{ "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": 3, "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": 4, "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...miscontrolsdispossessedfoulsfouledaerials_wonaerials_lostcarriesprogressive_carriescarries_into_final_thirdcarries_into_penalty_area
01ToloiAtalantaSampdoria07.0100.010.0...0.0069610.0013920.0111370.0069610.0153130.0102090.3865430.0078890.0157770.000000
11DjimsitiAtalantaSampdoria06.0000.06.0...0.0067340.0042090.0084180.0042090.0286200.0227270.4141410.0050510.0050510.000842
21HateboerAtalantaSampdoria06.0000.55.5...0.0057270.0050110.0136010.0021470.0171800.0100210.2848960.0114530.0100210.000716
31OkoliAtalantaSampdoria05.5000.55.0...0.0130180.0035500.0153850.0082840.0473370.0272190.2698220.0023670.0047340.000000
41ZorteaAtalantaSampdoria06.0000.55.5...0.0172790.0064790.0194380.0107990.0064790.0172790.4319650.0345570.0259180.002160
..................................................................
2715438TamezeVeronaLazio05.5000.05.5...0.0198140.0101010.0128210.0132090.0236990.0213680.3372180.0213680.0128210.003885
2715538HonglaVeronaLazio07.0100.59.5...0.0184330.0122890.0230410.0076800.0230410.0261140.3410140.0092170.0153610.003072
2715638LasagnaVeronaLazio07.0100.59.5...0.0464530.0228040.0160470.0084460.0261820.0413850.1908780.0219590.0109800.005912
2715738CaprariVeronaLazio06.0000.06.0...0.0339540.0197150.0153340.0270170.0029210.0098580.3913840.0427160.0277470.018620
2715838SimeoneVeronaLazio07.0100.010.0...0.0512630.0301550.0211080.0218620.0226160.0407090.2461360.0150770.0128160.006031
\n", "

27159 rows × 122 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", "27154 38 Tameze Verona Lazio 0 5.5 0 0 \n", "27155 38 Hongla Verona Lazio 0 7.0 1 0 \n", "27156 38 Lasagna Verona Lazio 0 7.0 1 0 \n", "27157 38 Caprari Verona Lazio 0 6.0 0 0 \n", "27158 38 Simeone Verona Lazio 0 7.0 1 0 \n", "\n", " cards_malus fantavote ... miscontrols dispossessed fouls \\\n", "0 0.0 10.0 ... 0.006961 0.001392 0.011137 \n", "1 0.0 6.0 ... 0.006734 0.004209 0.008418 \n", "2 0.5 5.5 ... 0.005727 0.005011 0.013601 \n", "3 0.5 5.0 ... 0.013018 0.003550 0.015385 \n", "4 0.5 5.5 ... 0.017279 0.006479 0.019438 \n", "... ... ... ... ... ... ... \n", "27154 0.0 5.5 ... 0.019814 0.010101 0.012821 \n", "27155 0.5 9.5 ... 0.018433 0.012289 0.023041 \n", "27156 0.5 9.5 ... 0.046453 0.022804 0.016047 \n", "27157 0.0 6.0 ... 0.033954 0.019715 0.015334 \n", "27158 0.0 10.0 ... 