 - val_loss: 2.6319 - val_distribution_lambda_14_loss: 0.6538 - val_distribution_lambda_15_loss: 1.4815 - val_distribution_lambda_16_loss: 0.4965\n", "Epoch 542/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7051 - distribution_lambda_14_loss: 0.6942 - distribution_lambda_15_loss: 1.5064 - distribution_lambda_16_loss: 0.5045 - val_loss: 2.6246 - val_distribution_lambda_14_loss: 0.6513 - val_distribution_lambda_15_loss: 1.4774 - val_distribution_lambda_16_loss: 0.4959\n", "Epoch 543/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6621 - distribution_lambda_14_loss: 0.6700 - distribution_lambda_15_loss: 1.4861 - distribution_lambda_16_loss: 0.5060 - val_loss: 2.6205 - val_distribution_lambda_14_loss: 0.6510 - val_distribution_lambda_15_loss: 1.4745 - val_distribution_lambda_16_loss: 0.4950\n", "Epoch 544/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6580 - distribution_lambda_14_loss: 0.6641 - distribution_lambda_15_loss: 1.4905 - distribution_lambda_16_loss: 0.5033 - val_loss: 2.6195 - val_distribution_lambda_14_loss: 0.6526 - val_distribution_lambda_15_loss: 1.4726 - val_distribution_lambda_16_loss: 0.4942\n", "Epoch 545/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6508 - distribution_lambda_14_loss: 0.6518 - distribution_lambda_15_loss: 1.4971 - distribution_lambda_16_loss: 0.5019 - val_loss: 2.6251 - val_distribution_lambda_14_loss: 0.6517 - val_distribution_lambda_15_loss: 1.4788 - val_distribution_lambda_16_loss: 0.4946\n", "Epoch 546/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6668 - distribution_lambda_14_loss: 0.6595 - distribution_lambda_15_loss: 1.5015 - distribution_lambda_16_loss: 0.5058 - val_loss: 2.6368 - val_distribution_lambda_14_loss: 0.6563 - val_distribution_lambda_15_loss: 1.4855 - val_distribution_lambda_16_loss: 0.4950\n", "Epoch 547/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6588 - distribution_lambda_14_loss: 0.6584 - distribution_lambda_15_loss: 1.4916 - distribution_lambda_16_loss: 0.5089 - val_loss: 2.6378 - val_distribution_lambda_14_loss: 0.6571 - val_distribution_lambda_15_loss: 1.4860 - val_distribution_lambda_16_loss: 0.4947\n", "Epoch 548/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6469 - distribution_lambda_14_loss: 0.6602 - distribution_lambda_15_loss: 1.4890 - distribution_lambda_16_loss: 0.4976 - val_loss: 2.6308 - val_distribution_lambda_14_loss: 0.6535 - val_distribution_lambda_15_loss: 1.4839 - val_distribution_lambda_16_loss: 0.4934\n", "Epoch 549/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6592 - distribution_lambda_14_loss: 0.6614 - distribution_lambda_15_loss: 1.4903 - distribution_lambda_16_loss: 0.5074 - val_loss: 2.6238 - val_distribution_lambda_14_loss: 0.6489 - val_distribution_lambda_15_loss: 1.4826 - val_distribution_lambda_16_loss: 0.4923\n", "Epoch 550/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6582 - distribution_lambda_14_loss: 0.6690 - distribution_lambda_15_loss: 1.4878 - distribution_lambda_16_loss: 0.5015 - val_loss: 2.6171 - val_distribution_lambda_14_loss: 0.6444 - val_distribution_lambda_15_loss: 1.4813 - val_distribution_lambda_16_loss: 0.4914\n", "Epoch 551/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6580 - distribution_lambda_14_loss: 0.6587 - distribution_lambda_15_loss: 1.4946 - distribution_lambda_16_loss: 0.5047 - val_loss: 2.6147 - val_distribution_lambda_14_loss: 0.6438 - val_distribution_lambda_15_loss: 1.4796 - val_distribution_lambda_16_loss: 0.4912\n", "Epoch 552/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6853 - distribution_lambda_14_loss: 0.6679 - distribution_lambda_15_loss: 1.5104 - distribution_lambda_16_loss: 0.5071 - val_loss: 2.6130 - val_distribution_lambda_14_loss: 0.6446 - val_distribution_lambda_15_loss: 1.4780 - val_distribution_lambda_16_loss: 0.4903\n", "Epoch 553/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.6582 - distribution_lambda_14_loss: 0.6626 - distribution_lambda_15_loss: 1.4947 - distribution_lambda_16_loss: 0.5009 - val_loss: 2.6093 - val_distribution_lambda_14_loss: 0.6435 - val_distribution_lambda_15_loss: 1.4765 - val_distribution_lambda_16_loss: 0.4893\n", "Epoch 554/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6369 - distribution_lambda_14_loss: 0.6435 - distribution_lambda_15_loss: 1.4967 - distribution_lambda_16_loss: 0.4967 - val_loss: 2.6062 - val_distribution_lambda_14_loss: 0.6424 - val_distribution_lambda_15_loss: 1.4752 - val_distribution_lambda_16_loss: 0.4886\n", "Epoch 555/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6515 - distribution_lambda_14_loss: 0.6680 - distribution_lambda_15_loss: 1.4877 - distribution_lambda_16_loss: 0.4958 - val_loss: 2.6032 - val_distribution_lambda_14_loss: 0.6414 - val_distribution_lambda_15_loss: 1.4735 - val_distribution_lambda_16_loss: 0.4883\n", "Epoch 556/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6571 - distribution_lambda_14_loss: 0.6644 - distribution_lambda_15_loss: 1.4903 - distribution_lambda_16_loss: 0.5023 - val_loss: 2.6038 - val_distribution_lambda_14_loss: 0.6427 - val_distribution_lambda_15_loss: 1.4729 - val_distribution_lambda_16_loss: 0.4881\n", "Epoch 557/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6632 - distribution_lambda_14_loss: 0.6595 - distribution_lambda_15_loss: 1.5001 - distribution_lambda_16_loss: 0.5036 - val_loss: 2.6049 - val_distribution_lambda_14_loss: 0.6448 - val_distribution_lambda_15_loss: 1.4725 - val_distribution_lambda_16_loss: 0.4876\n", "Epoch 558/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6532 - distribution_lambda_14_loss: 0.6585 - distribution_lambda_15_loss: 1.4983 - distribution_lambda_16_loss: 0.4964 - val_loss: 2.5992 - val_distribution_lambda_14_loss: 0.6415 - val_distribution_lambda_15_loss: 1.4713 - val_distribution_lambda_16_loss: 0.4864\n", "Epoch 559/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6517 - distribution_lambda_14_loss: 0.6511 - distribution_lambda_15_loss: 1.4990 - distribution_lambda_16_loss: 0.5016 - val_loss: 2.5938 - val_distribution_lambda_14_loss: 0.6389 - val_distribution_lambda_15_loss: 1.4697 - val_distribution_lambda_16_loss: 0.4853\n", "Epoch 560/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6545 - distribution_lambda_14_loss: 0.6625 - distribution_lambda_15_loss: 1.4960 - distribution_lambda_16_loss: 0.4959 - val_loss: 2.5924 - val_distribution_lambda_14_loss: 0.6386 - val_distribution_lambda_15_loss: 1.4693 - val_distribution_lambda_16_loss: 0.4845\n", "Epoch 561/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6536 - distribution_lambda_14_loss: 0.6608 - distribution_lambda_15_loss: 1.4944 - distribution_lambda_16_loss: 0.4984 - val_loss: 2.5960 - val_distribution_lambda_14_loss: 0.6425 - val_distribution_lambda_15_loss: 1.4693 - val_distribution_lambda_16_loss: 0.4842\n", "Epoch 562/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6434 - distribution_lambda_14_loss: 0.6531 - distribution_lambda_15_loss: 1.4953 - distribution_lambda_16_loss: 0.4950 - val_loss: 2.5944 - val_distribution_lambda_14_loss: 0.6423 - val_distribution_lambda_15_loss: 1.4683 - val_distribution_lambda_16_loss: 0.4838\n", "Epoch 563/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6364 - distribution_lambda_14_loss: 0.6497 - distribution_lambda_15_loss: 1.4912 - distribution_lambda_16_loss: 0.4955 - val_loss: 2.5916 - val_distribution_lambda_14_loss: 0.6403 - val_distribution_lambda_15_loss: 1.4679 - val_distribution_lambda_16_loss: 0.4834\n", "Epoch 564/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6460 - distribution_lambda_14_loss: 0.6594 - distribution_lambda_15_loss: 1.4903 - distribution_lambda_16_loss: 0.4962 - val_loss: 2.5890 - val_distribution_lambda_14_loss: 0.6370 - val_distribution_lambda_15_loss: 1.4692 - val_distribution_lambda_16_loss: 0.4828\n", "Epoch 565/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6121 - distribution_lambda_14_loss: 0.6454 - distribution_lambda_15_loss: 1.4744 - distribution_lambda_16_loss: 0.4923 - val_loss: 2.5847 - val_distribution_lambda_14_loss: 0.6324 - val_distribution_lambda_15_loss: 1.4698 - val_distribution_lambda_16_loss: 0.4825\n", "Epoch 566/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6642 - distribution_lambda_14_loss: 0.6583 - distribution_lambda_15_loss: 1.5078 - distribution_lambda_16_loss: 0.4981 - val_loss: 2.5841 - val_distribution_lambda_14_loss: 0.6324 - val_distribution_lambda_15_loss: 1.4693 - val_distribution_lambda_16_loss: 0.4824\n", "Epoch 567/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6422 - distribution_lambda_14_loss: 0.6457 - distribution_lambda_15_loss: 1.4976 - distribution_lambda_16_loss: 0.4990 - val_loss: 2.5856 - val_distribution_lambda_14_loss: 0.6344 - val_distribution_lambda_15_loss: 1.4688 - val_distribution_lambda_16_loss: 0.4824\n", "Epoch 568/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6184 - distribution_lambda_14_loss: 0.6433 - distribution_lambda_15_loss: 1.4836 - distribution_lambda_16_loss: 0.4915 - val_loss: 2.5884 - val_distribution_lambda_14_loss: 0.6355 - val_distribution_lambda_15_loss: 1.4704 - val_distribution_lambda_16_loss: 0.4825\n", "Epoch 569/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6318 - distribution_lambda_14_loss: 0.6451 - distribution_lambda_15_loss: 1.4923 - distribution_lambda_16_loss: 0.4944 - val_loss: 2.5891 - val_distribution_lambda_14_loss: 0.6359 - val_distribution_lambda_15_loss: 1.4710 - val_distribution_lambda_16_loss: 0.4822\n", "Epoch 570/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6311 - distribution_lambda_14_loss: 0.6402 - distribution_lambda_15_loss: 1.4985 - distribution_lambda_16_loss: 0.4924 - val_loss: 2.5859 - val_distribution_lambda_14_loss: 0.6349 - val_distribution_lambda_15_loss: 1.4698 - val_distribution_lambda_16_loss: 0.4812\n", "Epoch 571/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6140 - distribution_lambda_14_loss: 0.6358 - distribution_lambda_15_loss: 1.4870 - distribution_lambda_16_loss: 0.4912 - val_loss: 2.5838 - val_distribution_lambda_14_loss: 0.6343 - val_distribution_lambda_15_loss: 1.4690 - val_distribution_lambda_16_loss: 0.4805\n", "Epoch 572/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6222 - distribution_lambda_14_loss: 0.6455 - distribution_lambda_15_loss: 1.4874 - distribution_lambda_16_loss: 0.4893 - val_loss: 2.5860 - val_distribution_lambda_14_loss: 0.6376 - val_distribution_lambda_15_loss: 1.4685 - val_distribution_lambda_16_loss: 0.4800\n", "Epoch 573/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6306 - distribution_lambda_14_loss: 0.6437 - distribution_lambda_15_loss: 1.4926 - distribution_lambda_16_loss: 0.4943 - val_loss: 2.5846 - val_distribution_lambda_14_loss: 0.6375 - val_distribution_lambda_15_loss: 1.4678 - val_distribution_lambda_16_loss: 0.4792\n", "Epoch 574/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6394 - distribution_lambda_14_loss: 0.6445 - distribution_lambda_15_loss: 1.5034 - distribution_lambda_16_loss: 0.4916 - val_loss: 2.5757 - val_distribution_lambda_14_loss: 0.6302 - val_distribution_lambda_15_loss: 1.4672 - val_distribution_lambda_16_loss: 0.4782\n", "Epoch 575/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6311 - distribution_lambda_14_loss: 0.6482 - distribution_lambda_15_loss: 1.4901 - distribution_lambda_16_loss: 0.4928 - val_loss: 2.5794 - val_distribution_lambda_14_loss: 0.6337 - val_distribution_lambda_15_loss: 1.4680 - val_distribution_lambda_16_loss: 0.4777\n", "Epoch 576/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6227 - distribution_lambda_14_loss: 0.6543 - distribution_lambda_15_loss: 1.4814 - distribution_lambda_16_loss: 0.4870 - val_loss: 2.5817 - val_distribution_lambda_14_loss: 0.6359 - val_distribution_lambda_15_loss: 1.4684 - val_distribution_lambda_16_loss: 0.4773\n", "Epoch 577/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.6169 - distribution_lambda_14_loss: 0.6392 - distribution_lambda_15_loss: 1.4853 - distribution_lambda_16_loss: 0.4925 - val_loss: 2.5827 - val_distribution_lambda_14_loss: 0.6380 - val_distribution_lambda_15_loss: 1.4679 - val_distribution_lambda_16_loss: 0.4769\n", "Epoch 578/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6403 - distribution_lambda_14_loss: 0.6607 - distribution_lambda_15_loss: 1.4881 - distribution_lambda_16_loss: 0.4915 - val_loss: 2.5874 - val_distribution_lambda_14_loss: 0.6420 - val_distribution_lambda_15_loss: 1.4689 - val_distribution_lambda_16_loss: 0.4765\n", "Epoch 579/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6424 - distribution_lambda_14_loss: 0.6540 - distribution_lambda_15_loss: 1.4961 - distribution_lambda_16_loss: 0.4924 - val_loss: 2.5903 - val_distribution_lambda_14_loss: 0.6440 - val_distribution_lambda_15_loss: 1.4704 - val_distribution_lambda_16_loss: 0.4759\n", "Epoch 580/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6184 - distribution_lambda_14_loss: 0.6511 - distribution_lambda_15_loss: 1.4807 - distribution_lambda_16_loss: 0.4866 - val_loss: 2.5821 - val_distribution_lambda_14_loss: 0.6363 - val_distribution_lambda_15_loss: 1.4704 - val_distribution_lambda_16_loss: 0.4753\n", "Epoch 581/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6269 - distribution_lambda_14_loss: 0.6511 - distribution_lambda_15_loss: 1.4895 - distribution_lambda_16_loss: 0.4864 - val_loss: 2.5763 - val_distribution_lambda_14_loss: 0.6336 - val_distribution_lambda_15_loss: 1.4676 - val_distribution_lambda_16_loss: 0.4751\n", "Epoch 582/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6390 - distribution_lambda_14_loss: 0.6609 - distribution_lambda_15_loss: 1.4912 - distribution_lambda_16_loss: 0.4869 - val_loss: 2.5749 - val_distribution_lambda_14_loss: 0.6330 - val_distribution_lambda_15_loss: 1.4667 - val_distribution_lambda_16_loss: 0.4752\n", "Epoch 583/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6073 - distribution_lambda_14_loss: 0.6396 - distribution_lambda_15_loss: 1.4776 - distribution_lambda_16_loss: 0.4902 - val_loss: 2.5742 - val_distribution_lambda_14_loss: 0.6332 - val_distribution_lambda_15_loss: 1.4661 - val_distribution_lambda_16_loss: 0.4749\n", "Epoch 584/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6015 - distribution_lambda_14_loss: 0.6408 - distribution_lambda_15_loss: 1.4770 - distribution_lambda_16_loss: 0.4837 - val_loss: 2.5747 - val_distribution_lambda_14_loss: 0.6338 - val_distribution_lambda_15_loss: 1.4663 - val_distribution_lambda_16_loss: 0.4746\n", "Epoch 585/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5969 - distribution_lambda_14_loss: 0.6278 - distribution_lambda_15_loss: 1.4794 - distribution_lambda_16_loss: 0.4896 - val_loss: 2.5748 - val_distribution_lambda_14_loss: 0.6345 - val_distribution_lambda_15_loss: 1.4661 - val_distribution_lambda_16_loss: 0.4741\n", "Epoch 586/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6269 - distribution_lambda_14_loss: 0.6461 - distribution_lambda_15_loss: 1.4899 - distribution_lambda_16_loss: 0.4909 - val_loss: 2.5734 - val_distribution_lambda_14_loss: 0.6337 - val_distribution_lambda_15_loss: 1.4658 - val_distribution_lambda_16_loss: 0.4739\n", "Epoch 587/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6078 - distribution_lambda_14_loss: 0.6495 - distribution_lambda_15_loss: 1.4751 - distribution_lambda_16_loss: 0.4831 - val_loss: 2.5758 - val_distribution_lambda_14_loss: 0.6356 - val_distribution_lambda_15_loss: 1.4663 - val_distribution_lambda_16_loss: 0.4740\n", "Epoch 588/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5815 - distribution_lambda_14_loss: 0.6225 - distribution_lambda_15_loss: 1.4756 - distribution_lambda_16_loss: 0.4834 - val_loss: 2.5782 - val_distribution_lambda_14_loss: 0.6371 - val_distribution_lambda_15_loss: 1.4671 - val_distribution_lambda_16_loss: 0.4741\n", "Epoch 589/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6265 - distribution_lambda_14_loss: 0.6495 - distribution_lambda_15_loss: 1.4939 - distribution_lambda_16_loss: 0.4831 - val_loss: 2.5722 - val_distribution_lambda_14_loss: 0.6321 - val_distribution_lambda_15_loss: 1.4667 - val_distribution_lambda_16_loss: 0.4734\n", "Epoch 590/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5994 - distribution_lambda_14_loss: 0.6302 - distribution_lambda_15_loss: 1.4819 - distribution_lambda_16_loss: 0.4872 - val_loss: 2.5597 - val_distribution_lambda_14_loss: 0.6223 - val_distribution_lambda_15_loss: 1.4651 - val_distribution_lambda_16_loss: 0.4723\n", "Epoch 591/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5995 - distribution_lambda_14_loss: 0.6473 - distribution_lambda_15_loss: 1.4712 - distribution_lambda_16_loss: 0.4810 - val_loss: 2.5566 - val_distribution_lambda_14_loss: 0.6208 - val_distribution_lambda_15_loss: 1.4645 - val_distribution_lambda_16_loss: 0.4712\n", "Epoch 592/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6071 - distribution_lambda_14_loss: 0.6260 - distribution_lambda_15_loss: 1.4888 - distribution_lambda_16_loss: 0.4923 - val_loss: 2.5543 - val_distribution_lambda_14_loss: 0.6212 - val_distribution_lambda_15_loss: 1.4624 - val_distribution_lambda_16_loss: 0.4707\n", "Epoch 593/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5872 - distribution_lambda_14_loss: 0.6331 - distribution_lambda_15_loss: 1.4756 - distribution_lambda_16_loss: 0.4785 - val_loss: 2.5608 - val_distribution_lambda_14_loss: 0.6279 - val_distribution_lambda_15_loss: 1.4622 - val_distribution_lambda_16_loss: 0.4706\n", "Epoch 594/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6111 - distribution_lambda_14_loss: 0.6429 - distribution_lambda_15_loss: 1.4827 - distribution_lambda_16_loss: 0.4855 - val_loss: 2.5652 - val_distribution_lambda_14_loss: 0.6321 - val_distribution_lambda_15_loss: 1.4628 - val_distribution_lambda_16_loss: 0.4703\n", "Epoch 595/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5916 - distribution_lambda_14_loss: 0.6330 - distribution_lambda_15_loss: 1.4752 - distribution_lambda_16_loss: 0.4833 - val_loss: 2.5545 - val_distribution_lambda_14_loss: 0.6236 - val_distribution_lambda_15_loss: 1.4615 - val_distribution_lambda_16_loss: 0.4694\n", "Epoch 596/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6239 - distribution_lambda_14_loss: 0.6410 - distribution_lambda_15_loss: 1.4924 - distribution_lambda_16_loss: 0.4905 - val_loss: 2.5489 - val_distribution_lambda_14_loss: 0.6200 - val_distribution_lambda_15_loss: 1.4603 - val_distribution_lambda_16_loss: 0.4686\n", "Epoch 597/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5776 - distribution_lambda_14_loss: 0.6230 - distribution_lambda_15_loss: 1.4754 - distribution_lambda_16_loss: 0.4792 - val_loss: 2.5473 - val_distribution_lambda_14_loss: 0.6201 - val_distribution_lambda_15_loss: 1.4591 - val_distribution_lambda_16_loss: 0.4681\n", "Epoch 598/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6006 - distribution_lambda_14_loss: 0.6408 - distribution_lambda_15_loss: 1.4796 - distribution_lambda_16_loss: 0.4802 - val_loss: 2.5471 - val_distribution_lambda_14_loss: 0.6221 - val_distribution_lambda_15_loss: 1.4575 - val_distribution_lambda_16_loss: 0.4674\n", "Epoch 599/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6033 - distribution_lambda_14_loss: 0.6370 - distribution_lambda_15_loss: 1.4880 - distribution_lambda_16_loss: 0.4783 - val_loss: 2.5440 - val_distribution_lambda_14_loss: 0.6203 - val_distribution_lambda_15_loss: 1.4571 - val_distribution_lambda_16_loss: 0.4666\n", "Epoch 600/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5684 - distribution_lambda_14_loss: 0.6204 - distribution_lambda_15_loss: 1.4682 - distribution_lambda_16_loss: 0.4799 - val_loss: 2.5413 - val_distribution_lambda_14_loss: 0.6179 - val_distribution_lambda_15_loss: 1.4573 - val_distribution_lambda_16_loss: 0.4662\n", "Epoch 601/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.5901 - distribution_lambda_14_loss: 0.6238 - distribution_lambda_15_loss: 1.4859 - distribution_lambda_16_loss: 0.4804 - val_loss: 2.5364 - val_distribution_lambda_14_loss: 0.6162 - val_distribution_lambda_15_loss: 1.4542 - val_distribution_lambda_16_loss: 0.4659\n", "Epoch 602/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5803 - distribution_lambda_14_loss: 0.6125 - distribution_lambda_15_loss: 1.4790 - distribution_lambda_16_loss: 0.4888 - val_loss: 2.5370 - val_distribution_lambda_14_loss: 0.6180 - val_distribution_lambda_15_loss: 1.4530 - val_distribution_lambda_16_loss: 0.4659\n", "Epoch 603/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5820 - distribution_lambda_14_loss: 0.6307 - distribution_lambda_15_loss: 1.4765 - distribution_lambda_16_loss: 0.4748 - val_loss: 2.5391 - val_distribution_lambda_14_loss: 0.6207 - val_distribution_lambda_15_loss: 1.4526 - val_distribution_lambda_16_loss: 0.4659\n", "Epoch 604/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6046 - distribution_lambda_14_loss: 0.6361 - distribution_lambda_15_loss: 1.4865 - distribution_lambda_16_loss: 0.4820 - val_loss: 2.5410 - val_distribution_lambda_14_loss: 0.6223 - val_distribution_lambda_15_loss: 1.4534 - val_distribution_lambda_16_loss: 0.4652\n", "Epoch 605/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5919 - distribution_lambda_14_loss: 0.6332 - distribution_lambda_15_loss: 1.4836 - distribution_lambda_16_loss: 0.4751 - val_loss: 2.5445 - val_distribution_lambda_14_loss: 0.6230 - val_distribution_lambda_15_loss: 1.4568 - val_distribution_lambda_16_loss: 0.4648\n", "Epoch 606/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6048 - distribution_lambda_14_loss: 0.6411 - distribution_lambda_15_loss: 1.4886 - distribution_lambda_16_loss: 0.4750 - val_loss: 2.5402 - val_distribution_lambda_14_loss: 0.6198 - val_distribution_lambda_15_loss: 1.4558 - val_distribution_lambda_16_loss: 0.4646\n", "Epoch 607/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5827 - distribution_lambda_14_loss: 0.6388 - distribution_lambda_15_loss: 1.4725 - distribution_lambda_16_loss: 0.4714 - val_loss: 2.5379 - val_distribution_lambda_14_loss: 0.6189 - val_distribution_lambda_15_loss: 1.4548 - val_distribution_lambda_16_loss: 0.4642\n", "Epoch 608/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5959 - distribution_lambda_14_loss: 0.6383 - distribution_lambda_15_loss: 1.4785 - distribution_lambda_16_loss: 0.4791 - val_loss: 2.5397 - val_distribution_lambda_14_loss: 0.6232 - val_distribution_lambda_15_loss: 1.4528 - val_distribution_lambda_16_loss: 0.4637\n", "Epoch 609/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5808 - distribution_lambda_14_loss: 0.6343 - distribution_lambda_15_loss: 1.4699 - distribution_lambda_16_loss: 0.4766 - val_loss: 2.5535 - val_distribution_lambda_14_loss: 0.6350 - val_distribution_lambda_15_loss: 1.4546 - val_distribution_lambda_16_loss: 0.4639\n", "Epoch 610/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6039 - distribution_lambda_14_loss: 0.6318 - distribution_lambda_15_loss: 1.4944 - distribution_lambda_16_loss: 0.4777 - val_loss: 2.5647 - val_distribution_lambda_14_loss: 0.6375 - val_distribution_lambda_15_loss: 1.4632 - val_distribution_lambda_16_loss: 0.4640\n", "Epoch 611/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5765 - distribution_lambda_14_loss: 0.6187 - distribution_lambda_15_loss: 1.4848 - distribution_lambda_16_loss: 0.4730 - val_loss: 2.5559 - val_distribution_lambda_14_loss: 0.6294 - val_distribution_lambda_15_loss: 1.4629 - val_distribution_lambda_16_loss: 0.4636\n", "Epoch 612/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5963 - distribution_lambda_14_loss: 0.6340 - distribution_lambda_15_loss: 1.4811 - distribution_lambda_16_loss: 0.4812 - val_loss: 2.5460 - val_distribution_lambda_14_loss: 0.6226 - val_distribution_lambda_15_loss: 1.4606 - val_distribution_lambda_16_loss: 0.4628\n", "Epoch 613/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5891 - distribution_lambda_14_loss: 0.6234 - distribution_lambda_15_loss: 1.4875 - distribution_lambda_16_loss: 0.4782 - val_loss: 2.5431 - val_distribution_lambda_14_loss: 0.6205 - val_distribution_lambda_15_loss: 1.4604 - val_distribution_lambda_16_loss: 0.4622\n", "Epoch 614/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6041 - distribution_lambda_14_loss: 0.6260 - distribution_lambda_15_loss: 1.4914 - distribution_lambda_16_loss: 0.4867 - val_loss: 2.5415 - val_distribution_lambda_14_loss: 0.6208 - val_distribution_lambda_15_loss: 1.4588 - val_distribution_lambda_16_loss: 0.4619\n", "Epoch 615/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6073 - distribution_lambda_14_loss: 0.6373 - distribution_lambda_15_loss: 1.4904 - distribution_lambda_16_loss: 0.4795 - val_loss: 2.5403 - val_distribution_lambda_14_loss: 0.6222 - val_distribution_lambda_15_loss: 1.4564 - val_distribution_lambda_16_loss: 0.4617\n", "Epoch 616/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6063 - distribution_lambda_14_loss: 0.6341 - distribution_lambda_15_loss: 1.4860 - distribution_lambda_16_loss: 0.4862 - val_loss: 2.5489 - val_distribution_lambda_14_loss: 0.6269 - val_distribution_lambda_15_loss: 1.4597 - val_distribution_lambda_16_loss: 0.4622\n", "Epoch 617/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6096 - distribution_lambda_14_loss: 0.6391 - distribution_lambda_15_loss: 1.4926 - distribution_lambda_16_loss: 0.4779 - val_loss: 2.5519 - val_distribution_lambda_14_loss: 0.6250 - val_distribution_lambda_15_loss: 1.4641 - val_distribution_lambda_16_loss: 0.4628\n", "Epoch 618/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5888 - distribution_lambda_14_loss: 0.6308 - distribution_lambda_15_loss: 1.4812 - distribution_lambda_16_loss: 0.4767 - val_loss: 2.5495 - val_distribution_lambda_14_loss: 0.6226 - val_distribution_lambda_15_loss: 1.4643 - val_distribution_lambda_16_loss: 0.4626\n", "Epoch 619/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5848 - distribution_lambda_14_loss: 0.6334 - distribution_lambda_15_loss: 1.4766 - distribution_lambda_16_loss: 0.4749 - val_loss: 2.5465 - val_distribution_lambda_14_loss: 0.6218 - val_distribution_lambda_15_loss: 1.4623 - val_distribution_lambda_16_loss: 0.4624\n", "Epoch 620/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5932 - distribution_lambda_14_loss: 0.6324 - distribution_lambda_15_loss: 1.4819 - distribution_lambda_16_loss: 0.4789 - val_loss: 2.5458 - val_distribution_lambda_14_loss: 0.6229 - val_distribution_lambda_15_loss: 1.4606 - val_distribution_lambda_16_loss: 0.4623\n", "Epoch 621/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.6050 - distribution_lambda_14_loss: 0.6283 - distribution_lambda_15_loss: 1.4954 - distribution_lambda_16_loss: 0.4813 - val_loss: 2.5419 - val_distribution_lambda_14_loss: 0.6218 - val_distribution_lambda_15_loss: 1.4582 - val_distribution_lambda_16_loss: 0.4619\n", "Epoch 622/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5732 - distribution_lambda_14_loss: 0.6257 - distribution_lambda_15_loss: 1.4738 - distribution_lambda_16_loss: 0.4736 - val_loss: 2.5377 - val_distribution_lambda_14_loss: 0.6206 - val_distribution_lambda_15_loss: 1.4558 - val_distribution_lambda_16_loss: 0.4613\n", "Epoch 623/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5900 - distribution_lambda_14_loss: 0.6256 - distribution_lambda_15_loss: 1.4885 - distribution_lambda_16_loss: 0.4759 - val_loss: 2.5321 - val_distribution_lambda_14_loss: 0.6172 - val_distribution_lambda_15_loss: 1.4540 - val_distribution_lambda_16_loss: 0.4609\n", "Epoch 624/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5693 - distribution_lambda_14_loss: 0.6151 - distribution_lambda_15_loss: 1.4775 - distribution_lambda_16_loss: 0.4768 - val_loss: 2.5317 - val_distribution_lambda_14_loss: 0.6174 - val_distribution_lambda_15_loss: 1.4534 - val_distribution_lambda_16_loss: 0.4610\n", "Epoch 625/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.5983 - distribution_lambda_14_loss: 0.6462 - distribution_lambda_15_loss: 1.4805 - distribution_lambda_16_loss: 0.4716 - val_loss: 2.5335 - val_distribution_lambda_14_loss: 0.6204 - val_distribution_lambda_15_loss: 1.4526 - val_distribution_lambda_16_loss: 0.4605\n", "Epoch 626/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5549 - distribution_lambda_14_loss: 0.6164 - distribution_lambda_15_loss: 1.4665 - distribution_lambda_16_loss: 0.4720 - val_loss: 2.5375 - val_distribution_lambda_14_loss: 0.6250 - val_distribution_lambda_15_loss: 1.4523 - val_distribution_lambda_16_loss: 0.4602\n", "Epoch 627/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5689 - distribution_lambda_14_loss: 0.6398 - distribution_lambda_15_loss: 1.4590 - distribution_lambda_16_loss: 0.4701 - val_loss: 2.5352 - val_distribution_lambda_14_loss: 0.6237 - val_distribution_lambda_15_loss: 1.4515 - val_distribution_lambda_16_loss: 0.4600\n", "Epoch 628/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5865 - distribution_lambda_14_loss: 0.6320 - distribution_lambda_15_loss: 1.4793 - distribution_lambda_16_loss: 0.4752 - val_loss: 2.5378 - val_distribution_lambda_14_loss: 0.6235 - val_distribution_lambda_15_loss: 1.4535 - val_distribution_lambda_16_loss: 0.4608\n", "Epoch 629/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5606 - distribution_lambda_14_loss: 0.6128 - distribution_lambda_15_loss: 1.4724 - distribution_lambda_16_loss: 0.4754 - val_loss: 2.5378 - val_distribution_lambda_14_loss: 0.6226 - val_distribution_lambda_15_loss: 1.4540 - val_distribution_lambda_16_loss: 0.4613\n", "Epoch 630/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5776 - distribution_lambda_14_loss: 0.6281 - distribution_lambda_15_loss: 1.4742 - distribution_lambda_16_loss: 0.4753 - val_loss: 2.5317 - val_distribution_lambda_14_loss: 0.6193 - val_distribution_lambda_15_loss: 1.4517 - val_distribution_lambda_16_loss: 0.4607\n", "Epoch 631/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5887 - distribution_lambda_14_loss: 0.6245 - distribution_lambda_15_loss: 1.4857 - distribution_lambda_16_loss: 0.4785 - val_loss: 2.5292 - val_distribution_lambda_14_loss: 0.6179 - val_distribution_lambda_15_loss: 1.4511 - val_distribution_lambda_16_loss: 0.4603\n", "Epoch 632/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5558 - distribution_lambda_14_loss: 0.6198 - distribution_lambda_15_loss: 1.4637 - distribution_lambda_16_loss: 0.4723 - val_loss: 2.5283 - val_distribution_lambda_14_loss: 0.6169 - val_distribution_lambda_15_loss: 1.4510 - val_distribution_lambda_16_loss: 0.4604\n", "Epoch 633/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5642 - distribution_lambda_14_loss: 0.6154 - distribution_lambda_15_loss: 1.4714 - distribution_lambda_16_loss: 0.4775 - val_loss: 2.5258 - val_distribution_lambda_14_loss: 0.6158 - val_distribution_lambda_15_loss: 1.4497 - val_distribution_lambda_16_loss: 0.4603\n", "Epoch 634/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5943 - distribution_lambda_14_loss: 0.6273 - distribution_lambda_15_loss: 1.4894 - distribution_lambda_16_loss: 0.4775 - val_loss: 2.5226 - val_distribution_lambda_14_loss: 0.6140 - val_distribution_lambda_15_loss: 1.4483 - val_distribution_lambda_16_loss: 0.4603\n", "Epoch 635/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5670 - distribution_lambda_14_loss: 0.6164 - distribution_lambda_15_loss: 1.4786 - distribution_lambda_16_loss: 0.4720 - val_loss: 2.5196 - val_distribution_lambda_14_loss: 0.6135 - val_distribution_lambda_15_loss: 1.4463 - val_distribution_lambda_16_loss: 0.4598\n", "Epoch 636/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5667 - distribution_lambda_14_loss: 0.6139 - distribution_lambda_15_loss: 1.4805 - distribution_lambda_16_loss: 0.4723 - val_loss: 2.5215 - val_distribution_lambda_14_loss: 0.6148 - val_distribution_lambda_15_loss: 1.4472 - val_distribution_lambda_16_loss: 0.4596\n", "Epoch 637/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5628 - distribution_lambda_14_loss: 0.6107 - distribution_lambda_15_loss: 1.4790 - distribution_lambda_16_loss: 0.4731 - val_loss: 2.5221 - val_distribution_lambda_14_loss: 0.6157 - val_distribution_lambda_15_loss: 1.4475 - val_distribution_lambda_16_loss: 0.4590\n", "Epoch 638/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5665 - distribution_lambda_14_loss: 0.6122 - distribution_lambda_15_loss: 1.4816 - distribution_lambda_16_loss: 0.4727 - val_loss: 2.5296 - val_distribution_lambda_14_loss: 0.6210 - val_distribution_lambda_15_loss: 1.4500 - val_distribution_lambda_16_loss: 0.4586\n", "Epoch 639/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5762 - distribution_lambda_14_loss: 0.6195 - distribution_lambda_15_loss: 1.4842 - distribution_lambda_16_loss: 0.4725 - val_loss: 2.5380 - val_distribution_lambda_14_loss: 0.6260 - val_distribution_lambda_15_loss: 1.4536 - val_distribution_lambda_16_loss: 0.4584\n", "Epoch 640/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5835 - distribution_lambda_14_loss: 0.6354 - distribution_lambda_15_loss: 1.4727 - distribution_lambda_16_loss: 0.4755 - val_loss: 2.5327 - val_distribution_lambda_14_loss: 0.6228 - val_distribution_lambda_15_loss: 1.4518 - val_distribution_lambda_16_loss: 0.4580\n", "Epoch 641/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5636 - distribution_lambda_14_loss: 0.6191 - distribution_lambda_15_loss: 1.4747 - distribution_lambda_16_loss: 0.4698 - val_loss: 2.5245 - val_distribution_lambda_14_loss: 0.6186 - val_distribution_lambda_15_loss: 1.4489 - val_distribution_lambda_16_loss: 0.4570\n", "Epoch 642/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5444 - distribution_lambda_14_loss: 0.6125 - distribution_lambda_15_loss: 1.4614 - distribution_lambda_16_loss: 0.4706 - val_loss: 2.5183 - val_distribution_lambda_14_loss: 0.6155 - val_distribution_lambda_15_loss: 1.4468 - val_distribution_lambda_16_loss: 0.4560\n", "Epoch 643/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5569 - distribution_lambda_14_loss: 0.6093 - distribution_lambda_15_loss: 1.4756 - distribution_lambda_16_loss: 0.4719 - val_loss: 2.5153 - val_distribution_lambda_14_loss: 0.6145 - val_distribution_lambda_15_loss: 1.4455 - val_distribution_lambda_16_loss: 0.4552\n", "Epoch 644/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5457 - distribution_lambda_14_loss: 0.6246 - distribution_lambda_15_loss: 1.4605 - distribution_lambda_16_loss: 0.4605 - val_loss: 2.5145 - val_distribution_lambda_14_loss: 0.6149 - val_distribution_lambda_15_loss: 1.4447 - val_distribution_lambda_16_loss: 0.4549\n", "Epoch 645/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5487 - distribution_lambda_14_loss: 0.6188 - distribution_lambda_15_loss: 1.4644 - distribution_lambda_16_loss: 0.4655 - val_loss: 2.5136 - val_distribution_lambda_14_loss: 0.6146 - val_distribution_lambda_15_loss: 1.4444 - val_distribution_lambda_16_loss: 0.4546\n", "Epoch 646/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5616 - distribution_lambda_14_loss: 0.6199 - distribution_lambda_15_loss: 1.4700 - distribution_lambda_16_loss: 0.4717 - val_loss: 2.5128 - val_distribution_lambda_14_loss: 0.6137 - val_distribution_lambda_15_loss: 1.4444 - val_distribution_lambda_16_loss: 0.4547\n", "Epoch 647/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5677 - distribution_lambda_14_loss: 0.6179 - distribution_lambda_15_loss: 1.4827 - distribution_lambda_16_loss: 0.4670 - val_loss: 2.5126 - val_distribution_lambda_14_loss: 0.6140 - val_distribution_lambda_15_loss: 1.4437 - val_distribution_lambda_16_loss: 0.4549\n", "Epoch 648/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5295 - distribution_lambda_14_loss: 0.6053 - distribution_lambda_15_loss: 1.4565 - distribution_lambda_16_loss: 0.4677 - val_loss: 2.5145 - val_distribution_lambda_14_loss: 0.6179 - val_distribution_lambda_15_loss: 1.4421 - val_distribution_lambda_16_loss: 0.4545\n", "Epoch 649/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.5612 - distribution_lambda_14_loss: 0.6083 - distribution_lambda_15_loss: 1.4723 - distribution_lambda_16_loss: 0.4807 - val_loss: 2.5083 - val_distribution_lambda_14_loss: 0.6115 - val_distribution_lambda_15_loss: 1.4430 - val_distribution_lambda_16_loss: 0.4538\n", "Epoch 650/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5632 - distribution_lambda_14_loss: 0.6131 - distribution_lambda_15_loss: 1.4799 - distribution_lambda_16_loss: 0.4702 - val_loss: 2.5036 - val_distribution_lambda_14_loss: 0.6034 - val_distribution_lambda_15_loss: 1.4463 - val_distribution_lambda_16_loss: 0.4539\n", "Epoch 651/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5594 - distribution_lambda_14_loss: 0.6148 - distribution_lambda_15_loss: 1.4787 - distribution_lambda_16_loss: 0.4659 - val_loss: 2.5016 - val_distribution_lambda_14_loss: 0.6029 - val_distribution_lambda_15_loss: 1.4447 - val_distribution_lambda_16_loss: 0.4540\n", "Epoch 652/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5528 - distribution_lambda_14_loss: 0.6138 - distribution_lambda_15_loss: 1.4656 - distribution_lambda_16_loss: 0.4734 - val_loss: 2.4976 - val_distribution_lambda_14_loss: 0.6016 - val_distribution_lambda_15_loss: 1.4425 - val_distribution_lambda_16_loss: 0.4535\n", "Epoch 653/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.5693 - distribution_lambda_14_loss: 0.6266 - distribution_lambda_15_loss: 1.4727 - distribution_lambda_16_loss: 0.4700 - val_loss: 2.4969 - val_distribution_lambda_14_loss: 0.6028 - val_distribution_lambda_15_loss: 1.4410 - val_distribution_lambda_16_loss: 0.4531\n", "Epoch 654/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5592 - distribution_lambda_14_loss: 0.6270 - distribution_lambda_15_loss: 1.4669 - distribution_lambda_16_loss: 0.4653 - val_loss: 2.4961 - val_distribution_lambda_14_loss: 0.6039 - val_distribution_lambda_15_loss: 1.4396 - val_distribution_lambda_16_loss: 0.4526\n", "Epoch 655/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5532 - distribution_lambda_14_loss: 0.6252 - distribution_lambda_15_loss: 1.4642 - distribution_lambda_16_loss: 0.4638 - val_loss: 2.5032 - val_distribution_lambda_14_loss: 0.6098 - val_distribution_lambda_15_loss: 1.4409 - val_distribution_lambda_16_loss: 0.4525\n", "Epoch 656/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5665 - distribution_lambda_14_loss: 0.6066 - distribution_lambda_15_loss: 1.4823 - distribution_lambda_16_loss: 0.4775 - val_loss: 2.5126 - val_distribution_lambda_14_loss: 0.6134 - val_distribution_lambda_15_loss: 1.4462 - val_distribution_lambda_16_loss: 0.4530\n", "Epoch 657/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5522 - distribution_lambda_14_loss: 0.6234 - distribution_lambda_15_loss: 1.4659 - distribution_lambda_16_loss: 0.4629 - val_loss: 2.5166 - val_distribution_lambda_14_loss: 0.6135 - val_distribution_lambda_15_loss: 1.4500 - val_distribution_lambda_16_loss: 0.4532\n", "Epoch 658/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5577 - distribution_lambda_14_loss: 0.6169 - distribution_lambda_15_loss: 1.4706 - distribution_lambda_16_loss: 0.4702 - val_loss: 2.5190 - val_distribution_lambda_14_loss: 0.6149 - val_distribution_lambda_15_loss: 1.4516 - val_distribution_lambda_16_loss: 0.4525\n", "Epoch 659/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5691 - distribution_lambda_14_loss: 0.6278 - distribution_lambda_15_loss: 1.4727 - distribution_lambda_16_loss: 0.4686 - val_loss: 2.5180 - val_distribution_lambda_14_loss: 0.6155 - val_distribution_lambda_15_loss: 1.4507 - val_distribution_lambda_16_loss: 0.4518\n", "Epoch 660/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5611 - distribution_lambda_14_loss: 0.6173 - distribution_lambda_15_loss: 1.4730 - distribution_lambda_16_loss: 0.4708 - val_loss: 2.5096 - val_distribution_lambda_14_loss: 0.6131 - val_distribution_lambda_15_loss: 1.4452 - val_distribution_lambda_16_loss: 0.4513\n", "Epoch 661/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5673 - distribution_lambda_14_loss: 0.6200 - distribution_lambda_15_loss: 1.4742 - distribution_lambda_16_loss: 0.4731 - val_loss: 2.4995 - val_distribution_lambda_14_loss: 0.6075 - val_distribution_lambda_15_loss: 1.4410 - val_distribution_lambda_16_loss: 0.4510\n", "Epoch 662/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5373 - distribution_lambda_14_loss: 0.5979 - distribution_lambda_15_loss: 1.4676 - distribution_lambda_16_loss: 0.4717 - val_loss: 2.4946 - val_distribution_lambda_14_loss: 0.6048 - val_distribution_lambda_15_loss: 1.4393 - val_distribution_lambda_16_loss: 0.4505\n", "Epoch 663/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5412 - distribution_lambda_14_loss: 0.6173 - distribution_lambda_15_loss: 1.4576 - distribution_lambda_16_loss: 0.4663 - val_loss: 2.4950 - val_distribution_lambda_14_loss: 0.6070 - val_distribution_lambda_15_loss: 1.4374 - val_distribution_lambda_16_loss: 0.4506\n", "Epoch 664/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5491 - distribution_lambda_14_loss: 0.6170 - distribution_lambda_15_loss: 1.4651 - distribution_lambda_16_loss: 0.4670 - val_loss: 2.4967 - val_distribution_lambda_14_loss: 0.6105 - val_distribution_lambda_15_loss: 1.4355 - val_distribution_lambda_16_loss: 0.4507\n", "Epoch 665/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5473 - distribution_lambda_14_loss: 0.6194 - distribution_lambda_15_loss: 1.4685 - distribution_lambda_16_loss: 0.4595 - val_loss: 2.4989 - val_distribution_lambda_14_loss: 0.6145 - val_distribution_lambda_15_loss: 1.4338 - val_distribution_lambda_16_loss: 0.4506\n", "Epoch 666/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5484 - distribution_lambda_14_loss: 0.5957 - distribution_lambda_15_loss: 1.4758 - distribution_lambda_16_loss: 0.4769 - val_loss: 2.4864 - val_distribution_lambda_14_loss: 0.6020 - val_distribution_lambda_15_loss: 1.4341 - val_distribution_lambda_16_loss: 0.4503\n", "Epoch 667/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.5294 - distribution_lambda_14_loss: 0.6020 - distribution_lambda_15_loss: 1.4692 - distribution_lambda_16_loss: 0.4582 - val_loss: 2.4814 - val_distribution_lambda_14_loss: 0.5968 - val_distribution_lambda_15_loss: 1.4346 - val_distribution_lambda_16_loss: 0.4500\n", "Epoch 668/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5567 - distribution_lambda_14_loss: 0.6214 - distribution_lambda_15_loss: 1.4696 - distribution_lambda_16_loss: 0.4657 - val_loss: 2.4868 - val_distribution_lambda_14_loss: 0.6006 - val_distribution_lambda_15_loss: 1.4354 - val_distribution_lambda_16_loss: 0.4509\n", "Epoch 669/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5671 - distribution_lambda_14_loss: 0.6189 - distribution_lambda_15_loss: 1.4811 - distribution_lambda_16_loss: 0.4671 - val_loss: 2.4832 - val_distribution_lambda_14_loss: 0.5954 - val_distribution_lambda_15_loss: 1.4359 - val_distribution_lambda_16_loss: 0.4519\n", "Epoch 670/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5196 - distribution_lambda_14_loss: 0.6059 - distribution_lambda_15_loss: 1.4569 - distribution_lambda_16_loss: 0.4567 - val_loss: 2.4804 - val_distribution_lambda_14_loss: 0.5935 - val_distribution_lambda_15_loss: 1.4346 - val_distribution_lambda_16_loss: 0.4523\n", "Epoch 671/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5164 - distribution_lambda_14_loss: 0.5928 - distribution_lambda_15_loss: 1.4597 - distribution_lambda_16_loss: 0.4639 - val_loss: 2.4798 - val_distribution_lambda_14_loss: 0.5957 - val_distribution_lambda_15_loss: 1.4324 - val_distribution_lambda_16_loss: 0.4517\n", "Epoch 672/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5171 - distribution_lambda_14_loss: 0.5922 - distribution_lambda_15_loss: 1.4615 - distribution_lambda_16_loss: 0.4634 - val_loss: 2.4822 - val_distribution_lambda_14_loss: 0.5998 - val_distribution_lambda_15_loss: 1.4327 - val_distribution_lambda_16_loss: 0.4497\n", "Epoch 673/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.5248 - distribution_lambda_14_loss: 0.6067 - distribution_lambda_15_loss: 1.4569 - distribution_lambda_16_loss: 0.4612 - val_loss: 2.4798 - val_distribution_lambda_14_loss: 0.6002 - val_distribution_lambda_15_loss: 1.4315 - val_distribution_lambda_16_loss: 0.4482\n", "Epoch 674/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5259 - distribution_lambda_14_loss: 0.6041 - distribution_lambda_15_loss: 1.4599 - distribution_lambda_16_loss: 0.4619 - val_loss: 2.4762 - val_distribution_lambda_14_loss: 0.5988 - val_distribution_lambda_15_loss: 1.4300 - val_distribution_lambda_16_loss: 0.4474\n", "Epoch 675/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5215 - distribution_lambda_14_loss: 0.6028 - distribution_lambda_15_loss: 1.4575 - distribution_lambda_16_loss: 0.4612 - val_loss: 2.4753 - val_distribution_lambda_14_loss: 0.5989 - val_distribution_lambda_15_loss: 1.4293 - val_distribution_lambda_16_loss: 0.4471\n", "Epoch 676/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5310 - distribution_lambda_14_loss: 0.6003 - distribution_lambda_15_loss: 1.4612 - distribution_lambda_16_loss: 0.4694 - val_loss: 2.4758 - val_distribution_lambda_14_loss: 0.5997 - val_distribution_lambda_15_loss: 1.4289 - val_distribution_lambda_16_loss: 0.4472\n", "Epoch 677/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5388 - distribution_lambda_14_loss: 0.6088 - distribution_lambda_15_loss: 1.4665 - distribution_lambda_16_loss: 0.4635 - val_loss: 2.4815 - val_distribution_lambda_14_loss: 0.6035 - val_distribution_lambda_15_loss: 1.4299 - val_distribution_lambda_16_loss: 0.4481\n", "Epoch 678/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5194 - distribution_lambda_14_loss: 0.5916 - distribution_lambda_15_loss: 1.4677 - distribution_lambda_16_loss: 0.4601 - val_loss: 2.4751 - val_distribution_lambda_14_loss: 0.5949 - val_distribution_lambda_15_loss: 1.4318 - val_distribution_lambda_16_loss: 0.4485\n", "Epoch 679/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5318 - distribution_lambda_14_loss: 0.6054 - distribution_lambda_15_loss: 1.4665 - distribution_lambda_16_loss: 0.4598 - val_loss: 2.4701 - val_distribution_lambda_14_loss: 0.5888 - val_distribution_lambda_15_loss: 1.4331 - val_distribution_lambda_16_loss: 0.4482\n", "Epoch 680/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5350 - distribution_lambda_14_loss: 0.5966 - distribution_lambda_15_loss: 1.4699 - distribution_lambda_16_loss: 0.4684 - val_loss: 2.4683 - val_distribution_lambda_14_loss: 0.5889 - val_distribution_lambda_15_loss: 1.4311 - val_distribution_lambda_16_loss: 0.4482\n", "Epoch 681/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5755 - distribution_lambda_14_loss: 0.6244 - distribution_lambda_15_loss: 1.4834 - distribution_lambda_16_loss: 0.4678 - val_loss: 2.4663 - val_distribution_lambda_14_loss: 0.5882 - val_distribution_lambda_15_loss: 1.4306 - val_distribution_lambda_16_loss: 0.4476\n", "Epoch 682/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5185 - distribution_lambda_14_loss: 0.5982 - distribution_lambda_15_loss: 1.4552 - distribution_lambda_16_loss: 0.4651 - val_loss: 2.4624 - val_distribution_lambda_14_loss: 0.5852 - val_distribution_lambda_15_loss: 1.4303 - val_distribution_lambda_16_loss: 0.4469\n", "Epoch 683/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5345 - distribution_lambda_14_loss: 0.6072 - distribution_lambda_15_loss: 1.4599 - distribution_lambda_16_loss: 0.4674 - val_loss: 2.4655 - val_distribution_lambda_14_loss: 0.5869 - val_distribution_lambda_15_loss: 1.4322 - val_distribution_lambda_16_loss: 0.4464\n", "Epoch 684/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5266 - distribution_lambda_14_loss: 0.5935 - distribution_lambda_15_loss: 1.4645 - distribution_lambda_16_loss: 0.4687 - val_loss: 2.4632 - val_distribution_lambda_14_loss: 0.5862 - val_distribution_lambda_15_loss: 1.4312 - val_distribution_lambda_16_loss: 0.4458\n", "Epoch 685/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5171 - distribution_lambda_14_loss: 0.6080 - distribution_lambda_15_loss: 1.4535 - distribution_lambda_16_loss: 0.4556 - val_loss: 2.4579 - val_distribution_lambda_14_loss: 0.5837 - val_distribution_lambda_15_loss: 1.4283 - val_distribution_lambda_16_loss: 0.4458\n", "Epoch 686/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5553 - distribution_lambda_14_loss: 0.6108 - distribution_lambda_15_loss: 1.4753 - distribution_lambda_16_loss: 0.4692 - val_loss: 2.4568 - val_distribution_lambda_14_loss: 0.5834 - val_distribution_lambda_15_loss: 1.4273 - val_distribution_lambda_16_loss: 0.4461\n", "Epoch 687/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5326 - distribution_lambda_14_loss: 0.6086 - distribution_lambda_15_loss: 1.4617 - distribution_lambda_16_loss: 0.4623 - val_loss: 2.4591 - val_distribution_lambda_14_loss: 0.5865 - val_distribution_lambda_15_loss: 1.4256 - val_distribution_lambda_16_loss: 0.4470\n", "Epoch 688/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5412 - distribution_lambda_14_loss: 0.6099 - distribution_lambda_15_loss: 1.4625 - distribution_lambda_16_loss: 0.4688 - val_loss: 2.4600 - val_distribution_lambda_14_loss: 0.5881 - val_distribution_lambda_15_loss: 1.4244 - val_distribution_lambda_16_loss: 0.4475\n", "Epoch 689/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5263 - distribution_lambda_14_loss: 0.6029 - distribution_lambda_15_loss: 1.4590 - distribution_lambda_16_loss: 0.4644 - val_loss: 2.4526 - val_distribution_lambda_14_loss: 0.5831 - val_distribution_lambda_15_loss: 1.4230 - val_distribution_lambda_16_loss: 0.4465\n", "Epoch 690/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5270 - distribution_lambda_14_loss: 0.6155 - distribution_lambda_15_loss: 1.4583 - distribution_lambda_16_loss: 0.4532 - val_loss: 2.4475 - val_distribution_lambda_14_loss: 0.5807 - val_distribution_lambda_15_loss: 1.4214 - val_distribution_lambda_16_loss: 0.4453\n", "Epoch 691/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5344 - distribution_lambda_14_loss: 0.6059 - distribution_lambda_15_loss: 1.4639 - distribution_lambda_16_loss: 0.4646 - val_loss: 2.4450 - val_distribution_lambda_14_loss: 0.5788 - val_distribution_lambda_15_loss: 1.4214 - val_distribution_lambda_16_loss: 0.4448\n", "Epoch 692/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5235 - distribution_lambda_14_loss: 0.5819 - distribution_lambda_15_loss: 1.4733 - distribution_lambda_16_loss: 0.4683 - val_loss: 2.4482 - val_distribution_lambda_14_loss: 0.5808 - val_distribution_lambda_15_loss: 1.4224 - val_distribution_lambda_16_loss: 0.4449\n", "Epoch 693/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5269 - distribution_lambda_14_loss: 0.6003 - distribution_lambda_15_loss: 1.4614 - distribution_lambda_16_loss: 0.4652 - val_loss: 2.4540 - val_distribution_lambda_14_loss: 0.5835 - val_distribution_lambda_15_loss: 1.4259 - val_distribution_lambda_16_loss: 0.4447\n", "Epoch 694/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5008 - distribution_lambda_14_loss: 0.5892 - distribution_lambda_15_loss: 1.4592 - distribution_lambda_16_loss: 0.4525 - val_loss: 2.4468 - val_distribution_lambda_14_loss: 0.5780 - val_distribution_lambda_15_loss: 1.4248 - val_distribution_lambda_16_loss: 0.4440\n", "Epoch 695/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5141 - distribution_lambda_14_loss: 0.5984 - distribution_lambda_15_loss: 1.4572 - distribution_lambda_16_loss: 0.4585 - val_loss: 2.4456 - val_distribution_lambda_14_loss: 0.5773 - val_distribution_lambda_15_loss: 1.4248 - val_distribution_lambda_16_loss: 0.4435\n", "Epoch 696/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4961 - distribution_lambda_14_loss: 0.5884 - distribution_lambda_15_loss: 1.4499 - distribution_lambda_16_loss: 0.4578 - val_loss: 2.4477 - val_distribution_lambda_14_loss: 0.5792 - val_distribution_lambda_15_loss: 1.4255 - val_distribution_lambda_16_loss: 0.4430\n", "Epoch 697/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.5043 - distribution_lambda_14_loss: 0.5937 - distribution_lambda_15_loss: 1.4529 - distribution_lambda_16_loss: 0.4576 - val_loss: 2.4445 - val_distribution_lambda_14_loss: 0.5792 - val_distribution_lambda_15_loss: 1.4226 - val_distribution_lambda_16_loss: 0.4427\n", "Epoch 698/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5071 - distribution_lambda_14_loss: 0.5886 - distribution_lambda_15_loss: 1.4536 - distribution_lambda_16_loss: 0.4649 - val_loss: 2.4419 - val_distribution_lambda_14_loss: 0.5789 - val_distribution_lambda_15_loss: 1.4205 - val_distribution_lambda_16_loss: 0.4425\n", "Epoch 699/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5191 - distribution_lambda_14_loss: 0.6037 - distribution_lambda_15_loss: 1.4599 - distribution_lambda_16_loss: 0.4555 - val_loss: 2.4456 - val_distribution_lambda_14_loss: 0.5829 - val_distribution_lambda_15_loss: 1.4205 - val_distribution_lambda_16_loss: 0.4423\n", "Epoch 700/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4871 - distribution_lambda_14_loss: 0.5908 - distribution_lambda_15_loss: 1.4481 - distribution_lambda_16_loss: 0.4482 - val_loss: 2.4495 - val_distribution_lambda_14_loss: 0.5846 - val_distribution_lambda_15_loss: 1.4226 - val_distribution_lambda_16_loss: 0.4423\n", "Epoch 701/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5138 - distribution_lambda_14_loss: 0.6011 - distribution_lambda_15_loss: 1.4478 - distribution_lambda_16_loss: 0.4648 - val_loss: 2.4583 - val_distribution_lambda_14_loss: 0.5873 - val_distribution_lambda_15_loss: 1.4279 - val_distribution_lambda_16_loss: 0.4431\n", "Epoch 702/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5070 - distribution_lambda_14_loss: 0.5923 - distribution_lambda_15_loss: 1.4613 - distribution_lambda_16_loss: 0.4534 - val_loss: 2.4646 - val_distribution_lambda_14_loss: 0.5899 - val_distribution_lambda_15_loss: 1.4309 - val_distribution_lambda_16_loss: 0.4438\n", "Epoch 703/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5105 - distribution_lambda_14_loss: 0.5995 - distribution_lambda_15_loss: 1.4503 - distribution_lambda_16_loss: 0.4607 - val_loss: 2.4553 - val_distribution_lambda_14_loss: 0.5825 - val_distribution_lambda_15_loss: 1.4286 - val_distribution_lambda_16_loss: 0.4442\n", "Epoch 704/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5014 - distribution_lambda_14_loss: 0.5843 - distribution_lambda_15_loss: 1.4536 - distribution_lambda_16_loss: 0.4635 - val_loss: 2.4483 - val_distribution_lambda_14_loss: 0.5773 - val_distribution_lambda_15_loss: 1.4270 - val_distribution_lambda_16_loss: 0.4439\n", "Epoch 705/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5006 - distribution_lambda_14_loss: 0.5944 - distribution_lambda_15_loss: 1.4499 - distribution_lambda_16_loss: 0.4563 - val_loss: 2.4517 - val_distribution_lambda_14_loss: 0.5808 - val_distribution_lambda_15_loss: 1.4267 - val_distribution_lambda_16_loss: 0.4442\n", "Epoch 706/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5212 - distribution_lambda_14_loss: 0.6009 - distribution_lambda_15_loss: 1.4595 - distribution_lambda_16_loss: 0.4608 - val_loss: 2.4547 - val_distribution_lambda_14_loss: 0.5834 - val_distribution_lambda_15_loss: 1.4264 - val_distribution_lambda_16_loss: 0.4449\n", "Epoch 707/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5008 - distribution_lambda_14_loss: 0.5855 - distribution_lambda_15_loss: 1.4605 - distribution_lambda_16_loss: 0.4547 - val_loss: 2.4501 - val_distribution_lambda_14_loss: 0.5777 - val_distribution_lambda_15_loss: 1.4269 - val_distribution_lambda_16_loss: 0.4455\n", "Epoch 708/2000\n", "8/8 [==============================] - 0s 9ms/step - loss: 2.5162 - distribution_lambda_14_loss: 0.5818 - distribution_lambda_15_loss: 1.4648 - distribution_lambda_16_loss: 0.4696 - val_loss: 2.4516 - val_distribution_lambda_14_loss: 0.5816 - val_distribution_lambda_15_loss: 1.4248 - val_distribution_lambda_16_loss: 0.4453\n", "Epoch 709/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5138 - distribution_lambda_14_loss: 0.5969 - distribution_lambda_15_loss: 1.4581 - distribution_lambda_16_loss: 0.4588 - val_loss: 2.4511 - val_distribution_lambda_14_loss: 0.5825 - val_distribution_lambda_15_loss: 1.4247 - val_distribution_lambda_16_loss: 0.4438\n", "Epoch 710/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5226 - distribution_lambda_14_loss: 0.5870 - distribution_lambda_15_loss: 1.4686 - distribution_lambda_16_loss: 0.4671 - val_loss: 2.4467 - val_distribution_lambda_14_loss: 0.5810 - val_distribution_lambda_15_loss: 1.4235 - val_distribution_lambda_16_loss: 0.4422\n", "Epoch 711/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5197 - distribution_lambda_14_loss: 0.5892 - distribution_lambda_15_loss: 1.4606 - distribution_lambda_16_loss: 0.4698 - val_loss: 2.4471 - val_distribution_lambda_14_loss: 0.5820 - val_distribution_lambda_15_loss: 1.4234 - val_distribution_lambda_16_loss: 0.4417\n", "Epoch 712/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5143 - distribution_lambda_14_loss: 0.5856 - distribution_lambda_15_loss: 1.4644 - distribution_lambda_16_loss: 0.4643 - val_loss: 2.4525 - val_distribution_lambda_14_loss: 0.5879 - val_distribution_lambda_15_loss: 1.4230 - val_distribution_lambda_16_loss: 0.4417\n", "Epoch 713/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4858 - distribution_lambda_14_loss: 0.5917 - distribution_lambda_15_loss: 1.4386 - distribution_lambda_16_loss: 0.4555 - val_loss: 2.4481 - val_distribution_lambda_14_loss: 0.5852 - val_distribution_lambda_15_loss: 1.4216 - val_distribution_lambda_16_loss: 0.4413\n", "Epoch 714/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5276 - distribution_lambda_14_loss: 0.6105 - distribution_lambda_15_loss: 1.4627 - distribution_lambda_16_loss: 0.4545 - val_loss: 2.4436 - val_distribution_lambda_14_loss: 0.5809 - val_distribution_lambda_15_loss: 1.4217 - val_distribution_lambda_16_loss: 0.4410\n", "Epoch 715/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4823 - distribution_lambda_14_loss: 0.5833 - distribution_lambda_15_loss: 1.4472 - distribution_lambda_16_loss: 0.4518 - val_loss: 2.4392 - val_distribution_lambda_14_loss: 0.5797 - val_distribution_lambda_15_loss: 1.4190 - val_distribution_lambda_16_loss: 0.4404\n", "Epoch 716/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4995 - distribution_lambda_14_loss: 0.6080 - distribution_lambda_15_loss: 1.4415 - distribution_lambda_16_loss: 0.4499 - val_loss: 2.4360 - val_distribution_lambda_14_loss: 0.5791 - val_distribution_lambda_15_loss: 1.4169 - val_distribution_lambda_16_loss: 0.4400\n", "Epoch 717/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5064 - distribution_lambda_14_loss: 0.5923 - distribution_lambda_15_loss: 1.4570 - distribution_lambda_16_loss: 0.4571 - val_loss: 2.4293 - val_distribution_lambda_14_loss: 0.5747 - val_distribution_lambda_15_loss: 1.4147 - val_distribution_lambda_16_loss: 0.4399\n", "Epoch 718/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5299 - distribution_lambda_14_loss: 0.6134 - distribution_lambda_15_loss: 1.4583 - distribution_lambda_16_loss: 0.4582 - val_loss: 2.4247 - val_distribution_lambda_14_loss: 0.5703 - val_distribution_lambda_15_loss: 1.4142 - val_distribution_lambda_16_loss: 0.4402\n", "Epoch 719/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4882 - distribution_lambda_14_loss: 0.5783 - distribution_lambda_15_loss: 1.4529 - distribution_lambda_16_loss: 0.4570 - val_loss: 2.4221 - val_distribution_lambda_14_loss: 0.5672 - val_distribution_lambda_15_loss: 1.4142 - val_distribution_lambda_16_loss: 0.4406\n", "Epoch 720/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4867 - distribution_lambda_14_loss: 0.5743 - distribution_lambda_15_loss: 1.4513 - distribution_lambda_16_loss: 0.4611 - val_loss: 2.4231 - val_distribution_lambda_14_loss: 0.5676 - val_distribution_lambda_15_loss: 1.4147 - val_distribution_lambda_16_loss: 0.4409\n", "Epoch 721/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.5217 - distribution_lambda_14_loss: 0.6064 - distribution_lambda_15_loss: 1.4591 - distribution_lambda_16_loss: 0.4562 - val_loss: 2.4294 - val_distribution_lambda_14_loss: 0.5736 - val_distribution_lambda_15_loss: 1.4153 - val_distribution_lambda_16_loss: 0.4405\n", "Epoch 722/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4824 - distribution_lambda_14_loss: 0.5812 - distribution_lambda_15_loss: 1.4502 - distribution_lambda_16_loss: 0.4510 - val_loss: 2.4343 - val_distribution_lambda_14_loss: 0.5788 - val_distribution_lambda_15_loss: 1.4161 - val_distribution_lambda_16_loss: 0.4394\n", "Epoch 723/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4750 - distribution_lambda_14_loss: 0.5894 - distribution_lambda_15_loss: 1.4336 - distribution_lambda_16_loss: 0.4520 - val_loss: 2.4310 - val_distribution_lambda_14_loss: 0.5769 - val_distribution_lambda_15_loss: 1.4156 - val_distribution_lambda_16_loss: 0.4384\n", "Epoch 724/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4834 - distribution_lambda_14_loss: 0.5848 - distribution_lambda_15_loss: 1.4451 - distribution_lambda_16_loss: 0.4534 - val_loss: 2.4262 - val_distribution_lambda_14_loss: 0.5719 - val_distribution_lambda_15_loss: 1.4161 - val_distribution_lambda_16_loss: 0.4382\n", "Epoch 725/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5174 - distribution_lambda_14_loss: 0.5888 - distribution_lambda_15_loss: 1.4633 - distribution_lambda_16_loss: 0.4654 - val_loss: 2.4317 - val_distribution_lambda_14_loss: 0.5770 - val_distribution_lambda_15_loss: 1.4167 - val_distribution_lambda_16_loss: 0.4380\n", "Epoch 726/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4625 - distribution_lambda_14_loss: 0.5764 - distribution_lambda_15_loss: 1.4372 - distribution_lambda_16_loss: 0.4489 - val_loss: 2.4332 - val_distribution_lambda_14_loss: 0.5795 - val_distribution_lambda_15_loss: 1.4160 - val_distribution_lambda_16_loss: 0.4378\n", "Epoch 727/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5105 - distribution_lambda_14_loss: 0.5883 - distribution_lambda_15_loss: 1.4603 - distribution_lambda_16_loss: 0.4620 - val_loss: 2.4325 - val_distribution_lambda_14_loss: 0.5797 - val_distribution_lambda_15_loss: 1.4148 - val_distribution_lambda_16_loss: 0.4380\n", "Epoch 728/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5344 - distribution_lambda_14_loss: 0.6051 - distribution_lambda_15_loss: 1.4663 - distribution_lambda_16_loss: 0.4630 - val_loss: 2.4415 - val_distribution_lambda_14_loss: 0.5870 - val_distribution_lambda_15_loss: 1.4163 - val_distribution_lambda_16_loss: 0.4382\n", "Epoch 729/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5199 - distribution_lambda_14_loss: 0.5946 - distribution_lambda_15_loss: 1.4556 - distribution_lambda_16_loss: 0.4697 - val_loss: 2.4416 - val_distribution_lambda_14_loss: 0.5862 - val_distribution_lambda_15_loss: 1.4173 - val_distribution_lambda_16_loss: 0.4381\n", "Epoch 730/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4735 - distribution_lambda_14_loss: 0.5867 - distribution_lambda_15_loss: 1.4436 - distribution_lambda_16_loss: 0.4433 - val_loss: 2.4355 - val_distribution_lambda_14_loss: 0.5807 - val_distribution_lambda_15_loss: 1.4167 - val_distribution_lambda_16_loss: 0.4381\n", "Epoch 731/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4977 - distribution_lambda_14_loss: 0.5840 - distribution_lambda_15_loss: 1.4559 - distribution_lambda_16_loss: 0.4578 - val_loss: 2.4290 - val_distribution_lambda_14_loss: 0.5737 - val_distribution_lambda_15_loss: 1.4171 - val_distribution_lambda_16_loss: 0.4382\n", "Epoch 732/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4574 - distribution_lambda_14_loss: 0.5725 - distribution_lambda_15_loss: 1.4343 - distribution_lambda_16_loss: 0.4506 - val_loss: 2.4288 - val_distribution_lambda_14_loss: 0.5723 - val_distribution_lambda_15_loss: 1.4178 - val_distribution_lambda_16_loss: 0.4386\n", "Epoch 733/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5079 - distribution_lambda_14_loss: 0.5802 - distribution_lambda_15_loss: 1.4623 - distribution_lambda_16_loss: 0.4654 - val_loss: 2.4339 - val_distribution_lambda_14_loss: 0.5736 - val_distribution_lambda_15_loss: 1.4212 - val_distribution_lambda_16_loss: 0.4390\n", "Epoch 734/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4919 - distribution_lambda_14_loss: 0.5818 - distribution_lambda_15_loss: 1.4534 - distribution_lambda_16_loss: 0.4568 - val_loss: 2.4334 - val_distribution_lambda_14_loss: 0.5734 - val_distribution_lambda_15_loss: 1.4214 - val_distribution_lambda_16_loss: 0.4386\n", "Epoch 735/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4892 - distribution_lambda_14_loss: 0.5881 - distribution_lambda_15_loss: 1.4491 - distribution_lambda_16_loss: 0.4519 - val_loss: 2.4365 - val_distribution_lambda_14_loss: 0.5775 - val_distribution_lambda_15_loss: 1.4211 - val_distribution_lambda_16_loss: 0.4378\n", "Epoch 736/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4847 - distribution_lambda_14_loss: 0.5792 - distribution_lambda_15_loss: 1.4552 - distribution_lambda_16_loss: 0.4502 - val_loss: 2.4354 - val_distribution_lambda_14_loss: 0.5791 - val_distribution_lambda_15_loss: 1.4189 - val_distribution_lambda_16_loss: 0.4374\n", "Epoch 737/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5106 - distribution_lambda_14_loss: 0.5868 - distribution_lambda_15_loss: 1.4601 - distribution_lambda_16_loss: 0.4637 - val_loss: 2.4343 - val_distribution_lambda_14_loss: 0.5808 - val_distribution_lambda_15_loss: 1.4164 - val_distribution_lambda_16_loss: 0.4372\n", "Epoch 738/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4883 - distribution_lambda_14_loss: 0.5961 - distribution_lambda_15_loss: 1.4402 - distribution_lambda_16_loss: 0.4520 - val_loss: 2.4268 - val_distribution_lambda_14_loss: 0.5760 - val_distribution_lambda_15_loss: 1.4136 - val_distribution_lambda_16_loss: 0.4373\n", "Epoch 739/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4994 - distribution_lambda_14_loss: 0.5974 - distribution_lambda_15_loss: 1.4472 - distribution_lambda_16_loss: 0.4548 - val_loss: 2.4217 - val_distribution_lambda_14_loss: 0.5709 - val_distribution_lambda_15_loss: 1.4132 - val_distribution_lambda_16_loss: 0.4376\n", "Epoch 740/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4851 - distribution_lambda_14_loss: 0.5766 - distribution_lambda_15_loss: 1.4469 - distribution_lambda_16_loss: 0.4616 - val_loss: 2.4207 - val_distribution_lambda_14_loss: 0.5708 - val_distribution_lambda_15_loss: 1.4126 - val_distribution_lambda_16_loss: 0.4373\n", "Epoch 741/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4741 - distribution_lambda_14_loss: 0.5611 - distribution_lambda_15_loss: 1.4517 - distribution_lambda_16_loss: 0.4613 - val_loss: 2.4243 - val_distribution_lambda_14_loss: 0.5745 - val_distribution_lambda_15_loss: 1.4129 - val_distribution_lambda_16_loss: 0.4369\n", "Epoch 742/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4584 - distribution_lambda_14_loss: 0.5639 - distribution_lambda_15_loss: 1.4360 - distribution_lambda_16_loss: 0.4585 - val_loss: 2.4296 - val_distribution_lambda_14_loss: 0.5769 - val_distribution_lambda_15_loss: 1.4153 - val_distribution_lambda_16_loss: 0.4374\n", "Epoch 743/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4814 - distribution_lambda_14_loss: 0.5867 - distribution_lambda_15_loss: 1.4451 - distribution_lambda_16_loss: 0.4497 - val_loss: 2.4252 - val_distribution_lambda_14_loss: 0.5711 - val_distribution_lambda_15_loss: 1.4159 - val_distribution_lambda_16_loss: 0.4382\n", "Epoch 744/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4692 - distribution_lambda_14_loss: 0.5668 - distribution_lambda_15_loss: 1.4481 - distribution_lambda_16_loss: 0.4542 - val_loss: 2.4218 - val_distribution_lambda_14_loss: 0.5675 - val_distribution_lambda_15_loss: 1.4159 - val_distribution_lambda_16_loss: 0.4385\n", "Epoch 745/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.4699 - distribution_lambda_14_loss: 0.5758 - distribution_lambda_15_loss: 1.4444 - distribution_lambda_16_loss: 0.4497 - val_loss: 2.4263 - val_distribution_lambda_14_loss: 