0.051263 0.030155 0.021108 \n", "\n", " fouled aerials_won aerials_lost carries progressive_carries \\\n", "0 0.006961 0.015313 0.010209 0.386543 0.007889 \n", "1 0.004209 0.028620 0.022727 0.414141 0.005051 \n", "2 0.002147 0.017180 0.010021 0.284896 0.011453 \n", "3 0.008284 0.047337 0.027219 0.269822 0.002367 \n", "4 0.010799 0.006479 0.017279 0.431965 0.034557 \n", "... ... ... ... ... ... \n", "27154 0.013209 0.023699 0.021368 0.337218 0.021368 \n", "27155 0.007680 0.023041 0.026114 0.341014 0.009217 \n", "27156 0.008446 0.026182 0.041385 0.190878 0.021959 \n", "27157 0.027017 0.002921 0.009858 0.391384 0.042716 \n", "27158 0.021862 0.022616 0.040709 0.246136 0.015077 \n", "\n", " carries_into_final_third carries_into_penalty_area \n", "0 0.015777 0.000000 \n", "1 0.005051 0.000842 \n", "2 0.010021 0.000716 \n", "3 0.004734 0.000000 \n", "4 0.025918 0.002160 \n", "... ... ... \n", "27154 0.012821 0.003885 \n", "27155 0.015361 0.003072 \n", "27156 0.010980 0.005912 \n", "27157 0.027747 0.018620 \n", "27158 0.012816 0.006031 \n", "\n", "[27159 rows x 122 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db = pd.concat([db1, db2, db3], ignore_index = True) \n", "\n", "db" ] }, { "cell_type": "code", "execution_count": 5, "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...20.0000000.220000-3.000000108.0266.0532.000000148.000000149.000000247.00000014.0
11SkorupskiBolognaLazio06.5-200.04.5...40.2000000.2500003.200000129.0329.0773.000000169.000000219.000000402.00000024.0
21VicarioEmpoliSpezia05.5-100.04.5...32.3000000.2800002.300000117.0346.0869.000000123.000000139.000000489.00000028.0
31GolliniFiorentinaCremonese15.0-200.03.0...18.6166670.2200001.11666745.5114.0556.16666792.833333155.000000258.6666678.5
41HandanovicInterLecce06.5-100.05.5...12.5000000.270000-2.50000031.062.0345.00000054.00000059.000000112.0000002.0
..................................................................
184331ConsigliSassuoloSalernitana05.0-300.02.0...31.0000000.300000-12.000000153.0380.0946.000000154.000000249.000000409.00000024.0
184431ZoetSpeziaSampdoria06.5-100.05.5...14.5666670.213333-0.43333356.0171.0316.33333349.66666764.333333160.3333335.0
184531Milinkovic-Savic V.TorinoLazio06.0000.06.0...31.5000000.240000-4.500000224.0762.01196.000000142.000000236.000000387.00000025.0
184631SilvestriUdineseCremonese16.0000.06.0...37.5000000.3000000.500000121.0316.0687.000000120.000000237.000000441.00000011.0
184731Montipo'VeronaBologna16.5-100.05.5...38.7000000.260000-4.300000280.0616.0745.00000099.000000227.000000401.00000022.0
\n", "

1848 rows × 102 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", "1843 31 Consigli Sassuolo Salernitana 0 5.0 \n", "1844 31 Zoet Spezia Sampdoria 0 6.5 \n", "1845 31 Milinkovic-Savic V. Torino Lazio 0 6.0 \n", "1846 31 Silvestri Udinese Cremonese 1 6.0 \n", "1847 31 Montipo' Verona Bologna 1 6.5 \n", "\n", " goals assists cards_malus fantavote ... gk_psxg \\\n", "0 0 0 0.5 5.5 ... 20.000000 \n", "1 -2 0 0.0 4.5 ... 40.200000 \n", "2 -1 0 0.0 4.5 ... 32.300000 \n", "3 -2 0 0.0 3.0 ... 18.616667 \n", "4 -1 0 0.0 5.5 ... 12.500000 \n", "... ... ... ... ... ... ... \n", "1843 -3 0 0.0 2.0 ... 31.000000 \n", "1844 -1 0 0.0 5.5 ... 14.566667 \n", "1845 0 0 0.0 6.0 ... 31.500000 \n", "1846 0 0 0.0 6.0 ... 37.500000 \n", "1847 -1 0 0.0 5.5 ... 38.700000 \n", "\n", " gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n", "0 0.220000 -3.000000 \n", "1 0.250000 3.200000 \n", "2 0.280000 2.300000 \n", "3 0.220000 1.116667 \n", "4 0.270000 -2.500000 \n", "... ... ... \n", "1843 0.300000 -12.000000 \n", "1844 0.213333 -0.433333 \n", "1845 0.240000 -4.500000 \n", "1846 0.300000 0.500000 \n", "1847 0.260000 -4.300000 \n", "\n", " gk_passes_completed_launched gk_passes_launched gk_passes \\\n", "0 108.0 266.0 532.000000 \n", "1 129.0 329.0 773.000000 \n", "2 117.0 346.0 869.000000 \n", "3 45.5 114.0 556.166667 \n", "4 31.0 62.0 345.000000 \n", "... ... ... ... \n", "1843 153.0 380.0 946.000000 \n", "1844 56.0 171.0 316.333333 \n", "1845 224.0 762.0 1196.000000 \n", "1846 121.0 316.0 687.000000 \n", "1847 280.0 616.0 745.000000 \n", "\n", " gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n", "0 148.000000 149.000000 247.000000 14.0 \n", "1 169.000000 219.000000 402.000000 24.0 \n", "2 123.000000 139.000000 489.000000 28.0 \n", "3 92.833333 155.000000 258.666667 8.5 \n", "4 54.000000 59.000000 112.000000 2.0 \n", "... ... ... ... ... \n", "1843 154.000000 249.000000 409.000000 24.0 \n", "1844 49.666667 64.333333 160.333333 5.0 \n", "1845 142.000000 236.000000 387.000000 25.0 \n", "1846 120.000000 237.000000 441.000000 11.0 \n", "1847 99.000000 227.000000 401.000000 22.0 \n", "\n", "[1848 rows x 102 columns]" ] }, "execution_count": 5, "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": 6, "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": 7, "id": "493b0495", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_5820\\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
AtalantaAtalanta25.050.031.0341.02790.050.032.06.08.00...338.0356.0040.001.008.01.001865.0389.0472.045.200
BolognaBologna27.053.431.0341.02790.039.032.04.04.00...376.0365.0052.005.004.01.001687.0379.0306.055.300
CremoneseCremonese32.043.231.0341.02790.027.013.04.06.00...345.0372.0052.004.006.00.001745.0594.0462.056.300
EmpoliEmpoli31.047.431.0341.02790.025.013.01.01.00...384.0341.0060.002.001.00.001607.0412.0330.055.500
FiorentinaFiorentina29.056.631.0341.02790.035.025.04.06.00...460.0371.0078.002.006.02.001625.0425.0504.045.700
VeronaHellas Verona36.042.031.0341.02790.024.018.01.01.00...337.0438.0032.001.001.02.001728.0619.0615.050.200
InterInter24.056.231.0341.02790.050.035.04.05.00...368.0336.0029.003.005.01.001443.0344.0443.043.700
JuventusJuventus29.048.631.0341.02790.047.037.03.05.00...348.0328.0039.000.005.00.001556.0381.0390.049.400
LazioLazio22.051.931.0341.02790.048.029.05.07.00...421.0304.0055.001.007.01.001677.0319.0319.050.000
LecceLecce29.041.731.0341.02790.024.017.01.02.00...378.0425.0057.004.002.02.001694.0582.0466.055.500
MilanMilan29.054.031.0341.02790.048.039.03.03.00...378.0369.0031.005.003.03.001617.0387.0456.045.900