0.5687 - val_distribution_lambda_15_loss: 1.4186 - val_distribution_lambda_16_loss: 0.4390\n", "Epoch 746/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4767 - distribution_lambda_14_loss: 0.5634 - distribution_lambda_15_loss: 1.4508 - distribution_lambda_16_loss: 0.4625 - val_loss: 2.4354 - val_distribution_lambda_14_loss: 0.5744 - val_distribution_lambda_15_loss: 1.4219 - val_distribution_lambda_16_loss: 0.4390\n", "Epoch 747/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4646 - distribution_lambda_14_loss: 0.5720 - distribution_lambda_15_loss: 1.4444 - distribution_lambda_16_loss: 0.4482 - val_loss: 2.4322 - val_distribution_lambda_14_loss: 0.5725 - val_distribution_lambda_15_loss: 1.4207 - val_distribution_lambda_16_loss: 0.4390\n", "Epoch 748/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5046 - distribution_lambda_14_loss: 0.5963 - distribution_lambda_15_loss: 1.4518 - distribution_lambda_16_loss: 0.4566 - val_loss: 2.4339 - val_distribution_lambda_14_loss: 0.5745 - val_distribution_lambda_15_loss: 1.4200 - val_distribution_lambda_16_loss: 0.4395\n", "Epoch 749/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4659 - distribution_lambda_14_loss: 0.5893 - distribution_lambda_15_loss: 1.4311 - distribution_lambda_16_loss: 0.4455 - val_loss: 2.4278 - val_distribution_lambda_14_loss: 0.5702 - val_distribution_lambda_15_loss: 1.4183 - val_distribution_lambda_16_loss: 0.4392\n", "Epoch 750/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4804 - distribution_lambda_14_loss: 0.5894 - distribution_lambda_15_loss: 1.4484 - distribution_lambda_16_loss: 0.4427 - val_loss: 2.4255 - val_distribution_lambda_14_loss: 0.5679 - val_distribution_lambda_15_loss: 1.4183 - val_distribution_lambda_16_loss: 0.4392\n", "Epoch 751/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5033 - distribution_lambda_14_loss: 0.5980 - distribution_lambda_15_loss: 1.4470 - distribution_lambda_16_loss: 0.4583 - val_loss: 2.4216 - val_distribution_lambda_14_loss: 0.5660 - val_distribution_lambda_15_loss: 1.4169 - val_distribution_lambda_16_loss: 0.4388\n", "Epoch 752/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4876 - distribution_lambda_14_loss: 0.5803 - distribution_lambda_15_loss: 1.4550 - distribution_lambda_16_loss: 0.4524 - val_loss: 2.4201 - val_distribution_lambda_14_loss: 0.5668 - val_distribution_lambda_15_loss: 1.4150 - val_distribution_lambda_16_loss: 0.4383\n", "Epoch 753/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4229 - distribution_lambda_14_loss: 0.5603 - distribution_lambda_15_loss: 1.4167 - distribution_lambda_16_loss: 0.4459 - val_loss: 2.4171 - val_distribution_lambda_14_loss: 0.5645 - val_distribution_lambda_15_loss: 1.4144 - val_distribution_lambda_16_loss: 0.4381\n", "Epoch 754/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.5045 - distribution_lambda_14_loss: 0.5890 - distribution_lambda_15_loss: 1.4638 - distribution_lambda_16_loss: 0.4517 - val_loss: 2.4147 - val_distribution_lambda_14_loss: 0.5619 - val_distribution_lambda_15_loss: 1.4153 - val_distribution_lambda_16_loss: 0.4376\n", "Epoch 755/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4822 - distribution_lambda_14_loss: 0.5881 - distribution_lambda_15_loss: 1.4435 - distribution_lambda_16_loss: 0.4506 - val_loss: 2.4161 - val_distribution_lambda_14_loss: 0.5611 - val_distribution_lambda_15_loss: 1.4176 - val_distribution_lambda_16_loss: 0.4374\n", "Epoch 756/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4744 - distribution_lambda_14_loss: 0.5786 - distribution_lambda_15_loss: 1.4506 - distribution_lambda_16_loss: 0.4452 - val_loss: 2.4142 - val_distribution_lambda_14_loss: 0.5596 - val_distribution_lambda_15_loss: 1.4169 - val_distribution_lambda_16_loss: 0.4377\n", "Epoch 757/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4819 - distribution_lambda_14_loss: 0.5895 - distribution_lambda_15_loss: 1.4412 - distribution_lambda_16_loss: 0.4511 - val_loss: 2.4096 - val_distribution_lambda_14_loss: 0.5614 - val_distribution_lambda_15_loss: 1.4112 - val_distribution_lambda_16_loss: 0.4370\n", "Epoch 758/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4654 - distribution_lambda_14_loss: 0.5672 - distribution_lambda_15_loss: 1.4438 - distribution_lambda_16_loss: 0.4544 - val_loss: 2.4104 - val_distribution_lambda_14_loss: 0.5672 - val_distribution_lambda_15_loss: 1.4072 - val_distribution_lambda_16_loss: 0.4359\n", "Epoch 759/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4469 - distribution_lambda_14_loss: 0.5682 - distribution_lambda_15_loss: 1.4329 - distribution_lambda_16_loss: 0.4459 - val_loss: 2.4121 - val_distribution_lambda_14_loss: 0.5702 - val_distribution_lambda_15_loss: 1.4064 - val_distribution_lambda_16_loss: 0.4355\n", "Epoch 760/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4863 - distribution_lambda_14_loss: 0.5890 - distribution_lambda_15_loss: 1.4438 - distribution_lambda_16_loss: 0.4534 - val_loss: 2.4032 - val_distribution_lambda_14_loss: 0.5628 - val_distribution_lambda_15_loss: 1.4051 - val_distribution_lambda_16_loss: 0.4353\n", "Epoch 761/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4501 - distribution_lambda_14_loss: 0.5645 - distribution_lambda_15_loss: 1.4433 - distribution_lambda_16_loss: 0.4423 - val_loss: 2.3989 - val_distribution_lambda_14_loss: 0.5598 - val_distribution_lambda_15_loss: 1.4042 - val_distribution_lambda_16_loss: 0.4349\n", "Epoch 762/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4511 - distribution_lambda_14_loss: 0.5836 - distribution_lambda_15_loss: 1.4280 - distribution_lambda_16_loss: 0.4395 - val_loss: 2.3981 - val_distribution_lambda_14_loss: 0.5601 - val_distribution_lambda_15_loss: 1.4037 - val_distribution_lambda_16_loss: 0.4343\n", "Epoch 763/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4655 - distribution_lambda_14_loss: 0.5645 - distribution_lambda_15_loss: 1.4514 - distribution_lambda_16_loss: 0.4495 - val_loss: 2.4031 - val_distribution_lambda_14_loss: 0.5633 - val_distribution_lambda_15_loss: 1.4055 - val_distribution_lambda_16_loss: 0.4343\n", "Epoch 764/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4631 - distribution_lambda_14_loss: 0.5841 - distribution_lambda_15_loss: 1.4334 - distribution_lambda_16_loss: 0.4456 - val_loss: 2.4155 - val_distribution_lambda_14_loss: 0.5737 - val_distribution_lambda_15_loss: 1.4076 - val_distribution_lambda_16_loss: 0.4342\n", "Epoch 765/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4427 - distribution_lambda_14_loss: 0.5726 - distribution_lambda_15_loss: 1.4252 - distribution_lambda_16_loss: 0.4448 - val_loss: 2.4232 - val_distribution_lambda_14_loss: 0.5828 - val_distribution_lambda_15_loss: 1.4068 - val_distribution_lambda_16_loss: 0.4336\n", "Epoch 766/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4587 - distribution_lambda_14_loss: 0.5762 - distribution_lambda_15_loss: 1.4389 - distribution_lambda_16_loss: 0.4436 - val_loss: 2.4123 - val_distribution_lambda_14_loss: 0.5720 - val_distribution_lambda_15_loss: 1.4070 - val_distribution_lambda_16_loss: 0.4333\n", "Epoch 767/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4454 - distribution_lambda_14_loss: 0.5659 - distribution_lambda_15_loss: 1.4364 - distribution_lambda_16_loss: 0.4432 - val_loss: 2.4059 - val_distribution_lambda_14_loss: 0.5642 - val_distribution_lambda_15_loss: 1.4082 - val_distribution_lambda_16_loss: 0.4335\n", "Epoch 768/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4370 - distribution_lambda_14_loss: 0.5707 - distribution_lambda_15_loss: 1.4156 - distribution_lambda_16_loss: 0.4507 - val_loss: 2.4017 - val_distribution_lambda_14_loss: 0.5601 - val_distribution_lambda_15_loss: 1.4079 - val_distribution_lambda_16_loss: 0.4337\n", "Epoch 769/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.4750 - distribution_lambda_14_loss: 0.5573 - distribution_lambda_15_loss: 1.4540 - distribution_lambda_16_loss: 0.4638 - val_loss: 2.4040 - val_distribution_lambda_14_loss: 0.5629 - val_distribution_lambda_15_loss: 1.4075 - val_distribution_lambda_16_loss: 0.4336\n", "Epoch 770/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4776 - distribution_lambda_14_loss: 0.5921 - distribution_lambda_15_loss: 1.4332 - distribution_lambda_16_loss: 0.4523 - val_loss: 2.4064 - val_distribution_lambda_14_loss: 0.5665 - val_distribution_lambda_15_loss: 1.4064 - val_distribution_lambda_16_loss: 0.4336\n", "Epoch 771/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4677 - distribution_lambda_14_loss: 0.5704 - distribution_lambda_15_loss: 1.4502 - distribution_lambda_16_loss: 0.4471 - val_loss: 2.4014 - val_distribution_lambda_14_loss: 0.5623 - val_distribution_lambda_15_loss: 1.4053 - val_distribution_lambda_16_loss: 0.4338\n", "Epoch 772/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4479 - distribution_lambda_14_loss: 0.5654 - distribution_lambda_15_loss: 1.4396 - distribution_lambda_16_loss: 0.4429 - val_loss: 2.3998 - val_distribution_lambda_14_loss: 0.5604 - val_distribution_lambda_15_loss: 1.4051 - val_distribution_lambda_16_loss: 0.4343\n", "Epoch 773/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4770 - distribution_lambda_14_loss: 0.5690 - distribution_lambda_15_loss: 1.4566 - distribution_lambda_16_loss: 0.4514 - val_loss: 2.4009 - val_distribution_lambda_14_loss: 0.5615 - val_distribution_lambda_15_loss: 1.4049 - val_distribution_lambda_16_loss: 0.4345\n", "Epoch 774/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4419 - distribution_lambda_14_loss: 0.5670 - distribution_lambda_15_loss: 1.4335 - distribution_lambda_16_loss: 0.4414 - val_loss: 2.3963 - val_distribution_lambda_14_loss: 0.5569 - val_distribution_lambda_15_loss: 1.4047 - val_distribution_lambda_16_loss: 0.4347\n", "Epoch 775/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4572 - distribution_lambda_14_loss: 0.5779 - distribution_lambda_15_loss: 1.4335 - distribution_lambda_16_loss: 0.4458 - val_loss: 2.3929 - val_distribution_lambda_14_loss: 0.5532 - val_distribution_lambda_15_loss: 1.4051 - val_distribution_lambda_16_loss: 0.4347\n", "Epoch 776/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4498 - distribution_lambda_14_loss: 0.5782 - distribution_lambda_15_loss: 1.4285 - distribution_lambda_16_loss: 0.4431 - val_loss: 2.3964 - val_distribution_lambda_14_loss: 0.5588 - val_distribution_lambda_15_loss: 1.4032 - val_distribution_lambda_16_loss: 0.4345\n", "Epoch 777/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4398 - distribution_lambda_14_loss: 0.5546 - distribution_lambda_15_loss: 1.4328 - distribution_lambda_16_loss: 0.4523 - val_loss: 2.4008 - val_distribution_lambda_14_loss: 0.5649 - val_distribution_lambda_15_loss: 1.4015 - val_distribution_lambda_16_loss: 0.4344\n", "Epoch 778/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4735 - distribution_lambda_14_loss: 0.5772 - distribution_lambda_15_loss: 1.4470 - distribution_lambda_16_loss: 0.4493 - val_loss: 2.3996 - val_distribution_lambda_14_loss: 0.5641 - val_distribution_lambda_15_loss: 1.4008 - val_distribution_lambda_16_loss: 0.4346\n", "Epoch 779/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4435 - distribution_lambda_14_loss: 0.5596 - distribution_lambda_15_loss: 1.4397 - distribution_lambda_16_loss: 0.4442 - val_loss: 2.4015 - val_distribution_lambda_14_loss: 0.5664 - val_distribution_lambda_15_loss: 1.4013 - val_distribution_lambda_16_loss: 0.4337\n", "Epoch 780/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4743 - distribution_lambda_14_loss: 0.5737 - distribution_lambda_15_loss: 1.4458 - distribution_lambda_16_loss: 0.4548 - val_loss: 2.3961 - val_distribution_lambda_14_loss: 0.5620 - val_distribution_lambda_15_loss: 1.4013 - val_distribution_lambda_16_loss: 0.4329\n", "Epoch 781/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4636 - distribution_lambda_14_loss: 0.5869 - distribution_lambda_15_loss: 1.4372 - distribution_lambda_16_loss: 0.4395 - val_loss: 2.4021 - val_distribution_lambda_14_loss: 0.5692 - val_distribution_lambda_15_loss: 1.4004 - val_distribution_lambda_16_loss: 0.4326\n", "Epoch 782/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4389 - distribution_lambda_14_loss: 0.5542 - distribution_lambda_15_loss: 1.4339 - distribution_lambda_16_loss: 0.4509 - val_loss: 2.4002 - val_distribution_lambda_14_loss: 0.5686 - val_distribution_lambda_15_loss: 1.3992 - val_distribution_lambda_16_loss: 0.4323\n", "Epoch 783/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4443 - distribution_lambda_14_loss: 0.5708 - distribution_lambda_15_loss: 1.4352 - distribution_lambda_16_loss: 0.4383 - val_loss: 2.3849 - val_distribution_lambda_14_loss: 0.5553 - val_distribution_lambda_15_loss: 1.3973 - val_distribution_lambda_16_loss: 0.4322\n", "Epoch 784/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4415 - distribution_lambda_14_loss: 0.5599 - distribution_lambda_15_loss: 1.4328 - distribution_lambda_16_loss: 0.4488 - val_loss: 2.3833 - val_distribution_lambda_14_loss: 0.5529 - val_distribution_lambda_15_loss: 1.3973 - val_distribution_lambda_16_loss: 0.4332\n", "Epoch 785/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4707 - distribution_lambda_14_loss: 0.5735 - distribution_lambda_15_loss: 1.4481 - distribution_lambda_16_loss: 0.4492 - val_loss: 2.3858 - val_distribution_lambda_14_loss: 0.5559 - val_distribution_lambda_15_loss: 1.3962 - val_distribution_lambda_16_loss: 0.4337\n", "Epoch 786/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4730 - distribution_lambda_14_loss: 0.5777 - distribution_lambda_15_loss: 1.4439 - distribution_lambda_16_loss: 0.4514 - val_loss: 2.3910 - val_distribution_lambda_14_loss: 0.5609 - val_distribution_lambda_15_loss: 1.3967 - val_distribution_lambda_16_loss: 0.4334\n", "Epoch 787/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4763 - distribution_lambda_14_loss: 0.5730 - distribution_lambda_15_loss: 1.4474 - distribution_lambda_16_loss: 0.4559 - val_loss: 2.3845 - val_distribution_lambda_14_loss: 0.5534 - val_distribution_lambda_15_loss: 1.3978 - val_distribution_lambda_16_loss: 0.4333\n", "Epoch 788/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4418 - distribution_lambda_14_loss: 0.5792 - distribution_lambda_15_loss: 1.4249 - distribution_lambda_16_loss: 0.4377 - val_loss: 2.3831 - val_distribution_lambda_14_loss: 0.5534 - val_distribution_lambda_15_loss: 1.3969 - val_distribution_lambda_16_loss: 0.4328\n", "Epoch 789/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4631 - distribution_lambda_14_loss: 0.5839 - distribution_lambda_15_loss: 1.4348 - distribution_lambda_16_loss: 0.4444 - val_loss: 2.3820 - val_distribution_lambda_14_loss: 0.5544 - val_distribution_lambda_15_loss: 1.3949 - val_distribution_lambda_16_loss: 0.4327\n", "Epoch 790/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4832 - distribution_lambda_14_loss: 0.5794 - distribution_lambda_15_loss: 1.4467 - distribution_lambda_16_loss: 0.4571 - val_loss: 2.3788 - val_distribution_lambda_14_loss: 0.5536 - val_distribution_lambda_15_loss: 1.3929 - val_distribution_lambda_16_loss: 0.4322\n", "Epoch 791/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4501 - distribution_lambda_14_loss: 0.5735 - distribution_lambda_15_loss: 1.4354 - distribution_lambda_16_loss: 0.4412 - val_loss: 2.3719 - val_distribution_lambda_14_loss: 0.5482 - val_distribution_lambda_15_loss: 1.3921 - val_distribution_lambda_16_loss: 0.4315\n", "Epoch 792/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4318 - distribution_lambda_14_loss: 0.5551 - distribution_lambda_15_loss: 1.4253 - distribution_lambda_16_loss: 0.4513 - val_loss: 2.3686 - val_distribution_lambda_14_loss: 0.5442 - val_distribution_lambda_15_loss: 1.3933 - val_distribution_lambda_16_loss: 0.4311\n", "Epoch 793/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.4519 - distribution_lambda_14_loss: 0.5824 - distribution_lambda_15_loss: 1.4305 - distribution_lambda_16_loss: 0.4390 - val_loss: 2.3689 - val_distribution_lambda_14_loss: 0.5433 - val_distribution_lambda_15_loss: 1.3941 - val_distribution_lambda_16_loss: 0.4316\n", "Epoch 794/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4658 - distribution_lambda_14_loss: 0.5847 - distribution_lambda_15_loss: 1.4354 - distribution_lambda_16_loss: 0.4457 - val_loss: 2.3697 - val_distribution_lambda_14_loss: 0.5456 - val_distribution_lambda_15_loss: 1.3926 - val_distribution_lambda_16_loss: 0.4315\n", "Epoch 795/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4620 - distribution_lambda_14_loss: 0.5803 - distribution_lambda_15_loss: 1.4393 - distribution_lambda_16_loss: 0.4424 - val_loss: 2.3709 - val_distribution_lambda_14_loss: 0.5479 - val_distribution_lambda_15_loss: 1.3919 - val_distribution_lambda_16_loss: 0.4310\n", "Epoch 796/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4827 - distribution_lambda_14_loss: 0.5807 - distribution_lambda_15_loss: 1.4435 - distribution_lambda_16_loss: 0.4585 - val_loss: 2.3718 - val_distribution_lambda_14_loss: 0.5480 - val_distribution_lambda_15_loss: 1.3931 - val_distribution_lambda_16_loss: 0.4307\n", "Epoch 797/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4316 - distribution_lambda_14_loss: 0.5584 - distribution_lambda_15_loss: 1.4337 - distribution_lambda_16_loss: 0.4396 - val_loss: 2.3678 - val_distribution_lambda_14_loss: 0.5458 - val_distribution_lambda_15_loss: 1.3921 - val_distribution_lambda_16_loss: 0.4299\n", "Epoch 798/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4560 - distribution_lambda_14_loss: 0.5744 - distribution_lambda_15_loss: 1.4341 - distribution_lambda_16_loss: 0.4475 - val_loss: 2.3644 - val_distribution_lambda_14_loss: 0.5443 - val_distribution_lambda_15_loss: 1.3906 - val_distribution_lambda_16_loss: 0.4295\n", "Epoch 799/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4340 - distribution_lambda_14_loss: 0.5430 - distribution_lambda_15_loss: 1.4411 - distribution_lambda_16_loss: 0.4499 - val_loss: 2.3653 - val_distribution_lambda_14_loss: 0.5467 - val_distribution_lambda_15_loss: 1.3901 - val_distribution_lambda_16_loss: 0.4285\n", "Epoch 800/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4588 - distribution_lambda_14_loss: 0.5668 - distribution_lambda_15_loss: 1.4410 - distribution_lambda_16_loss: 0.4510 - val_loss: 2.3670 - val_distribution_lambda_14_loss: 0.5434 - val_distribution_lambda_15_loss: 1.3957 - val_distribution_lambda_16_loss: 0.4279\n", "Epoch 801/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4247 - distribution_lambda_14_loss: 0.5555 - distribution_lambda_15_loss: 1.4276 - distribution_lambda_16_loss: 0.4417 - val_loss: 2.3671 - val_distribution_lambda_14_loss: 0.5427 - val_distribution_lambda_15_loss: 1.3965 - val_distribution_lambda_16_loss: 0.4279\n", "Epoch 802/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4278 - distribution_lambda_14_loss: 0.5635 - distribution_lambda_15_loss: 1.4147 - distribution_lambda_16_loss: 0.4497 - val_loss: 2.3719 - val_distribution_lambda_14_loss: 0.5476 - val_distribution_lambda_15_loss: 1.3966 - val_distribution_lambda_16_loss: 0.4278\n", "Epoch 803/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4545 - distribution_lambda_14_loss: 0.5636 - distribution_lambda_15_loss: 1.4439 - distribution_lambda_16_loss: 0.4470 - val_loss: 2.3742 - val_distribution_lambda_14_loss: 0.5496 - val_distribution_lambda_15_loss: 1.3969 - val_distribution_lambda_16_loss: 0.4276\n", "Epoch 804/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4198 - distribution_lambda_14_loss: 0.5440 - distribution_lambda_15_loss: 1.4246 - distribution_lambda_16_loss: 0.4512 - val_loss: 2.3703 - val_distribution_lambda_14_loss: 0.5463 - val_distribution_lambda_15_loss: 1.3968 - val_distribution_lambda_16_loss: 0.4272\n", "Epoch 805/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4350 - distribution_lambda_14_loss: 0.5543 - distribution_lambda_15_loss: 1.4282 - distribution_lambda_16_loss: 0.4525 - val_loss: 2.3657 - val_distribution_lambda_14_loss: 0.5440 - val_distribution_lambda_15_loss: 1.3950 - val_distribution_lambda_16_loss: 0.4267\n", "Epoch 806/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4254 - distribution_lambda_14_loss: 0.5412 - distribution_lambda_15_loss: 1.4357 - distribution_lambda_16_loss: 0.4484 - val_loss: 2.3602 - val_distribution_lambda_14_loss: 0.5408 - val_distribution_lambda_15_loss: 1.3928 - val_distribution_lambda_16_loss: 0.4266\n", "Epoch 807/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4516 - distribution_lambda_14_loss: 0.5680 - distribution_lambda_15_loss: 1.4414 - distribution_lambda_16_loss: 0.4422 - val_loss: 2.3614 - val_distribution_lambda_14_loss: 0.5412 - val_distribution_lambda_15_loss: 1.3932 - val_distribution_lambda_16_loss: 0.4271\n", "Epoch 808/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4075 - distribution_lambda_14_loss: 0.5474 - distribution_lambda_15_loss: 1.4202 - distribution_lambda_16_loss: 0.4399 - val_loss: 2.3597 - val_distribution_lambda_14_loss: 0.5409 - val_distribution_lambda_15_loss: 1.3916 - val_distribution_lambda_16_loss: 0.4272\n", "Epoch 809/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4372 - distribution_lambda_14_loss: 0.5612 - distribution_lambda_15_loss: 1.4285 - distribution_lambda_16_loss: 0.4474 - val_loss: 2.3571 - val_distribution_lambda_14_loss: 0.5410 - val_distribution_lambda_15_loss: 1.3897 - val_distribution_lambda_16_loss: 0.4264\n", "Epoch 810/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4445 - distribution_lambda_14_loss: 0.5668 - distribution_lambda_15_loss: 1.4389 - distribution_lambda_16_loss: 0.4388 - val_loss: 2.3649 - val_distribution_lambda_14_loss: 0.5496 - val_distribution_lambda_15_loss: 1.3894 - val_distribution_lambda_16_loss: 0.4260\n", "Epoch 811/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4368 - distribution_lambda_14_loss: 0.5524 - distribution_lambda_15_loss: 1.4270 - distribution_lambda_16_loss: 0.4574 - val_loss: 2.3621 - val_distribution_lambda_14_loss: 0.5475 - val_distribution_lambda_15_loss: 1.3884 - val_distribution_lambda_16_loss: 0.4262\n", "Epoch 812/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4311 - distribution_lambda_14_loss: 0.5539 - distribution_lambda_15_loss: 1.4322 - distribution_lambda_16_loss: 0.4451 - val_loss: 2.3631 - val_distribution_lambda_14_loss: 0.5449 - val_distribution_lambda_15_loss: 1.3916 - val_distribution_lambda_16_loss: 0.4267\n", "Epoch 813/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4324 - distribution_lambda_14_loss: 0.5680 - distribution_lambda_15_loss: 1.4217 - distribution_lambda_16_loss: 0.4428 - val_loss: 2.3623 - val_distribution_lambda_14_loss: 0.5408 - val_distribution_lambda_15_loss: 1.3950 - val_distribution_lambda_16_loss: 0.4265\n", "Epoch 814/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4300 - distribution_lambda_14_loss: 0.5533 - distribution_lambda_15_loss: 1.4371 - distribution_lambda_16_loss: 0.4395 - val_loss: 2.3606 - val_distribution_lambda_14_loss: 0.5394 - val_distribution_lambda_15_loss: 1.3949 - val_distribution_lambda_16_loss: 0.4263\n", "Epoch 815/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4627 - distribution_lambda_14_loss: 0.5618 - distribution_lambda_15_loss: 1.4493 - distribution_lambda_16_loss: 0.4516 - val_loss: 2.3646 - val_distribution_lambda_14_loss: 0.5463 - val_distribution_lambda_15_loss: 1.3925 - val_distribution_lambda_16_loss: 0.4258\n", "Epoch 816/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4470 - distribution_lambda_14_loss: 0.5717 - distribution_lambda_15_loss: 1.4323 - distribution_lambda_16_loss: 0.4430 - val_loss: 2.3686 - val_distribution_lambda_14_loss: 0.5525 - val_distribution_lambda_15_loss: 1.3903 - val_distribution_lambda_16_loss: 0.4258\n", "Epoch 817/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.4127 - distribution_lambda_14_loss: 0.5543 - distribution_lambda_15_loss: 1.4195 - distribution_lambda_16_loss: 0.4390 - val_loss: 2.3631 - val_distribution_lambda_14_loss: 0.5493 - val_distribution_lambda_15_loss: 1.3884 - val_distribution_lambda_16_loss: 0.4254\n", "Epoch 818/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4283 - distribution_lambda_14_loss: 0.5565 - distribution_lambda_15_loss: 1.4207 - distribution_lambda_16_loss: 0.4510 - val_loss: 2.3621 - val_distribution_lambda_14_loss: 0.5501 - val_distribution_lambda_15_loss: 1.3867 - val_distribution_lambda_16_loss: 0.4253\n", "Epoch 819/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4243 - distribution_lambda_14_loss: 0.5506 - distribution_lambda_15_loss: 1.4220 - distribution_lambda_16_loss: 0.4517 - val_loss: 2.3551 - val_distribution_lambda_14_loss: 0.5435 - val_distribution_lambda_15_loss: 1.3862 - val_distribution_lambda_16_loss: 0.4254\n", "Epoch 820/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4023 - distribution_lambda_14_loss: 0.5411 - distribution_lambda_15_loss: 1.4194 - distribution_lambda_16_loss: 0.4418 - val_loss: 2.3479 - val_distribution_lambda_14_loss: 0.5342 - val_distribution_lambda_15_loss: 1.3879 - val_distribution_lambda_16_loss: 0.4258\n", "Epoch 821/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4141 - distribution_lambda_14_loss: 0.5661 - distribution_lambda_15_loss: 1.4120 - distribution_lambda_16_loss: 0.4360 - val_loss: 2.3464 - val_distribution_lambda_14_loss: 0.5314 - val_distribution_lambda_15_loss: 1.3888 - val_distribution_lambda_16_loss: 0.4262\n", "Epoch 822/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4335 - distribution_lambda_14_loss: 0.5614 - distribution_lambda_15_loss: 1.4346 - distribution_lambda_16_loss: 0.4375 - val_loss: 2.3500 - val_distribution_lambda_14_loss: 0.5328 - val_distribution_lambda_15_loss: 1.3904 - val_distribution_lambda_16_loss: 0.4269\n", "Epoch 823/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4246 - distribution_lambda_14_loss: 0.5462 - distribution_lambda_15_loss: 1.4362 - distribution_lambda_16_loss: 0.4421 - val_loss: 2.3652 - val_distribution_lambda_14_loss: 0.5474 - val_distribution_lambda_15_loss: 1.3905 - val_distribution_lambda_16_loss: 0.4272\n", "Epoch 824/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4397 - distribution_lambda_14_loss: 0.5675 - distribution_lambda_15_loss: 1.4243 - distribution_lambda_16_loss: 0.4479 - val_loss: 2.3711 - val_distribution_lambda_14_loss: 0.5534 - val_distribution_lambda_15_loss: 1.3902 - val_distribution_lambda_16_loss: 0.4276\n", "Epoch 825/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4411 - distribution_lambda_14_loss: 0.5588 - distribution_lambda_15_loss: 1.4356 - distribution_lambda_16_loss: 0.4467 - val_loss: 2.3571 - val_distribution_lambda_14_loss: 0.5390 - val_distribution_lambda_15_loss: 1.3901 - val_distribution_lambda_16_loss: 0.4280\n", "Epoch 826/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4408 - distribution_lambda_14_loss: 0.5565 - distribution_lambda_15_loss: 1.4436 - distribution_lambda_16_loss: 0.4407 - val_loss: 2.3515 - val_distribution_lambda_14_loss: 0.5322 - val_distribution_lambda_15_loss: 1.3909 - val_distribution_lambda_16_loss: 0.4284\n", "Epoch 827/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4524 - distribution_lambda_14_loss: 0.5635 - distribution_lambda_15_loss: 1.4363 - distribution_lambda_16_loss: 0.4527 - val_loss: 2.3519 - val_distribution_lambda_14_loss: 0.5336 - val_distribution_lambda_15_loss: 1.3901 - val_distribution_lambda_16_loss: 0.4282\n", "Epoch 828/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3965 - distribution_lambda_14_loss: 0.5323 - distribution_lambda_15_loss: 1.4269 - distribution_lambda_16_loss: 0.4374 - val_loss: 2.3500 - val_distribution_lambda_14_loss: 0.5348 - val_distribution_lambda_15_loss: 1.3874 - val_distribution_lambda_16_loss: 0.4277\n", "Epoch 829/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4406 - distribution_lambda_14_loss: 0.5489 - distribution_lambda_15_loss: 1.4376 - distribution_lambda_16_loss: 0.4541 - val_loss: 2.3462 - val_distribution_lambda_14_loss: 0.5318 - val_distribution_lambda_15_loss: 1.3867 - val_distribution_lambda_16_loss: 0.4277\n", "Epoch 830/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3851 - distribution_lambda_14_loss: 0.5393 - distribution_lambda_15_loss: 1.4119 - distribution_lambda_16_loss: 0.4339 - val_loss: 2.3447 - val_distribution_lambda_14_loss: 0.5299 - val_distribution_lambda_15_loss: 1.3867 - val_distribution_lambda_16_loss: 0.4282\n", "Epoch 831/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4077 - distribution_lambda_14_loss: 0.5582 - distribution_lambda_15_loss: 1.4143 - distribution_lambda_16_loss: 0.4352 - val_loss: 2.3461 - val_distribution_lambda_14_loss: 0.5304 - val_distribution_lambda_15_loss: 1.3869 - val_distribution_lambda_16_loss: 0.4288\n", "Epoch 832/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4282 - distribution_lambda_14_loss: 0.5538 - distribution_lambda_15_loss: 1.4306 - distribution_lambda_16_loss: 0.4438 - val_loss: 2.3515 - val_distribution_lambda_14_loss: 0.5397 - val_distribution_lambda_15_loss: 1.3845 - val_distribution_lambda_16_loss: 0.4273\n", "Epoch 833/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4316 - distribution_lambda_14_loss: 0.5554 - distribution_lambda_15_loss: 1.4307 - distribution_lambda_16_loss: 0.4455 - val_loss: 2.3481 - val_distribution_lambda_14_loss: 0.5382 - val_distribution_lambda_15_loss: 1.3845 - val_distribution_lambda_16_loss: 0.4255\n", "Epoch 834/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4055 - distribution_lambda_14_loss: 0.5425 - distribution_lambda_15_loss: 1.4261 - distribution_lambda_16_loss: 0.4369 - val_loss: 2.3313 - val_distribution_lambda_14_loss: 0.5245 - val_distribution_lambda_15_loss: 1.3822 - val_distribution_lambda_16_loss: 0.4246\n", "Epoch 835/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4689 - distribution_lambda_14_loss: 0.5857 - distribution_lambda_15_loss: 1.4340 - distribution_lambda_16_loss: 0.4492 - val_loss: 2.3296 - val_distribution_lambda_14_loss: 0.5242 - val_distribution_lambda_15_loss: 1.3813 - val_distribution_lambda_16_loss: 0.4241\n", "Epoch 836/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4556 - distribution_lambda_14_loss: 0.5739 - distribution_lambda_15_loss: 1.4388 - distribution_lambda_16_loss: 0.4430 - val_loss: 2.3296 - val_distribution_lambda_14_loss: 0.5249 - val_distribution_lambda_15_loss: 1.3810 - val_distribution_lambda_16_loss: 0.4237\n", "Epoch 837/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4299 - distribution_lambda_14_loss: 0.5514 - distribution_lambda_15_loss: 1.4379 - distribution_lambda_16_loss: 0.4405 - val_loss: 2.3312 - val_distribution_lambda_14_loss: 0.5275 - val_distribution_lambda_15_loss: 1.3804 - val_distribution_lambda_16_loss: 0.4233\n", "Epoch 838/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3981 - distribution_lambda_14_loss: 0.5418 - distribution_lambda_15_loss: 1.4132 - distribution_lambda_16_loss: 0.4432 - val_loss: 2.3383 - val_distribution_lambda_14_loss: 0.5338 - val_distribution_lambda_15_loss: 1.3807 - val_distribution_lambda_16_loss: 0.4238\n", "Epoch 839/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4256 - distribution_lambda_14_loss: 0.5499 - distribution_lambda_15_loss: 1.4366 - distribution_lambda_16_loss: 0.4391 - val_loss: 2.3427 - val_distribution_lambda_14_loss: 0.5361 - val_distribution_lambda_15_loss: 1.3823 - val_distribution_lambda_16_loss: 0.4242\n", "Epoch 840/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4172 - distribution_lambda_14_loss: 0.5475 - distribution_lambda_15_loss: 1.4316 - distribution_lambda_16_loss: 0.4381 - val_loss: 2.3428 - val_distribution_lambda_14_loss: 0.5353 - val_distribution_lambda_15_loss: 1.3831 - val_distribution_lambda_16_loss: 0.4243\n", "Epoch 841/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.4152 - distribution_lambda_14_loss: 0.5417 - distribution_lambda_15_loss: 1.4237 - distribution_lambda_16_loss: 0.4497 - val_loss: 2.3305 - val_distribution_lambda_14_loss: 0.5240 - val_distribution_lambda_15_loss: 1.3823 - val_distribution_lambda_16_loss: 0.4242\n", "Epoch 842/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4238 - distribution_lambda_14_loss: 0.5424 - distribution_lambda_15_loss: 1.4415 - distribution_lambda_16_loss: 0.4399 - val_loss: 2.3282 - val_distribution_lambda_14_loss: 0.5219 - val_distribution_lambda_15_loss: 1.3829 - val_distribution_lambda_16_loss: 0.4234\n", "Epoch 843/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4111 - distribution_lambda_14_loss: 0.5608 - distribution_lambda_15_loss: 1.4090 - distribution_lambda_16_loss: 0.4413 - val_loss: 2.3329 - val_distribution_lambda_14_loss: 0.5260 - val_distribution_lambda_15_loss: 1.3837 - val_distribution_lambda_16_loss: 0.4232\n", "Epoch 844/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3828 - distribution_lambda_14_loss: 0.5376 - distribution_lambda_15_loss: 1.4070 - distribution_lambda_16_loss: 0.4382 - val_loss: 2.3367 - val_distribution_lambda_14_loss: 0.5304 - val_distribution_lambda_15_loss: 1.3829 - val_distribution_lambda_16_loss: 0.4234\n", "Epoch 845/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4178 - distribution_lambda_14_loss: 0.5466 - distribution_lambda_15_loss: 1.4220 - distribution_lambda_16_loss: 0.4492 - val_loss: 2.3329 - val_distribution_lambda_14_loss: 0.5280 - val_distribution_lambda_15_loss: 1.3815 - val_distribution_lambda_16_loss: 0.4235\n", "Epoch 846/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4013 - distribution_lambda_14_loss: 0.5362 - distribution_lambda_15_loss: 1.4192 - distribution_lambda_16_loss: 0.4459 - val_loss: 2.3265 - val_distribution_lambda_14_loss: 0.5204 - val_distribution_lambda_15_loss: 1.3823 - val_distribution_lambda_16_loss: 0.4238\n", "Epoch 847/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4053 - distribution_lambda_14_loss: 0.5378 - distribution_lambda_15_loss: 1.4246 - distribution_lambda_16_loss: 0.4430 - val_loss: 2.3278 - val_distribution_lambda_14_loss: 0.5200 - val_distribution_lambda_15_loss: 1.3830 - val_distribution_lambda_16_loss: 0.4248\n", "Epoch 848/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4026 - distribution_lambda_14_loss: 0.5413 - distribution_lambda_15_loss: 1.4205 - distribution_lambda_16_loss: 0.4408 - val_loss: 2.3325 - val_distribution_lambda_14_loss: 0.5237 - val_distribution_lambda_15_loss: 1.3838 - val_distribution_lambda_16_loss: 0.4250\n", "Epoch 849/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3984 - distribution_lambda_14_loss: 0.5413 - distribution_lambda_15_loss: 1.4198 - distribution_lambda_16_loss: 0.4373 - val_loss: 2.3328 - val_distribution_lambda_14_loss: 0.5243 - val_distribution_lambda_15_loss: 1.3842 - val_distribution_lambda_16_loss: 0.4243\n", "Epoch 850/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3622 - distribution_lambda_14_loss: 0.5232 - distribution_lambda_15_loss: 1.4018 - distribution_lambda_16_loss: 0.4372 - val_loss: 2.3289 - val_distribution_lambda_14_loss: 0.5213 - val_distribution_lambda_15_loss: 1.3837 - val_distribution_lambda_16_loss: 0.4239\n", "Epoch 851/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3952 - distribution_lambda_14_loss: 0.5420 - distribution_lambda_15_loss: 1.4137 - distribution_lambda_16_loss: 0.4395 - val_loss: 2.3300 - val_distribution_lambda_14_loss: 0.5246 - val_distribution_lambda_15_loss: 1.3817 - val_distribution_lambda_16_loss: 0.4238\n", "Epoch 852/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4199 - distribution_lambda_14_loss: 0.5268 - distribution_lambda_15_loss: 1.4409 - distribution_lambda_16_loss: 0.4522 - val_loss: 2.3349 - val_distribution_lambda_14_loss: 0.5292 - val_distribution_lambda_15_loss: 1.3816 - val_distribution_lambda_16_loss: 0.4240\n", "Epoch 853/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3873 - distribution_lambda_14_loss: 0.5400 - distribution_lambda_15_loss: 1.4172 - distribution_lambda_16_loss: 0.4301 - val_loss: 2.3303 - val_distribution_lambda_14_loss: 0.5246 - val_distribution_lambda_15_loss: 1.3817 - val_distribution_lambda_16_loss: 0.4239\n", "Epoch 854/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4300 - distribution_lambda_14_loss: 0.5532 - distribution_lambda_15_loss: 1.4312 - distribution_lambda_16_loss: 0.4456 - val_loss: 2.3291 - val_distribution_lambda_14_loss: 0.5237 - val_distribution_lambda_15_loss: 1.3818 - val_distribution_lambda_16_loss: 0.4236\n", "Epoch 855/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4005 - distribution_lambda_14_loss: 0.5362 - distribution_lambda_15_loss: 1.4239 - distribution_lambda_16_loss: 0.4403 - val_loss: 2.3353 - val_distribution_lambda_14_loss: 0.5277 - val_distribution_lambda_15_loss: 1.3842 - val_distribution_lambda_16_loss: 0.4234\n", "Epoch 856/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3924 - distribution_lambda_14_loss: 0.5426 - distribution_lambda_15_loss: 1.4095 - distribution_lambda_16_loss: 0.4402 - val_loss: 2.3402 - val_distribution_lambda_14_loss: 0.5325 - val_distribution_lambda_15_loss: 1.3844 - val_distribution_lambda_16_loss: 0.4234\n", "Epoch 857/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4318 - distribution_lambda_14_loss: 0.5543 - distribution_lambda_15_loss: 1.4332 - distribution_lambda_16_loss: 0.4442 - val_loss: 2.3383 - val_distribution_lambda_14_loss: 0.5326 - val_distribution_lambda_15_loss: 1.3824 - val_distribution_lambda_16_loss: 0.4233\n", "Epoch 858/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3713 - distribution_lambda_14_loss: 0.5318 - distribution_lambda_15_loss: 1.4104 - distribution_lambda_16_loss: 0.4291 - val_loss: 2.3407 - val_distribution_lambda_14_loss: 0.5364 - val_distribution_lambda_15_loss: 1.3813 - val_distribution_lambda_16_loss: 0.4231\n", "Epoch 859/2000\n", "8/8 [==============================] - 0s 9ms/step - loss: 2.3985 - distribution_lambda_14_loss: 0.5456 - distribution_lambda_15_loss: 1.4254 - distribution_lambda_16_loss: 0.4275 - val_loss: 2.3319 - val_distribution_lambda_14_loss: 0.5296 - val_distribution_lambda_15_loss: 1.3799 - val_distribution_lambda_16_loss: 0.4225\n", "Epoch 860/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3901 - distribution_lambda_14_loss: 0.5373 - distribution_lambda_15_loss: 1.4104 - distribution_lambda_16_loss: 0.4423 - val_loss: 2.3190 - val_distribution_lambda_14_loss: 0.5180 - val_distribution_lambda_15_loss: 1.3787 - val_distribution_lambda_16_loss: 0.4222\n", "Epoch 861/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4108 - distribution_lambda_14_loss: 0.5348 - distribution_lambda_15_loss: 1.4311 - distribution_lambda_16_loss: 0.4449 - val_loss: 2.3177 - val_distribution_lambda_14_loss: 0.5164 - val_distribution_lambda_15_loss: 1.3789 - val_distribution_lambda_16_loss: 0.4224\n", "Epoch 862/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3958 - distribution_lambda_14_loss: 0.5407 - distribution_lambda_15_loss: 1.4185 - distribution_lambda_16_loss: 0.4366 - val_loss: 2.3267 - val_distribution_lambda_14_loss: 0.5222 - val_distribution_lambda_15_loss: 1.3817 - val_distribution_lambda_16_loss: 0.4229\n", "Epoch 863/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4055 - distribution_lambda_14_loss: 0.5279 - distribution_lambda_15_loss: 1.4236 - distribution_lambda_16_loss: 0.4540 - val_loss: 2.3286 - val_distribution_lambda_14_loss: 0.5234 - val_distribution_lambda_15_loss: 1.3824 - val_distribution_lambda_16_loss: 0.4228\n", "Epoch 864/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3442 - distribution_lambda_14_loss: 0.5120 - distribution_lambda_15_loss: 1.4005 - distribution_lambda_16_loss: 0.4317 - val_loss: 2.3245 - val_distribution_lambda_14_loss: 0.5227 - val_distribution_lambda_15_loss: 1.3797 - val_distribution_lambda_16_loss: 0.4222\n", "Epoch 865/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.3934 - distribution_lambda_14_loss: 0.5383 - distribution_lambda_15_loss: 1.4176 - distribution_lambda_16_loss: 0.4376 - val_loss: 2.3170 - val_distribution_lambda_14_loss: 0.5164 - val_distribution_lambda_15_loss: 1.3791 - val_distribution_lambda_16_loss: 0.4215\n", "Epoch 866/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4257 - distribution_lambda_14_loss: 0.5538 - distribution_lambda_15_loss: 1.4292 - distribution_lambda_16_loss: 0.4427 - val_loss: 2.3130 - val_distribution_lambda_14_loss: 0.5132 - val_distribution_lambda_15_loss: 1.3792 - val_distribution_lambda_16_loss: 0.4206\n", "Epoch 867/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3765 - distribution_lambda_14_loss: 0.5397 - distribution_lambda_15_loss: 1.4043 - distribution_lambda_16_loss: 0.4325 - val_loss: 2.3179 - val_distribution_lambda_14_loss: 0.5145 - val_distribution_lambda_15_loss: 1.3839 - val_distribution_lambda_16_loss: 0.4194\n", "Epoch 868/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4061 - distribution_lambda_14_loss: 0.5507 - distribution_lambda_15_loss: 1.4265 - distribution_lambda_16_loss: 0.4289 - val_loss: 2.3247 - val_distribution_lambda_14_loss: 0.5192 - val_distribution_lambda_15_loss: 1.3866 - val_distribution_lambda_16_loss: 0.4189\n", "Epoch 869/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3999 - distribution_lambda_14_loss: 0.5289 - distribution_lambda_15_loss: 1.4251 - distribution_lambda_16_loss: 0.4458 - val_loss: 2.3193 - val_distribution_lambda_14_loss: 0.5208 - val_distribution_lambda_15_loss: 1.3802 - val_distribution_lambda_16_loss: 0.4183\n", "Epoch 870/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4063 - distribution_lambda_14_loss: 0.5313 - distribution_lambda_15_loss: 1.4317 - distribution_lambda_16_loss: 0.4434 - val_loss: 2.3133 - val_distribution_lambda_14_loss: 0.5202 - val_distribution_lambda_15_loss: 1.3757 - val_distribution_lambda_16_loss: 0.4174\n", "Epoch 871/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4071 - distribution_lambda_14_loss: 0.5296 - distribution_lambda_15_loss: 1.4285 - distribution_lambda_16_loss: 0.4490 - val_loss: 2.3127 - val_distribution_lambda_14_loss: 0.5232 - val_distribution_lambda_15_loss: 1.3733 - val_distribution_lambda_16_loss: 0.4162\n", "Epoch 872/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3610 - distribution_lambda_14_loss: 0.5293 - distribution_lambda_15_loss: 1.3976 - distribution_lambda_16_loss: 0.4341 - val_loss: 2.3069 - val_distribution_lambda_14_loss: 0.5194 - val_distribution_lambda_15_loss: 1.3721 - val_distribution_lambda_16_loss: 0.4155\n", "Epoch 873/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4044 - distribution_lambda_14_loss: 0.5464 - distribution_lambda_15_loss: 1.4177 - distribution_lambda_16_loss: 0.4403 - val_loss: 2.3162 - val_distribution_lambda_14_loss: 0.5216 - val_distribution_lambda_15_loss: 1.3789 - val_distribution_lambda_16_loss: 0.4156\n", "Epoch 874/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4069 - distribution_lambda_14_loss: 0.5281 - distribution_lambda_15_loss: 1.4297 - distribution_lambda_16_loss: 0.4492 - val_loss: 2.3226 - val_distribution_lambda_14_loss: 0.5220 - val_distribution_lambda_15_loss: 1.3848 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 875/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3890 - distribution_lambda_14_loss: 0.5301 - distribution_lambda_15_loss: 1.4170 - distribution_lambda_16_loss: 0.4419 - val_loss: 2.3147 - val_distribution_lambda_14_loss: 0.5191 - val_distribution_lambda_15_loss: 1.3797 - val_distribution_lambda_16_loss: 0.4159\n", "Epoch 876/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4289 - distribution_lambda_14_loss: 0.5408 - distribution_lambda_15_loss: 1.4375 - distribution_lambda_16_loss: 0.4506 - val_loss: 2.3033 - val_distribution_lambda_14_loss: 0.5136 - val_distribution_lambda_15_loss: 1.3739 - val_distribution_lambda_16_loss: 0.4159\n", "Epoch 877/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4164 - distribution_lambda_14_loss: 0.5484 - distribution_lambda_15_loss: 1.4273 - distribution_lambda_16_loss: 0.4408 - val_loss: 2.2976 - val_distribution_lambda_14_loss: 0.5073 - val_distribution_lambda_15_loss: 1.3745 - val_distribution_lambda_16_loss: 0.4158\n", "Epoch 878/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3900 - distribution_lambda_14_loss: 0.5284 - distribution_lambda_15_loss: 1.4177 - distribution_lambda_16_loss: 0.4438 - val_loss: 2.2985 - val_distribution_lambda_14_loss: 0.5095 - val_distribution_lambda_15_loss: 1.3732 - val_distribution_lambda_16_loss: 0.4158\n", "Epoch 879/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3820 - distribution_lambda_14_loss: 0.5371 - distribution_lambda_15_loss: 1.4132 - distribution_lambda_16_loss: 0.4318 - val_loss: 2.3092 - val_distribution_lambda_14_loss: 0.5203 - val_distribution_lambda_15_loss: 1.3735 - val_distribution_lambda_16_loss: 0.4155\n", "Epoch 880/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3820 - distribution_lambda_14_loss: 0.5321 - distribution_lambda_15_loss: 1.4063 - distribution_lambda_16_loss: 0.4435 - val_loss: 2.3105 - val_distribution_lambda_14_loss: 0.5214 - val_distribution_lambda_15_loss: 1.3740 - val_distribution_lambda_16_loss: 0.4151\n", "Epoch 881/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3880 - distribution_lambda_14_loss: 0.5426 - distribution_lambda_15_loss: 1.4114 - distribution_lambda_16_loss: 0.4341 - val_loss: 2.3138 - val_distribution_lambda_14_loss: 0.5266 - val_distribution_lambda_15_loss: 1.3721 - val_distribution_lambda_16_loss: 0.4151\n", "Epoch 882/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4015 - distribution_lambda_14_loss: 0.5431 - distribution_lambda_15_loss: 1.4213 - distribution_lambda_16_loss: 0.4370 - val_loss: 2.3135 - val_distribution_lambda_14_loss: 0.5274 - val_distribution_lambda_15_loss: 1.3706 - val_distribution_lambda_16_loss: 0.4155\n", "Epoch 883/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3996 - distribution_lambda_14_loss: 0.5274 - distribution_lambda_15_loss: 1.4195 - distribution_lambda_16_loss: 0.4526 - val_loss: 2.2994 - val_distribution_lambda_14_loss: 0.5159 - val_distribution_lambda_15_loss: 1.3686 - val_distribution_lambda_16_loss: 0.4149\n", "Epoch 884/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4077 - distribution_lambda_14_loss: 0.5441 - distribution_lambda_15_loss: 1.4289 - distribution_lambda_16_loss: 0.4348 - val_loss: 2.2920 - val_distribution_lambda_14_loss: 0.5121 - val_distribution_lambda_15_loss: 1.3656 - val_distribution_lambda_16_loss: 0.4142\n", "Epoch 885/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3728 - distribution_lambda_14_loss: 0.5349 - distribution_lambda_15_loss: 1.4070 - distribution_lambda_16_loss: 0.4309 - val_loss: 2.2924 - val_distribution_lambda_14_loss: 0.5142 - val_distribution_lambda_15_loss: 1.3640 - val_distribution_lambda_16_loss: 0.4141\n", "Epoch 886/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3796 - distribution_lambda_14_loss: 0.5311 - distribution_lambda_15_loss: 1.4111 - distribution_lambda_16_loss: 0.4375 - val_loss: 2.2902 - val_distribution_lambda_14_loss: 0.5140 - val_distribution_lambda_15_loss: 1.3621 - val_distribution_lambda_16_loss: 0.4141\n", "Epoch 887/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3964 - distribution_lambda_14_loss: 0.5367 - distribution_lambda_15_loss: 1.4232 - distribution_lambda_16_loss: 0.4364 - val_loss: 2.2933 - val_distribution_lambda_14_loss: 0.5160 - val_distribution_lambda_15_loss: 1.3628 - val_distribution_lambda_16_loss: 0.4145\n", "Epoch 888/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4039 - distribution_lambda_14_loss: 0.5361 - distribution_lambda_15_loss: 1.4317 - distribution_lambda_16_loss: 0.4360 - val_loss: 2.3163 - val_distribution_lambda_14_loss: 0.5367 - val_distribution_lambda_15_loss: 1.3644 - val_distribution_lambda_16_loss: 0.4152\n", "Epoch 889/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.3469 - distribution_lambda_14_loss: 0.5257 - distribution_lambda_15_loss: 1.3987 - distribution_lambda_16_loss: 0.4225 - val_loss: 2.3401 - val_distribution_lambda_14_loss: 0.5559 - val_distribution_lambda_15_loss: 1.3685 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 890/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3940 - distribution_lambda_14_loss: 0.5525 - distribution_lambda_15_loss: 1.4049 - distribution_lambda_16_loss: 0.4365 - val_loss: 2.3180 - val_distribution_lambda_14_loss: 0.5348 - val_distribution_lambda_15_loss: 1.3675 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 891/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3870 - distribution_lambda_14_loss: 0.5405 - distribution_lambda_15_loss: 1.4065 - distribution_lambda_16_loss: 0.4400 - val_loss: 2.2901 - val_distribution_lambda_14_loss: 0.5084 - val_distribution_lambda_15_loss: 1.3660 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 892/2000\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.3699 - distribution_lambda_14_loss: 0.5299 - distribution_lambda_15_loss: 1.4055 - distribution_lambda_16_loss: 0.4345 - val_loss: 2.2915 - val_distribution_lambda_14_loss: 0.5077 - val_distribution_lambda_15_loss: 1.3677 - val_distribution_lambda_16_loss: 0.4161\n", "Epoch 893/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3653 - distribution_lambda_14_loss: 0.5225 - distribution_lambda_15_loss: 1.4049 - distribution_lambda_16_loss: 0.4379 - val_loss: 2.2956 - val_distribution_lambda_14_loss: 0.5097 - val_distribution_lambda_15_loss: 1.3690 - val_distribution_lambda_16_loss: 0.4168\n", "Epoch 894/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3788 - distribution_lambda_14_loss: 0.5539 - distribution_lambda_15_loss: 1.4016 - distribution_lambda_16_loss: 0.4233 - val_loss: 2.3104 - val_distribution_lambda_14_loss: 0.5203 - val_distribution_lambda_15_loss: 1.3723 - val_distribution_lambda_16_loss: 0.4178\n", "Epoch 895/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4026 - distribution_lambda_14_loss: 0.5337 - distribution_lambda_15_loss: 1.4233 - distribution_lambda_16_loss: 0.4455 - val_loss: 2.3107 - val_distribution_lambda_14_loss: 0.5214 - val_distribution_lambda_15_loss: 1.3714 - val_distribution_lambda_16_loss: 0.4179\n", "Epoch 896/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3873 - distribution_lambda_14_loss: 0.5380 - distribution_lambda_15_loss: 1.4109 - distribution_lambda_16_loss: 0.4384 - val_loss: 2.3038 - val_distribution_lambda_14_loss: 0.5169 - val_distribution_lambda_15_loss: 1.3697 - val_distribution_lambda_16_loss: 0.4172\n", "Epoch 897/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4022 - distribution_lambda_14_loss: 0.5343 - distribution_lambda_15_loss: 1.4231 - distribution_lambda_16_loss: 0.4447 - val_loss: 2.3010 - val_distribution_lambda_14_loss: 0.5148 - val_distribution_lambda_15_loss: 1.3694 - val_distribution_lambda_16_loss: 0.4168\n", "Epoch 898/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3712 - distribution_lambda_14_loss: 0.5212 - distribution_lambda_15_loss: 1.4044 - distribution_lambda_16_loss: 0.4456 - val_loss: 2.2936 - val_distribution_lambda_14_loss: 0.5091 - val_distribution_lambda_15_loss: 1.3684 - val_distribution_lambda_16_loss: 0.4162\n", "Epoch 899/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3589 - distribution_lambda_14_loss: 0.5217 - distribution_lambda_15_loss: 1.4014 - distribution_lambda_16_loss: 0.4358 - val_loss: 2.2883 - val_distribution_lambda_14_loss: 0.5062 - val_distribution_lambda_15_loss: 1.3664 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 900/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3741 - distribution_lambda_14_loss: 0.5144 - distribution_lambda_15_loss: 1.4159 - distribution_lambda_16_loss: 0.4438 - val_loss: 2.2902 - val_distribution_lambda_14_loss: 0.5072 - val_distribution_lambda_15_loss: 1.3673 - val_distribution_lambda_16_loss: 0.4157\n", "Epoch 901/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3870 - distribution_lambda_14_loss: 0.5195 - distribution_lambda_15_loss: 1.4208 - distribution_lambda_16_loss: 0.4467 - val_loss: 2.2967 - val_distribution_lambda_14_loss: 0.5113 - val_distribution_lambda_15_loss: 1.3695 - val_distribution_lambda_16_loss: 0.4159\n", "Epoch 902/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4059 - distribution_lambda_14_loss: 0.5232 - distribution_lambda_15_loss: 1.4327 - distribution_lambda_16_loss: 0.4499 - val_loss: 2.2992 - val_distribution_lambda_14_loss: 0.5100 - val_distribution_lambda_15_loss: 1.3733 - val_distribution_lambda_16_loss: 0.4158\n", "Epoch 903/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3944 - distribution_lambda_14_loss: 0.5441 - distribution_lambda_15_loss: 1.4201 - distribution_lambda_16_loss: 0.4302 - val_loss: 2.2899 - val_distribution_lambda_14_loss: 0.5026 - val_distribution_lambda_15_loss: 1.3721 - val_distribution_lambda_16_loss: 0.4152\n", "Epoch 904/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3903 - distribution_lambda_14_loss: 0.5359 - distribution_lambda_15_loss: 1.4154 - distribution_lambda_16_loss: 0.4390 - val_loss: 2.2829 - val_distribution_lambda_14_loss: 0.5005 - val_distribution_lambda_15_loss: 1.3678 - val_distribution_lambda_16_loss: 0.4146\n", "Epoch 905/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4127 - distribution_lambda_14_loss: 0.5424 - distribution_lambda_15_loss: 1.4303 - distribution_lambda_16_loss: 0.4400 - val_loss: 2.2828 - val_distribution_lambda_14_loss: 0.5017 - val_distribution_lambda_15_loss: 1.3665 - val_distribution_lambda_16_loss: 0.4145\n", "Epoch 906/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3372 - distribution_lambda_14_loss: 0.5178 - distribution_lambda_15_loss: 1.3977 - distribution_lambda_16_loss: 0.4217 - val_loss: 2.2827 - val_distribution_lambda_14_loss: 0.5034 - val_distribution_lambda_15_loss: 1.3649 - val_distribution_lambda_16_loss: 0.4145\n", "Epoch 907/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3760 - distribution_lambda_14_loss: 0.5274 - distribution_lambda_15_loss: 1.4114 - distribution_lambda_16_loss: 0.4372 - val_loss: 2.2806 - val_distribution_lambda_14_loss: 0.5029 - val_distribution_lambda_15_loss: 1.3631 - val_distribution_lambda_16_loss: 0.4146\n", "Epoch 908/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3910 - distribution_lambda_14_loss: 0.5393 - distribution_lambda_15_loss: 1.4177 - distribution_lambda_16_loss: 0.4340 - val_loss: 2.2779 - val_distribution_lambda_14_loss: 0.5006 - val_distribution_lambda_15_loss: 1.3621 - val_distribution_lambda_16_loss: 0.4152\n", "Epoch 909/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3770 - distribution_lambda_14_loss: 0.5282 - distribution_lambda_15_loss: 1.4113 - distribution_lambda_16_loss: 0.4375 - val_loss: 2.2758 - val_distribution_lambda_14_loss: 0.4966 - val_distribution_lambda_15_loss: 1.3640 - val_distribution_lambda_16_loss: 0.4152\n", "Epoch 910/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3894 - distribution_lambda_14_loss: 0.5375 - distribution_lambda_15_loss: 1.4171 - distribution_lambda_16_loss: 0.4349 - val_loss: 2.2836 - val_distribution_lambda_14_loss: 0.5000 - val_distribution_lambda_15_loss: 1.3689 - val_distribution_lambda_16_loss: 0.4147\n", "Epoch 911/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3916 - distribution_lambda_14_loss: 0.5343 - distribution_lambda_15_loss: 1.4141 - distribution_lambda_16_loss: 0.4432 - val_loss: 2.2853 - val_distribution_lambda_14_loss: 0.4990 - val_distribution_lambda_15_loss: 1.3716 - val_distribution_lambda_16_loss: 0.4146\n", "Epoch 912/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3900 - distribution_lambda_14_loss: 0.5233 - distribution_lambda_15_loss: 1.4225 - distribution_lambda_16_loss: 0.4442 - val_loss: 2.2849 - val_distribution_lambda_14_loss: 0.4982 - val_distribution_lambda_15_loss: 1.3717 - val_distribution_lambda_16_loss: 0.4150\n", "Epoch 913/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.3888 - distribution_lambda_14_loss: 0.5383 - distribution_lambda_15_loss: 1.4101 - distribution_lambda_16_loss: 0.4404 - val_loss: 2.2902 - val_distribution_lambda_14_loss: 0.5028 - val_distribution_lambda_15_loss: 1.3718 - val_distribution_lambda_16_loss: 0.4156\n", "Epoch 914/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3794 - distribution_lambda_14_loss: 0.5166 - distribution_lambda_15_loss: 1.4168 - distribution_lambda_16_loss: 0.4460 - val_loss: 2.2921 - val_distribution_lambda_14_loss: 0.5065 - val_distribution_lambda_15_loss: 1.3704 - val_distribution_lambda_16_loss: 0.4152\n", "Epoch 915/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3718 - distribution_lambda_14_loss: 0.5168 - distribution_lambda_15_loss: 1.4146 - distribution_lambda_16_loss: 0.4404 - val_loss: 2.2956 - val_distribution_lambda_14_loss: 0.5112 - val_distribution_lambda_15_loss: 1.3698 - val_distribution_lambda_16_loss: 0.4146\n", "Epoch 916/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3794 - distribution_lambda_14_loss: 0.5256 - distribution_lambda_15_loss: 1.4116 - distribution_lambda_16_loss: 0.4421 - val_loss: 2.2904 - val_distribution_lambda_14_loss: 0.5072 - val_distribution_lambda_15_loss: 1.3689 - val_distribution_lambda_16_loss: 0.4143\n", "Epoch 917/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3815 - distribution_lambda_14_loss: 0.5384 - distribution_lambda_15_loss: 1.4085 - distribution_lambda_16_loss: 0.4347 - val_loss: 2.2811 - val_distribution_lambda_14_loss: 0.5007 - val_distribution_lambda_15_loss: 1.3666 - val_distribution_lambda_16_loss: 0.4138\n", "Epoch 918/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3713 - distribution_lambda_14_loss: 0.5221 - distribution_lambda_15_loss: 1.4162 - distribution_lambda_16_loss: 0.4330 - val_loss: 2.2776 - val_distribution_lambda_14_loss: 0.4982 - val_distribution_lambda_15_loss: 1.3654 - val_distribution_lambda_16_loss: 0.4140\n", "Epoch 919/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3894 - distribution_lambda_14_loss: 0.5281 - distribution_lambda_15_loss: 1.4229 - distribution_lambda_16_loss: 0.4383 - val_loss: 2.2779 - val_distribution_lambda_14_loss: 0.4988 - val_distribution_lambda_15_loss: 1.3649 - val_distribution_lambda_16_loss: 0.4142\n", "Epoch 920/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3308 - distribution_lambda_14_loss: 0.5156 - distribution_lambda_15_loss: 1.3939 - distribution_lambda_16_loss: 0.4214 - val_loss: 2.2818 - val_distribution_lambda_14_loss: 0.5034 - val_distribution_lambda_15_loss: 1.3640 - val_distribution_lambda_16_loss: 0.4144\n", "Epoch 921/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3410 - distribution_lambda_14_loss: 0.5232 - distribution_lambda_15_loss: 1.3940 - distribution_lambda_16_loss: 0.4238 - val_loss: 2.2865 - val_distribution_lambda_14_loss: 0.5074 - val_distribution_lambda_15_loss: 1.3644 - val_distribution_lambda_16_loss: 0.4147\n", "Epoch 922/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3885 - distribution_lambda_14_loss: 0.5223 - distribution_lambda_15_loss: 1.4308 - distribution_lambda_16_loss: 0.4354 - val_loss: 2.2894 - val_distribution_lambda_14_loss: 0.5083 - val_distribution_lambda_15_loss: 1.3662 - val_distribution_lambda_16_loss: 0.4149\n", "Epoch 923/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3618 - distribution_lambda_14_loss: 0.5281 - distribution_lambda_15_loss: 1.4051 - distribution_lambda_16_loss: 0.4286 - val_loss: 2.2958 - val_distribution_lambda_14_loss: 0.5141 - val_distribution_lambda_15_loss: 1.3673 - val_distribution_lambda_16_loss: 0.4144\n", "Epoch 924/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3847 - distribution_lambda_14_loss: 0.5298 - distribution_lambda_15_loss: 1.4074 - distribution_lambda_16_loss: 0.4476 - val_loss: 2.2913 - val_distribution_lambda_14_loss: 0.5109 - val_distribution_lambda_15_loss: 1.3663 - val_distribution_lambda_16_loss: 0.4142\n", "Epoch 925/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3467 - distribution_lambda_14_loss: 0.5195 - distribution_lambda_15_loss: 1.3970 - distribution_lambda_16_loss: 0.4303 - val_loss: 2.2898 - val_distribution_lambda_14_loss: 0.5114 - val_distribution_lambda_15_loss: 1.3645 - val_distribution_lambda_16_loss: 0.4139\n", "Epoch 926/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3629 - distribution_lambda_14_loss: 0.5114 - distribution_lambda_15_loss: 1.4153 - distribution_lambda_16_loss: 0.4362 - val_loss: 2.2805 - val_distribution_lambda_14_loss: 0.5030 - val_distribution_lambda_15_loss: 1.3640 - val_distribution_lambda_16_loss: 0.4135\n", "Epoch 927/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3627 - distribution_lambda_14_loss: 0.5223 - distribution_lambda_15_loss: 1.4016 - distribution_lambda_16_loss: 0.4388 - val_loss: 2.2746 - val_distribution_lambda_14_loss: 0.4976 - val_distribution_lambda_15_loss: 1.3631 - val_distribution_lambda_16_loss: 0.4138\n", "Epoch 928/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3754 - distribution_lambda_14_loss: 0.5343 - distribution_lambda_15_loss: 1.4111 - distribution_lambda_16_loss: 0.4301 - val_loss: 2.2697 - val_distribution_lambda_14_loss: 0.4928 - val_distribution_lambda_15_loss: 1.3628 - val_distribution_lambda_16_loss: 0.4141\n", "Epoch 929/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3406 - distribution_lambda_14_loss: 0.5169 - distribution_lambda_15_loss: 1.3999 - distribution_lambda_16_loss: 0.4238 - val_loss: 2.2679 - val_distribution_lambda_14_loss: 0.4919 - val_distribution_lambda_15_loss: 1.3616 - val_distribution_lambda_16_loss: 0.4144\n", "Epoch 930/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3862 - distribution_lambda_14_loss: 0.5237 - distribution_lambda_15_loss: 1.4182 - distribution_lambda_16_loss: 0.4444 - val_loss: 2.2657 - val_distribution_lambda_14_loss: 0.4914 - val_distribution_lambda_15_loss: 1.3598 - val_distribution_lambda_16_loss: 0.4145\n", "Epoch 931/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3564 - distribution_lambda_14_loss: 0.5190 - distribution_lambda_15_loss: 1.4050 - distribution_lambda_16_loss: 0.4324 - val_loss: 2.2627 - val_distribution_lambda_14_loss: 0.4899 - val_distribution_lambda_15_loss: 1.3581 - val_distribution_lambda_16_loss: 0.4147\n", "Epoch 932/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4040 - distribution_lambda_14_loss: 0.5337 - distribution_lambda_15_loss: 1.4246 - distribution_lambda_16_loss: 0.4457 - val_loss: 2.2632 - val_distribution_lambda_14_loss: 0.4915 - val_distribution_lambda_15_loss: 1.3568 - val_distribution_lambda_16_loss: 0.4148\n", "Epoch 933/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3067 - distribution_lambda_14_loss: 0.5067 - distribution_lambda_15_loss: 1.3786 - distribution_lambda_16_loss: 0.4214 - val_loss: 2.2732 - val_distribution_lambda_14_loss: 0.4992 - val_distribution_lambda_15_loss: 1.3594 - val_distribution_lambda_16_loss: 0.4146\n", "Epoch 934/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3615 - distribution_lambda_14_loss: 0.5208 - distribution_lambda_15_loss: 1.3999 - distribution_lambda_16_loss: 0.4409 - val_loss: 2.2771 - val_distribution_lambda_14_loss: 0.5025 - val_distribution_lambda_15_loss: 1.3617 - val_distribution_lambda_16_loss: 0.4129\n", "Epoch 935/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3821 - distribution_lambda_14_loss: 0.5313 - distribution_lambda_15_loss: 1.4156 - distribution_lambda_16_loss: 0.4352 - val_loss: 2.2708 - val_distribution_lambda_14_loss: 0.5004 - val_distribution_lambda_15_loss: 1.3587 - val_distribution_lambda_16_loss: 0.4117\n", "Epoch 936/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3536 - distribution_lambda_14_loss: 0.5209 - distribution_lambda_15_loss: 1.3962 - distribution_lambda_16_loss: 0.4365 - val_loss: 2.2714 - val_distribution_lambda_14_loss: 0.5034 - val_distribution_lambda_15_loss: 1.3565 - val_distribution_lambda_16_loss: 0.4115\n", "Epoch 937/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.3600 - distribution_lambda_14_loss: 0.5284 - distribution_lambda_15_loss: 1.3964 - distribution_lambda_16_loss: 0.4352 - val_loss: 2.2769 - val_distribution_lambda_14_loss: 0.5097 - val_distribution_lambda_15_loss: 1.3560 - val_distribution_lambda_16_loss: 0.4112\n", "Epoch 938/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3816 - distribution_lambda_14_loss: 0.5288 - distribution_lambda_15_loss: 1.4107 - distribution_lambda_16_loss: 0.4421 - val_loss: 2.2695 - val_distribution_lambda_14_loss: 0.5018 - val_distribution_lambda_15_loss: 1.3568 - val_distribution_lambda_16_loss: 0.4109\n", "Epoch 939/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3292 - distribution_lambda_14_loss: 0.5086 - distribution_lambda_15_loss: 1.3916 - distribution_lambda_16_loss: 0.4290 - val_loss: 2.2662 - val_distribution_lambda_14_loss: 0.4941 - val_distribution_lambda_15_loss: 1.3611 - val_distribution_lambda_16_loss: 0.4109\n", "Epoch 940/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3908 - distribution_lambda_14_loss: 0.5359 - distribution_lambda_15_loss: 1.4226 - distribution_lambda_16_loss: 0.4323 - val_loss: 2.2680 - val_distribution_lambda_14_loss: 0.4935 - val_distribution_lambda_15_loss: 1.3632 - val_distribution_lambda_16_loss: 0.4113\n", "Epoch 941/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3454 - distribution_lambda_14_loss: 0.5112 - distribution_lambda_15_loss: 1.3993 - distribution_lambda_16_loss: 0.4348 - val_loss: 2.2685 - val_distribution_lambda_14_loss: 0.4936 - val_distribution_lambda_15_loss: 1.3634 - val_distribution_lambda_16_loss: 0.4115\n", "Epoch 942/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3807 - distribution_lambda_14_loss: 0.5199 - distribution_lambda_15_loss: 1.4240 - distribution_lambda_16_loss: 0.4368 - val_loss: 2.2731 - val_distribution_lambda_14_loss: 0.4953 - val_distribution_lambda_15_loss: 1.3653 - val_distribution_lambda_16_loss: 0.4124\n", "Epoch 943/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3656 - distribution_lambda_14_loss: 0.5217 - distribution_lambda_15_loss: 1.4045 - distribution_lambda_16_loss: 0.4394 - val_loss: 2.2697 - val_distribution_lambda_14_loss: 0.4918 - val_distribution_lambda_15_loss: 1.3643 - val_distribution_lambda_16_loss: 0.4136\n", "Epoch 944/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3290 - distribution_lambda_14_loss: 0.5024 - distribution_lambda_15_loss: 1.3979 - distribution_lambda_16_loss: 0.4287 - val_loss: 2.2681 - val_distribution_lambda_14_loss: 0.4916 - val_distribution_lambda_15_loss: 1.3627 - val_distribution_lambda_16_loss: 0.4138\n", "Epoch 945/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3297 - distribution_lambda_14_loss: 0.4928 - distribution_lambda_15_loss: 1.4070 - distribution_lambda_16_loss: 0.4299 - val_loss: 2.2688 - val_distribution_lambda_14_loss: 0.4937 - val_distribution_lambda_15_loss: 1.3610 - val_distribution_lambda_16_loss: 0.4140\n", "Epoch 946/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3375 - distribution_lambda_14_loss: 0.5200 - distribution_lambda_15_loss: 1.3871 - distribution_lambda_16_loss: 0.4303 - val_loss: 2.2701 - val_distribution_lambda_14_loss: 0.4958 - val_distribution_lambda_15_loss: 1.3599 - val_distribution_lambda_16_loss: 0.4143\n", "Epoch 947/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3715 - distribution_lambda_14_loss: 0.5221 - distribution_lambda_15_loss: 1.4093 - distribution_lambda_16_loss: 0.4401 - val_loss: 2.2774 - val_distribution_lambda_14_loss: 0.5027 - val_distribution_lambda_15_loss: 1.3603 - val_distribution_lambda_16_loss: 0.4143\n", "Epoch 948/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3164 - distribution_lambda_14_loss: 0.4964 - distribution_lambda_15_loss: 1.3916 - distribution_lambda_16_loss: 0.4284 - val_loss: 2.2758 - val_distribution_lambda_14_loss: 0.4998 - val_distribution_lambda_15_loss: 1.3620 - val_distribution_lambda_16_loss: 0.4140\n", "Epoch 949/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3713 - distribution_lambda_14_loss: 0.5373 - distribution_lambda_15_loss: 1.4056 - distribution_lambda_16_loss: 0.4284 - val_loss: 2.2692 - val_distribution_lambda_14_loss: 0.4945 - val_distribution_lambda_15_loss: 1.3618 - val_distribution_lambda_16_loss: 0.4129\n", "Epoch 950/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3638 - distribution_lambda_14_loss: 0.5189 - distribution_lambda_15_loss: 1.4065 - distribution_lambda_16_loss: 0.4384 - val_loss: 2.2683 - val_distribution_lambda_14_loss: 0.4953 - val_distribution_lambda_15_loss: 1.3611 - val_distribution_lambda_16_loss: 0.4119\n", "Epoch 951/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3500 - distribution_lambda_14_loss: 0.5225 - distribution_lambda_15_loss: 1.3942 - distribution_lambda_16_loss: 0.4333 - val_loss: 2.2711 - val_distribution_lambda_14_loss: 0.4994 - val_distribution_lambda_15_loss: 1.3596 - val_distribution_lambda_16_loss: 0.4120\n", "Epoch 952/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3452 - distribution_lambda_14_loss: 0.5145 - distribution_lambda_15_loss: 1.3949 - distribution_lambda_16_loss: 0.4357 - val_loss: 2.2796 - val_distribution_lambda_14_loss: 0.5083 - val_distribution_lambda_15_loss: 1.3587 - val_distribution_lambda_16_loss: 0.4126\n", "Epoch 953/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3337 - distribution_lambda_14_loss: 0.5159 - distribution_lambda_15_loss: 1.3883 - distribution_lambda_16_loss: 0.4295 - val_loss: 2.2804 - val_distribution_lambda_14_loss: 0.5083 - val_distribution_lambda_15_loss: 1.3587 - val_distribution_lambda_16_loss: 0.4134\n", "Epoch 954/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3709 - distribution_lambda_14_loss: 0.5305 - distribution_lambda_15_loss: 1.4111 - distribution_lambda_16_loss: 0.4292 - val_loss: 2.2747 - val_distribution_lambda_14_loss: 0.5013 - val_distribution_lambda_15_loss: 1.3601 - val_distribution_lambda_16_loss: 0.4133\n", "Epoch 955/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3587 - distribution_lambda_14_loss: 0.5259 - distribution_lambda_15_loss: 1.4052 - distribution_lambda_16_loss: 0.4276 - val_loss: 2.2729 - val_distribution_lambda_14_loss: 0.5006 - val_distribution_lambda_15_loss: 1.3591 - val_distribution_lambda_16_loss: 0.4132\n", "Epoch 956/2000\n", "8/8 [==============================] - 0s 10ms/step - loss: 2.3394 - distribution_lambda_14_loss: 0.5156 - distribution_lambda_15_loss: 1.3910 - distribution_lambda_16_loss: 0.4328 - val_loss: 2.2704 - val_distribution_lambda_14_loss: 0.5000 - val_distribution_lambda_15_loss: 1.3574 - val_distribution_lambda_16_loss: 0.4130\n", "Epoch 957/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3731 - distribution_lambda_14_loss: 0.5231 - distribution_lambda_15_loss: 1.4177 - distribution_lambda_16_loss: 0.4324 - val_loss: 2.2657 - val_distribution_lambda_14_loss: 0.4969 - val_distribution_lambda_15_loss: 1.3564 - val_distribution_lambda_16_loss: 0.4123\n", "Epoch 958/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3470 - distribution_lambda_14_loss: 0.5139 - distribution_lambda_15_loss: 1.3968 - distribution_lambda_16_loss: 0.4362 - val_loss: 2.2581 - val_distribution_lambda_14_loss: 0.4920 - val_distribution_lambda_15_loss: 1.3547 - val_distribution_lambda_16_loss: 0.4114\n", "Epoch 959/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3562 - distribution_lambda_14_loss: 0.5149 - distribution_lambda_15_loss: 1.4065 - distribution_lambda_16_loss: 0.4349 - val_loss: 2.2567 - val_distribution_lambda_14_loss: 0.4911 - val_distribution_lambda_15_loss: 1.3545 - val_distribution_lambda_16_loss: 0.4111\n", "Epoch 960/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3673 - distribution_lambda_14_loss: 0.5216 - distribution_lambda_15_loss: 1.4084 - distribution_lambda_16_loss: 0.4373 - val_loss: 2.2603 - val_distribution_lambda_14_loss: 0.4925 - val_distribution_lambda_15_loss: 1.3567 - val_distribution_lambda_16_loss: 0.4110\n", "Epoch 961/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.3415 - distribution_lambda_14_loss: 0.5051 - distribution_lambda_15_loss: 1.4107 - distribution_lambda_16_loss: 0.4257 - val_loss: 2.2597 - val_distribution_lambda_14_loss: 0.4890 - val_distribution_lambda_15_loss: 1.3593 - val_distribution_lambda_16_loss: 0.4114\n", "Epoch 962/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3228 - distribution_lambda_14_loss: 0.5003 - distribution_lambda_15_loss: 1.3952 - distribution_lambda_16_loss: 0.4273 - val_loss: 2.2605 - val_distribution_lambda_14_loss: 0.4878 - val_distribution_lambda_15_loss: 1.3617 - val_distribution_lambda_16_loss: 0.4110\n", "Epoch 963/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3059 - distribution_lambda_14_loss: 0.4990 - distribution_lambda_15_loss: 1.3867 - distribution_lambda_16_loss: 0.4201 - val_loss: 2.2624 - val_distribution_lambda_14_loss: 0.4918 - val_distribution_lambda_15_loss: 1.3603 - val_distribution_lambda_16_loss: 0.4103\n", "Epoch 964/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3375 - distribution_lambda_14_loss: 0.5046 - distribution_lambda_15_loss: 1.4053 - distribution_lambda_16_loss: 0.4277 - val_loss: 2.2649 - val_distribution_lambda_14_loss: 0.4967 - val_distribution_lambda_15_loss: 1.3581 - val_distribution_lambda_16_loss: 0.4102\n", "Epoch 965/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3477 - distribution_lambda_14_loss: 0.5181 - distribution_lambda_15_loss: 1.3936 - distribution_lambda_16_loss: 0.4360 - val_loss: 2.2582 - val_distribution_lambda_14_loss: 0.4919 - val_distribution_lambda_15_loss: 1.3557 - val_distribution_lambda_16_loss: 0.4105\n", "Epoch 966/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3605 - distribution_lambda_14_loss: 0.5209 - distribution_lambda_15_loss: 1.4063 - distribution_lambda_16_loss: 0.4333 - val_loss: 2.2501 - val_distribution_lambda_14_loss: 0.4856 - val_distribution_lambda_15_loss: 1.3543 - val_distribution_lambda_16_loss: 0.4102\n", "Epoch 967/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3703 - distribution_lambda_14_loss: 0.5344 - distribution_lambda_15_loss: 1.4061 - distribution_lambda_16_loss: 0.4298 - val_loss: 2.2499 - val_distribution_lambda_14_loss: 0.4845 - val_distribution_lambda_15_loss: 1.3558 - val_distribution_lambda_16_loss: 0.4097\n", "Epoch 968/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3163 - distribution_lambda_14_loss: 0.4967 - distribution_lambda_15_loss: 1.3942 - distribution_lambda_16_loss: 0.4254 - val_loss: 2.2537 - val_distribution_lambda_14_loss: 0.4892 - val_distribution_lambda_15_loss: 1.3554 - val_distribution_lambda_16_loss: 0.4091\n", "Epoch 969/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3618 - distribution_lambda_14_loss: 0.5350 - distribution_lambda_15_loss: 1.3954 - distribution_lambda_16_loss: 0.4314 - val_loss: 2.2541 - val_distribution_lambda_14_loss: 0.4914 - val_distribution_lambda_15_loss: 1.3540 - val_distribution_lambda_16_loss: 0.4087\n", "Epoch 970/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3231 - distribution_lambda_14_loss: 0.5109 - distribution_lambda_15_loss: 1.3859 - distribution_lambda_16_loss: 0.4263 - val_loss: 2.2537 - val_distribution_lambda_14_loss: 0.4916 - val_distribution_lambda_15_loss: 1.3531 - val_distribution_lambda_16_loss: 0.4090\n", "Epoch 971/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3266 - distribution_lambda_14_loss: 0.4832 - distribution_lambda_15_loss: 1.4075 - distribution_lambda_16_loss: 0.4358 - val_loss: 2.2561 - val_distribution_lambda_14_loss: 0.4949 - val_distribution_lambda_15_loss: 1.3517 - val_distribution_lambda_16_loss: 0.4095\n", "Epoch 972/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3681 - distribution_lambda_14_loss: 0.5342 - distribution_lambda_15_loss: 1.4111 - distribution_lambda_16_loss: 0.4227 - val_loss: 2.2426 - val_distribution_lambda_14_loss: 0.4821 - val_distribution_lambda_15_loss: 1.3507 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 973/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3460 - distribution_lambda_14_loss: 0.5321 - distribution_lambda_15_loss: 1.3998 - distribution_lambda_16_loss: 0.4141 - val_loss: 2.2392 - val_distribution_lambda_14_loss: 0.4784 - val_distribution_lambda_15_loss: 1.3504 - val_distribution_lambda_16_loss: 0.4104\n", "Epoch 974/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3361 - distribution_lambda_14_loss: 0.5271 - distribution_lambda_15_loss: 1.3889 - distribution_lambda_16_loss: 0.4200 - val_loss: 2.2393 - val_distribution_lambda_14_loss: 0.4782 - val_distribution_lambda_15_loss: 1.3508 - val_distribution_lambda_16_loss: 0.4103\n", "Epoch 975/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3490 - distribution_lambda_14_loss: 0.5145 - distribution_lambda_15_loss: 1.4040 - distribution_lambda_16_loss: 0.4305 - val_loss: 2.2460 - val_distribution_lambda_14_loss: 0.4824 - val_distribution_lambda_15_loss: 1.3537 - val_distribution_lambda_16_loss: 0.4099\n", "Epoch 976/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3488 - distribution_lambda_14_loss: 0.5130 - distribution_lambda_15_loss: 1.4051 - distribution_lambda_16_loss: 0.4306 - val_loss: 2.2588 - val_distribution_lambda_14_loss: 0.4944 - val_distribution_lambda_15_loss: 1.3546 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 977/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3761 - distribution_lambda_14_loss: 0.5294 - distribution_lambda_15_loss: 1.4143 - distribution_lambda_16_loss: 0.4324 - val_loss: 2.2620 - val_distribution_lambda_14_loss: 0.4972 - val_distribution_lambda_15_loss: 1.3550 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 978/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3593 - distribution_lambda_14_loss: 0.5197 - distribution_lambda_15_loss: 1.4018 - distribution_lambda_16_loss: 0.4379 - val_loss: 2.2497 - val_distribution_lambda_14_loss: 0.4870 - val_distribution_lambda_15_loss: 1.3530 - val_distribution_lambda_16_loss: 0.4097\n", "Epoch 979/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3531 - distribution_lambda_14_loss: 0.5160 - distribution_lambda_15_loss: 1.4025 - distribution_lambda_16_loss: 0.4347 - val_loss: 2.2456 - val_distribution_lambda_14_loss: 0.4839 - val_distribution_lambda_15_loss: 1.3522 - val_distribution_lambda_16_loss: 0.4095\n", "Epoch 980/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3382 - distribution_lambda_14_loss: 0.5118 - distribution_lambda_15_loss: 1.3888 - distribution_lambda_16_loss: 0.4376 - val_loss: 2.2489 - val_distribution_lambda_14_loss: 0.4873 - val_distribution_lambda_15_loss: 1.3514 - val_distribution_lambda_16_loss: 0.4102\n", "Epoch 981/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3444 - distribution_lambda_14_loss: 0.5164 - distribution_lambda_15_loss: 1.4023 - distribution_lambda_16_loss: 0.4257 - val_loss: 2.2533 - val_distribution_lambda_14_loss: 0.4925 - val_distribution_lambda_15_loss: 1.3496 - val_distribution_lambda_16_loss: 0.4112\n", "Epoch 982/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3392 - distribution_lambda_14_loss: 0.5235 - distribution_lambda_15_loss: 1.3899 - distribution_lambda_16_loss: 0.4258 - val_loss: 2.2563 - val_distribution_lambda_14_loss: 0.4954 - val_distribution_lambda_15_loss: 1.3492 - val_distribution_lambda_16_loss: 0.4117\n", "Epoch 983/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3366 - distribution_lambda_14_loss: 0.5119 - distribution_lambda_15_loss: 1.4034 - distribution_lambda_16_loss: 0.4214 - val_loss: 2.2547 - val_distribution_lambda_14_loss: 0.4944 - val_distribution_lambda_15_loss: 1.3489 - val_distribution_lambda_16_loss: 0.4115\n", "Epoch 984/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3391 - distribution_lambda_14_loss: 0.5228 - distribution_lambda_15_loss: 1.3912 - distribution_lambda_16_loss: 0.4251 - val_loss: 2.2465 - val_distribution_lambda_14_loss: 0.4870 - val_distribution_lambda_15_loss: 1.3483 - val_distribution_lambda_16_loss: 0.4112\n", "Epoch 985/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.3423 - distribution_lambda_14_loss: 0.4994 - distribution_lambda_15_loss: 1.4045 - distribution_lambda_16_loss: 0.4384 - val_loss: 2.2405 - val_distribution_lambda_14_loss: 0.4816 - val_distribution_lambda_15_loss: 1.3487 - val_distribution_lambda_16_loss: 0.4102\n", "Epoch 986/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.2932 - distribution_lambda_14_loss: 0.4963 - distribution_lambda_15_loss: 1.3872 - distribution_lambda_16_loss: 0.4096 - val_loss: 2.2445 - val_distribution_lambda_14_loss: 0.4834 - val_distribution_lambda_15_loss: 1.3518 - val_distribution_lambda_16_loss: 0.4093\n", "Epoch 987/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3099 - distribution_lambda_14_loss: 0.5151 - distribution_lambda_15_loss: 1.3830 - distribution_lambda_16_loss: 0.4118 - val_loss: 2.2564 - val_distribution_lambda_14_loss: 0.4931 - val_distribution_lambda_15_loss: 1.3547 - val_distribution_lambda_16_loss: 0.4086\n", "Epoch 988/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.2965 - distribution_lambda_14_loss: 0.4911 - distribution_lambda_15_loss: 1.3811 - distribution_lambda_16_loss: 0.4244 - val_loss: 2.2565 - val_distribution_lambda_14_loss: 0.4944 - val_distribution_lambda_15_loss: 1.3538 - val_distribution_lambda_16_loss: 0.4084\n", "Epoch 989/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3282 - distribution_lambda_14_loss: 0.5020 - distribution_lambda_15_loss: 1.3905 - distribution_lambda_16_loss: 0.4357 - val_loss: 2.2523 - val_distribution_lambda_14_loss: 0.4940 - val_distribution_lambda_15_loss: 1.3501 - val_distribution_lambda_16_loss: 0.4082\n", "Epoch 990/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3412 - distribution_lambda_14_loss: 0.5190 - distribution_lambda_15_loss: 1.3984 - distribution_lambda_16_loss: 0.4239 - val_loss: 2.2424 - val_distribution_lambda_14_loss: 0.4869 - val_distribution_lambda_15_loss: 1.3474 - val_distribution_lambda_16_loss: 0.4081\n", "Epoch 991/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3540 - distribution_lambda_14_loss: 0.5018 - distribution_lambda_15_loss: 1.4117 - distribution_lambda_16_loss: 0.4405 - val_loss: 2.2438 - val_distribution_lambda_14_loss: 0.4879 - val_distribution_lambda_15_loss: 1.3476 - val_distribution_lambda_16_loss: 0.4083\n", "Epoch 992/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3120 - distribution_lambda_14_loss: 0.5014 - distribution_lambda_15_loss: 1.3801 - distribution_lambda_16_loss: 0.4305 - val_loss: 2.2357 - val_distribution_lambda_14_loss: 0.4805 - val_distribution_lambda_15_loss: 1.3468 - val_distribution_lambda_16_loss: 0.4085\n", "Epoch 993/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.2814 - distribution_lambda_14_loss: 0.4891 - distribution_lambda_15_loss: 1.3724 - distribution_lambda_16_loss: 0.4199 - val_loss: 2.2312 - val_distribution_lambda_14_loss: 0.4766 - val_distribution_lambda_15_loss: 1.3460 - val_distribution_lambda_16_loss: 0.4086\n", "Epoch 994/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3234 - distribution_lambda_14_loss: 0.5115 - distribution_lambda_15_loss: 1.3850 - distribution_lambda_16_loss: 0.4269 - val_loss: 2.2406 - val_distribution_lambda_14_loss: 0.4851 - val_distribution_lambda_15_loss: 1.3460 - val_distribution_lambda_16_loss: 0.4095\n", "Epoch 995/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3835 - distribution_lambda_14_loss: 0.5295 - distribution_lambda_15_loss: 1.4168 - distribution_lambda_16_loss: 0.4372 - val_loss: 2.2437 - val_distribution_lambda_14_loss: 0.4866 - val_distribution_lambda_15_loss: 1.3471 - val_distribution_lambda_16_loss: 0.4100\n", "Epoch 996/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3196 - distribution_lambda_14_loss: 0.5139 - distribution_lambda_15_loss: 1.3784 - distribution_lambda_16_loss: 0.4273 - val_loss: 2.2354 - val_distribution_lambda_14_loss: 0.4789 - val_distribution_lambda_15_loss: 1.3468 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 997/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3753 - distribution_lambda_14_loss: 0.5247 - distribution_lambda_15_loss: 1.4152 - distribution_lambda_16_loss: 0.4354 - val_loss: 2.2278 - val_distribution_lambda_14_loss: 0.4738 - val_distribution_lambda_15_loss: 1.3444 - val_distribution_lambda_16_loss: 0.4096\n", "Epoch 998/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3234 - distribution_lambda_14_loss: 0.5078 - distribution_lambda_15_loss: 1.3811 - distribution_lambda_16_loss: 0.4345 - val_loss: 2.2324 - val_distribution_lambda_14_loss: 0.4769 - val_distribution_lambda_15_loss: 1.3456 - val_distribution_lambda_16_loss: 0.4099\n", "Epoch 999/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.2870 - distribution_lambda_14_loss: 0.4900 - distribution_lambda_15_loss: 1.3735 - distribution_lambda_16_loss: 0.4235 - val_loss: 2.2409 - val_distribution_lambda_14_loss: 0.4846 - val_distribution_lambda_15_loss: 1.3465 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 1000/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3589 - distribution_lambda_14_loss: 0.5149 - distribution_lambda_15_loss: 1.4148 - distribution_lambda_16_loss: 0.4292 - val_loss: 2.2393 - val_distribution_lambda_14_loss: 0.4821 - val_distribution_lambda_15_loss: 1.3477 - val_distribution_lambda_16_loss: 0.4094\n", "Epoch 1001/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2987 - distribution_lambda_14_loss: 0.4940 - distribution_lambda_15_loss: 1.3885 - distribution_lambda_16_loss: 0.4162 - val_loss: 2.2444 - val_distribution_lambda_14_loss: 0.4856 - val_distribution_lambda_15_loss: 1.3497 - val_distribution_lambda_16_loss: 0.4091\n", "Epoch 1002/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3243 - distribution_lambda_14_loss: 0.5007 - distribution_lambda_15_loss: 1.3973 - distribution_lambda_16_loss: 0.4264 - val_loss: 2.2604 - val_distribution_lambda_14_loss: 0.4992 - val_distribution_lambda_15_loss: 1.3518 - val_distribution_lambda_16_loss: 0.4094\n", "Epoch 1003/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3514 - distribution_lambda_14_loss: 0.5215 - distribution_lambda_15_loss: 1.4027 - distribution_lambda_16_loss: 0.4272 - val_loss: 2.2437 - val_distribution_lambda_14_loss: 0.4853 - val_distribution_lambda_15_loss: 1.3496 - val_distribution_lambda_16_loss: 0.4088\n", "Epoch 1004/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3506 - distribution_lambda_14_loss: 0.5099 - distribution_lambda_15_loss: 1.4096 - distribution_lambda_16_loss: 0.4311 - val_loss: 2.2356 - val_distribution_lambda_14_loss: 0.4799 - val_distribution_lambda_15_loss: 1.3480 - val_distribution_lambda_16_loss: 0.4077\n", "Epoch 1005/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3188 - distribution_lambda_14_loss: 0.5178 - distribution_lambda_15_loss: 1.3797 - distribution_lambda_16_loss: 0.4212 - val_loss: 2.2406 - val_distribution_lambda_14_loss: 0.4857 - val_distribution_lambda_15_loss: 1.3477 - val_distribution_lambda_16_loss: 0.4072\n", "Epoch 1006/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.2848 - distribution_lambda_14_loss: 0.4929 - distribution_lambda_15_loss: 1.3737 - distribution_lambda_16_loss: 0.4182 - val_loss: 2.2444 - val_distribution_lambda_14_loss: 0.4902 - val_distribution_lambda_15_loss: 1.3468 - val_distribution_lambda_16_loss: 0.4074\n", "Epoch 1007/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3249 - distribution_lambda_14_loss: 0.5000 - distribution_lambda_15_loss: 1.3934 - distribution_lambda_16_loss: 0.4315 - val_loss: 2.2377 - val_distribution_lambda_14_loss: 0.4842 - val_distribution_lambda_15_loss: 1.3463 - val_distribution_lambda_16_loss: 0.4073\n", "Epoch 1008/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3337 - distribution_lambda_14_loss: 0.4984 - distribution_lambda_15_loss: 1.4018 - distribution_lambda_16_loss: 0.4335 - val_loss: 2.2351 - val_distribution_lambda_14_loss: 0.4805 - val_distribution_lambda_15_loss: 1.3477 - val_distribution_lambda_16_loss: 0.4070\n", "Epoch 1009/2000\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.3292 - distribution_lambda_14_loss: 0.5101 - distribution_lambda_15_loss: 1.3967 - distribution_lambda_16_loss: 0.4225 - val_loss: 2.2445 - val_distribution_lambda_14_loss: 0.4876 - val_distribution_lambda_15_loss: 1.3498 - val_distribution_lambda_16_loss: 0.4071\n", "Epoch 1010/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3071 - distribution_lambda_14_loss: 0.4932 - distribution_lambda_15_loss: 1.3910 - distribution_lambda_16_loss: 0.4230 - val_loss: 2.2515 - val_distribution_lambda_14_loss: 0.4963 - val_distribution_lambda_15_loss: 1.3480 - val_distribution_lambda_16_loss: 0.4072\n", "Epoch 1011/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3455 - distribution_lambda_14_loss: 0.5052 - distribution_lambda_15_loss: 1.4100 - distribution_lambda_16_loss: 0.4303 - val_loss: 2.2383 - val_distribution_lambda_14_loss: 0.4855 - val_distribution_lambda_15_loss: 1.3453 - val_distribution_lambda_16_loss: 0.4075\n", "Epoch 1012/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3462 - distribution_lambda_14_loss: 0.5201 - distribution_lambda_15_loss: 1.3931 - distribution_lambda_16_loss: 0.4330 - val_loss: 2.2285 - val_distribution_lambda_14_loss: 0.4761 - val_distribution_lambda_15_loss: 1.3445 - val_distribution_lambda_16_loss: 0.4079\n", "Epoch 1013/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3196 - distribution_lambda_14_loss: 0.5129 - distribution_lambda_15_loss: 1.3879 - distribution_lambda_16_loss: 0.4188 - val_loss: 2.2310 - val_distribution_lambda_14_loss: 0.4765 - val_distribution_lambda_15_loss: 1.3458 - val_distribution_lambda_16_loss: 0.4088\n", "Epoch 1014/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3147 - distribution_lambda_14_loss: 0.4974 - distribution_lambda_15_loss: 1.3879 - distribution_lambda_16_loss: 0.4295 - val_loss: 2.2486 - val_distribution_lambda_14_loss: 0.4905 - val_distribution_lambda_15_loss: 1.3482 - val_distribution_lambda_16_loss: 0.4098\n", "Epoch 1015/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3296 - distribution_lambda_14_loss: 0.5090 - distribution_lambda_15_loss: 1.3893 - distribution_lambda_16_loss: 0.4314 - val_loss: 2.2434 - val_distribution_lambda_14_loss: 0.4840 - val_distribution_lambda_15_loss: 1.3489 - val_distribution_lambda_16_loss: 0.4105\n", "Epoch 1016/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3451 - distribution_lambda_14_loss: 0.5176 - distribution_lambda_15_loss: 1.3953 - distribution_lambda_16_loss: 0.4322 - val_loss: 2.2334 - val_distribution_lambda_14_loss: 0.4757 - val_distribution_lambda_15_loss: 1.3471 - val_distribution_lambda_16_loss: 0.4106\n", "Epoch 1017/2000\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.3335 - distribution_lambda_14_loss: 0.5025 - distribution_lambda_15_loss: 1.3952 - distribution_lambda_16_loss: 0.4357 - val_loss: 2.2352 - val_distribution_lambda_14_loss: 0.4775 - val_distribution_lambda_15_loss: 1.3467 - val_distribution_lambda_16_loss: 0.4110\n", "Epoch 1018/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2974 - distribution_lambda_14_loss: 0.4987 - distribution_lambda_15_loss: 1.3775 - distribution_lambda_16_loss: 0.4212 - val_loss: 2.2353 - val_distribution_lambda_14_loss: 0.4773 - val_distribution_lambda_15_loss: 1.3464 - val_distribution_lambda_16_loss: 0.4116\n", "Epoch 1019/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3384 - distribution_lambda_14_loss: 0.5095 - distribution_lambda_15_loss: 1.4012 - distribution_lambda_16_loss: 0.4277 - val_loss: 2.2349 - val_distribution_lambda_14_loss: 0.4745 - val_distribution_lambda_15_loss: 1.3486 - val_distribution_lambda_16_loss: 0.4119\n", "Epoch 1020/2000\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3227 - distribution_lambda_14_loss: 0.5165 - distribution_lambda_15_loss: 1.3865 - distribution_lambda_16_loss: 0.4197 - val_loss: 2.2334 - val_distribution_lambda_14_loss: 0.4737 - val_distribution_lambda_15_loss: 1.3476 - val_distribution_lambda_16_loss: 0.4120\n", "Epoch 1021/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2826 - distribution_lambda_14_loss: 0.5063 - distribution_lambda_15_loss: 1.3627 - distribution_lambda_16_loss: 0.4136 - val_loss: 2.2291 - val_distribution_lambda_14_loss: 0.4718 - val_distribution_lambda_15_loss: 1.3456 - val_distribution_lambda_16_loss: 0.4116\n", "Epoch 1022/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3165 - distribution_lambda_14_loss: 0.4942 - distribution_lambda_15_loss: 1.3920 - distribution_lambda_16_loss: 0.4303 - val_loss: 2.2325 - val_distribution_lambda_14_loss: 0.4762 - val_distribution_lambda_15_loss: 1.3452 - val_distribution_lambda_16_loss: 0.4110\n", "Epoch 1023/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3142 - distribution_lambda_14_loss: 0.5055 - distribution_lambda_15_loss: 1.3888 - distribution_lambda_16_loss: 0.4199 - val_loss: 2.2509 - val_distribution_lambda_14_loss: 0.4902 - val_distribution_lambda_15_loss: 1.3501 - val_distribution_lambda_16_loss: 0.4107\n", "Epoch 1024/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3222 - distribution_lambda_14_loss: 0.4993 - distribution_lambda_15_loss: 1.3978 - distribution_lambda_16_loss: 0.4251 - val_loss: 2.2493 - val_distribution_lambda_14_loss: 0.4903 - val_distribution_lambda_15_loss: 1.3486 - val_distribution_lambda_16_loss: 0.4104\n", "Epoch 1025/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3127 - distribution_lambda_14_loss: 0.4995 - distribution_lambda_15_loss: 1.3896 - distribution_lambda_16_loss: 0.4235 - val_loss: 2.2356 - val_distribution_lambda_14_loss: 0.4782 - val_distribution_lambda_15_loss: 1.3475 - val_distribution_lambda_16_loss: 0.4099\n", "Epoch 1026/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3140 - distribution_lambda_14_loss: 0.4901 - distribution_lambda_15_loss: 1.3903 - distribution_lambda_16_loss: 0.4335 - val_loss: 2.2321 - val_distribution_lambda_14_loss: 0.4762 - val_distribution_lambda_15_loss: 1.3464 - val_distribution_lambda_16_loss: 0.4094\n", "Epoch 1027/2000\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2689 - distribution_lambda_14_loss: 0.4915 - distribution_lambda_15_loss: 1.3664 - distribution_lambda_16_loss: 0.4110 - val_loss: 2.2370 - val_distribution_lambda_14_loss: 0.4829 - val_distribution_lambda_15_loss: 1.3453 - val_distribution_lambda_16_loss: 0.4088\n" ] } ], "source": [ "load_model_gk = False # load scaler and model weights for goalkeeper player predictor\n", "refit_model_gk = True\n", "\n", "if(load_model_gk):\n", " scaler_gk = pickle.load(open('saves/scaler_gk.pkl', 'rb'))\n", " \n", " X_gk_train = scaler_gk.transform(X_gk_train_)\n", " X_gk_test = scaler_gk.transform(X_gk_test_)\n", " \n", " \n", "n_epochs = 2000\n", "\n", "n_samples = X_gk_train.shape[0]\n", "\n", "batch_size = 128\n", "\n", "X_gk_len = X_gk_train.shape[1]\n", "y_gk_len = y_gk_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 1.5\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 30)\n", "neg_log_likelihood = lambda x, rv_x: -rv_x.log_prob(x)\n", "\n", "\n", "inputs = tfk.layers.Input(shape=(X_gk_len,), name=\"input\")\n", "x = tfk.layers.Dense(16, activation=\"sigmoid\") (inputs)\n", "x = tfk.layers.Dropout(0.3)(x)\n", "x = tfk.layers.Dense(16, activation=\"sigmoid\") (x)\n", "\n", "\n", "prob_dist_params = 4\n", "\n", "def prob_dist(t): \n", " return tfp.distributions.SinhArcsinh(loc=t[..., 0], scale=1e-3 + tf.math.softplus(t[..., 1]), skewness = t[..., 2], \n", " tailweight = tailweight_min + tailweight_range * tf.math.sigmoid(t[..., 3]),\n", " allow_nan_stats = False)\n", "\n", "x1 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x1)\n", "out_1 = tfp.layers.DistributionLambda(prob_dist)(x1)\n", "\n", "x2 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "\n", "x22 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x22)\n", "\n", "x23 = tfk.layers.Dense(1, activation=\"sigmoid\")(x2)\n", "out_3 = tfp.layers.DistributionLambda(lambda t: tfp.distributions.Bernoulli(probs = t[..., 0]))(x23)\n", "\n", "\n", "modelb_gk = tf.keras.Model(inputs, [out_1, out_2, out_3])\n", "\n", "modelb_gk.compile(optimizer=tf.keras.optimizers.Nadam(learning_rate = 0.001), \n", " loss=neg_log_likelihood)\n", "\n", "if(load_model_gk):\n", " modelb_gk.load_weights('saves/modelb_gk')\n", "\n", "if( (not load_model_gk) or refit_model_gk): \n", " modelb_gk.fit(X_gk_train.astype('float32'), [y_gk_train[:, 0].astype('float32'), y_gk_train[:, 1].astype('float32'), y_gk_train[:, 2].astype('int')], \n", " validation_data = (X_gk_test.astype('float32'), [y_gk_test[:, 0].astype('float32'), y_gk_test[:, 1].astype('float32'), y_gk_test[:, 2].astype('int')]),\n", " batch_size = batch_size, shuffle = True, epochs=n_epochs, verbose=True, callbacks = [callback])" ] }, { "cell_type": "code", "execution_count": 58, "id": "39a9bdc6", "metadata": {}, "outputs": [], "source": [ "def sample_predict_gk(X, iterations = 100):\n", " y = np.zeros((3, X.shape[0]))\n", " \n", " dist = modelb_gk(X)\n", " \n", " for i in range(iterations):\n", " y[0, :] += dist[0].sample()\n", " y[1, :] += dist[1].sample()\n", " y[2, :] += dist[2].sample()\n", " \n", " return y.transpose() / iterations\n" ] }, { "cell_type": "code", "execution_count": 59, "id": "c41cf448", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.2959033040611633\n", "0.4342943294016782\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.19144084876983292\n", "0.3805971703037422\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_gk_train_predict = sample_predict_gk(X_gk_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_train[:, 0], y_gk_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_train[:, 1], y_gk_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_train[:, 0], y_gk_train_predict[:, 0]))\n", "print(r2_score(y_gk_train[:, 1], y_gk_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_gk_test_predict = sample_predict_gk(X_gk_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_test[:, 0], y_gk_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_test[:, 1], y_gk_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_test[:, 0], y_gk_test_predict[:, 0]))\n", "print(r2_score(y_gk_test[:, 1], y_gk_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "91869883", "metadata": {}, "source": [ "Use the following codes to save the scalers and the model weights" ] }, { "cell_type": "code", "execution_count": 60, "id": "cecf5392", "metadata": {}, "outputs": [], "source": [ "save_model_of = True\n", "save_model_gk = True\n", "\n", "if(save_model_of):\n", " pickle.dump(scaler, open('saves/scaler.pkl', 'wb'))\n", " modelb.save_weights('saves/modelb')\n", " \n", "if(save_model_gk):\n", " pickle.dump(scaler_gk, open('saves/scaler_gk.pkl', 'wb'))\n", " modelb_gk.save_weights('saves/modelb_gk')\n", " " ] }, { "cell_type": "markdown", "id": "32635a0e", "metadata": {}, "source": [ "Generalized prediction function for a player (playing for team against opp_team, at home or not)\n", "\n", "Estimate prediction mean and sigma (using a custom definitions).\n", "\n", "Generate a plot.\n" ] }, { "cell_type": "code", "execution_count": 61, "id": "ddf433f9", "metadata": {}, "outputs": [], "source": [ "def vote_predict_NNb(player, team, opp_team, home = 1, plot = 0, log = 0, oldseason = False):\n", " if(players['r'][player] == 'P'):\n", " ptest = player_match_data_ext_gk(player, team, opp_team, oldseason = oldseason)\n", "\n", " x_ptest = np.array(ptest)[:, 3:]\n", " r = np.array(ptest)[0, 0]\n", "\n", " # add home and role\n", " xadd = np.zeros((1, 1))\n", " xadd[0, 0] = home\n", "\n", " x_ptest = np.concatenate((x_ptest, xadd), axis = 1)\n", "\n", " x_scaled = scaler_gk.transform(x_ptest)\n", "\n", " dist = modelb_gk(x_scaled)\n", " \n", " clean_shoot_prob = dist[2].probs.numpy()[0]\n", " else:\n", " ptest = player_match_data_ext(player, team, opp_team, oldseason = oldseason)\n", "\n", " x_ptest = np.array(ptest)[:, 4:]\n", " r = np.array(ptest)[0, 0]\n", "\n", " # add home and role\n", " xadd = np.zeros((1, 4))\n", " xadd[0, 0] = home\n", " xadd[0, 1] = r == 'D'\n", " xadd[0, 2] = r == 'C'\n", " xadd[0, 3] = r == 'A'\n", "\n", " x_ptest = np.concatenate((x_ptest, xadd), axis = 1)\n", "\n", " x_scaled = scaler.transform(x_ptest)\n", "\n", " dist = modelb(x_scaled)\n", " \n", " \n", " x = np.arange(0, 40, 0.002)\n", "\n", " px1 = dist[0].prob(x);\n", " px2 = dist[1].prob(x);\n", "\n", " \n", " #sample1 = dist[0].sample(10000)\n", " #sample2 = dist[1].sample(10000)\n", " \n", " m1 = np.average(x, weights = px1)\n", " m2 = np.average(x, weights = px2)\n", " \n", " #m1 = np.mean(sample1)\n", " #m2 = np.mean(sample2)\n", " \n", " #s1 = np.std(sample1)\n", " #s2 = np.std(sample2)\n", " \n", " # not standard deviation, but expected range extimated by quantile \n", " \n", " if(players['r'][player] == 'P'):\n", " s1 = ( dist[0].quantile(0.9545) - m1 ) / 2\n", " s2 = -( dist[1].quantile(1 - 0.9) - m2 ) / 2\n", " else:\n", " s1 = ( dist[0].quantile(0.9545) - m1 ) / 2\n", " s2 = ( dist[1].quantile(0.9) - m2 ) / 2\n", " \n", "\n", " \n", " #y_pred_m = np.array([dist[0].loc, dist[1].loc]).flatten()\n", " y_pred_m = np.array([m1, m2]).flatten()\n", " #y_pred_s = np.array([dist[0].scale, dist[1].scale]).flatten()\n", " y_pred_s = np.array([s1, s2]).flatten()\n", " \n", " clean_sheet_text = ''\n", " if(players['r'][player] == 'P'):\n", " clean_sheet_text = ' (' + \"{:.1f}\".format(clean_shoot_prob*100) + '% cs)'\n", " \n", " if(plot):\n", " ax = plt.gca()\n", " \n", " plt.plot(x, px1, \n", " label = 'MV ' + \"{:.2f}\".format(y_pred_m[0]) + ' ± ' + \"{:.2f}\".format(2 * y_pred_s[0]),\n", " color = 'b')\n", " plt.plot(x, px2, \n", " label = 'FV ' + \"{:.2f}\".format(y_pred_m[1]) + ' + ' + \"{:.2f}\".format(2 * y_pred_s[1]) + clean_sheet_text,\n", " color = 'g')\n", " \n", " plt.fill_between(x, px1, color = 'lightblue')\n", " plt.fill_between(x, px2, color = 'lightgreen')\n", " \n", " plt.legend()\n", " \n", " plt.vlines(x = y_pred_m[0], color = 'b', ymin = 0, ymax = 3, linestyle = 'dashed')\n", " plt.vlines(x = y_pred_m[1], color = 'g', ymin = 0, ymax = 3, linestyle = 'dashed')\n", " \n", " plt.title(player + ' (' + team + ' vs ' + opp_team + ')')\n", " \n", " plt.xlim([0, 15])\n", " \n", " if(players['r'][player] == 'P'): \n", " plt.ylim([0, 2.5])\n", " else:\n", " plt.ylim([0, 1.5])\n", " \n", " plt.show()\n", " \n", " if(log):\n", " print(player + ': ' + \n", " 'MV ' + \"{:.2f}\".format(y_pred_m[0]) + ' ± ' + \"{:.2f}\".format(2 * y_pred_s[0]) +\n", " '; FV ' + \"{:.2f}\".format(y_pred_m[1]) + ' + ' + \"{:.2f}\".format(2 * y_pred_s[1]) + clean_sheet_text);\n", " return [y_pred_m, y_pred_s, dist]\n" ] }, { "cell_type": "markdown", "id": "98817aa0", "metadata": {}, "source": [ "Load Serie A calendar. " ] }, { "cell_type": "code", "execution_count": 62, "id": "d31bad38", "metadata": {}, "outputs": [], "source": [ "cal = np.array(pd.read_excel('fantacalcio/seriea_calendar.xlsx', header = None))\n", "\n", "cal_df = pd.DataFrame(columns = ['matchday', 'team1', 'team2'])\n", "\n", "matchday = 0\n", "\n", "for i in range(cal.shape[0]):\n", " if(cal[i, 0][0].isnumeric()):\n", " matchday = matchday + 1\n", " continue\n", " \n", " teams = cal[i, 0].split('-')\n", " \n", " frame = pd.DataFrame([[matchday, teams[0], teams[1]]], columns = cal_df.columns)\n", "\n", " cal_df = pd.concat([cal_df, frame], ignore_index = True)\n", " " ] }, { "cell_type": "code", "execution_count": 63, "id": "62b9f588", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayteam1team2
01FiorentinaCremonese
11VeronaNapoli
21JuventusSassuolo
31LazioBologna
41LecceInter
............
37538LecceBologna
37638SassuoloFiorentina
37738MilanVerona
37838TorinoInter
37938UdineseJuventus
\n", "

380 rows × 3 columns

\n", "
" ], "text/plain": [ " matchday team1 team2\n", "0 1 Fiorentina Cremonese\n", "1 1 Verona Napoli\n", "2 1 Juventus Sassuolo\n", "3 1 Lazio Bologna\n", "4 1 Lecce Inter\n", ".. ... ... ...\n", "375 38 Lecce Bologna\n", "376 38 Sassuolo Fiorentina\n", "377 38 Milan Verona\n", "378 38 Torino Inter\n", "379 38 Udinese Juventus\n", "\n", "[380 rows x 3 columns]" ] }, "execution_count": 63, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cal_df" ] }, { "cell_type": "markdown", "id": "62872819", "metadata": {}, "source": [ "Function for generating a prediction for a player, taking match data from a given matchday, according to Serie A calendar." ] }, { "cell_type": "code", "execution_count": 64, "id": "861a06ce", "metadata": {}, "outputs": [], "source": [ "matchday = 20" ] }, { "cell_type": "code", "execution_count": 65, "id": "c58ba41d", "metadata": {}, "outputs": [], "source": [ "def PlayerMatch(player, match = matchday):\n", " team = players.loc[player]['team']\n", " \n", " for i in range (cal_df.shape[0]):\n", " if(cal_df['matchday'][i] == match):\n", " if(cal_df['team1'][i] == team):\n", " home = 1\n", " oppteam = cal_df['team2'][i]\n", " elif(cal_df['team2'][i] == team):\n", " home = 0\n", " oppteam = cal_df['team1'][i]\n", " \n", " return [player, team, oppteam, home]\n", "\n", "def predict_player(player, match = matchday, plot = 0, log = 0, oldseason = False):\n", " [player, team, oppteam, home] = PlayerMatch(player, match)\n", " return vote_predict_NNb(player, team, oppteam, home = home, plot = plot, log = log, oldseason = oldseason)" ] }, { "cell_type": "markdown", "id": "e8b63a98", "metadata": {}, "source": [ "Load current matchday playing probabilities for Serie A players." ] }, { "cell_type": "code", "execution_count": 66, "id": "f79792b6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
starterpercentage
player
Skorupski1.0100
Posch1.0100
Soumaoro1.0100
Lucumi'1.0100
Cambiaso1.0100
.........
Verdi0.055
Kallon0.455
Piccoli0.055
Ngonge0.025
Braaf0.040
\n", "

440 rows × 2 columns

\n", "
" ], "text/plain": [ " starter percentage\n", "player \n", "Skorupski 1.0 100\n", "Posch 1.0 100\n", "Soumaoro 1.0 100\n", "Lucumi' 1.0 100\n", "Cambiaso 1.0 100\n", "... ... ...\n", "Verdi 0.0 55\n", "Kallon 0.4 55\n", "Piccoli 0.0 55\n", "Ngonge 0.0 25\n", "Braaf 0.0 40\n", "\n", "[440 rows x 2 columns]" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probables = pd.read_excel('mid_outputs/match_probable_players.xlsx', index_col = 0) \n", "\n", "probables" ] }, { "cell_type": "markdown", "id": "e4751014", "metadata": {}, "source": [ "Generate prediction data for each Serie A player for the current matchday.\n", "\n", "Output to excel file, using a template made for data elaboration." ] }, { "cell_type": "code", "execution_count": 67, "id": "5e63c2b7", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 6.26 ± 0.88; FV 5.69 + 1.33 (68.3% cs)\n", "Provedel: MV 6.31 ± 0.77; FV 5.74 + 1.23 (69.4% cs)\n", "Vicario: MV 6.39 ± 0.80; FV 5.73 + 1.10 (43.4% cs)\n", "Szczesny: MV 6.23 ± 0.72; FV 5.70 + 1.25 (68.3% cs)\n", "Falcone: MV 6.31 ± 0.75; FV 5.46 + 1.16 (25.4% cs)\n", "Silvestri: MV 6.38 ± 0.81; FV 5.79 + 1.16 (52.9% cs)\n", "Rui Patricio: MV 6.03 ± 0.74; FV 3.50 + 2.20 (2.5% cs)\n", "Milinkovic-Savic V.: MV 6.34 ± 0.77; FV 5.32 + 1.19 (18.3% cs)\n", "Sepe: MV 6.39 ± 0.82; FV 5.10 + 1.40 (10.3% cs)\n", "Maignan: MV 6.37 ± 0.77; FV 5.79 + 1.16 (55.4% cs)\n", "Onana: MV 6.24 ± 0.80; FV 5.69 + 1.31 (68.2% cs)\n", "Audero: MV 6.21 ± 0.74; FV 3.71 + 1.97 (2.7% cs)\n", "Musso: MV 6.31 ± 0.75; FV 5.76 + 1.24 (70.2% cs)\n", "Carnesecchi: MV 6.36 ± 0.84; FV 5.39 + 1.41 (20.2% cs)\n", "Montipo': MV 6.29 ± 0.76; FV 4.09 + 1.72 (3.7% cs)\n", "Di Gregorio: MV 6.23 ± 0.74; FV 4.16 + 1.67 (4.4% cs)\n", "Tatarusanu: MV 6.17 ± 0.65; FV 5.09 + 1.24 (21.7% cs)\n", "Consigli: MV 6.22 ± 0.75; FV 4.18 + 1.75 (5.4% cs)\n", "Dragowski: MV 6.11 ± 0.70; FV 3.95 + 1.76 (4.1% cs)\n", "Terracciano: MV 5.92 ± 0.74; FV 3.28 + 2.35 (2.1% cs)\n", "Sportiello: MV 6.19 ± 0.72; FV 5.65 + 1.28 (68.7% cs)\n", "Skorupski: MV 6.23 ± 0.69; FV 5.18 + 1.19 (20.8% cs)\n", "Perin: MV 6.33 ± 0.81; FV 5.75 + 1.31 (71.8% cs)\n", "Handanovic: MV 6.20 ± 0.84; FV 5.65 + 1.39 (67.0% cs)\n", "Zoet: MV 6.30 ± 0.77; FV 5.48 + 1.26 (31.3% cs)\n", "Gollini: MV 6.26 ± 0.88; FV 5.69 + 1.33 (68.3% cs)\n", "Ochoa: MV 6.45 ± 0.87; FV 5.39 + 1.33 (16.6% cs)\n", "Pegolo: MV 6.23 ± 0.79; FV 4.63 + 1.65 (10.1% cs)\n", "Mirante: MV 6.37 ± 0.77; FV 5.79 + 1.16 (55.4% cs)\n", "Sarr M.: MV 6.36 ± 0.84; FV 5.39 + 1.41 (20.2% cs)\n", "Lamanna: MV 6.23 ± 0.74; FV 4.16 + 1.67 (4.4% cs)\n", "Ujkani: MV 6.39 ± 0.80; FV 5.73 + 1.10 (43.4% cs)\n", "Berisha: MV 6.34 ± 0.77; FV 5.32 + 1.19 (18.3% cs)\n", "Marchetti: MV 6.11 ± 0.70; FV 3.95 + 1.76 (4.1% cs)\n", "Perilli: MV 6.29 ± 0.76; FV 4.09 + 1.72 (3.7% cs)\n", "Padelli: MV 6.38 ± 0.81; FV 5.79 + 1.16 (52.9% cs)\n", "Perisan: MV 6.39 ± 0.80; FV 5.73 + 1.10 (43.4% cs)\n", "Bardi: MV 6.23 ± 0.69; FV 5.18 + 1.19 (20.8% cs)\n", "Cordaz: MV 6.24 ± 0.80; FV 5.69 + 1.31 (68.2% cs)\n", "Pinsoglio: MV 6.23 ± 0.72; FV 5.70 + 1.25 (68.3% cs)\n", "Fiorillo: MV 6.39 ± 0.82; FV 5.10 + 1.40 (10.3% cs)\n", "Cragno: MV 6.23 ± 0.74; FV 4.16 + 1.67 (4.4% cs)\n", "Sirigu: MV 5.92 ± 0.74; FV 3.28 + 2.35 (2.1% cs)\n", "Cerofolini: MV 5.92 ± 0.74; FV 3.28 + 2.35 (2.1% cs)\n", "Rossi F.: MV 6.31 ± 0.75; FV 5.76 + 1.24 (70.2% cs)\n", "Ravaglia F.: MV 6.23 ± 0.69; FV 5.18 + 1.19 (20.8% cs)\n", "Brancolini: MV 6.31 ± 0.75; FV 5.46 + 1.16 (25.4% cs)\n", "Bleve: MV 6.31 ± 0.75; FV 5.46 + 1.16 (25.4% cs)\n", "Berardi A.: MV 6.29 ± 0.76; FV 4.09 + 1.72 (3.7% cs)\n", "Russo A.: MV 6.22 ± 0.75; FV 4.18 + 1.75 (5.4% cs)\n", "Gemello: MV 6.34 ± 0.77; FV 5.32 + 1.19 (18.3% cs)\n", "Ravaglia: MV 6.21 ± 0.74; FV 3.71 + 1.97 (2.7% cs)\n", "Boer: MV 6.03 ± 0.74; FV 3.50 + 2.20 (2.5% cs)\n", "Adamonis: MV 6.31 ± 0.77; FV 5.74 + 1.23 (69.4% cs)\n", "Marfella: MV 6.26 ± 0.88; FV 5.69 + 1.33 (68.3% cs)\n", "Zovko: MV 6.09 ± 0.73; FV 3.89 + 1.87 (3.9% cs)\n", "Piana: MV 6.38 ± 0.81; FV 5.79 + 1.16 (52.9% cs)\n", "Bagnolini: MV 6.23 ± 0.69; FV 5.18 + 1.19 (20.8% cs)\n", "Luis Maximiano: MV 6.15 ± 0.75; FV 5.59 + 1.31 (68.2% cs)\n", "Svilar: MV 6.03 ± 0.74; FV 3.50 + 2.20 (2.5% cs)\n", "Sorrentino A.: MV 6.23 ± 0.74; FV 4.16 + 1.67 (4.4% cs)\n", "Ciezkowski: MV 6.36 ± 0.84; FV 5.39 + 1.41 (20.2% cs)\n", "Chiesa M.: MV 6.29 ± 0.76; FV 4.09 + 1.72 (3.7% cs)\n", "Saro: MV 6.36 ± 0.84; FV 5.39 + 1.41 (20.2% cs)\n", "Vasquez D.: MV 6.43 ± 0.83; FV 5.85 + 1.20 (61.9% cs)\n", "Turk: MV 6.21 ± 0.74; FV 3.71 + 1.97 (2.7% cs)\n", "Dimarco: MV 6.30 ± 1.04; FV 6.94 + 2.36\n", "Smalling: MV 5.86 ± 1.14; FV 5.99 + 1.37\n", "Doig: MV 6.12 ± 1.01; FV 6.58 + 1.83\n", "Carlos Augusto: MV 5.86 ± 1.01; FV 5.96 + 1.24\n", "Kim: MV 6.31 ± 1.07; FV 6.88 + 2.14\n", "Hernandez T.: MV 6.29 ± 1.13; FV 6.95 + 2.44\n", "Udogie: MV 6.27 ± 1.10; FV 7.07 + 2.72\n", "Parisi: MV 6.17 ± 0.85; FV 6.47 + 1.43\n", "Romagnoli: MV 6.21 ± 0.99; FV 6.54 + 1.63\n", "Di Lorenzo: MV 6.23 ± 0.88; FV 6.62 + 1.67\n", "Danilo: MV 6.30 ± 0.98; FV 6.82 + 2.00\n", "Mazzocchi: MV 6.09 ± 0.94; FV 6.45 + 1.58\n", "Mario Rui: MV 6.23 ± 0.90; FV 6.54 + 1.52\n", "Bastoni S.: MV 6.07 ± 0.96; FV 6.42 + 1.58\n", "Valeri: MV 6.05 ± 0.75; FV 6.25 + 1.22\n", "Posch: MV 6.27 ± 1.14; FV 7.15 + 2.93\n", "Rodrigo Becao: MV 6.23 ± 0.90; FV 6.57 + 1.57\n", "Tomori: MV 6.15 ± 0.88; FV 6.43 + 1.36\n", "Baschirotto: MV 6.30 ± 1.01; FV 6.89 + 2.17\n", "Juan Jesus: MV 6.18 ± 0.76; FV 6.47 + 1.34\n", "Ibanez: MV 5.69 ± 1.01; FV 5.72 + 1.04\n", "Demiral: MV 6.24 ± 0.86; FV 6.63 + 1.64\n", "Scalvini: MV 6.30 ± 1.02; FV 6.91 + 2.26\n", "Bijol: MV 6.13 ± 1.02; FV 6.62 + 1.94\n", "Toloi: MV 6.25 ± 0.85; FV 6.57 + 1.52\n", "Depaoli: MV 5.83 ± 1.00; FV 6.15 + 1.51\n", "Mancini: MV 5.78 ± 0.81; FV 5.77 + 0.68\n", "Bremer: MV 6.00 ± 1.16; FV 6.44 + 1.91\n", "Ebuehi: MV 6.07 ± 0.76; FV 6.30 + 1.14\n", "Dumfries: MV 6.19 ± 1.13; FV 6.88 + 2.49\n", "Schuurs: MV 6.05 ± 0.67; FV 6.10 + 0.65\n", "Darmian: MV 6.21 ± 0.95; FV 6.75 + 2.04\n", "Kalulu: MV 5.97 ± 1.07; FV 6.23 + 1.41\n", "Vojvoda: MV 5.97 ± 0.82; FV 6.13 + 0.99\n", "Maehle: MV 6.17 ± 0.78; FV 6.45 + 1.42\n", "Holm: MV 5.96 ± 0.83; FV 6.15 + 1.12\n", "Bastoni: MV 6.08 ± 0.78; FV 6.19 + 0.87\n", "Gosens: MV 6.07 ± 0.71; FV 6.31 + 1.23\n", "Milenkovic: MV 5.73 ± 1.13; FV 5.73 + 1.28\n", "Rodriguez R.: MV 5.92 ± 0.68; FV 5.96 + 0.55\n", "Reca: MV 5.96 ± 0.92; FV 6.19 + 1.26\n", "Sernicola: MV 5.85 ± 0.78; FV 5.97 + 1.06\n", "Rrahmani: MV 6.25 ± 1.03; FV 6.75 + 1.96\n", "Kyriakopoulos: MV 5.84 ± 0.94; FV 6.01 + 1.18\n", "Martinez Quarta: MV 5.79 ± 1.07; FV 5.79 + 1.17\n", "Perez N.: MV 6.17 ± 0.88; FV 6.30 + 1.03\n", "Olivera: MV 6.10 ± 0.77; FV 6.44 + 1.46\n", "Calabria: MV 6.19 ± 1.05; FV 6.69 + 1.97\n", "Skriniar: MV 5.94 ± 0.68; FV 5.94 + 0.55\n", "Marusic: MV 6.00 ± 0.73; FV 6.04 + 0.68\n", "Lazzari: MV 6.02 ± 0.75; FV 6.07 + 0.67\n", "Augello: MV 5.72 ± 0.95; FV 5.90 + 1.21\n", "Ampadu: MV 5.80 ± 0.91; FV 5.71 + 0.81\n", "Ismajli: MV 6.05 ± 0.79; FV 6.06 + 0.72\n", "Cambiaso: MV 5.96 ± 0.70; FV 6.03 + 0.63\n", "Hysaj: MV 6.00 ± 0.68; FV 6.03 + 0.62\n", "Izzo: MV 5.86 ± 0.77; FV 5.82 + 0.62\n", "Biraghi: MV 5.71 ± 0.84; FV 5.68 + 0.73\n", "Medel: MV 5.96 ± 0.68; FV 5.96 + 0.54\n", "Bonucci: MV 6.24 ± 1.02; FV 6.77 + 2.00\n", "Acerbi: MV 6.09 ± 0.71; FV 6.16 + 0.75\n", "Spinazzola: MV 5.68 ± 0.78; FV 5.75 + 0.83\n", "Lykogiannis: MV 5.97 ± 0.63; FV 6.04 + 0.61\n", "Djidji: MV 5.86 ± 0.85; FV 5.95 + 0.94\n", "Lazaro: MV 5.96 ± 0.79; FV 6.04 + 0.78\n", "Gallo: MV 5.97 ± 0.69; FV 5.95 + 0.59\n", "Singo: MV 5.98 ± 0.75; FV 6.09 + 0.81\n", "Mari': MV 5.75 ± 1.19; FV 5.77 + 1.34\n", "Casale: MV 5.98 ± 0.75; FV 5.99 + 0.62\n", "Dodo': MV 5.56 ± 1.01; FV 5.48 + 0.87\n", "De Vrij: MV 5.94 ± 0.75; FV 6.06 + 0.82\n", "Patric: MV 6.05 ± 0.91; FV 5.98 + 0.82\n", "Luperto: MV 5.96 ± 0.97; FV 5.90 + 0.83\n", "Faraoni: MV 5.86 ± 0.76; FV 5.99 + 1.07\n", "Ceccherini: MV 5.77 ± 0.99; FV 5.85 + 1.22\n", "Umtiti: MV 6.19 ± 0.95; FV 6.30 + 1.12\n", "Aina: MV 5.98 ± 0.80; FV 6.16 + 1.00\n", "Caldirola: MV 5.71 ± 0.94; FV 5.61 + 0.80\n", "Soppy: MV 6.08 ± 0.79; FV 6.19 + 0.93\n", "Gendrey: MV 5.92 ± 0.68; FV 5.92 + 0.58\n", "Ferrari A.: MV 5.71 ± 1.10; FV 5.72 + 1.25\n", "Zappacosta: MV 6.20 ± 0.81; FV 6.49 + 1.46\n", "Bianchetti: MV 5.63 ± 0.93; FV 5.63 + 1.00\n", "Ferrari G.: MV 5.66 ± 1.16; FV 5.67 + 1.32\n", "Fazio: MV 5.77 ± 1.20; FV 5.80 + 1.38\n", "Hateboer: MV 6.13 ± 0.94; FV 6.64 + 1.95\n", "Rogerio: MV 5.63 ± 0.95; FV 5.66 + 0.93\n", "Buongiorno: MV 5.85 ± 0.73; FV 5.79 + 0.62\n", "Gunter: MV 5.67 ± 0.97; FV 5.68 + 1.08\n", "Colley: MV 5.71 ± 1.14; FV 5.74 + 1.35\n", "Troost-Ekong: MV 5.88 ± 0.84; FV 5.92 + 0.84\n", "Terzic: MV 5.90 ± 0.56; FV 5.88 + 0.41\n", "Toljan: MV 5.58 ± 0.95; FV 5.53 + 0.86\n", "Zortea: MV 6.13 ± 0.83; FV 6.50 + 1.54\n", "Soumaoro: MV 5.98 ± 0.82; FV 5.92 + 0.73\n", "Amian: MV 5.75 ± 0.81; FV 5.68 + 0.76\n", "Pongracic: MV 6.03 ± 0.80; FV 5.97 + 0.75\n", "Birindelli: MV 5.75 ± 0.76; FV 5.73 + 0.80\n", "Lucumi': MV 5.88 ± 0.70; FV 5.86 + 0.58\n", "Hien: MV 5.68 ± 0.86; FV 5.57 + 0.77\n", "Ehizibue: MV 6.06 ± 0.84; FV 6.42 + 1.57\n", "Masina: MV 6.13 ± 0.84; FV 6.64 + 1.81\n", "Gyomber: MV 5.79 ± 0.80; FV 5.71 + 0.68\n", "Alex Sandro: MV 5.76 ± 1.06; FV 5.69 + 0.94\n", "Pezzella Giu.: MV 5.95 ± 0.65; FV 5.98 + 0.54\n", "Bereszynski: MV 5.74 ± 0.79; FV 5.69 + 0.72\n", "Venuti: MV 5.59 ± 0.87; FV 5.54 + 0.82\n", "Palomino: MV 6.20 ± 0.80; FV 6.44 + 1.27\n", "Nuytinck: MV 5.79 ± 1.06; FV 5.74 + 1.08\n", "Marlon: MV 5.64 ± 0.78; FV 5.53 + 0.66\n", "Nikolaou: MV 5.70 ± 0.81; FV 5.58 + 0.65\n", "Igor: MV 5.56 ± 1.02; FV 5.45 + 0.81\n", "Okoli: MV 5.87 ± 0.68; FV 5.86 + 0.55\n", "Dawidowicz: MV 5.64 ± 0.99; FV 5.65 + 1.07\n", "Celik: MV 5.59 ± 0.85; FV 5.59 + 0.86\n", "Bellanova: MV 5.93 ± 0.76; FV 6.02 + 0.82\n", "Erlic: MV 5.71 ± 1.10; FV 5.66 + 1.11\n", "Ballo-Toure': MV 6.20 ± 0.77; FV 6.44 + 1.27\n", "Dest: MV 5.85 ± 0.80; FV 5.84 + 0.67\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Stojanovic: MV 5.76 ± 0.87; FV 5.67 + 0.80\n", "Bradaric: MV 5.65 ± 0.89; FV 5.57 + 0.90\n", "Daniliuc: MV 5.73 ± 1.03; FV 5.67 + 0.99\n", "Zima: MV 5.85 ± 0.75; FV 5.83 + 0.67\n", "Quagliata: MV 5.80 ± 0.69; FV 5.84 + 0.66\n", "Ebosse: MV 5.81 ± 0.66; FV 5.81 + 0.52\n", "Aiwu: MV 5.78 ± 0.95; FV 5.83 + 1.06\n", "Lochoshvili: MV 5.67 ± 0.85; FV 5.59 + 0.88\n", "Bronn: MV 5.75 ± 0.71; FV 5.70 + 0.60\n", "Thiaw: MV 6.04 ± 0.79; FV 6.11 + 0.79\n", "Zeefuik: MV 5.73 ± 0.92; FV 5.74 + 0.99\n", "Ghiglione: MV 5.70 ± 0.87; FV 5.72 + 1.02\n", "Rugani: MV 6.00 ± 0.65; FV 6.02 + 0.52\n", "De Sciglio: MV 5.92 ± 0.69; FV 5.99 + 0.63\n", "Djimsiti: MV 6.13 ± 0.75; FV 6.22 + 0.87\n", "Caldara: MV 5.70 ± 0.99; FV 5.60 + 0.82\n", "Murru: MV 5.59 ± 0.94; FV 5.62 + 1.05\n", "Karsdorp: MV 5.61 ± 0.90; FV 5.63 + 0.83\n", "Bonifazi: MV 5.85 ± 0.70; FV 5.81 + 0.56\n", "Kjaer: MV 5.94 ± 0.67; FV 5.93 + 0.52\n", "Magnani: MV 5.59 ± 0.87; FV 5.47 + 0.71\n", "Walukiewicz: MV 5.78 ± 0.85; FV 5.69 + 0.75\n", "Ayhan: MV 5.63 ± 1.22; FV 5.61 + 1.28\n", "Amione: MV 5.55 ± 0.90; FV 5.47 + 0.91\n", "Ruggeri: MV 6.05 ± 0.66; FV 6.07 + 0.63\n", "De Winter: MV 5.89 ± 0.84; FV 5.83 + 0.68\n", "Ostigard: MV 5.92 ± 0.62; FV 5.94 + 0.52\n", "Wisniewski: MV 5.82 ± 0.89; FV 5.81 + 0.87\n", "Radovanovic: MV 5.61 ± 0.74; FV 5.50 + 0.62\n", "Dermaku: MV 6.06 ± 0.85; FV 6.12 + 0.92\n", "D'ambrosio: MV 6.13 ± 0.73; FV 6.24 + 0.91\n", "De Silvestri: MV 5.99 ± 0.84; FV 6.18 + 1.06\n", "Sala: MV 5.85 ± 0.80; FV 5.86 + 0.77\n", "Chiriches: MV 5.67 ± 1.11; FV 5.58 + 0.98\n", "Donati: MV 5.76 ± 1.03; FV 5.68 + 0.98\n", "Gabbia: MV 5.87 ± 0.68; FV 5.80 + 0.55\n", "Kumbulla: MV 5.60 ± 0.76; FV 5.60 + 0.75\n", "Adopo: MV 5.95 ± 0.69; FV 6.00 + 0.59\n", "Pirola: MV 5.55 ± 0.93; FV 5.44 + 0.74\n", "Lovato: MV 5.63 ± 0.94; FV 5.54 + 0.77\n", "Tuia: MV 5.90 ± 0.89; FV 6.01 + 1.07\n", "Ferrer: MV 5.81 ± 0.87; FV 5.77 + 0.81\n", "Antov: MV 5.61 ± 1.07; FV 5.53 + 0.97\n", "Vasquez: MV 5.70 ± 0.89; FV 5.62 + 0.91\n", "Zanoli: MV 5.82 ± 0.70; FV 5.83 + 0.56\n", "Gatti: MV 5.88 ± 0.90; FV 5.81 + 0.78\n", "Gila: MV 6.00 ± 0.91; FV 5.97 + 0.81\n", "Sambia: MV 5.89 ± 0.79; FV 5.89 + 0.66\n", "Moutinho J.: MV 5.84 ± 0.98; FV 5.80 + 0.89\n", "Conti: MV 5.89 ± 1.03; FV 6.00 + 1.28\n", "Marrone: MV 5.55 ± 0.96; FV 5.44 + 0.81\n", "Tonelli: MV 5.67 ± 0.88; FV 5.55 + 0.75\n", "Murillo: MV 5.53 ± 0.76; FV 5.44 + 0.69\n", "Radu: MV 5.74 ± 1.03; FV 5.69 + 0.94\n", "Paletta: MV 5.77 ± 0.93; FV 5.75 + 0.98\n", "Florenzi: MV 6.15 ± 0.86; FV 6.39 + 1.27\n", "Fares: MV 5.87 ± 0.74; FV 5.87 + 0.66\n", "Marchizza: MV 5.64 ± 0.85; FV 5.64 + 0.85\n", "Romagna: MV 5.76 ± 0.97; FV 5.84 + 1.03\n", "Ranieri L.: MV 5.61 ± 0.82; FV 5.59 + 0.86\n", "Cassandro: MV 6.07 ± 0.86; FV 6.16 + 0.96\n", "Muldur: MV 5.65 ± 0.88; FV 5.62 + 0.81\n", "Carboni: MV 5.64 ± 0.87; FV 5.53 + 0.80\n", "Amey: MV 6.10 ± 0.80; FV 6.23 + 0.92\n", "Ferrarini: MV 5.77 ± 0.93; FV 5.75 + 0.98\n", "Vina: MV 5.62 ± 0.93; FV 5.62 + 0.89\n", "Zanotti: MV 6.03 ± 0.78; FV 6.16 + 0.91\n", "Ruan: MV 5.56 ± 1.03; FV 5.44 + 0.73\n", "Coppola D.: MV 5.62 ± 0.83; FV 5.53 + 0.80\n", "Cacace: MV 5.91 ± 0.72; FV 5.91 + 0.61\n", "Bayeye: MV 5.93 ± 0.80; FV 6.01 + 0.81\n", "Ebosele: MV 6.05 ± 0.82; FV 6.13 + 0.82\n", "Buta: MV 6.05 ± 0.80; FV 6.14 + 0.83\n", "Abankwah: MV 6.05 ± 0.80; FV 6.14 + 0.83\n", "Guessand A.: MV 6.05 ± 0.80; FV 6.14 + 0.83\n", "Cabal: MV 5.85 ± 0.85; FV 5.91 + 0.84\n", "Sosa: MV 5.72 ± 0.85; FV 5.63 + 0.70\n", "Guarino: MV 5.94 ± 0.86; FV 6.00 + 0.87\n", "Carboni F.: MV 5.78 ± 0.93; FV 5.75 + 0.95\n", "Zaccagni: MV 6.49 ± 1.38; FV 8.19 + 5.10\n", "Kvaratskhelia: MV 6.52 ± 1.50; FV 8.50 + 5.86\n", "Milinkovic-Savic: MV 6.37 ± 1.30; FV 7.62 + 3.90\n", "Barella: MV 6.36 ± 1.24; FV 7.47 + 3.54\n", "Zielinski: MV 6.34 ± 0.96; FV 6.90 + 2.14\n", "Luis Alberto: MV 6.38 ± 1.14; FV 7.22 + 2.91\n", "Strefezza: MV 6.41 ± 1.17; FV 7.50 + 3.48\n", "Felipe Anderson: MV 6.29 ± 1.30; FV 7.52 + 3.86\n", "Diaz B.: MV 6.27 ± 1.32; FV 7.49 + 3.83\n", "Koopmeiners: MV 6.49 ± 1.29; FV 7.84 + 4.20\n", "Vlasic: MV 6.21 ± 1.16; FV 6.94 + 2.59\n", "Calhanoglu: MV 6.35 ± 1.07; FV 7.05 + 2.53\n", "Frattesi: MV 6.01 ± 1.11; FV 6.49 + 1.94\n", "Zambo Anguissa: MV 6.30 ± 1.01; FV 6.89 + 2.22\n", "Elmas: MV 6.24 ± 1.00; FV 6.96 + 2.49\n", "Pereyra: MV 6.33 ± 1.09; FV 7.11 + 2.68\n", "Miranchuk: MV 6.20 ± 1.24; FV 7.04 + 2.89\n", "Samardzic: MV 6.31 ± 1.09; FV 7.13 + 2.78\n", "Politano: MV 6.25 ± 0.91; FV 6.74 + 1.91\n", "Rabiot: MV 6.21 ± 1.08; FV 6.87 + 2.34\n", "Radonjic: MV 6.16 ± 1.04; FV 6.74 + 2.17\n", "Lobotka: MV 6.18 ± 0.75; FV 6.43 + 1.21\n", "Tonali: MV 6.31 ± 1.11; FV 6.98 + 2.46\n", "Lazovic: MV 6.07 ± 1.10; FV 6.60 + 2.05\n", "Bonaventura: MV 5.88 ± 0.96; FV 6.04 + 1.20\n", "Pellegrini Lo.: MV 5.88 ± 1.12; FV 6.09 + 1.49\n", "Pessina: MV 5.93 ± 0.97; FV 6.18 + 1.40\n", "Kostic: MV 6.19 ± 1.02; FV 6.68 + 1.91\n", "Lovric: MV 6.25 ± 0.89; FV 6.71 + 1.82\n", "Ferguson: MV 6.24 ± 1.04; FV 6.88 + 2.25\n", "Ciurria: MV 5.98 ± 1.08; FV 6.39 + 1.75\n", "Ikone': MV 5.83 ± 1.05; FV 6.07 + 1.40\n", "Baldanzi: MV 6.25 ± 1.04; FV 6.98 + 2.53\n", "Candreva: MV 6.05 ± 1.09; FV 6.36 + 1.69\n", "Bennacer: MV 6.18 ± 0.79; FV 6.40 + 1.17\n", "El Shaarawy: MV 5.90 ± 0.85; FV 6.07 + 1.08\n", "Pasalic: MV 6.31 ± 1.24; FV 7.44 + 3.58\n", "Orsolini: MV 6.27 ± 1.34; FV 7.49 + 3.84\n", "Bandinelli: MV 6.01 ± 0.85; FV 6.23 + 1.19\n", "Mkhitaryan: MV 6.16 ± 1.04; FV 6.73 + 2.09\n", "Colpani: MV 5.94 ± 0.83; FV 6.10 + 1.22\n", "Pogba: MV 6.06 ± 0.93; FV 6.21 + 1.15\n", "Sensi: MV 5.88 ± 1.05; FV 5.99 + 1.28\n", "Chiesa: MV 6.24 ± 1.07; FV 6.82 + 2.22\n", "Lukic: MV 6.07 ± 1.00; FV 6.45 + 1.63\n", "Fagioli: MV 6.21 ± 1.02; FV 6.77 + 2.08\n", "Messias: MV 6.15 ± 1.21; FV 6.97 + 2.88\n", "Arslan: MV 6.03 ± 0.70; FV 6.12 + 0.77\n", "Brozovic: MV 6.18 ± 0.87; FV 6.56 + 1.59\n", "Verdi: MV 6.03 ± 0.87; FV 6.35 + 1.48\n", "Barak: MV 5.71 ± 0.90; FV 5.81 + 1.03\n", "Matic: MV 5.86 ± 0.85; FV 5.98 + 1.05\n", "Soriano: MV 6.07 ± 0.86; FV 6.27 + 1.14\n", "Dominguez: MV 6.19 ± 1.10; FV 6.78 + 2.22\n", "Ranocchia F.: MV 5.88 ± 0.84; FV 6.01 + 1.11\n", "Cristante: MV 5.70 ± 0.91; FV 5.75 + 0.96\n", "Bajrami: MV 5.94 ± 0.94; FV 6.18 + 1.28\n", "Ricci S.: MV 6.04 ± 0.71; FV 6.11 + 0.70\n", "Thorstvedt: MV 5.86 ± 0.86; FV 6.01 + 1.13\n", "De Ketelaere: MV 5.97 ± 0.73; FV 6.03 + 0.73\n", "Saponara: MV 5.85 ± 1.02; FV 6.09 + 1.37\n", "Vecino: MV 6.05 ± 0.91; FV 6.24 + 1.15\n", "Locatelli: MV 6.09 ± 0.74; FV 6.20 + 0.82\n", "Zaniolo: MV 5.66 ± 0.88; FV 5.75 + 1.00\n", "Traore' Hj.: MV 5.89 ± 0.99; FV 6.19 + 1.48\n", "Maldini: MV 5.97 ± 1.00; FV 6.32 + 1.68\n", "Coulibaly L.: MV 5.93 ± 1.13; FV 6.23 + 1.75\n", "Gonzalez J.: MV 6.11 ± 1.03; FV 6.62 + 1.98\n", "Vilhena: MV 5.78 ± 0.91; FV 5.96 + 1.19\n", "De Roon: MV 6.08 ± 0.68; FV 6.13 + 0.68\n", "Mandragora: MV 5.76 ± 0.87; FV 5.76 + 0.93\n", "Haas: MV 5.98 ± 0.81; FV 6.19 + 1.20\n", "Wijnaldum: MV 5.70 ± 0.95; FV 5.74 + 1.00\n", "Bourabia: MV 5.86 ± 0.81; FV 5.87 + 0.78\n", "Sottil: MV 5.87 ± 1.02; FV 6.10 + 1.39\n", "Agudelo: MV 5.80 ± 0.72; FV 5.83 + 0.69\n", "Makengo: MV 6.00 ± 0.64; FV 6.04 + 0.58\n", "Zalewski: MV 5.78 ± 0.75; FV 5.81 + 0.79\n", "Aebischer: MV 6.03 ± 0.90; FV 6.40 + 1.51\n", "Ederson D.s.: MV 6.12 ± 0.95; FV 6.45 + 1.55\n", "Miretti: MV 6.00 ± 0.75; FV 6.09 + 0.81\n", "Blin: MV 6.03 ± 0.60; FV 6.03 + 0.49\n", "Hjulmand: MV 6.15 ± 1.00; FV 6.30 + 1.37\n", "Cataldi: MV 5.97 ± 0.67; FV 5.97 + 0.54\n", "Paredes: MV 5.83 ± 0.74; FV 5.80 + 0.60\n", "Djuricic: MV 5.66 ± 1.04; FV 5.86 + 1.30\n", "Linetty: MV 5.90 ± 0.88; FV 6.06 + 1.08\n", "Walace: MV 5.96 ± 0.67; FV 5.99 + 0.55\n", "Marin: MV 5.85 ± 1.00; FV 5.89 + 1.06\n", "Mckennie: MV 5.89 ± 0.86; FV 6.11 + 1.29\n", "Pobega: MV 6.15 ± 0.92; FV 6.50 + 1.61\n", "Volpato: MV 5.69 ± 1.13; FV 5.69 + 1.19\n", "Camara Ma.: MV 5.93 ± 0.78; FV 5.97 + 0.73\n", "Cuadrado: MV 6.05 ± 0.98; FV 6.20 + 1.24\n", "Ndombele': MV 5.88 ± 0.64; FV 5.90 + 0.49\n", "Amrabat: MV 5.73 ± 0.93; FV 5.65 + 0.86\n", "Tameze: MV 5.75 ± 0.86; FV 5.81 + 0.99\n", "Gyasi: MV 5.86 ± 1.14; FV 6.22 + 1.76\n", "Ilic: MV 5.84 ± 0.86; FV 5.88 + 0.94\n", "Harroui: MV 5.81 ± 0.80; FV 5.93 + 1.07\n", "Pickel: MV 5.74 ± 0.77; FV 5.80 + 0.94\n", "Moro N.: MV 5.96 ± 0.65; FV 6.05 + 0.64\n", "Duncan: MV 5.72 ± 0.82; FV 5.74 + 0.89\n", "Miguel Veloso: MV 5.84 ± 0.73; FV 5.84 + 0.72\n", "Ekdal: MV 5.77 ± 0.69; FV 5.72 + 0.62\n", "Nicolussi Caviglia: MV 5.83 ± 0.95; FV 6.10 + 1.37\n", "Schouten: MV 5.93 ± 0.69; FV 5.98 + 0.59\n", "Rovella: MV 5.81 ± 1.04; FV 5.75 + 1.02\n", "Crnigoj: MV 5.89 ± 0.82; FV 6.07 + 1.05\n", "Romero L.: MV 6.27 ± 0.98; FV 6.84 + 2.13\n", "Basic: MV 6.00 ± 0.66; FV 6.03 + 0.59\n", "Sabiri: MV 5.69 ± 1.01; FV 5.89 + 1.32\n", "Terracciano F.: MV 5.98 ± 0.63; FV 5.99 + 0.59\n", "Castagnetti: MV 5.75 ± 0.67; FV 5.77 + 0.61\n", "Oudin: MV 6.03 ± 0.63; FV 6.07 + 0.57\n", "D'alessandro: MV 5.96 ± 0.65; FV 5.93 + 0.62\n", "Grassi: MV 5.94 ± 0.67; FV 5.95 + 0.57\n", "Krunic: MV 6.00 ± 0.64; FV 6.03 + 0.57\n", "Rincon: MV 5.65 ± 0.92; FV 5.66 + 0.98\n", "Machin: MV 5.81 ± 0.91; FV 5.80 + 1.00\n", "Leris: MV 5.67 ± 0.83; FV 5.78 + 1.07\n", "Meite': MV 5.73 ± 0.86; FV 5.66 + 0.87\n", "Vieira: MV 5.64 ± 0.89; FV 5.72 + 1.08\n", "Esposito Sa.: MV 5.82 ± 0.85; FV 5.77 + 0.80\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Henderson L.: MV 5.89 ± 0.73; FV 5.94 + 0.78\n", "Obiang: MV 5.85 ± 0.68; FV 5.87 + 0.74\n", "Lopez M.: MV 5.80 ± 0.84; FV 5.83 + 0.81\n", "Saelemaekers: MV 6.03 ± 0.81; FV 6.14 + 0.97\n", "Maggiore: MV 5.91 ± 0.76; FV 6.02 + 0.90\n", "Akpa Akpro: MV 5.95 ± 0.89; FV 6.02 + 0.94\n", "Kovalenko: MV 5.89 ± 0.76; FV 5.99 + 0.85\n", "Maleh: MV 6.10 ± 0.89; FV 6.46 + 1.67\n", "Matheus Henrique: MV 5.74 ± 0.77; FV 5.77 + 0.77\n", "Asllani: MV 5.99 ± 0.64; FV 6.02 + 0.57\n", "Ceide: MV 5.75 ± 0.81; FV 5.79 + 0.77\n", "Gagliardini: MV 5.93 ± 0.65; FV 5.99 + 0.67\n", "Bove: MV 5.62 ± 0.68; FV 5.64 + 0.75\n", "Bianco: MV 5.75 ± 0.86; FV 5.71 + 0.89\n", "Vranckx: MV 5.94 ± 0.69; FV 5.96 + 0.61\n", "Marcos Antonio: MV 5.90 ± 0.59; FV 5.88 + 0.42\n", "Fazzini: MV 5.79 ± 0.66; FV 5.70 + 0.59\n", "D'andrea: MV 5.94 ± 0.77; FV 6.07 + 1.10\n", "Sulemana I.: MV 5.78 ± 0.62; FV 5.77 + 0.62\n", "Tahirovic: MV 5.69 ± 0.73; FV 5.72 + 0.77\n", "Benassi: MV 5.74 ± 0.70; FV 5.77 + 0.78\n", "Barberis: MV 5.73 ± 0.85; FV 5.68 + 0.78\n", "Kastanos: MV 5.78 ± 0.66; FV 5.82 + 0.60\n", "Vignato: MV 5.93 ± 0.71; FV 6.03 + 0.68\n", "Valoti: MV 5.75 ± 0.69; FV 5.69 + 0.63\n", "Winks: MV 5.71 ± 0.87; FV 5.67 + 0.87\n", "Gaetano: MV 5.95 ± 0.82; FV 6.06 + 0.90\n", "Zurkowski: MV 6.01 ± 1.11; FV 6.45 + 1.92\n", "Castrovilli: MV 5.79 ± 0.92; FV 5.85 + 1.04\n", "Bohinen: MV 5.74 ± 0.59; FV 5.76 + 0.49\n", "Hrustic: MV 5.53 ± 0.66; FV 5.56 + 0.61\n", "Iling-Junior: MV 6.00 ± 0.77; FV 6.07 + 0.78\n", "Capezzi: MV 5.85 ± 0.71; FV 5.91 + 0.69\n", "Molina S.: MV 5.80 ± 0.88; FV 5.85 + 1.04\n", "Bakayoko: MV 5.86 ± 0.70; FV 5.77 + 0.60\n", "Scozzarella: MV 5.81 ± 0.91; FV 5.80 + 1.00\n", "Demme: MV 6.03 ± 0.80; FV 6.29 + 1.31\n", "Askildsen: MV 5.71 ± 0.62; FV 5.75 + 0.52\n", "Darboe: MV 5.73 ± 1.01; FV 5.75 + 1.00\n", "Urbanski: MV 6.05 ± 0.78; FV 6.17 + 0.87\n", "Bertini: MV 6.07 ± 0.88; FV 6.17 + 0.97\n", "Hongla: MV 5.62 ± 0.69; FV 5.66 + 0.80\n", "Yepes: MV 5.60 ± 0.94; FV 5.51 + 0.88\n", "Trimboli: MV 5.78 ± 0.93; FV 5.78 + 1.00\n", "Pafundi: MV 6.06 ± 0.80; FV 6.18 + 0.88\n", "Milanese: MV 5.76 ± 0.91; FV 5.76 + 0.99\n", "Helgason: MV 5.84 ± 0.64; FV 5.88 + 0.50\n", "Adli: MV 5.95 ± 0.81; FV 5.98 + 0.83\n", "Vignato S.: MV 5.77 ± 0.93; FV 5.72 + 0.91\n", "Bondo: MV 5.81 ± 0.86; FV 5.75 + 0.85\n", "Samek: MV 6.08 ± 0.88; FV 6.20 + 1.04\n", "Zerbin: MV 5.99 ± 0.73; FV 6.07 + 0.81\n", "Ilkhan: MV 5.85 ± 0.84; FV 5.84 + 0.77\n", "Degli Innocenti: MV 5.97 ± 0.92; FV 6.04 + 0.99\n", "Acella: MV 5.83 ± 0.93; FV 5.90 + 1.09\n", "Garbett: MV 5.94 ± 0.81; FV 6.04 + 0.86\n", "Carboni V.: MV 5.99 ± 0.75; FV 6.08 + 0.79\n", "Cipot: MV 5.87 ± 0.86; FV 5.89 + 0.89\n", "Osimhen: MV 6.55 ± 1.57; FV 8.64 + 6.25\n", "Dybala: MV 6.39 ± 1.26; FV 7.60 + 3.82\n", "Martinez L.: MV 6.44 ± 1.50; FV 8.14 + 5.20\n", "Rafael Leao: MV 6.45 ± 1.47; FV 8.26 + 5.32\n", "Immobile: MV 6.45 ± 1.53; FV 8.33 + 5.60\n", "Lookman: MV 6.58 ± 1.53; FV 8.60 + 6.09\n", "Vlahovic: MV 6.34 ± 1.50; FV 7.90 + 4.79\n", "Arnautovic: MV 6.40 ± 1.42; FV 7.98 + 4.76\n", "Dia: MV 6.07 ± 1.39; FV 6.92 + 3.09\n", "Dzeko: MV 6.32 ± 1.46; FV 7.72 + 4.44\n", "Milik: MV 6.29 ± 1.18; FV 7.33 + 3.31\n", "Nzola: MV 6.09 ± 1.43; FV 6.99 + 3.28\n", "Beto: MV 6.26 ± 1.40; FV 7.56 + 4.11\n", "Abraham: MV 6.03 ± 1.26; FV 6.74 + 2.63\n", "Giroud: MV 6.29 ± 1.39; FV 7.67 + 4.22\n", "Deulofeu: MV 6.43 ± 1.30; FV 7.80 + 4.18\n", "Correa: MV 6.22 ± 1.21; FV 7.14 + 3.12\n", "Pedro: MV 6.22 ± 1.09; FV 6.83 + 2.28\n", "Lozano: MV 6.22 ± 1.16; FV 7.12 + 3.00\n", "Lukaku: MV 6.16 ± 1.33; FV 7.09 + 3.20\n", "Lauriente': MV 5.99 ± 1.09; FV 6.34 + 1.75\n", "Simeone: MV 6.28 ± 1.40; FV 7.64 + 4.23\n", "Cabral: MV 5.88 ± 1.07; FV 6.20 + 1.62\n", "Rebic: MV 6.25 ± 1.37; FV 7.46 + 3.87\n", "Bonazzoli: MV 5.97 ± 1.12; FV 6.42 + 1.92\n", "Berardi: MV 6.21 ± 1.36; FV 7.32 + 3.63\n", "Caprari: MV 5.93 ± 1.08; FV 6.29 + 1.71\n", "Di Maria: MV 6.29 ± 1.36; FV 7.60 + 4.01\n", "Piatek: MV 5.91 ± 1.22; FV 6.37 + 2.09\n", "Kouame': MV 5.93 ± 1.10; FV 6.32 + 1.75\n", "Hojlund: MV 6.35 ± 1.40; FV 7.76 + 4.39\n", "Sanabria: MV 6.05 ± 1.24; FV 6.74 + 2.59\n", "Zapata D.: MV 6.27 ± 1.29; FV 7.45 + 3.75\n", "Kean: MV 6.12 ± 1.26; FV 6.96 + 2.90\n", "Ceesay: MV 6.18 ± 1.24; FV 7.09 + 3.07\n", "Pinamonti: MV 5.79 ± 1.06; FV 6.12 + 1.59\n", "Gonzalez N.: MV 6.08 ± 1.17; FV 6.67 + 2.30\n", "Colombo: MV 6.22 ± 1.38; FV 7.41 + 3.81\n", "Mota: MV 5.91 ± 1.14; FV 6.29 + 1.76\n", "Dessers: MV 5.94 ± 0.99; FV 6.33 + 1.76\n", "Muriel: MV 6.39 ± 1.38; FV 7.83 + 4.39\n", "Okereke: MV 5.82 ± 1.07; FV 6.15 + 1.61\n", "Alvarez A.: MV 5.92 ± 1.06; FV 6.29 + 1.65\n", "Jovic: MV 5.72 ± 1.11; FV 5.98 + 1.45\n", "Barrow: MV 6.15 ± 1.32; FV 7.10 + 3.22\n", "Caputo: MV 6.01 ± 1.23; FV 6.63 + 2.43\n", "Banda: MV 6.08 ± 0.96; FV 6.48 + 1.77\n", "Ciofani D.: MV 6.05 ± 1.08; FV 6.63 + 2.25\n", "Petagna: MV 5.82 ± 0.92; FV 5.99 + 1.25\n", "Di Francesco F.: MV 6.17 ± 1.26; FV 7.04 + 2.97\n", "Boga: MV 6.53 ± 1.38; FV 7.97 + 4.49\n", "Cambiaghi: MV 6.07 ± 0.91; FV 6.38 + 1.42\n", "Djuric: MV 5.97 ± 0.78; FV 6.16 + 1.27\n", "Henry: MV 5.79 ± 1.06; FV 6.17 + 1.72\n", "Success: MV 6.05 ± 0.83; FV 6.23 + 1.16\n", "Gabbiadini: MV 5.72 ± 1.08; FV 5.98 + 1.46\n", "Origi: MV 6.05 ± 1.15; FV 6.64 + 2.32\n", "Lammers: MV 5.80 ± 0.91; FV 6.03 + 1.40\n", "Satriano: MV 5.86 ± 0.94; FV 6.13 + 1.44\n", "Zirkzee: MV 6.13 ± 1.18; FV 6.96 + 2.83\n", "Kallon: MV 5.81 ± 0.85; FV 6.05 + 1.42\n", "Solbakken: MV 5.73 ± 1.00; FV 5.77 + 1.03\n", "Lasagna: MV 5.71 ± 0.90; FV 5.98 + 1.50\n", "Nestorovski: MV 6.15 ± 0.93; FV 6.78 + 2.38\n", "Pellegri: MV 5.85 ± 0.99; FV 6.18 + 1.67\n", "Botheim: MV 5.85 ± 1.02; FV 6.20 + 1.64\n", "Gytkjaer: MV 5.75 ± 0.80; FV 5.87 + 1.11\n", "Belotti: MV 5.57 ± 0.69; FV 5.65 + 0.87\n", "Raspadori: MV 6.01 ± 0.92; FV 6.46 + 1.84\n", "Buonaiuto: MV 5.97 ± 0.73; FV 6.03 + 0.80\n", "Verde: MV 6.00 ± 1.07; FV 6.44 + 1.88\n", "Destro: MV 5.94 ± 1.22; FV 6.39 + 2.09\n", "Sansone: MV 6.11 ± 1.12; FV 6.77 + 2.42\n", "Pjaca: MV 5.89 ± 0.80; FV 5.99 + 0.83\n", "Zanimacchia: MV 5.80 ± 0.74; FV 5.84 + 0.83\n", "Strelec: MV 5.90 ± 0.65; FV 5.90 + 0.61\n", "Seck: MV 6.00 ± 0.62; FV 6.00 + 0.55\n", "Quagliarella: MV 5.75 ± 0.88; FV 5.95 + 1.33\n", "Piccoli: MV 5.79 ± 0.85; FV 6.07 + 1.53\n", "Tsadjout: MV 5.92 ± 0.83; FV 6.11 + 1.26\n", "Shomurodov: MV 5.85 ± 1.00; FV 6.13 + 1.47\n", "Cancellieri: MV 5.87 ± 0.60; FV 5.84 + 0.45\n", "Antiste: MV 5.76 ± 0.89; FV 5.93 + 1.20\n", "Afena-Gyan: MV 5.60 ± 0.72; FV 5.65 + 0.82\n", "Soule': MV 6.01 ± 0.99; FV 6.18 + 1.24\n", "Ngonge: MV 5.77 ± 0.91; FV 5.81 + 1.06\n", "Defrel: MV 5.72 ± 0.77; FV 5.82 + 1.05\n", "Karamoh: MV 5.88 ± 0.67; FV 5.90 + 0.57\n", "Ibrahimovic: MV 6.43 ± 1.41; FV 8.05 + 4.89\n", "Pussetto: MV 5.79 ± 0.97; FV 6.05 + 1.48\n", "Voelkerling Persson: MV 6.09 ± 0.83; FV 6.16 + 0.90\n", "Valencia D.: MV 5.65 ± 0.66; FV 5.69 + 0.79\n", "Edera: MV 5.91 ± 0.83; FV 5.97 + 0.85\n", "Oddei: MV 5.91 ± 0.85; FV 6.03 + 1.06\n", "Braaf: MV 5.89 ± 1.08; FV 6.22 + 1.59\n", "Raimondo: MV 6.11 ± 0.83; FV 6.25 + 1.00\n", "Kaio Jorge: MV 6.00 ± 0.75; FV 6.06 + 0.75\n", "De Luca: MV 5.81 ± 0.94; FV 5.82 + 1.02\n", "Lazetic: MV 6.04 ± 0.88; FV 6.14 + 1.03\n", "Montevago: MV 5.62 ± 0.70; FV 5.70 + 0.99\n", "Krollis: MV 5.83 ± 0.90; FV 5.83 + 0.93\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
MussoPAtalantaSampdoria11.0906.3056400.3774085.7575360.6199936.1804760.3949400.2323101.2101176.3057230.762046-0.5034791.19027270.224476
Rossi F.PAtalantaSampdoria10.016.3056400.3774085.7575360.6199936.1804760.3949400.2323101.2101176.3057230.762046-0.5034791.19027270.224476
SportielloPAtalantaSampdoria10.056.1931150.3585485.6508500.6378856.0949470.3877890.1864541.2211286.2292890.770664-0.5227611.19812068.716019
ScalviniDAtalantaSampdoria11.0806.2977600.5080606.9087791.1318256.2526110.5927020.0563761.1037865.8462351.1220850.5724021.9998180.000000
HateboerDAtalantaSampdoria11.0806.1338400.4715916.6352500.9762416.0115080.5152270.1748931.1530115.7474611.0471800.5281171.9997840.000000
............................................................
DjuricAVeronaUdinese01.0905.9726280.3884656.1630570.6349405.8338130.3964620.2558971.2751095.6613060.8501970.3968841.9996880.000000
PiccoliAVeronaUdinese00.0555.7918790.4271786.0671330.7644885.6358270.4358090.2615411.2372025.4011850.8926260.4792681.9996860.000000
KallonAVeronaUdinese00.4555.8051680.4232216.0472780.7098775.6634240.4408570.2356091.2340815.4522990.8813910.4429271.9996810.000000
LasagnaAVeronaUdinese00.6605.7092090.4486415.9820990.7492685.5540410.4652920.2441181.2105995.3381850.8951070.4658371.9996740.000000
NgongeAVeronaUdinese00.0255.7704540.4528625.8095380.5280655.7445370.5381300.0357481.1977535.5227810.9059100.2279521.9994110.000000
\n", "

547 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Musso P Atalanta Sampdoria 1 1.0 90 6.305640 0.377408 \n", "Rossi F. P Atalanta Sampdoria 1 0.0 1 6.305640 0.377408 \n", "Sportiello P Atalanta Sampdoria 1 0.0 5 6.193115 0.358548 \n", "Scalvini D Atalanta Sampdoria 1 1.0 80 6.297760 0.508060 \n", "Hateboer D Atalanta Sampdoria 1 1.0 80 6.133840 0.471591 \n", "... ... ... ... ... ... ... ... ... \n", "Djuric A Verona Udinese 0 1.0 90 5.972628 0.388465 \n", "Piccoli A Verona Udinese 0 0.0 55 5.791879 0.427178 \n", "Kallon A Verona Udinese 0 0.4 55 5.805168 0.423221 \n", "Lasagna A Verona Udinese 0 0.6 60 5.709209 0.448641 \n", "Ngonge A Verona Udinese 0 0.0 25 5.770454 0.452862 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Musso 5.757536 0.619993 6.180476 0.394940 0.232310 \n", "Rossi F. 5.757536 0.619993 6.180476 0.394940 0.232310 \n", "Sportiello 5.650850 0.637885 6.094947 0.387789 0.186454 \n", "Scalvini 6.908779 1.131825 6.252611 0.592702 0.056376 \n", "Hateboer 6.635250 0.976241 6.011508 0.515227 0.174893 \n", "... ... ... ... ... ... \n", "Djuric 6.163057 0.634940 5.833813 0.396462 0.255897 \n", "Piccoli 6.067133 0.764488 5.635827 0.435809 0.261541 \n", "Kallon 6.047278 0.709877 5.663424 0.440857 0.235609 \n", "Lasagna 5.982099 0.749268 5.554041 0.465292 0.244118 \n", "Ngonge 5.809538 0.528065 5.744537 0.538130 0.035748 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Musso 1.210117 6.305723 0.762046 -0.503479 1.190272 \n", "Rossi F. 1.210117 6.305723 0.762046 -0.503479 1.190272 \n", "Sportiello 1.221128 6.229289 0.770664 -0.522761 1.198120 \n", "Scalvini 1.103786 5.846235 1.122085 0.572402 1.999818 \n", "Hateboer 1.153011 5.747461 1.047180 0.528117 1.999784 \n", "... ... ... ... ... ... \n", "Djuric 1.275109 5.661306 0.850197 0.396884 1.999688 \n", "Piccoli 1.237202 5.401185 0.892626 0.479268 1.999686 \n", "Kallon 1.234081 5.452299 0.881391 0.442927 1.999681 \n", "Lasagna 1.210599 5.338185 0.895107 0.465837 1.999674 \n", "Ngonge 1.197753 5.522781 0.905910 0.227952 1.999411 \n", "\n", " Clean Sheet % \n", "player \n", "Musso 70.224476 \n", "Rossi F. 70.224476 \n", "Sportiello 68.716019 \n", "Scalvini 0.000000 \n", "Hateboer 0.000000 \n", "... ... \n", "Djuric 0.000000 \n", "Piccoli 0.000000 \n", "Kallon 0.000000 \n", "Lasagna 0.000000 \n", "Ngonge 0.000000 \n", "\n", "[547 rows x 19 columns]" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matchday_out = 20\n", "\n", "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "for i in range(players.shape[0]):\n", " try:\n", " [player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", " \n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home, log = 1)\n", " \n", " role = players['r'][player] \n", " \n", " starter = 0\n", " voteperc = 0\n", " \n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", " \n", " if(player in probables.index):\n", " starter = probables['starter'][player]\n", " voteperc = probables['percentage'][player]\n", " \n", " row = [player, role, team, oppteam, home, \n", " starter, voteperc, \n", " mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs]\n", " \n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", " \n", " output = pd.concat([output, row_df])\n", " \n", " except:\n", " print(players.index[i] + ' no data')\n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['team', 'role', 'FV'], ascending = [True, False, False])\n", "#output.to_excel('outputs/pred_matchday_' + str(matchday_out) + '.xlsx')\n", "\n", "output" ] }, { "cell_type": "code", "execution_count": 68, "id": "6befd611", "metadata": {}, "outputs": [], "source": [ "import shutil\n", "\n", "template_file = 'outputs/pred_matchday_base.xlsx'\n", "dest_file = 'outputs/pred_matchday_' + str(matchday_out) + '.xlsx'\n", "\n", "shutil.copyfile(template_file, dest_file)\n", "\n", "with pd.ExcelWriter(dest_file, mode = 'a', engine=\"openpyxl\", if_sheet_exists = 'replace') as writer: \n", " output.to_excel(writer, sheet_name='data')" ] }, { "cell_type": "markdown", "id": "eed7a7ac", "metadata": {}, "source": [ "Predict average Serie A performance for each player" ] }, { "cell_type": "code", "execution_count": 69, "id": "2b637a15", "metadata": {}, "outputs": [], "source": [ "gk_starters = ['Maignan', 'Sepe', 'Silvestri', 'Consigli', 'Provedel', 'Di Gregorio', 'Meret', 'Milinkovic-Savic V.',\n", " 'Terracciano', 'Handanovic', 'Szczesny', 'Skorupski', 'Vicario', 'Musso', 'Radu I.', 'Rui Patricio',\n", " 'Montipo\\'', 'Falcone', 'Dragowski', 'Audero']" ] }, { "cell_type": "code", "execution_count": 70, "id": "60d73507", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret (6.03, 0.43); (5.52, 0.72)\n", "Provedel (6.26, 0.37); (5.68, 0.61)\n", "Vicario (6.45, 0.42); (5.69, 0.59)\n", "Szczesny (6.19, 0.38); (5.60, 0.67)\n", "Falcone (6.33, 0.38); (5.04, 0.64)\n", "Silvestri (6.38, 0.40); (5.28, 0.63)\n", "Rui Patricio (5.95, 0.36); (5.14, 0.73)\n", "Milinkovic-Savic V. (6.32, 0.38); (5.23, 0.61)\n", "Sepe (6.40, 0.40); (5.11, 0.68)\n", "Maignan (6.36, 0.39); (5.42, 0.62)\n", "Onana (6.21, 0.36); (4.73, 0.75)\n", "Audero (6.33, 0.38); (4.48, 0.77)\n", "Musso (6.25, 0.38); (5.53, 0.63)\n", "Carnesecchi (6.39, 0.42); (5.37, 0.67)\n", "Montipo' (6.31, 0.37); (4.50, 0.75)\n", "Di Gregorio (6.23, 0.37); (4.28, 0.83)\n", "Tatarusanu (5.99, 0.33); (4.03, 0.84)\n", "Consigli (6.23, 0.35); (4.79, 0.70)\n", "Dragowski (6.29, 0.37); (4.85, 0.69)\n", "Terracciano (6.02, 0.37); (3.84, 0.97)\n", "Sportiello (6.07, 0.38); (5.43, 0.69)\n", "Skorupski (6.19, 0.36); (4.36, 0.78)\n", "Perin (6.33, 0.44); (5.76, 0.66)\n", "Handanovic (6.04, 0.37); (4.27, 0.89)\n", "Zoet (6.35, 0.40); (5.74, 0.61)\n", "Gollini (6.03, 0.43); (5.52, 0.72)\n", "Ochoa (6.41, 0.41); (5.09, 0.70)\n", "Pegolo (6.31, 0.39); (5.34, 0.68)\n", "Mirante (6.36, 0.39); (5.42, 0.62)\n", "Sarr M. (6.39, 0.42); (5.37, 0.67)\n", "Lamanna (6.23, 0.37); (4.28, 0.83)\n", "Ujkani (6.45, 0.42); (5.69, 0.59)\n", "Berisha (6.32, 0.38); (5.23, 0.61)\n", "Marchetti (6.29, 0.37); (4.85, 0.69)\n", "Perilli (6.31, 0.37); (4.50, 0.75)\n", "Padelli (6.38, 0.40); (5.28, 0.63)\n", "Perisan (6.45, 0.42); (5.69, 0.59)\n", "Bardi (6.19, 0.36); (4.36, 0.78)\n", "Cordaz (6.21, 0.36); (4.73, 0.75)\n", "Pinsoglio (6.19, 0.38); (5.60, 0.67)\n", "Fiorillo (6.40, 0.40); (5.11, 0.68)\n", "Cragno (6.23, 0.37); (4.28, 0.83)\n", "Sirigu (6.02, 0.37); (3.84, 0.97)\n", "Cerofolini (6.02, 0.37); (3.84, 0.97)\n", "Rossi F. (6.25, 0.38); (5.53, 0.63)\n", "Ravaglia F. (6.19, 0.36); (4.36, 0.78)\n", "Brancolini (6.33, 0.38); (5.04, 0.64)\n", "Bleve (6.33, 0.38); (5.04, 0.64)\n", "Berardi A. (6.31, 0.37); (4.50, 0.75)\n", "Russo A. (6.23, 0.35); (4.79, 0.70)\n", "Gemello (6.32, 0.38); (5.23, 0.61)\n", "Ravaglia (6.33, 0.38); (4.48, 0.77)\n", "Boer (5.95, 0.36); (5.14, 0.73)\n", "Adamonis (6.26, 0.37); (5.68, 0.61)\n", "Marfella (6.03, 0.43); (5.52, 0.72)\n", "Zovko (6.28, 0.38); (4.77, 0.73)\n", "Piana (6.38, 0.40); (5.28, 0.63)\n", "Bagnolini (6.19, 0.36); (4.36, 0.78)\n", "Luis Maximiano (5.48, 0.37); (5.14, 0.81)\n", "Svilar (5.95, 0.36); (5.14, 0.73)\n", "Sorrentino A. (6.23, 0.37); (4.28, 0.83)\n", "Ciezkowski (6.39, 0.42); (5.37, 0.67)\n", "Chiesa M. (6.31, 0.37); (4.50, 0.75)\n", "Saro (6.39, 0.42); (5.37, 0.67)\n", "Vasquez D. (6.38, 0.41); (5.58, 0.64)\n", "Turk (6.33, 0.38); (4.48, 0.77)\n", "Dimarco (6.23, 0.51); (6.79, 1.05)\n", "Smalling (6.23, 0.50); (6.73, 0.97)\n", "Doig (6.23, 0.50); (6.75, 1.00)\n", "Carlos Augusto (6.04, 0.53); (6.47, 0.94)\n", "Kim (6.31, 0.50); (6.92, 1.13)\n", "Hernandez T. (6.19, 0.54); (6.76, 1.11)\n", "Udogie (6.15, 0.54); (6.74, 1.13)\n", "Parisi (6.18, 0.44); (6.52, 0.77)\n", "Romagnoli (6.19, 0.49); (6.52, 0.82)\n", "Di Lorenzo (6.25, 0.45); (6.67, 0.88)\n", "Danilo (6.25, 0.49); (6.75, 0.98)\n", "Mazzocchi (6.08, 0.47); (6.46, 0.79)\n", "Mario Rui (6.25, 0.47); (6.63, 0.84)\n", "Bastoni S. (6.10, 0.48); (6.50, 0.86)\n", "Valeri (6.04, 0.36); (6.21, 0.50)\n", "Posch (6.09, 0.57); (6.72, 1.16)\n", "Rodrigo Becao (6.11, 0.43); (6.35, 0.64)\n", "Tomori (6.15, 0.50); (6.52, 0.82)\n", "Baschirotto (6.21, 0.50); (6.71, 0.99)\n", "Juan Jesus (6.22, 0.41); (6.61, 0.82)\n", "Ibanez (6.04, 0.50); (6.25, 0.72)\n", "Demiral (6.13, 0.48); (6.52, 0.83)\n", "Scalvini (6.07, 0.53); (6.49, 0.92)\n", "Bijol (5.98, 0.55); (6.22, 0.84)\n", "Toloi (6.15, 0.49); (6.45, 0.74)\n", "Depaoli (6.04, 0.51); (6.50, 0.96)\n", "Mancini (6.04, 0.35); (6.08, 0.32)\n", "Bremer (5.97, 0.57); (6.26, 0.86)\n", "Ebuehi (6.06, 0.38); (6.29, 0.57)\n", "Dumfries (6.04, 0.52); (6.52, 0.99)\n", "Schuurs (6.09, 0.35); (6.16, 0.36)\n", "Darmian (6.11, 0.45); (6.54, 0.87)\n", "Kalulu (5.91, 0.57); (6.12, 0.80)\n", "Vojvoda (5.97, 0.43); (6.13, 0.52)\n", "Maehle (6.02, 0.38); (6.23, 0.57)\n", "Holm (5.99, 0.41); (6.18, 0.58)\n", "Bastoni (6.03, 0.47); (6.10, 0.49)\n", "Gosens (5.98, 0.35); (6.14, 0.50)\n", "Milenkovic (5.96, 0.56); (6.23, 0.85)\n", "Rodriguez R. (5.93, 0.36); (5.94, 0.31)\n", "Reca (5.99, 0.45); (6.25, 0.65)\n", "Sernicola (5.92, 0.39); (6.08, 0.52)\n", "Rrahmani (6.24, 0.48); (6.72, 0.95)\n", "Kyriakopoulos (5.89, 0.45); (6.03, 0.59)\n", "Martinez Quarta (6.01, 0.50); (6.24, 0.66)\n", "Perez N. (6.04, 0.48); (6.07, 0.52)\n", "Olivera (6.11, 0.40); (6.52, 0.80)\n", "Calabria (6.08, 0.51); (6.48, 0.89)\n", "Skriniar (5.75, 0.43); (5.66, 0.35)\n", "Marusic (5.95, 0.37); (5.97, 0.35)\n", "Lazzari (5.98, 0.38); (5.99, 0.35)\n", "Augello (5.82, 0.43); (6.01, 0.53)\n", "Ampadu (5.81, 0.46); (5.74, 0.41)\n", "Ismajli (6.02, 0.40); (6.03, 0.37)\n", "Cambiaso (5.89, 0.39); (5.91, 0.37)\n", "Hysaj (5.96, 0.34); (6.00, 0.31)\n", "Izzo (5.98, 0.36); (6.01, 0.31)\n", "Biraghi (5.94, 0.37); (6.01, 0.33)\n", "Medel (5.88, 0.39); (5.83, 0.33)\n", "Bonucci (6.16, 0.49); (6.59, 0.88)\n", "Acerbi (6.05, 0.39); (6.15, 0.38)\n", "Spinazzola (5.95, 0.34); (6.01, 0.32)\n", "Lykogiannis (5.92, 0.34); (6.01, 0.34)\n", "Djidji (5.77, 0.47); (5.85, 0.55)\n", "Lazaro (5.91, 0.45); (5.94, 0.44)\n", "Gallo (5.88, 0.36); (5.83, 0.30)\n", "Singo (5.99, 0.40); (6.12, 0.44)\n", "Mari' (5.87, 0.58); (6.01, 0.78)\n", "Casale (5.95, 0.38); (5.92, 0.34)\n", "Dodo' (5.70, 0.49); (5.62, 0.43)\n", "De Vrij (5.78, 0.44); (5.81, 0.48)\n", "Patric (6.01, 0.41); (5.97, 0.37)\n", "Luperto (5.90, 0.52); (5.85, 0.47)\n", "Faraoni (5.99, 0.40); (6.24, 0.66)\n", "Ceccherini (5.90, 0.50); (6.03, 0.64)\n", "Umtiti (6.02, 0.47); (6.00, 0.46)\n", "Aina (5.96, 0.44); (6.15, 0.59)\n", "Caldirola (5.81, 0.45); (5.72, 0.38)\n", "Soppy (5.76, 0.42); (5.76, 0.45)\n", "Gendrey (5.83, 0.35); (5.81, 0.30)\n", "Ferrari A. (5.82, 0.53); (5.87, 0.64)\n", "Zappacosta (6.04, 0.39); (6.24, 0.56)\n", "Bianchetti (5.72, 0.47); (5.76, 0.57)\n", "Ferrari G. (5.77, 0.56); (5.86, 0.72)\n", "Fazio (5.70, 0.61); (5.69, 0.65)\n", "Hateboer (5.83, 0.44); (5.98, 0.60)\n", "Rogerio (5.70, 0.45); (5.69, 0.45)\n", "Buongiorno (5.85, 0.40); (5.78, 0.35)\n", "Gunter (5.76, 0.48); (5.81, 0.56)\n", "Colley (5.78, 0.56); (5.81, 0.66)\n", "Troost-Ekong (5.81, 0.47); (5.78, 0.47)\n", "Terzic (5.94, 0.28); (5.90, 0.21)\n", "Toljan (5.65, 0.44); (5.56, 0.40)\n", "Zortea (5.93, 0.42); (6.18, 0.66)\n", "Soumaoro (5.85, 0.50); (5.77, 0.44)\n", "Amian (5.75, 0.40); (5.67, 0.39)\n", "Pongracic (5.87, 0.40); (5.82, 0.34)\n", "Birindelli (5.80, 0.38); (5.82, 0.41)\n", "Lucumi' (5.77, 0.40); (5.70, 0.35)\n", "Hien (5.78, 0.40); (5.67, 0.34)\n", "Ehizibue (5.89, 0.40); (6.05, 0.57)\n", "Masina (6.04, 0.43); (6.40, 0.74)\n", "Gyomber (5.72, 0.46); (5.62, 0.38)\n", "Alex Sandro (5.76, 0.52); (5.69, 0.48)\n", "Pezzella Giu. (5.89, 0.33); (5.91, 0.27)\n", "Bereszynski (5.76, 0.42); (5.68, 0.40)\n", "Venuti (5.72, 0.40); (5.64, 0.37)\n", "Palomino (6.11, 0.50); (6.40, 0.75)\n", "Nuytinck (5.85, 0.49); (5.83, 0.49)\n", "Marlon (5.73, 0.37); (5.61, 0.31)\n", "Nikolaou (5.73, 0.40); (5.62, 0.33)\n", "Igor (5.70, 0.47); (5.59, 0.38)\n", "Okoli (5.67, 0.45); (5.55, 0.39)\n", "Dawidowicz (5.74, 0.49); (5.74, 0.52)\n", "Celik (5.77, 0.40); (5.65, 0.38)\n", "Bellanova (5.78, 0.42); (5.78, 0.46)\n", "Erlic (5.79, 0.49); (5.74, 0.48)\n", "Ballo-Toure' (6.11, 0.38); (6.38, 0.63)\n", "Dest (5.72, 0.43); (5.66, 0.39)\n", "Stojanovic (5.73, 0.45); (5.67, 0.45)\n", "Bradaric (5.62, 0.46); (5.55, 0.45)\n", "Daniliuc (5.70, 0.56); (5.65, 0.54)\n", "Zima (5.81, 0.41); (5.77, 0.37)\n", "Quagliata (5.91, 0.31); (5.95, 0.28)\n", "Ebosse (5.69, 0.37); (5.58, 0.34)\n", "Aiwu (5.85, 0.46); (5.86, 0.48)\n", "Lochoshvili (5.74, 0.40); (5.66, 0.40)\n", "Bronn (5.67, 0.39); (5.57, 0.33)\n", "Thiaw (5.98, 0.42); (6.05, 0.43)\n", "Zeefuik (5.86, 0.44); (5.89, 0.44)\n", "Ghiglione (5.75, 0.43); (5.72, 0.48)\n", "Rugani (5.96, 0.32); (5.97, 0.26)\n", "De Sciglio (5.89, 0.35); (5.96, 0.33)\n", "Djimsiti (5.95, 0.41); (6.01, 0.39)\n", "Caldara (5.71, 0.48); (5.61, 0.41)\n", "Murru (5.66, 0.45); (5.66, 0.50)\n", "Karsdorp (5.85, 0.39); (5.80, 0.34)\n", "Bonifazi (5.74, 0.42); (5.65, 0.35)\n", "Kjaer (5.91, 0.36); (5.86, 0.30)\n", "Magnani (5.68, 0.42); (5.56, 0.33)\n", "Walukiewicz (5.75, 0.44); (5.67, 0.41)\n", "Ayhan (5.70, 0.57); (5.67, 0.58)\n", "Amione (5.60, 0.44); (5.49, 0.43)\n", "Ruggeri (5.93, 0.35); (5.99, 0.30)\n", "De Winter (5.83, 0.45); (5.76, 0.38)\n", "Ostigard (5.93, 0.31); (5.97, 0.27)\n", "Wisniewski (5.83, 0.44); (5.83, 0.45)\n", "Radovanovic (5.55, 0.41); (5.43, 0.34)\n", "Dermaku (5.88, 0.42); (5.89, 0.39)\n", "D'ambrosio (6.10, 0.37); (6.22, 0.44)\n", "De Silvestri (5.85, 0.45); (6.03, 0.61)\n", "Sala (5.89, 0.39); (5.95, 0.40)\n", "Chiriches (5.75, 0.50); (5.64, 0.42)\n", "Donati (5.87, 0.50); (5.82, 0.48)\n", "Gabbia (5.78, 0.37); (5.70, 0.31)\n", "Kumbulla (5.77, 0.34); (5.69, 0.30)\n", "Adopo (5.95, 0.37); (5.98, 0.32)\n", "Pirola (5.52, 0.51); (5.41, 0.39)\n", "Lovato (5.60, 0.53); (5.51, 0.44)\n", "Tuia (5.74, 0.47); (5.82, 0.56)\n", "Ferrer (5.81, 0.44); (5.77, 0.42)\n", "Antov (5.68, 0.52); (5.62, 0.49)\n", "Vasquez (5.77, 0.43); (5.69, 0.42)\n", "Zanoli (5.92, 0.32); (5.94, 0.25)\n", "Gatti (5.82, 0.44); (5.78, 0.39)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Gila (5.93, 0.43); (5.91, 0.38)\n", "Sambia (5.81, 0.48); (5.71, 0.40)\n", "Moutinho J. (5.86, 0.49); (5.81, 0.44)\n", "Conti (5.94, 0.54); (6.09, 0.71)\n", "Marrone (5.61, 0.47); (5.51, 0.41)\n", "Tonelli (5.64, 0.46); (5.54, 0.42)\n", "Murillo (5.58, 0.36); (5.47, 0.32)\n", "Radu (5.72, 0.48); (5.65, 0.45)\n", "Paletta (5.83, 0.47); (5.82, 0.52)\n", "Florenzi (6.08, 0.42); (6.29, 0.56)\n", "Fares (5.80, 0.38); (5.77, 0.36)\n", "Marchizza (5.71, 0.40); (5.65, 0.41)\n", "Romagna (5.85, 0.46); (5.89, 0.51)\n", "Ranieri L. (5.74, 0.42); (5.79, 0.53)\n", "Cassandro (5.88, 0.43); (5.90, 0.40)\n", "Muldur (5.71, 0.42); (5.63, 0.39)\n", "Carboni (5.70, 0.43); (5.58, 0.41)\n", "Amey (5.96, 0.42); (6.04, 0.44)\n", "Ferrarini (5.83, 0.47); (5.82, 0.52)\n", "Vina (5.80, 0.43); (5.71, 0.40)\n", "Zanotti (5.86, 0.45); (5.91, 0.51)\n", "Ruan (5.64, 0.45); (5.55, 0.32)\n", "Coppola D. (5.70, 0.40); (5.57, 0.36)\n", "Cacace (5.83, 0.39); (5.79, 0.34)\n", "Bayeye (5.88, 0.45); (5.92, 0.45)\n", "Ebosele (5.87, 0.46); (5.87, 0.46)\n", "Buta (5.89, 0.45); (5.90, 0.46)\n", "Abankwah (5.89, 0.45); (5.90, 0.46)\n", "Guessand A. (5.89, 0.45); (5.90, 0.46)\n", "Cabal (5.98, 0.39); (6.06, 0.37)\n", "Sosa (5.68, 0.47); (5.58, 0.42)\n", "Guarino (5.87, 0.47); (5.90, 0.50)\n", "Carboni F. (5.85, 0.48); (5.84, 0.49)\n", "Zaccagni (6.46, 0.68); (8.04, 2.39)\n", "Kvaratskhelia (6.53, 0.76); (8.54, 2.98)\n", "Milinkovic-Savic (6.33, 0.65); (7.57, 1.92)\n", "Barella (6.30, 0.58); (7.24, 1.55)\n", "Zielinski (6.36, 0.51); (7.00, 1.18)\n", "Luis Alberto (6.35, 0.56); (7.16, 1.40)\n", "Strefezza (6.33, 0.55); (7.21, 1.47)\n", "Felipe Anderson (6.23, 0.64); (7.32, 1.75)\n", "Diaz B. (6.17, 0.63); (7.09, 1.54)\n", "Koopmeiners (6.37, 0.63); (7.58, 1.88)\n", "Vlasic (6.21, 0.58); (7.00, 1.37)\n", "Calhanoglu (6.30, 0.53); (6.97, 1.20)\n", "Frattesi (6.11, 0.58); (6.79, 1.24)\n", "Zambo Anguissa (6.32, 0.54); (7.02, 1.26)\n", "Elmas (6.27, 0.53); (7.04, 1.33)\n", "Pereyra (6.23, 0.54); (6.90, 1.20)\n", "Miranchuk (6.19, 0.62); (7.06, 1.47)\n", "Samardzic (6.21, 0.53); (6.87, 1.20)\n", "Politano (6.29, 0.49); (6.88, 1.10)\n", "Rabiot (6.15, 0.55); (6.73, 1.08)\n", "Radonjic (6.18, 0.53); (6.83, 1.18)\n", "Lobotka (6.22, 0.40); (6.54, 0.72)\n", "Tonali (6.22, 0.53); (6.82, 1.11)\n", "Lazovic (6.17, 0.55); (6.76, 1.11)\n", "Bonaventura (6.15, 0.55); (6.78, 1.18)\n", "Pellegrini Lo. (6.18, 0.62); (7.05, 1.50)\n", "Pessina (6.05, 0.51); (6.45, 0.86)\n", "Kostic (6.10, 0.49); (6.51, 0.84)\n", "Lovric (6.17, 0.44); (6.52, 0.76)\n", "Ferguson (6.09, 0.49); (6.58, 0.94)\n", "Ciurria (6.13, 0.58); (6.81, 1.24)\n", "Ikone' (6.00, 0.55); (6.47, 0.98)\n", "Baldanzi (6.25, 0.53); (6.99, 1.27)\n", "Candreva (5.97, 0.59); (6.31, 0.93)\n", "Bennacer (6.13, 0.40); (6.39, 0.62)\n", "El Shaarawy (6.19, 0.47); (6.77, 1.07)\n", "Pasalic (6.12, 0.59); (6.88, 1.35)\n", "Orsolini (6.18, 0.64); (7.09, 1.55)\n", "Bandinelli (5.97, 0.44); (6.23, 0.67)\n", "Mkhitaryan (6.08, 0.48); (6.50, 0.87)\n", "Colpani (6.02, 0.46); (6.36, 0.81)\n", "Pogba (5.94, 0.46); (6.03, 0.53)\n", "Sensi (6.02, 0.55); (6.41, 0.95)\n", "Chiesa (6.15, 0.52); (6.62, 0.96)\n", "Lukic (6.05, 0.52); (6.44, 0.89)\n", "Fagioli (6.13, 0.49); (6.59, 0.90)\n", "Messias (6.04, 0.55); (6.58, 1.07)\n", "Arslan (5.97, 0.36); (6.06, 0.38)\n", "Brozovic (6.20, 0.47); (6.62, 0.86)\n", "Verdi (6.13, 0.45); (6.51, 0.80)\n", "Barak (5.90, 0.47); (6.20, 0.74)\n", "Matic (6.09, 0.39); (6.31, 0.56)\n", "Soriano (6.00, 0.39); (6.10, 0.41)\n", "Dominguez (6.10, 0.50); (6.51, 0.87)\n", "Ranocchia F. (5.96, 0.45); (6.25, 0.73)\n", "Cristante (5.92, 0.45); (6.07, 0.60)\n", "Bajrami (5.86, 0.50); (6.14, 0.73)\n", "Ricci S. (6.06, 0.37); (6.14, 0.38)\n", "Thorstvedt (5.92, 0.43); (6.14, 0.65)\n", "De Ketelaere (5.88, 0.39); (5.98, 0.49)\n", "Saponara (6.01, 0.51); (6.46, 0.92)\n", "Vecino (5.94, 0.46); (6.06, 0.55)\n", "Locatelli (6.03, 0.37); (6.13, 0.40)\n", "Zaniolo (5.87, 0.48); (6.09, 0.74)\n", "Traore' Hj. (5.98, 0.52); (6.38, 0.91)\n", "Maldini (6.00, 0.50); (6.39, 0.90)\n", "Coulibaly L. (5.94, 0.59); (6.25, 0.94)\n", "Gonzalez J. (5.99, 0.48); (6.33, 0.78)\n", "Vilhena (5.78, 0.46); (5.99, 0.65)\n", "De Roon (5.98, 0.37); (6.02, 0.35)\n", "Mandragora (5.93, 0.44); (6.09, 0.58)\n", "Haas (5.91, 0.40); (6.05, 0.56)\n", "Wijnaldum (5.93, 0.45); (5.98, 0.50)\n", "Bourabia (5.89, 0.40); (5.92, 0.38)\n", "Sottil (6.05, 0.53); (6.56, 1.01)\n", "Agudelo (5.83, 0.35); (5.85, 0.35)\n", "Makengo (5.98, 0.34); (6.01, 0.32)\n", "Zalewski (6.00, 0.33); (6.04, 0.31)\n", "Aebischer (5.95, 0.45); (6.24, 0.72)\n", "Ederson D.s. (5.87, 0.45); (6.04, 0.60)\n", "Miretti (5.92, 0.38); (5.99, 0.42)\n", "Blin (5.97, 0.30); (5.97, 0.23)\n", "Hjulmand (5.97, 0.51); (6.01, 0.55)\n", "Cataldi (5.93, 0.34); (5.91, 0.28)\n", "Paredes (5.81, 0.37); (5.76, 0.32)\n", "Djuricic (5.72, 0.51); (5.92, 0.67)\n", "Linetty (5.90, 0.45); (6.06, 0.59)\n", "Walace (5.88, 0.37); (5.82, 0.33)\n", "Marin (5.78, 0.54); (5.82, 0.61)\n", "Mckennie (5.77, 0.43); (5.92, 0.58)\n", "Pobega (6.04, 0.42); (6.29, 0.67)\n", "Volpato (5.99, 0.56); (6.40, 0.95)\n", "Camara Ma. (6.10, 0.34); (6.14, 0.33)\n", "Cuadrado (5.90, 0.51); (5.98, 0.57)\n", "Ndombele' (5.87, 0.32); (5.89, 0.25)\n", "Amrabat (5.77, 0.48); (5.66, 0.40)\n", "Tameze (5.82, 0.41); (5.88, 0.44)\n", "Gyasi (5.83, 0.54); (6.11, 0.77)\n", "Ilic (5.93, 0.41); (5.99, 0.41)\n", "Harroui (5.86, 0.40); (6.02, 0.59)\n", "Pickel (5.79, 0.40); (5.90, 0.52)\n", "Moro N. (5.93, 0.35); (6.00, 0.32)\n", "Duncan (5.88, 0.41); (6.02, 0.52)\n", "Miguel Veloso (5.95, 0.35); (5.97, 0.32)\n", "Ekdal (5.79, 0.34); (5.74, 0.31)\n", "Nicolussi Caviglia (5.84, 0.49); (6.16, 0.76)\n", "Schouten (5.92, 0.38); (5.91, 0.34)\n", "Rovella (5.87, 0.50); (5.82, 0.47)\n", "Crnigoj (5.92, 0.42); (6.14, 0.63)\n", "Romero L. (6.22, 0.49); (6.81, 1.06)\n", "Basic (5.97, 0.33); (5.99, 0.29)\n", "Sabiri (5.72, 0.48); (5.85, 0.58)\n", "Terracciano F. (6.01, 0.31); (6.01, 0.28)\n", "Castagnetti (5.83, 0.31); (5.87, 0.25)\n", "Oudin (5.96, 0.31); (6.00, 0.26)\n", "D'alessandro (6.02, 0.32); (6.03, 0.30)\n", "Grassi (5.92, 0.35); (5.93, 0.30)\n", "Krunic (5.99, 0.33); (6.02, 0.31)\n", "Rincon (5.70, 0.43); (5.68, 0.44)\n", "Machin (5.86, 0.47); (5.89, 0.55)\n", "Leris (5.70, 0.41); (5.80, 0.53)\n", "Meite' (5.76, 0.43); (5.67, 0.41)\n", "Vieira (5.68, 0.44); (5.76, 0.55)\n", "Esposito Sa. (5.83, 0.42); (5.81, 0.41)\n", "Henderson L. (5.87, 0.38); (5.95, 0.46)\n", "Obiang (5.90, 0.31); (5.92, 0.28)\n", "Lopez M. (5.86, 0.40); (5.85, 0.40)\n", "Saelemaekers (5.91, 0.39); (5.99, 0.46)\n", "Maggiore (5.91, 0.38); (6.01, 0.47)\n", "Akpa Akpro (5.86, 0.48); (5.90, 0.53)\n", "Kovalenko (5.91, 0.37); (6.00, 0.42)\n", "Maleh (5.96, 0.38); (6.05, 0.46)\n", "Matheus Henrique (5.81, 0.36); (5.83, 0.35)\n", "Asllani (5.97, 0.34); (5.99, 0.30)\n", "Ceide (5.84, 0.38); (5.87, 0.35)\n", "Gagliardini (5.86, 0.34); (5.87, 0.39)\n", "Bove (5.74, 0.33); (5.71, 0.32)\n", "Bianco (5.96, 0.40); (6.03, 0.43)\n", "Vranckx (5.89, 0.37); (5.96, 0.36)\n", "Marcos Antonio (5.88, 0.30); (5.86, 0.22)\n", "Fazzini (5.77, 0.33); (5.69, 0.31)\n", "D'andrea (5.97, 0.37); (6.06, 0.44)\n", "Sulemana I. (5.88, 0.30); (5.89, 0.26)\n", "Tahirovic (5.93, 0.32); (5.95, 0.28)\n", "Benassi (5.79, 0.34); (5.81, 0.34)\n", "Barberis (5.82, 0.41); (5.77, 0.39)\n", "Kastanos (5.80, 0.33); (5.82, 0.32)\n", "Vignato (5.90, 0.38); (5.96, 0.38)\n", "Valoti (5.77, 0.35); (5.73, 0.33)\n", "Winks (5.77, 0.42); (5.73, 0.42)\n", "Gaetano (5.99, 0.41); (6.11, 0.47)\n", "Zurkowski (6.05, 0.55); (6.54, 1.01)\n", "Castrovilli (5.95, 0.49); (6.25, 0.74)\n", "Bohinen (5.68, 0.31); (5.69, 0.25)\n", "Hrustic (5.60, 0.31); (5.65, 0.26)\n", "Iling-Junior (5.92, 0.39); (5.96, 0.40)\n", "Capezzi (5.87, 0.35); (5.88, 0.34)\n", "Molina S. (5.81, 0.46); (5.94, 0.60)\n", "Bakayoko (5.74, 0.40); (5.61, 0.36)\n", "Scozzarella (5.86, 0.47); (5.89, 0.55)\n", "Demme (6.04, 0.41); (6.32, 0.64)\n", "Askildsen (5.65, 0.31); (5.69, 0.27)\n", "Darboe (5.96, 0.46); (5.97, 0.46)\n", "Urbanski (5.93, 0.42); (6.00, 0.45)\n", "Bertini (5.98, 0.43); (6.05, 0.47)\n", "Hongla (5.66, 0.34); (5.70, 0.36)\n", "Yepes (5.66, 0.45); (5.55, 0.41)\n", "Trimboli (5.83, 0.45); (5.83, 0.48)\n", "Pafundi (5.92, 0.45); (5.98, 0.50)\n", "Milanese (5.79, 0.45); (5.76, 0.46)\n", "Helgason (5.81, 0.32); (5.83, 0.25)\n", "Adli (5.76, 0.44); (5.82, 0.53)\n", "Vignato S. (5.82, 0.49); (5.76, 0.48)\n", "Bondo (5.88, 0.42); (5.87, 0.40)\n", "Samek (5.90, 0.42); (5.95, 0.41)\n", "Zerbin (6.01, 0.37); (6.11, 0.42)\n", "Ilkhan (5.82, 0.47); (5.79, 0.42)\n", "Degli Innocenti (5.88, 0.50); (5.92, 0.53)\n", "Acella (5.86, 0.46); (5.90, 0.50)\n", "Garbett (5.90, 0.45); (5.97, 0.48)\n", "Carboni V. (5.84, 0.45); (5.85, 0.50)\n", "Cipot (5.89, 0.42); (5.96, 0.46)\n", "Osimhen (6.56, 0.79); (8.66, 3.15)\n", "Dybala (6.50, 0.68); (8.10, 2.42)\n", "Martinez L. (6.37, 0.74); (7.97, 2.43)\n", "Rafael Leao (6.40, 0.70); (7.96, 2.34)\n", "Immobile (6.43, 0.76); (8.22, 2.68)\n", "Lookman (6.47, 0.75); (8.27, 2.72)\n", "Vlahovic (6.28, 0.74); (7.66, 2.18)\n", "Arnautovic (6.28, 0.69); (7.60, 2.05)\n", "Dia (6.13, 0.69); (7.16, 1.72)\n", "Dzeko (6.27, 0.70); (7.59, 2.07)\n", "Milik (6.22, 0.58); (7.09, 1.46)\n", "Nzola (6.13, 0.71); (7.13, 1.74)\n", "Beto (6.16, 0.68); (7.19, 1.74)\n", "Abraham (6.30, 0.69); (7.59, 2.02)\n", "Giroud (6.21, 0.65); (7.29, 1.74)\n", "Deulofeu (6.35, 0.64); (7.55, 1.89)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Correa (6.12, 0.55); (6.85, 1.33)\n", "Pedro (6.17, 0.56); (6.81, 1.17)\n", "Lozano (6.22, 0.62); (7.23, 1.64)\n", "Lukaku (6.06, 0.60); (6.78, 1.30)\n", "Lauriente' (6.14, 0.57); (6.74, 1.15)\n", "Simeone (6.28, 0.72); (7.66, 2.16)\n", "Cabral (6.08, 0.61); (6.80, 1.34)\n", "Rebic (6.15, 0.65); (7.07, 1.57)\n", "Bonazzoli (5.97, 0.52); (6.40, 0.92)\n", "Berardi (6.30, 0.70); (7.68, 2.14)\n", "Caprari (6.07, 0.59); (6.72, 1.24)\n", "Di Maria (6.22, 0.66); (7.34, 1.78)\n", "Piatek (5.97, 0.60); (6.53, 1.15)\n", "Kouame' (6.12, 0.61); (6.87, 1.37)\n", "Hojlund (6.17, 0.67); (7.15, 1.67)\n", "Sanabria (6.05, 0.61); (6.72, 1.27)\n", "Zapata D. (6.07, 0.60); (6.79, 1.34)\n", "Kean (6.03, 0.61); (6.70, 1.24)\n", "Ceesay (6.04, 0.58); (6.61, 1.15)\n", "Pinamonti (5.89, 0.54); (6.31, 0.95)\n", "Gonzalez N. (6.24, 0.63); (7.23, 1.66)\n", "Colombo (6.12, 0.65); (6.99, 1.54)\n", "Mota (6.03, 0.59); (6.58, 1.13)\n", "Dessers (5.97, 0.56); (6.46, 1.05)\n", "Muriel (6.23, 0.65); (7.25, 1.69)\n", "Okereke (5.90, 0.56); (6.36, 0.98)\n", "Alvarez A. (6.02, 0.56); (6.55, 1.05)\n", "Jovic (5.95, 0.57); (6.45, 1.04)\n", "Barrow (6.02, 0.62); (6.63, 1.22)\n", "Caputo (6.01, 0.62); (6.65, 1.24)\n", "Banda (5.94, 0.43); (6.11, 0.58)\n", "Ciofani D. (6.07, 0.60); (6.75, 1.29)\n", "Petagna (5.86, 0.49); (6.13, 0.74)\n", "Di Francesco F. (6.03, 0.58); (6.53, 1.06)\n", "Boga (6.44, 0.68); (7.87, 2.22)\n", "Cambiaghi (6.07, 0.48); (6.43, 0.78)\n", "Djuric (6.07, 0.42); (6.39, 0.76)\n", "Henry (5.89, 0.56); (6.31, 0.96)\n", "Success (5.96, 0.38); (6.03, 0.42)\n", "Gabbiadini (5.81, 0.56); (6.12, 0.84)\n", "Origi (5.89, 0.52); (6.23, 0.83)\n", "Lammers (5.83, 0.47); (6.07, 0.72)\n", "Satriano (5.81, 0.47); (6.04, 0.69)\n", "Zirkzee (6.02, 0.54); (6.57, 1.08)\n", "Kallon (5.87, 0.45); (6.15, 0.74)\n", "Solbakken (5.95, 0.50); (6.03, 0.58)\n", "Lasagna (5.76, 0.48); (6.06, 0.79)\n", "Nestorovski (6.06, 0.42); (6.41, 0.85)\n", "Pellegri (5.86, 0.48); (6.21, 0.84)\n", "Botheim (5.87, 0.50); (6.27, 0.87)\n", "Gytkjaer (5.82, 0.44); (6.05, 0.69)\n", "Belotti (5.66, 0.35); (5.72, 0.40)\n", "Raspadori (6.04, 0.52); (6.61, 1.09)\n", "Buonaiuto (5.95, 0.36); (6.02, 0.33)\n", "Verde (6.04, 0.53); (6.54, 1.02)\n", "Destro (5.92, 0.62); (6.39, 1.06)\n", "Sansone (5.93, 0.50); (6.31, 0.86)\n", "Pjaca (5.82, 0.43); (5.96, 0.51)\n", "Zanimacchia (5.83, 0.37); (5.86, 0.35)\n", "Strelec (5.92, 0.32); (5.92, 0.31)\n", "Seck (6.05, 0.32); (6.07, 0.29)\n", "Quagliarella (5.78, 0.45); (5.97, 0.65)\n", "Piccoli (5.84, 0.46); (6.14, 0.79)\n", "Tsadjout (5.90, 0.47); (6.17, 0.75)\n", "Shomurodov (6.03, 0.56); (6.60, 1.13)\n", "Cancellieri (5.81, 0.30); (5.77, 0.24)\n", "Antiste (5.82, 0.44); (6.05, 0.68)\n", "Afena-Gyan (5.61, 0.35); (5.69, 0.37)\n", "Soule' (5.86, 0.48); (5.97, 0.54)\n", "Ngonge (5.87, 0.44); (5.91, 0.46)\n", "Defrel (5.75, 0.40); (5.90, 0.59)\n", "Karamoh (5.89, 0.35); (5.89, 0.33)\n", "Ibrahimovic (6.35, 0.67); (7.70, 2.08)\n", "Pussetto (5.82, 0.50); (6.10, 0.77)\n", "Voelkerling Persson (5.91, 0.40); (5.92, 0.36)\n", "Valencia D. (5.69, 0.32); (5.70, 0.40)\n", "Edera (5.83, 0.48); (5.85, 0.48)\n", "Oddei (6.00, 0.39); (6.10, 0.44)\n", "Braaf (6.01, 0.54); (6.37, 0.86)\n", "Raimondo (5.94, 0.43); (6.01, 0.45)\n", "Kaio Jorge (5.93, 0.37); (5.97, 0.38)\n", "De Luca (5.85, 0.46); (5.86, 0.47)\n", "Lazetic (5.91, 0.48); (5.98, 0.57)\n", "Montevago (5.63, 0.34); (5.67, 0.41)\n", "Krollis (5.80, 0.46); (5.79, 0.47)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
MussoPAtalantaAvg111006.2506220.3784115.5302090.6295296.1310170.3999600.2193811.2040456.0269300.821359-0.4323021.11303743.711811
Rossi F.PAtalantaAvg1006.2506220.3784115.5302090.6295296.1310170.3999600.2193811.2040456.0269300.821359-0.4323021.11303743.711811
SportielloPAtalantaAvg1006.0729750.3807525.4300700.6916475.9765730.4163460.1706811.2279546.0594330.839207-0.5246991.15570948.146455
DemiralDAtalantaAvg11806.1326700.4841496.5179650.8305366.0595690.5538850.0977961.1391265.8194251.0246320.4458161.9997450.000000
ScalviniDAtalantaAvg11756.0682070.5271716.4926870.9178966.0198910.6143020.0581501.1005395.6968411.0777940.4745661.9997290.000000
............................................................
HenryAVeronaAvg11805.8874870.5599786.3071550.9575405.6305450.5534240.3360221.0777265.4318861.0148790.5345261.9997420.000000
KallonAVeronaAvg10805.8711920.4507606.1458010.7379645.7018550.4593090.2690801.1973835.5215180.9037410.4511431.9997000.000000
PiccoliAVeronaAvg10305.8402130.4550196.1359790.7917625.6580570.4556410.2909131.2004155.4409440.9118310.4872741.9997010.000000
LasagnaAVeronaAvg11755.7644750.4837056.0596230.7936675.5786510.4926070.2748591.1664235.3669970.9235460.4810541.9996930.000000
NgongeAVeronaAvg1005.8706720.4413425.9067400.4608755.9010170.545786-0.0412911.2123175.7249160.8636730.1539651.9994430.000000
\n", "

547 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Musso P Atalanta Avg 1 1 100 6.250622 0.378411 \n", "Rossi F. P Atalanta Avg 1 0 0 6.250622 0.378411 \n", "Sportiello P Atalanta Avg 1 0 0 6.072975 0.380752 \n", "Demiral D Atalanta Avg 1 1 80 6.132670 0.484149 \n", "Scalvini D Atalanta Avg 1 1 75 6.068207 0.527171 \n", "... ... ... ... ... ... ... ... ... \n", "Henry A Verona Avg 1 1 80 5.887487 0.559978 \n", "Kallon A Verona Avg 1 0 80 5.871192 0.450760 \n", "Piccoli A Verona Avg 1 0 30 5.840213 0.455019 \n", "Lasagna A Verona Avg 1 1 75 5.764475 0.483705 \n", "Ngonge A Verona Avg 1 0 0 5.870672 0.441342 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Musso 5.530209 0.629529 6.131017 0.399960 0.219381 \n", "Rossi F. 5.530209 0.629529 6.131017 0.399960 0.219381 \n", "Sportiello 5.430070 0.691647 5.976573 0.416346 0.170681 \n", "Demiral 6.517965 0.830536 6.059569 0.553885 0.097796 \n", "Scalvini 6.492687 0.917896 6.019891 0.614302 0.058150 \n", "... ... ... ... ... ... \n", "Henry 6.307155 0.957540 5.630545 0.553424 0.336022 \n", "Kallon 6.145801 0.737964 5.701855 0.459309 0.269080 \n", "Piccoli 6.135979 0.791762 5.658057 0.455641 0.290913 \n", "Lasagna 6.059623 0.793667 5.578651 0.492607 0.274859 \n", "Ngonge 5.906740 0.460875 5.901017 0.545786 -0.041291 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Musso 1.204045 6.026930 0.821359 -0.432302 1.113037 \n", "Rossi F. 1.204045 6.026930 0.821359 -0.432302 1.113037 \n", "Sportiello 1.227954 6.059433 0.839207 -0.524699 1.155709 \n", "Demiral 1.139126 5.819425 1.024632 0.445816 1.999745 \n", "Scalvini 1.100539 5.696841 1.077794 0.474566 1.999729 \n", "... ... ... ... ... ... \n", "Henry 1.077726 5.431886 1.014879 0.534526 1.999742 \n", "Kallon 1.197383 5.521518 0.903741 0.451143 1.999700 \n", "Piccoli 1.200415 5.440944 0.911831 0.487274 1.999701 \n", "Lasagna 1.166423 5.366997 0.923546 0.481054 1.999693 \n", "Ngonge 1.212317 5.724916 0.863673 0.153965 1.999443 \n", "\n", " Clean Sheet % \n", "player \n", "Musso 43.711811 \n", "Rossi F. 43.711811 \n", "Sportiello 48.146455 \n", "Demiral 0.000000 \n", "Scalvini 0.000000 \n", "... ... \n", "Henry 0.000000 \n", "Kallon 0.000000 \n", "Piccoli 0.000000 \n", "Lasagna 0.000000 \n", "Ngonge 0.000000 \n", "\n", "[547 rows x 19 columns]" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "tot_matches = 2 # home and not home\n", "\n", "current_season_games = max(players_orig['games'])\n", "\n", "for i in range(players.shape[0]):\n", " home = 0\n", " \n", " for k in range(tot_matches):\n", " #matchday_out = k + 1\n", " #[player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", " \n", " player = players.index[i]\n", " team = players['team'][i]\n", " oppteam = 'Avg'\n", " home = not home\n", "\n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home)\n", "\n", " role = players['r'][player] \n", "\n", " starter = 0\n", " voteperc = 0\n", "\n", " games = max( players_orig['games'][i], players_orig['gk_games'][i] )\n", " mins = max( players_orig['minutes'][i], players_orig['gk_minutes'][i] )\n", " \n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", " \n", " starter = int( player in gk_starters )\n", " if(starter):\n", " voteperc = 100\n", " else:\n", " voteperc = 0\n", " else:\n", " starter = int ( 1 * (games >= current_season_games * 2/3 and mins / games >= 45 ) )\n", " voteperc = int( min( 1, games / current_season_games ) * 100) \n", "\n", " if(k == 0):\n", " row = [player, role, team, 'Avg', 1, starter, voteperc]\n", " \n", " numrow_ = [mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs] \n", "\n", " if(k == 0):\n", " numrow = numrow_\n", " else:\n", " for j in range(len(numrow)):\n", " numrow[j] += numrow_[j]\n", "\n", " for j in range(len(numrow)):\n", " numrow[j] /= tot_matches\n", " \n", " print(players.index[i] + ' (' + \"{:.2f}\".format(numrow[0]) + ', ' + \"{:.2f}\".format(numrow[1]) + \n", " '); (' + \"{:.2f}\".format(numrow[2]) + ', ' + \"{:.2f}\".format(numrow[3]) + ')' )\n", " \n", " row += numrow # list concat\n", " \n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", "\n", " output = pd.concat([output, row_df])\n", " \n", " \n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['team', 'role', 'FV'], ascending = [True, False, False])\n", "#output.to_excel('outputs/pred_matchday_' + str(matchday_out) + '.xlsx')\n", "\n", "output" ] }, { "cell_type": "code", "execution_count": 71, "id": "b47cbd63", "metadata": {}, "outputs": [], "source": [ "import shutil\n", "\n", "output = output.sort_values(['role', 'FV'], ascending = [False, False])\n", "\n", "template_file = 'outputs/pred_matchday_base.xlsx'\n", "dest_file = 'outputs/pred_avg_seriea.xlsx'\n", "\n", "shutil.copyfile(template_file, dest_file)\n", "\n", "with pd.ExcelWriter(dest_file, mode = 'a', engine=\"openpyxl\", if_sheet_exists = 'replace') as writer: \n", " output.to_excel(writer, sheet_name='data')" ] }, { "cell_type": "markdown", "id": "a9687e92", "metadata": {}, "source": [ "Same code but considering previous season" ] }, { "cell_type": "code", "execution_count": 41, "id": "89e1dc82", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret (5.79, 0.46); (5.22, 0.60)\n", "Provedel (6.40, 0.38); (4.78, 0.71)\n", "Maignan (6.38, 0.38); (5.01, 0.67)\n", "Silvestri (6.40, 0.38); (4.53, 0.74)\n", "Sepe (6.38, 0.37); (4.77, 0.71)\n", "Szczesny (6.29, 0.39); (5.05, 0.66)\n", "Consigli (6.31, 0.37); (4.42, 0.76)\n", "Falcone (6.33, 0.41); (5.23, 0.64)\n", "Musso (6.39, 0.37); (4.71, 0.72)\n", "Vicario (6.40, 0.38); (4.57, 0.74)\n", "Rui Patricio (6.36, 0.38); (4.57, 0.73)\n", "Milinkovic-Savic V. (6.28, 0.36); (4.68, 0.72)\n", "Audero (6.32, 0.36); (4.39, 0.77)\n", "Montipo' (6.37, 0.36); (4.63, 0.73)\n", "Sportiello (6.33, 0.41); (5.58, 0.59)\n", "Skorupski (6.39, 0.39); (4.61, 0.73)\n", "Di Gregorio (6.13, 0.40); (4.30, 0.76)\n", "Perin (6.23, 0.41); (5.53, 0.59)\n", "Handanovic (6.44, 0.39); (4.66, 0.73)\n", "Tatarusanu (6.06, 0.43); (5.47, 0.59)\n", "Gollini (6.03, 0.41); (5.40, 0.60)\n", "Dragowski (5.66, 0.42); (3.79, 0.84)\n", "Terracciano (6.22, 0.34); (4.44, 0.75)\n", "Berisha (6.26, 0.43); (5.58, 0.59)\n", "Radu I. (5.33, 0.40); (3.14, 0.99)\n", "Cragno (6.36, 0.36); (4.65, 0.72)\n", "Luis Maximiano (6.05, 0.46); (5.19, 0.62)\n", "Onana (6.23, 0.37); (5.38, 0.62)\n", "Carnesecchi (6.27, 0.45); (5.50, 0.60)\n", "Mirante (6.38, 0.38); (5.01, 0.67)\n", "Sarr M. (6.27, 0.42); (4.63, 0.72)\n", "Lamanna (6.13, 0.40); (4.30, 0.76)\n", "Ujkani (6.40, 0.38); (4.57, 0.74)\n", "Pegolo (6.28, 0.36); (4.38, 0.76)\n", "Perilli (6.22, 0.33); (4.29, 0.78)\n", "Padelli (6.45, 0.40); (4.62, 0.73)\n", "Perisan (6.45, 0.41); (5.30, 0.63)\n", "Bardi (6.40, 0.38); (4.71, 0.72)\n", "Cordaz (6.44, 0.39); (4.66, 0.73)\n", "Pinsoglio (6.26, 0.40); (5.18, 0.64)\n", "Fiorillo (6.33, 0.36); (4.62, 0.74)\n", "Sirigu (6.36, 0.36); (4.96, 0.68)\n", "Cerofolini (6.09, 0.35); (4.64, 0.72)\n", "Rossi F. (6.38, 0.37); (4.78, 0.70)\n", "Contini (6.18, 0.34); (4.22, 0.80)\n", "Brancolini (6.40, 0.37); (4.83, 0.70)\n", "Bleve (6.40, 0.37); (4.83, 0.70)\n", "Berardi A. (6.33, 0.35); (4.49, 0.75)\n", "Russo A. (6.24, 0.37); (5.24, 0.63)\n", "Gemello (6.26, 0.43); (5.64, 0.59)\n", "Ravaglia (6.37, 0.36); (4.57, 0.74)\n", "Zoet (5.55, 0.33); (2.93, 1.10)\n", "Boer (6.36, 0.38); (4.57, 0.73)\n", "Adamonis (6.16, 0.40); (4.50, 0.73)\n", "Marfella (6.37, 0.37); (5.05, 0.67)\n", "Zovko (6.38, 0.37); (4.50, 0.75)\n", "Piana (6.40, 0.38); (4.53, 0.74)\n", "Bagnolini (6.04, 0.36); (3.94, 0.82)\n", "Svilar (6.24, 0.40); (5.38, 0.61)\n", "Sorrentino A. (6.13, 0.40); (4.30, 0.76)\n", "Ciezkowski (6.27, 0.42); (4.63, 0.72)\n", "Micai (6.41, 0.37); (4.91, 0.69)\n", "Chiesa M. (6.22, 0.33); (4.29, 0.78)\n", "Saro (6.27, 0.42); (4.63, 0.72)\n", "Smalling (6.16, 0.46); (6.51, 0.80)\n", "Hernandez T. (6.24, 0.60); (6.99, 1.34)\n", "Kim (6.28, 0.45); (6.62, 0.73)\n", "Bastoni S. (6.08, 0.49); (6.43, 0.82)\n", "Udogie (6.04, 0.56); (6.54, 1.08)\n", "Dumfries (6.18, 0.51); (6.86, 1.22)\n", "Romagnoli (5.99, 0.48); (6.00, 0.39)\n", "Rodrigo Becao (6.00, 0.52); (6.13, 0.63)\n", "Parisi (5.87, 0.40); (5.88, 0.34)\n", "Mazzocchi (5.81, 0.40); (5.83, 0.36)\n", "Bremer (6.21, 0.47); (6.40, 0.55)\n", "Demiral (6.02, 0.52); (6.06, 0.49)\n", "Valeri (6.08, 0.35); (6.40, 0.67)\n", "Dimarco (6.17, 0.46); (6.58, 0.85)\n", "Di Lorenzo (6.15, 0.41); (6.31, 0.49)\n", "Ibanez (5.81, 0.51); (5.87, 0.58)\n", "Tomori (6.09, 0.39); (6.16, 0.36)\n", "Toloi (6.03, 0.48); (6.15, 0.56)\n", "Gosens (6.07, 0.34); (6.17, 0.40)\n", "Rrahmani (6.23, 0.50); (6.63, 0.85)\n", "Kalulu (6.20, 0.49); (6.56, 0.80)\n", "Bijol (6.07, 0.51); (6.47, 0.91)\n", "Doig (6.16, 0.51); (6.72, 1.05)\n", "Mario Rui (6.03, 0.42); (6.13, 0.44)\n", "Spinazzola (6.02, 0.32); (6.02, 0.34)\n", "Lazzari (6.01, 0.51); (6.38, 0.91)\n", "Mancini (5.76, 0.50); (5.72, 0.40)\n", "Danilo (6.12, 0.42); (6.25, 0.48)\n", "Kyriakopoulos (5.78, 0.52); (5.74, 0.45)\n", "Vojvoda (5.95, 0.37); (6.00, 0.40)\n", "Scalvini (5.98, 0.38); (6.05, 0.41)\n", "Carlos Augusto (5.83, 0.45); (5.95, 0.58)\n", "Skriniar (6.15, 0.46); (6.35, 0.59)\n", "Schuurs (6.03, 0.36); (6.07, 0.34)\n", "Juan Jesus (6.12, 0.44); (6.36, 0.63)\n", "Bonucci (6.21, 0.56); (6.77, 1.10)\n", "Calabria (6.10, 0.35); (6.36, 0.60)\n", "Bastoni (6.16, 0.41); (6.32, 0.50)\n", "Depaoli (5.74, 0.40); (5.78, 0.48)\n", "Darmian (6.06, 0.37); (6.30, 0.64)\n", "Sernicola (5.96, 0.41); (6.27, 0.77)\n", "Mari' (6.02, 0.59); (6.27, 0.86)\n", "Martinez Quarta (5.76, 0.50); (5.73, 0.49)\n", "Maehle (6.03, 0.30); (6.07, 0.36)\n", "Olivera (6.17, 0.38); (6.48, 0.66)\n", "Biraghi (5.87, 0.57); (6.14, 0.87)\n", "Medel (5.75, 0.54); (5.69, 0.42)\n", "Patric (5.77, 0.56); (5.77, 0.56)\n", "Rodriguez R. (5.88, 0.39); (5.89, 0.33)\n", "Aina (5.88, 0.36); (5.89, 0.33)\n", "Cambiaso (5.88, 0.51); (5.94, 0.54)\n", "Perez N. (5.74, 0.41); (5.70, 0.35)\n", "Holm (5.93, 0.41); (6.14, 0.65)\n", "Baschirotto (6.15, 0.47); (6.56, 0.86)\n", "Dodo' (5.72, 0.41); (5.70, 0.39)\n", "Hysaj (5.70, 0.40); (5.70, 0.41)\n", "Faraoni (6.07, 0.44); (6.44, 0.81)\n", "Bianchetti (5.74, 0.41); (5.79, 0.47)\n", "Milenkovic (5.80, 0.51); (5.79, 0.47)\n", "Marusic (5.68, 0.48); (5.65, 0.46)\n", "Colley (5.78, 0.53); (5.73, 0.39)\n", "Toljan (5.81, 0.38); (5.80, 0.33)\n", "Celik (5.90, 0.35); (5.89, 0.32)\n", "Ampadu (5.77, 0.51); (5.71, 0.39)\n", "Singo (6.14, 0.54); (6.63, 1.00)\n", "Casale (5.82, 0.41); (5.79, 0.34)\n", "Daniliuc (5.83, 0.55); (5.78, 0.46)\n", "Pongracic (5.88, 0.42); (5.86, 0.33)\n", "Soppy (5.87, 0.33); (5.84, 0.30)\n", "Kiwior (5.78, 0.39); (5.76, 0.32)\n", "Posch (5.96, 0.59); (6.46, 1.09)\n", "Masina (5.98, 0.42); (6.23, 0.72)\n", "Ghiglione (5.72, 0.37); (5.69, 0.32)\n", "De Vrij (5.81, 0.36); (5.79, 0.31)\n", "Alex Sandro (5.83, 0.34); (5.79, 0.29)\n", "Ceccherini (5.76, 0.48); (5.78, 0.49)\n", "Fazio (5.69, 0.58); (5.64, 0.55)\n", "Rogerio (5.77, 0.40); (5.75, 0.35)\n", "Reca (5.75, 0.38); (5.72, 0.32)\n", "Gunter (5.73, 0.53); (5.67, 0.44)\n", "Djidji (5.82, 0.46); (5.79, 0.36)\n", "Augello (5.77, 0.40); (5.84, 0.46)\n", "Bellanova (5.82, 0.42); (5.85, 0.43)\n", "Erlic (5.84, 0.54); (5.95, 0.67)\n", "Ismajli (5.64, 0.53); (5.58, 0.43)\n", "Ebuehi (5.64, 0.38); (5.57, 0.32)\n", "Kasius (5.96, 0.32); (5.95, 0.31)\n", "Lucumi' (5.77, 0.39); (5.73, 0.32)\n", "Hien (5.67, 0.45); (5.62, 0.37)\n", "Acerbi (6.01, 0.53); (6.29, 0.80)\n", "Zappacosta (6.08, 0.39); (6.28, 0.56)\n", "Chiriches (5.71, 0.53); (5.65, 0.42)\n", "Gyomber (5.68, 0.52); (5.62, 0.42)\n", "Pezzella Giu. (5.95, 0.37); (5.98, 0.36)\n", "Ferrari G. (5.69, 0.55); (5.63, 0.47)\n", "Bereszynski (5.66, 0.42); (5.60, 0.36)\n", "Hateboer (5.78, 0.34); (5.77, 0.31)\n", "Karsdorp (5.96, 0.43); (6.01, 0.39)\n", "Nuytinck (5.98, 0.52); (6.03, 0.50)\n", "Lykogiannis (5.72, 0.35); (5.69, 0.31)\n", "Buongiorno (5.87, 0.40); (5.85, 0.33)\n", "Nikolaou (5.66, 0.44); (5.62, 0.35)\n", "Lazaro (5.83, 0.42); (5.86, 0.41)\n", "Gallo (5.86, 0.41); (5.82, 0.34)\n", "Ayhan (5.71, 0.57); (5.77, 0.67)\n", "Dest (5.84, 0.36); (5.83, 0.32)\n", "Stojanovic (5.75, 0.51); (5.71, 0.47)\n", "Birindelli (5.75, 0.32); (5.72, 0.28)\n", "Gendrey (5.77, 0.35); (5.71, 0.30)\n", "Ebosse (5.86, 0.33); (5.81, 0.29)\n", "Lochoshvili (5.81, 0.37); (5.80, 0.32)\n", "Bronn (5.85, 0.35); (5.81, 0.29)\n", "Thiaw (6.00, 0.40); (6.06, 0.42)\n", "Izzo (5.76, 0.35); (5.68, 0.30)\n", "D'ambrosio (6.13, 0.38); (6.27, 0.46)\n", "Rugani (5.94, 0.34); (5.93, 0.29)\n", "De Sciglio (6.06, 0.50); (6.32, 0.74)\n", "Luperto (5.74, 0.59); (5.66, 0.47)\n", "De Silvestri (5.83, 0.52); (6.09, 0.81)\n", "Djimsiti (5.89, 0.45); (5.93, 0.44)\n", "Palomino (6.07, 0.47); (6.15, 0.43)\n", "Bonifazi (5.64, 0.50); (5.62, 0.38)\n", "Hristov (5.69, 0.47); (5.85, 0.69)\n", "Donati (5.65, 0.42); (5.59, 0.35)\n", "Umtiti (5.82, 0.48); (5.79, 0.39)\n", "Kjaer (6.01, 0.31); (6.00, 0.31)\n", "Igor (5.72, 0.53); (5.67, 0.42)\n", "Okoli (5.65, 0.47); (5.62, 0.38)\n", "Soumaoro (5.74, 0.52); (5.69, 0.40)\n", "Caldirola (5.75, 0.48); (5.69, 0.37)\n", "Ballo-Toure' (5.73, 0.32); (5.69, 0.28)\n", "Bradaric (5.82, 0.40); (5.82, 0.34)\n", "De Winter (5.77, 0.53); (5.70, 0.39)\n", "Quagliata (5.94, 0.32); (5.96, 0.33)\n", "Ferrari A. (5.75, 0.48); (5.82, 0.59)\n", "Florenzi (6.11, 0.39); (6.34, 0.58)\n", "Sala (5.85, 0.39); (5.99, 0.55)\n", "Caldara (5.82, 0.55); (5.78, 0.49)\n", "Murru (5.61, 0.40); (5.65, 0.54)\n", "Marlon (5.62, 0.39); (5.55, 0.32)\n", "Walukiewicz (5.69, 0.44); (5.65, 0.34)\n", "Kumbulla (5.78, 0.34); (5.72, 0.29)\n", "Amian (5.71, 0.52); (5.66, 0.46)\n", "Ostigard (6.00, 0.38); (6.06, 0.36)\n", "Sambia (5.70, 0.39); (5.64, 0.32)\n", "Aiwu (5.93, 0.43); (5.98, 0.44)\n", "Ehizibue (5.87, 0.30); (5.80, 0.27)\n", "Hendry (5.98, 0.44); (6.03, 0.44)\n", "Marrone (5.51, 0.45); (5.45, 0.38)\n", "Radovanovic (5.77, 0.51); (5.84, 0.58)\n", "Murillo (5.63, 0.35); (5.52, 0.29)\n", "Venuti (5.81, 0.33); (5.78, 0.30)\n", "Magnani (5.77, 0.46); (5.73, 0.35)\n", "Terzic (5.94, 0.30); (5.91, 0.29)\n", "Gabbia (5.61, 0.47); (5.56, 0.39)\n", "Zortea (5.80, 0.38); (5.82, 0.42)\n", "Dawidowicz (5.75, 0.39); (5.72, 0.32)\n", "Pirola (5.82, 0.32); (5.73, 0.27)\n", "Carboni (5.62, 0.45); (5.57, 0.36)\n", "Lovato (5.82, 0.50); (5.78, 0.38)\n", "Tuia (5.76, 0.45); (5.80, 0.48)\n", "Amione (5.63, 0.35); (5.56, 0.30)\n", "Vasquez (5.89, 0.43); (5.93, 0.40)\n", "Zima (5.87, 0.35); (5.86, 0.31)\n", "Coppola D. (5.99, 0.36); (6.00, 0.34)\n", "Gatti (5.95, 0.45); (5.99, 0.38)\n", "Gila (5.81, 0.49); (5.78, 0.40)\n", "Cabal (5.82, 0.43); (5.83, 0.39)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Sosa (5.64, 0.48); (5.57, 0.42)\n", "Conti (6.10, 0.55); (6.68, 1.13)\n", "Dermaku (5.90, 0.43); (5.93, 0.39)\n", "Tonelli (5.61, 0.47); (5.58, 0.38)\n", "Radu (5.65, 0.49); (5.59, 0.43)\n", "Paletta (5.82, 0.42); (5.83, 0.39)\n", "Fares (5.76, 0.36); (5.71, 0.32)\n", "Marchizza (5.64, 0.38); (5.57, 0.32)\n", "Romagna (5.85, 0.44); (5.87, 0.41)\n", "Ranieri L. (5.71, 0.37); (5.70, 0.38)\n", "Cetin (5.88, 0.52); (5.83, 0.40)\n", "Muldur (5.65, 0.42); (5.60, 0.36)\n", "Adopo (5.82, 0.44); (5.81, 0.38)\n", "Ferrer (5.86, 0.44); (5.86, 0.36)\n", "Ruggeri (5.85, 0.34); (5.84, 0.31)\n", "Antov (5.61, 0.51); (5.54, 0.43)\n", "Amey (5.95, 0.42); (6.01, 0.41)\n", "Ferrarini (5.82, 0.42); (5.83, 0.39)\n", "Kamenovic (6.19, 0.44); (6.40, 0.54)\n", "Vina (5.73, 0.48); (5.68, 0.39)\n", "Zanoli (5.93, 0.32); (5.91, 0.29)\n", "Zanotti (5.89, 0.39); (5.93, 0.41)\n", "Ruan (5.63, 0.56); (5.64, 0.39)\n", "Motoc (5.88, 0.41); (5.91, 0.38)\n", "Cacace (5.84, 0.35); (5.79, 0.29)\n", "Bayeye (5.92, 0.41); (5.97, 0.42)\n", "Ebosele (5.96, 0.44); (6.03, 0.42)\n", "Buta (5.92, 0.40); (5.97, 0.39)\n", "Ndiaye (5.93, 0.43); (5.98, 0.44)\n", "Abankwah (5.92, 0.40); (5.97, 0.39)\n", "Guessand A. (5.92, 0.40); (5.97, 0.39)\n", "Guarino (5.90, 0.43); (5.93, 0.40)\n", "Milinkovic-Savic (6.44, 0.62); (7.60, 1.86)\n", "Barella (6.33, 0.53); (6.93, 1.12)\n", "Kvaratskhelia (6.59, 0.70); (8.44, 2.82)\n", "Zaccagni (6.31, 0.59); (7.24, 1.55)\n", "Zielinski (6.23, 0.54); (6.91, 1.21)\n", "Luis Alberto (6.25, 0.62); (7.24, 1.62)\n", "Frattesi (6.03, 0.52); (6.46, 0.97)\n", "Politano (6.13, 0.41); (6.47, 0.72)\n", "Koopmeiners (6.24, 0.54); (6.86, 1.15)\n", "Vlasic (6.28, 0.56); (7.41, 1.76)\n", "Pereyra (6.12, 0.56); (6.67, 1.09)\n", "Felipe Anderson (6.23, 0.62); (7.34, 1.76)\n", "Calhanoglu (6.30, 0.64); (7.42, 1.80)\n", "Strefezza (6.34, 0.51); (7.12, 1.38)\n", "Diaz B. (6.12, 0.55); (6.74, 1.15)\n", "Pellegrini Lo. (6.25, 0.66); (7.62, 2.06)\n", "Zambo Anguissa (6.10, 0.37); (6.15, 0.36)\n", "Lobotka (6.23, 0.43); (6.55, 0.68)\n", "Malinovskyi (6.27, 0.59); (7.30, 1.67)\n", "Candreva (6.16, 0.67); (7.20, 1.71)\n", "Pasalic (6.24, 0.68); (7.77, 2.24)\n", "Bennacer (6.21, 0.44); (6.50, 0.69)\n", "Kostic (6.20, 0.49); (6.79, 1.07)\n", "Radonjic (6.27, 0.48); (7.03, 1.30)\n", "Samardzic (6.15, 0.47); (6.63, 0.95)\n", "Chiesa (6.25, 0.52); (7.04, 1.35)\n", "Lovric (6.19, 0.38); (6.53, 0.70)\n", "De Ketelaere (5.90, 0.34); (5.91, 0.36)\n", "Brozovic (6.17, 0.38); (6.38, 0.51)\n", "Pogba (5.93, 0.41); (5.99, 0.39)\n", "Bonaventura (6.10, 0.61); (6.68, 1.20)\n", "Sensi (5.84, 0.36); (5.93, 0.50)\n", "Bandinelli (5.84, 0.43); (5.94, 0.57)\n", "Ikone' (5.88, 0.40); (6.08, 0.65)\n", "Barak (6.20, 0.69); (7.64, 2.13)\n", "Mkhitaryan (6.21, 0.58); (6.99, 1.34)\n", "Pessina (5.85, 0.36); (5.86, 0.39)\n", "Tonali (6.28, 0.54); (6.88, 1.12)\n", "Arslan (5.93, 0.40); (5.99, 0.46)\n", "Lazovic (6.13, 0.39); (6.47, 0.73)\n", "Cristante (5.95, 0.48); (6.05, 0.53)\n", "Elmas (6.11, 0.39); (6.37, 0.63)\n", "Bajrami (6.24, 0.55); (7.04, 1.40)\n", "Vecino (6.06, 0.40); (6.33, 0.67)\n", "Paredes (5.72, 0.35); (5.66, 0.30)\n", "Mandragora (5.97, 0.41); (6.04, 0.47)\n", "Djuricic (5.78, 0.48); (6.05, 0.79)\n", "Lukic (6.07, 0.51); (6.47, 0.90)\n", "Soriano (5.86, 0.41); (5.85, 0.37)\n", "Zaniolo (5.91, 0.53); (6.20, 0.83)\n", "Sottil (6.01, 0.53); (6.53, 1.03)\n", "Traore' Hj. (6.18, 0.57); (7.13, 1.57)\n", "Messias (6.13, 0.60); (7.05, 1.52)\n", "Thorstvedt (5.95, 0.45); (6.28, 0.84)\n", "Cuadrado (6.25, 0.48); (6.63, 0.81)\n", "Locatelli (6.20, 0.48); (6.57, 0.81)\n", "Rabiot (5.77, 0.36); (5.74, 0.32)\n", "Dominguez (5.96, 0.41); (6.00, 0.39)\n", "Tameze (6.16, 0.44); (6.59, 0.87)\n", "Miranchuk (6.06, 0.56); (6.79, 1.28)\n", "Vilhena (5.73, 0.36); (5.76, 0.43)\n", "De Roon (6.00, 0.46); (6.24, 0.70)\n", "Verdi (6.25, 0.62); (7.47, 1.88)\n", "Walace (5.86, 0.41); (5.87, 0.36)\n", "Wijnaldum (5.89, 0.41); (5.91, 0.39)\n", "Mckennie (6.18, 0.51); (6.77, 1.08)\n", "Makengo (5.91, 0.48); (5.97, 0.49)\n", "Ricci S. (5.88, 0.39); (5.92, 0.36)\n", "Coulibaly L. (5.84, 0.45); (6.09, 0.75)\n", "Sabiri (6.04, 0.61); (6.92, 1.49)\n", "Miretti (6.06, 0.42); (6.14, 0.38)\n", "Colpani (6.10, 0.40); (6.54, 0.90)\n", "Haas (5.86, 0.37); (5.88, 0.36)\n", "Orsolini (6.14, 0.57); (7.08, 1.50)\n", "Matic (5.99, 0.32); (5.99, 0.32)\n", "Ascacibar (6.00, 0.37); (6.04, 0.38)\n", "Ederson D.s. (6.15, 0.54); (6.78, 1.19)\n", "Ciurria (5.89, 0.41); (6.01, 0.56)\n", "Gonzalez J. (6.05, 0.47); (6.48, 0.90)\n", "El Shaarawy (6.02, 0.46); (6.38, 0.84)\n", "Meite' (5.87, 0.36); (5.88, 0.34)\n", "Bourabia (6.17, 0.52); (6.95, 1.34)\n", "Ndombele' (5.92, 0.32); (5.91, 0.30)\n", "Henderson L. (5.96, 0.43); (6.18, 0.69)\n", "Maggiore (5.98, 0.45); (6.16, 0.63)\n", "Ilic (5.99, 0.41); (6.13, 0.52)\n", "Kovalenko (5.92, 0.44); (6.19, 0.72)\n", "Zalewski (5.83, 0.34); (5.80, 0.31)\n", "Pickel (5.88, 0.35); (5.97, 0.51)\n", "Ferguson (6.07, 0.51); (6.59, 1.02)\n", "Camara Ma. (6.10, 0.30); (6.18, 0.34)\n", "Saponara (6.21, 0.48); (6.77, 1.05)\n", "Rincon (5.77, 0.34); (5.76, 0.31)\n", "Cataldi (6.09, 0.44); (6.23, 0.51)\n", "Zurkowski (6.11, 0.52); (6.70, 1.11)\n", "Rovella (5.96, 0.38); (6.03, 0.46)\n", "Agudelo (5.93, 0.50); (6.31, 0.90)\n", "Amrabat (6.00, 0.38); (6.17, 0.56)\n", "Lopez M. (6.03, 0.46); (6.21, 0.60)\n", "Gyasi (5.88, 0.56); (6.36, 1.05)\n", "Pobega (6.15, 0.45); (6.50, 0.79)\n", "Harroui (5.84, 0.32); (5.82, 0.29)\n", "Ceide (5.96, 0.35); (5.97, 0.38)\n", "Baldanzi (6.25, 0.47); (7.03, 1.36)\n", "Blin (6.00, 0.30); (5.98, 0.30)\n", "Hjulmand (5.93, 0.53); (5.88, 0.42)\n", "D'alessandro (5.98, 0.30); (5.99, 0.36)\n", "Grassi (5.89, 0.44); (5.86, 0.34)\n", "Krunic (6.00, 0.32); (6.02, 0.35)\n", "Linetty (5.77, 0.32); (5.75, 0.30)\n", "Miguel Veloso (5.93, 0.48); (6.00, 0.51)\n", "Ekdal (5.74, 0.48); (5.73, 0.47)\n", "Schouten (6.01, 0.48); (6.24, 0.70)\n", "Villar (5.78, 0.32); (5.72, 0.28)\n", "Saelemaekers (6.00, 0.40); (6.15, 0.54)\n", "Vranckx (5.95, 0.39); (6.01, 0.39)\n", "Basic (5.83, 0.35); (5.84, 0.36)\n", "Aebischer (5.85, 0.30); (5.84, 0.29)\n", "Marcos Antonio (5.82, 0.32); (5.77, 0.28)\n", "Ranocchia F. (5.96, 0.41); (6.20, 0.68)\n", "Bistrovic (5.84, 0.31); (5.85, 0.32)\n", "Verre (5.67, 0.37); (5.62, 0.32)\n", "Gagliardini (6.10, 0.39); (6.38, 0.71)\n", "Barberis (5.72, 0.38); (5.71, 0.33)\n", "Leris (5.69, 0.35); (5.70, 0.41)\n", "Vieira (5.70, 0.34); (5.69, 0.34)\n", "Winks (5.85, 0.41); (5.90, 0.43)\n", "Castrovilli (5.97, 0.42); (6.14, 0.61)\n", "Maldini (6.11, 0.40); (6.71, 1.15)\n", "Marin (5.87, 0.51); (5.89, 0.48)\n", "Maleh (5.97, 0.37); (6.19, 0.65)\n", "Matheus Henrique (5.88, 0.39); (5.90, 0.34)\n", "Asllani (6.00, 0.39); (6.11, 0.49)\n", "Moro N. (5.84, 0.34); (5.83, 0.31)\n", "Oudin (6.01, 0.35); (6.09, 0.41)\n", "Duncan (5.92, 0.43); (6.10, 0.62)\n", "Molina S. (5.78, 0.38); (5.79, 0.37)\n", "Kastanos (5.83, 0.45); (5.83, 0.40)\n", "Valoti (5.78, 0.33); (5.72, 0.28)\n", "Gaetano (6.03, 0.36); (6.09, 0.39)\n", "Escalante (5.77, 0.42); (5.73, 0.35)\n", "Bohinen (5.82, 0.38); (5.84, 0.38)\n", "Terracciano F. (6.01, 0.30); (6.02, 0.34)\n", "Milanese (5.88, 0.44); (5.93, 0.44)\n", "Castagnetti (5.97, 0.33); (5.99, 0.34)\n", "Listkowski (5.93, 0.32); (5.91, 0.30)\n", "Adli (5.73, 0.33); (5.73, 0.32)\n", "Hrustic (5.66, 0.42); (5.61, 0.36)\n", "D'andrea (5.95, 0.34); (6.00, 0.43)\n", "Benassi (5.77, 0.32); (5.77, 0.33)\n", "Baez (5.92, 0.46); (5.97, 0.44)\n", "Vignato (5.87, 0.33); (5.87, 0.32)\n", "Obiang (5.86, 0.39); (5.84, 0.32)\n", "Askildsen (5.84, 0.33); (5.78, 0.29)\n", "Hongla (5.78, 0.37); (5.83, 0.45)\n", "Yepes (6.04, 0.33); (6.10, 0.35)\n", "Helgason (5.82, 0.33); (5.80, 0.29)\n", "Bondo (5.91, 0.42); (5.94, 0.37)\n", "Ellertsson (5.88, 0.38); (5.90, 0.34)\n", "Capezzi (5.93, 0.33); (5.92, 0.30)\n", "Jajalo (5.87, 0.33); (5.85, 0.30)\n", "Machin (5.84, 0.41); (5.86, 0.39)\n", "Bakayoko (5.80, 0.37); (5.74, 0.32)\n", "Scozzarella (5.84, 0.41); (5.86, 0.39)\n", "Fagioli (6.12, 0.46); (6.60, 0.94)\n", "Demme (6.00, 0.37); (6.19, 0.57)\n", "Akpa Akpro (5.90, 0.44); (5.95, 0.42)\n", "Darboe (5.90, 0.43); (6.01, 0.43)\n", "Bove (6.20, 0.36); (6.67, 0.90)\n", "Urbanski (5.92, 0.41); (5.96, 0.41)\n", "Bertini (5.94, 0.41); (5.99, 0.39)\n", "Cortinovis (5.85, 0.39); (5.89, 0.42)\n", "Romero L. (5.81, 0.31); (5.80, 0.31)\n", "Bianco (5.92, 0.40); (5.98, 0.46)\n", "Sher (5.96, 0.31); (5.94, 0.29)\n", "Nguiamba (6.04, 0.37); (6.08, 0.34)\n", "Volpato (6.23, 0.40); (7.16, 1.52)\n", "Praszelik (6.00, 0.30); (5.98, 0.30)\n", "Trimboli (5.85, 0.41); (5.90, 0.43)\n", "Pafundi (5.93, 0.40); (5.98, 0.40)\n", "Bjorkengren (5.94, 0.42); (6.00, 0.43)\n", "Vignato S. (5.88, 0.43); (5.91, 0.41)\n", "Samek (5.94, 0.42); (6.00, 0.43)\n", "Zerbin (5.95, 0.35); (5.99, 0.38)\n", "Ilkhan (5.75, 0.35); (5.71, 0.30)\n", "Degli Innocenti (5.94, 0.46); (5.99, 0.44)\n", "Fazzini (5.63, 0.48); (5.58, 0.38)\n", "Acella (5.95, 0.43); (6.03, 0.48)\n", "Tripi (5.92, 0.41); (5.95, 0.40)\n", "Garbett (5.92, 0.41); (5.97, 0.43)\n", "Iling-Junior (5.99, 0.50); (6.03, 0.45)\n", "Immobile (6.49, 0.72); (8.44, 2.88)\n", "Vlahovic (6.35, 0.70); (8.01, 2.47)\n", "Rafael Leao (6.46, 0.68); (8.11, 2.48)\n", "Martinez L. (6.32, 0.73); (8.24, 2.70)\n", "Dybala (6.33, 0.61); (7.56, 1.93)\n", "Arnautovic (6.23, 0.67); (7.74, 2.21)\n", "Beto (6.20, 0.69); (7.68, 2.18)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Giroud (6.25, 0.68); (7.80, 2.27)\n", "Osimhen (6.39, 0.71); (8.15, 2.58)\n", "Deulofeu (6.42, 0.64); (7.86, 2.22)\n", "Lukaku (6.47, 0.71); (8.41, 2.84)\n", "Milik (6.18, 0.56); (7.02, 1.39)\n", "Pedro (6.26, 0.61); (7.42, 1.81)\n", "Abraham (6.23, 0.71); (7.87, 2.37)\n", "Berardi (6.46, 0.68); (8.20, 2.60)\n", "Dia (6.25, 0.69); (7.86, 2.33)\n", "Lookman (6.44, 0.65); (8.01, 2.39)\n", "Simeone (6.18, 0.73); (7.79, 2.32)\n", "Correa (6.13, 0.59); (7.15, 1.63)\n", "Zapata D. (6.39, 0.69); (8.22, 2.64)\n", "Dzeko (6.30, 0.68); (7.94, 2.38)\n", "Nzola (5.88, 0.43); (6.24, 0.84)\n", "Sanabria (6.12, 0.58); (7.16, 1.62)\n", "Muriel (6.36, 0.68); (7.99, 2.41)\n", "Rebic (6.06, 0.49); (6.59, 1.03)\n", "Bonazzoli (6.16, 0.60); (7.25, 1.71)\n", "Caprari (6.36, 0.64); (7.86, 2.24)\n", "Di Maria (6.08, 0.65); (6.81, 1.40)\n", "Lozano (6.19, 0.58); (7.16, 1.57)\n", "Ceesay (6.07, 0.55); (6.97, 1.44)\n", "Pinamonti (6.11, 0.65); (7.38, 1.91)\n", "Kouame' (6.19, 0.61); (7.36, 1.79)\n", "Lauriente' (6.28, 0.69); (7.47, 1.95)\n", "Jovic (6.02, 0.61); (6.88, 1.46)\n", "Barrow (6.11, 0.61); (7.09, 1.58)\n", "Henry (6.07, 0.63); (7.08, 1.64)\n", "Piatek (6.03, 0.52); (6.87, 1.36)\n", "Gonzalez N. (6.24, 0.64); (7.47, 1.89)\n", "Dessers (6.09, 0.49); (6.91, 1.34)\n", "Caputo (6.02, 0.64); (6.99, 1.58)\n", "Raspadori (6.11, 0.67); (7.15, 1.70)\n", "Lammers (5.92, 0.39); (6.09, 0.62)\n", "Okereke (6.00, 0.55); (6.62, 1.19)\n", "Cabral (6.08, 0.48); (6.86, 1.29)\n", "Gabbiadini (6.10, 0.65); (7.24, 1.78)\n", "Belotti (6.21, 0.66); (7.62, 2.11)\n", "Origi (6.03, 0.56); (6.70, 1.22)\n", "Botheim (5.97, 0.42); (6.39, 0.88)\n", "Alvarez A. (6.13, 0.60); (7.13, 1.62)\n", "Verde (6.25, 0.52); (7.14, 1.47)\n", "Destro (6.06, 0.65); (7.23, 1.80)\n", "Kean (6.02, 0.56); (6.70, 1.26)\n", "Pellegri (5.84, 0.33); (5.91, 0.54)\n", "Satriano (5.89, 0.45); (6.28, 0.89)\n", "Success (6.24, 0.59); (7.14, 1.49)\n", "Mota (5.84, 0.41); (6.25, 0.86)\n", "Banda (5.98, 0.36); (6.06, 0.45)\n", "Hojlund (6.01, 0.43); (6.54, 1.01)\n", "Lasagna (5.89, 0.40); (6.19, 0.78)\n", "Pjaca (5.99, 0.47); (6.45, 0.97)\n", "Gytkjaer (5.85, 0.37); (6.14, 0.74)\n", "Petagna (5.99, 0.54); (6.66, 1.23)\n", "Nestorovski (6.07, 0.46); (6.53, 0.95)\n", "Zanimacchia (5.97, 0.34); (6.06, 0.45)\n", "Piccoli (5.70, 0.39); (5.67, 0.34)\n", "Kallon (5.80, 0.36); (5.82, 0.40)\n", "Ciofani D. (6.13, 0.41); (6.85, 1.25)\n", "Di Francesco F. (6.13, 0.47); (6.73, 1.09)\n", "Boga (5.98, 0.38); (6.02, 0.39)\n", "Zirkzee (6.04, 0.53); (6.82, 1.31)\n", "Quagliarella (5.88, 0.47); (6.24, 0.85)\n", "Ibrahimovic (6.36, 0.65); (7.89, 2.28)\n", "Shomurodov (6.04, 0.51); (6.80, 1.30)\n", "Djuric (5.89, 0.30); (5.86, 0.30)\n", "Strelec (5.77, 0.38); (5.95, 0.66)\n", "Antiste (5.75, 0.37); (5.80, 0.49)\n", "Seck (5.94, 0.33); (6.04, 0.51)\n", "Buonaiuto (6.05, 0.36); (6.19, 0.46)\n", "Sansone (6.00, 0.46); (6.40, 0.86)\n", "Pussetto (5.99, 0.55); (6.67, 1.24)\n", "Cambiaghi (5.91, 0.30); (5.89, 0.31)\n", "Colombo (6.01, 0.49); (6.74, 1.24)\n", "Afena-Gyan (5.87, 0.54); (6.22, 0.91)\n", "Defrel (5.84, 0.42); (6.00, 0.63)\n", "Karamoh (6.03, 0.33); (6.11, 0.39)\n", "Cancellieri (6.19, 0.49); (6.76, 1.09)\n", "Tsadjout (6.03, 0.42); (6.20, 0.57)\n", "Rodriguez P. (5.92, 0.34); (5.94, 0.34)\n", "Valencia D. (5.68, 0.32); (5.70, 0.29)\n", "Edera (5.92, 0.43); (5.98, 0.47)\n", "Oddei (6.12, 0.31); (6.11, 0.31)\n", "Raimondo (5.95, 0.43); (6.02, 0.45)\n", "Kristoffersen (5.89, 0.43); (5.94, 0.41)\n", "Kaio Jorge (5.98, 0.36); (6.03, 0.39)\n", "De Luca (5.86, 0.44); (5.92, 0.46)\n", "Soule' (6.01, 0.45); (6.08, 0.39)\n", "Lazetic (5.97, 0.41); (6.05, 0.46)\n", "Voelkerling Persson (5.94, 0.44); (6.01, 0.45)\n", "Sanca (5.91, 0.37); (5.94, 0.36)\n" ] } ], "source": [ "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "tot_matches = 2 # home and not home\n", "\n", "current_season_games = max(players_old['games'])\n", "\n", "for i in range(players.shape[0]):\n", " home = 0\n", " \n", " for k in range(tot_matches):\n", " #matchday_out = k + 1\n", " #[player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", " \n", " player = players.index[i]\n", " team = players['team'][i]\n", " oppteam = 'Avg'\n", " home = not home\n", " \n", " oldseason_ok = True\n", " \n", " try:\n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home, oldseason = True)\n", " games = max( players_old['games'][i], players_old['gk_games'][i] )\n", " mins = max( players_old['minutes'][i], players_old['gk_minutes'][i] )\n", " except:\n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home)\n", " oldseason_ok = False\n", " games = 0\n", " mins = 0\n", " \n", "\n", " role = players['r'][player] \n", "\n", " starter = 0\n", " voteperc = 0\n", " \n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", " \n", " starter = int( player in gk_starters )\n", " if(starter):\n", " voteperc = 100\n", " else:\n", " voteperc = 0\n", " else:\n", " starter = int ( 1 * (games >= current_season_games * 2/3 and mins / games >= 45 ) )\n", " voteperc = int( min( 1, games / current_season_games ) * 100) \n", " \n", " if (not oldseason_ok):\n", " starter = -1\n", " voteperc = -100\n", "\n", " if(k == 0):\n", " row = [player, role, team, 'Avg', 1, starter, voteperc]\n", " \n", " numrow_ = [mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs] \n", "\n", " if(k == 0):\n", " numrow = numrow_\n", " else:\n", " for j in range(len(numrow)):\n", " numrow[j] += numrow_[j]\n", "\n", " for j in range(len(numrow)):\n", " numrow[j] /= tot_matches\n", " \n", " print(players.index[i] + ' (' + \"{:.2f}\".format(numrow[0]) + ', ' + \"{:.2f}\".format(numrow[1]) + \n", " '); (' + \"{:.2f}\".format(numrow[2]) + ', ' + \"{:.2f}\".format(numrow[3]) + ')' )\n", " \n", " row += numrow # list concat\n", " \n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", "\n", " output = pd.concat([output, row_df])\n", " \n", " \n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['role', 'FV'], ascending = [False, False])\n", "\n", "template_file = 'outputs/pred_matchday_base.xlsx'\n", "dest_file = 'outputs/pred_avg_seriea_season2122.xlsx'\n", "\n", "shutil.copyfile(template_file, dest_file)\n", "\n", "with pd.ExcelWriter(dest_file, mode = 'a', engine=\"openpyxl\", if_sheet_exists = 'replace') as writer: \n", " output.to_excel(writer, sheet_name='data')" ] }, { "cell_type": "markdown", "id": "cf9df3bb", "metadata": {}, "source": [ "Various predictions." ] }, { "cell_type": "code", "execution_count": 28, "id": "7300f3c2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Terracciano: MV 6.30 ± 0.71; FV 4.72 + 1.43 (5.7% cs)\n", "Maignan: MV 6.27 ± 0.84; FV 5.66 + 1.16 (56.8% cs)\n", "Tatarusanu: MV 6.22 ± 0.78; FV 5.53 + 1.19 (45.2% cs)\n", "Handanovic: MV 5.89 ± 0.66; FV 3.40 + 1.88 (1.4% cs)\n", "Onana: MV 6.32 ± 0.73; FV 5.05 + 1.33 (11.7% cs)\n", "Sepe: MV 6.39 ± 0.74; FV 4.76 + 1.42 (6.4% cs)\n", "Di Gregorio: MV 5.83 ± 0.80; FV 3.91 + 1.59 (4.5% cs)\n", "Szczesny: MV 6.15 ± 0.77; FV 5.54 + 1.19 (47.8% cs)\n", "Audero: MV 6.34 ± 0.77; FV 5.27 + 1.28 (17.9% cs)\n", "Silvestri: MV 6.34 ± 0.71; FV 4.18 + 1.60 (2.7% cs)\n", "Carnesecchi: MV 6.17 ± 0.82; FV 5.58 + 1.17 (56.1% cs)\n", "Dragowski: MV 6.52 ± 0.82; FV 5.18 + 1.30 (13.1% cs)\n", "Milinkovic-Savic V.: MV 6.27 ± 0.77; FV 4.90 + 1.38 (12.4% cs)\n", "Sportiello: MV 6.32 ± 0.86; FV 5.06 + 1.31 (18.5% cs)\n", "Falcone: MV 6.34 ± 0.79; FV 5.47 + 1.21 (34.2% cs)\n", "Consigli: MV 6.12 ± 0.70; FV 4.86 + 1.35 (12.9% cs)\n", "Vicario: MV 6.32 ± 0.85; FV 5.64 + 1.17 (51.2% cs)\n" ] }, { "data": { "text/plain": [ "[array([6.31691631, 5.6403682 ]),\n", " array([0.42497158, 0.58689165], dtype=float32),\n", " [,\n", " ,\n", " ]]" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Terracciano', log = 1, plot = 0)\n", "predict_player('Maignan', log = 1, plot = 0)\n", "predict_player('Tatarusanu', log = 1, plot = 0)\n", "predict_player('Handanovic', log = 1, plot = 0)\n", "predict_player('Onana', log = 1, plot = 0)\n", "predict_player('Sepe', log = 1, plot = 0)\n", "predict_player('Di Gregorio', log = 1, plot = 0)\n", "predict_player('Szczesny', log = 1, plot = 0)\n", "predict_player('Audero', log = 1, plot = 0)\n", "predict_player('Silvestri', log = 1, plot = 0)\n", "predict_player('Carnesecchi', log = 1, plot = 0)\n", "predict_player('Dragowski', log = 1, plot = 0)\n", "predict_player('Milinkovic-Savic V.', log = 1, plot = 0)\n", "predict_player('Sportiello', log = 1, plot = 0)\n", "predict_player('Falcone', log = 1, plot = 0)\n", "predict_player('Consigli', log = 1, plot = 0)\n", "predict_player('Vicario', log = 1, plot = 0)" ] }, { "cell_type": "code", "execution_count": 36, "id": "bd126870", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Muriel: MV 6.20 ± 1.32; FV 7.29 + 3.53\n", "Tonali: MV 6.23 ± 0.95; FV 6.69 + 1.86\n", "Lobotka: MV 6.17 ± 0.72; FV 6.42 + 1.16\n", "Politano: MV 6.19 ± 0.77; FV 6.62 + 1.48\n", "Zapata D.: MV 6.09 ± 1.19; FV 7.18 + 3.36\n", "Frattesi: MV 6.23 ± 1.19; FV 7.37 + 3.58\n", "Gonzalez N.: MV 6.05 ± 1.07; FV 6.65 + 2.25\n", "Abraham: MV 6.20 ± 1.30; FV 7.66 + 4.26\n", "Pobega: MV 6.02 ± 0.68; FV 6.13 + 0.92\n", "Mario Rui: MV 6.10 ± 0.77; FV 6.25 + 0.98\n", "Cuadrado: MV 5.82 ± 0.95; FV 5.80 + 0.92\n", "Skriniar: MV 5.75 ± 0.68; FV 5.70 + 0.58\n", "Lukaku: MV 6.41 ± 1.42; FV 8.29 + 5.46\n" ] }, { "data": { "text/plain": [ "[array([6.41176047, 8.29456946]),\n", " array([0.70926785, 2.7289915 ], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Muriel', plot = 0, log = 1)\n", "predict_player('Tonali', plot = 0, log = 1)\n", "predict_player('Lobotka', plot = 0, log = 1)\n", "predict_player('Politano', plot = 0, log = 1)\n", "predict_player('Zapata D.', plot = 0, log = 1)\n", "predict_player('Frattesi', plot = 0, log = 1)\n", "predict_player('Gonzalez N.', plot = 0, log = 1)\n", "predict_player('Abraham', plot = 0, log = 1)\n", "predict_player('Pobega', plot = 0, log = 1)\n", "predict_player('Mario Rui', plot = 0, log = 1)\n", "predict_player('Cuadrado', plot = 0, log = 1)\n", "predict_player('Skriniar', plot = 0, log = 1)\n", "predict_player('Lukaku', plot = 0, log = 1)" ] }, { "cell_type": "code", "execution_count": 35, "id": "4b9f5a7d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Skriniar: MV 6.06 ± 0.88; FV 6.21 + 1.04\n", "Cuadrado: MV 6.11 ± 0.82; FV 6.33 + 1.20\n", "Bastoni: MV 6.10 ± 0.80; FV 6.23 + 0.95\n", "Barak: MV 6.08 ± 1.33; FV 7.10 + 3.33\n", "Politano: MV 6.08 ± 0.74; FV 6.35 + 1.22\n", "Smalling: MV 6.18 ± 0.92; FV 6.51 + 1.54\n", "Gosens: MV 6.02 ± 0.66; FV 6.08 + 0.75\n", "Skriniar: MV 5.75 ± 0.68; FV 5.70 + 0.58\n", "Cuadrado: MV 5.82 ± 0.95; FV 5.80 + 0.92\n", "Bastoni: MV 5.84 ± 0.91; FV 5.86 + 0.82\n", "Barak: MV 5.76 ± 0.70; FV 5.75 + 0.72\n", "Politano: MV 6.19 ± 0.77; FV 6.62 + 1.48\n", "Smalling: MV 6.17 ± 1.06; FV 6.60 + 1.91\n", "Gosens: MV 5.75 ± 0.65; FV 5.80 + 0.85\n" ] }, { "data": { "text/plain": [ "[array([5.75403311, 5.80380687]),\n", " array([0.3249786 , 0.42722106], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Skriniar', log = 1, oldseason= True)\n", "predict_player('Cuadrado', log = 1, oldseason= True)\n", "predict_player('Bastoni', log = 1, oldseason= True)\n", "predict_player('Barak', log = 1, oldseason= True)\n", "predict_player('Politano', log = 1, oldseason= True)\n", "predict_player('Smalling', log = 1, oldseason= True)\n", "predict_player('Gosens', log = 1, oldseason= True)\n", "\n", "predict_player('Skriniar', log = 1, oldseason= False)\n", "predict_player('Cuadrado', log = 1, oldseason= False)\n", "predict_player('Bastoni', log = 1, oldseason= False)\n", "predict_player('Barak', log = 1, oldseason= False)\n", "predict_player('Politano', log = 1, oldseason= False)\n", "predict_player('Smalling', log = 1, oldseason= False)\n", "predict_player('Gosens', log = 1, oldseason= False)" ] }, { "cell_type": "code", "execution_count": 34, "id": "10c7ad3e", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Rafael Leao: MV 6.34 ± 1.43; FV 7.95 + 4.79\n" ] }, { "data": { "text/plain": [ "[array([6.3442238 , 7.94607029]),\n", " array([0.71331024, 2.395806 ], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Rafael Leao', plot = 1, log = 1)" ] }, { "cell_type": "markdown", "id": "0a5de8a1", "metadata": {}, "source": [ "Code for predicting the probability distribution of total team points" ] }, { "cell_type": "code", "execution_count": 30, "id": "65f9a572", "metadata": {}, "outputs": [], "source": [ "squad = ['Falcone',\n", " 'Valeri',\n", " 'Di Lorenzo',\n", " 'Parisi',\n", " 'Mario Rui',\n", " 'Strefezza',\n", " 'Frattesi',\n", " 'Felipe Anderson',\n", " 'Beto',\n", " 'Abraham',\n", " 'Nzola']\n", "\n", "\n", "dist = [None] * len(squad)\n", "\n", "defenders = list([0]) * len(squad)\n", "\n", "\n", "for i in range(len(squad)):\n", " [X, y, dist[i]] = predict_player(squad[i], plot = 0, log = 0) \n", " \n", " if(players['r'][squad[i]] == 'D'):\n", " defenders[i] = 1" ] }, { "cell_type": "code", "execution_count": 31, "id": "2e78f674", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Avg Total Points = 75.96627577018738\n", "Avg Mod Points = 1.478\n", "Avg Clean Sheets = 0.364\n" ] } ], "source": [ "ITERS = 500\n", "\n", "MOD = True\n", "\n", "total_points = np.zeros(ITERS)\n", "clean_sheets = np.zeros(ITERS)\n", "mod_points = np.zeros(ITERS)\n", "\n", "mv_samples = [None] * len(squad)\n", "fv_samples = [None] * len(squad)\n", "\n", "for i in range(len(squad)):\n", " mv_samples[i] = dist[i][0].sample(ITERS)\n", " fv_samples[i] = dist[i][1].sample(ITERS)\n", " \n", "cs_samples = dist[0][2].sample(ITERS)\n", "\n", "for k in range(ITERS):\n", " d_points = list([0]) * len(squad)\n", " \n", " cleansheet = float(cs_samples[k])\n", " total_points[k] += cleansheet\n", " clean_sheets[k] += cleansheet\n", " \n", " for i in range(len(squad)): \n", " if(defenders[i] == 1):\n", " d_points[i] = float(mv_samples[i][k])\n", "\n", " total_points[k] += float(fv_samples[i][k])\n", " \n", " d_points.sort(reverse = True)\n", "\n", " if(MOD and d_points[3] > 0): # minimum 3 defenders to get MOD\n", " mod_avg = 0\n", " for j in range(3):\n", " mod_avg += round(d_points[j] * 2) / 2\n", " mod_avg /= 3\n", "\n", " if(mod_avg >= 7):\n", " mod_points[k] = 6\n", " elif(mod_avg >= 6.5):\n", " mod_points[k] = 3\n", " elif(mod_avg >= 6):\n", " mod_points[k] = 1\n", "\n", " total_points[k] += mod_points[k]\n", " \n", " \n", "print('Avg Total Points = ' + str(total_points.mean()))\n", "print('Avg Mod Points = ' + str(mod_points.mean()))\n", "print('Avg Clean Sheets = ' + str(clean_sheets.mean()))\n" ] }, { "cell_type": "code", "execution_count": 32, "id": "c5d752d8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "loc_0 = total_points.mean()\n", "\n", "squad_model = tf.keras.Sequential(\n", " [\n", " tf.keras.layers.Dense(3),\n", " tfp.layers.DistributionLambda(\n", " lambda t: tfp.distributions.SinhArcsinh(loc= loc_0 + t[..., 0], scale = 1e-3 + tf.math.softplus(t[..., 1]), \n", " skewness = t[..., 2], tailweight = 0.8) # fixed tailweight seems ok\n", " )\n", " ]\n", ")\n", "\n", "def negloglik(y, distr):\n", " return -distr.log_prob(y)\n", "\n", "squad_model.compile(optimizer=tf.optimizers.Adam(learning_rate=1), loss=negloglik)\n", "\n", "dummy_input = np.zeros(total_points.shape)[:, np.newaxis]\n", "squad_model.fit(dummy_input, total_points, epochs=100, verbose=False)" ] }, { "cell_type": "code", "execution_count": 33, "id": "9754ec4c", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "squad_points_dist = squad_model(np.zeros(1)[:, np.newaxis])\n", "\n", "\n", "x = np.arange(start = 0, stop = 200, step = 0.001)\n", "prb = squad_points_dist.prob(x)\n", "\n", "mn = total_points.mean()\n", "\n", "f, ax = plt.subplots(1, 2)\n", "\n", "ax[0].plot(x, prb)\n", "ax[0].fill_between(x, prb, color = 'lightblue')\n", "ax[0].vlines(x = mn, color = 'grey', ymin = 0, ymax = 3, linestyle = 'dashed', label = 'mean = ' + \"{:.2f}\".format(mn))\n", "\n", "ax[0].set_xlim([40, 120])\n", "ax[0].set_ylim([0, 0.12])\n", "\n", "ax[0].legend()\n", "\n", "#ax[0].hist(total_points, bins = 20, density = True)\n", "\n", "\n", "ax[1].text(0.1, 0.8, \"\\n\".join(squad), fontsize=10, transform=ax[1].transAxes, verticalalignment = 'top')\n", "\n", "text = \"\\n\".join(['Avg Total Points = ' + \"{:.2f}\".format(total_points.mean()), \n", " 'Avg Mod Points = ' + \"{:.2f}\".format(mod_points.mean()), \n", " 'Avg Clean Sheets = ' + \"{:.2f}\".format(clean_sheets.mean())])\n", "\n", "ax[1].text(0.5, 0.8, text, fontsize=10, transform=ax[1].transAxes, verticalalignment = 'top')\n", "\n", "ax[1].axis('off')\n", "\n", "\n", "\n", "plt.subplots_adjust(right=1.5)\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "30744d7a", "metadata": {}, "source": [ "Tensorflow seems to have a custom definition for SinhArcsinh distribution. \n", "\n", "Here the code to generate the probability density function is reproduced." ] }, { "cell_type": "code", "execution_count": 110, "id": "3ec6c3dc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 110, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# custom franction to calculate the probability density function\n", "\n", "def sinh_archsinh_pdf(x, mu, sigma, eps, delta):\n", "\n", " mul = np.sinh( np.arcsinh(2) * delta)\n", " \n", " mul = 2 / mul\n", " \n", " sigma_corr = sigma * mul\n", " \n", " z = (x - mu) / sigma_corr\n", " \n", " \n", " \n", " S = np.sinh( -eps + (1/delta) * np.arcsinh(z))\n", " \n", " f = np.exp(-0.5 * S * S)\n", "\n", " f /= np.sqrt(2 * np.pi)\n", " \n", " f *= 1 / ( sigma_corr * delta )\n", " \n", " f *= np.sqrt(1 + S * S)\n", " \n", " f /= np.sqrt(1 + z * z)\n", " \n", " return f\n", " \n", "\n", "x = np.arange(start = 0, stop = 15, step = 0.001)\n", "\n", "\n", "plt.plot(x, sinh_archsinh_pdf(x, 5.54, 1.4, 0.8, 1.68))\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "605dc968", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.13" } }, "nbformat": 4, "nbformat_minor": 5 }