MonzaMonza31.055.031.0341.02790.036.023.05.05.00...437.0385.0048.001.005.02.001608.0340.0357.048.800
NapoliNapoli26.061.831.0341.02790.065.051.06.07.00...405.0287.0039.001.006.02.001562.0322.0389.045.300
RomaRoma27.049.231.0341.02790.043.030.06.09.00...447.0344.0021.002.009.00.001621.0331.0426.043.700
SalernitanaSalernitana28.044.631.0341.02790.035.025.01.01.00...375.0357.0064.0010.001.02.001709.0448.0427.051.200
SampdoriaSampdoria37.047.431.0341.02790.020.016.01.02.00...449.0408.0075.006.002.00.001693.0535.0517.050.900
SassuoloSassuolo29.048.931.0341.02790.037.024.06.07.00...384.0307.0094.002.007.01.001611.0385.0329.053.900
SpeziaSpezia34.047.031.0341.02790.024.015.04.04.00...321.0396.0067.004.004.02.001708.0470.0424.052.600
TorinoTorino28.053.031.0341.02790.032.026.02.02.00...341.0409.0032.004.002.00.001597.0508.0474.051.700
UdineseUdinese27.048.131.0341.02790.041.036.01.02.00...412.0357.0050.003.002.01.001577.0326.0390.045.500
AvgAvg29.050.031.0341.02790.037.526.83.44.35...385.2362.7550.753.054.31.151646.5424.8424.849.815
\n", "

21 rows × 303 columns

\n", "
" ], "text/plain": [ " team team_players_used team_possession team_games \\\n", "Atalanta Atalanta 25.0 50.0 31.0 \n", "Bologna Bologna 27.0 53.4 31.0 \n", "Cremonese Cremonese 32.0 43.2 31.0 \n", "Empoli Empoli 31.0 47.4 31.0 \n", "Fiorentina Fiorentina 29.0 56.6 31.0 \n", "Verona Hellas Verona 36.0 42.0 31.0 \n", "Inter Inter 24.0 56.2 31.0 \n", "Juventus Juventus 29.0 48.6 31.0 \n", "Lazio Lazio 22.0 51.9 31.0 \n", "Lecce Lecce 29.0 41.7 31.0 \n", "Milan Milan 29.0 54.0 31.0 \n", "Monza Monza 31.0 55.0 31.0 \n", "Napoli Napoli 26.0 61.8 31.0 \n", "Roma Roma 27.0 49.2 31.0 \n", "Salernitana Salernitana 28.0 44.6 31.0 \n", "Sampdoria Sampdoria 37.0 47.4 31.0 \n", "Sassuolo Sassuolo 29.0 48.9 31.0 \n", "Spezia Spezia 34.0 47.0 31.0 \n", "Torino Torino 28.0 53.0 31.0 \n", "Udinese Udinese 27.0 48.1 31.0 \n", "Avg Avg 29.0 50.0 31.0 \n", "\n", " team_games_starts team_minutes team_goals team_assists \\\n", "Atalanta 341.0 2790.0 50.0 32.0 \n", "Bologna 341.0 2790.0 39.0 32.0 \n", "Cremonese 341.0 2790.0 27.0 13.0 \n", "Empoli 341.0 2790.0 25.0 13.0 \n", "Fiorentina 341.0 2790.0 35.0 25.0 \n", "Verona 341.0 2790.0 24.0 18.0 \n", "Inter 341.0 2790.0 50.0 35.0 \n", "Juventus 341.0 2790.0 47.0 37.0 \n", "Lazio 341.0 2790.0 48.0 29.0 \n", "Lecce 341.0 2790.0 24.0 17.0 \n", "Milan 341.0 2790.0 48.0 39.0 \n", "Monza 341.0 2790.0 36.0 23.0 \n", "Napoli 341.0 2790.0 65.0 51.0 \n", "Roma 341.0 2790.0 43.0 30.0 \n", "Salernitana 341.0 2790.0 35.0 25.0 \n", "Sampdoria 341.0 2790.0 20.0 16.0 \n", "Sassuolo 341.0 2790.0 37.0 24.0 \n", "Spezia 341.0 2790.0 24.0 15.0 \n", "Torino 341.0 2790.0 32.0 26.0 \n", "Udinese 341.0 2790.0 41.0 36.0 \n", "Avg 341.0 2790.0 37.5 26.8 \n", "\n", " team_pens_made team_pens_att ... vs_team_fouls \\\n", "Atalanta 6.0 8.00 ... 338.0 \n", "Bologna 4.0 4.00 ... 376.0 \n", "Cremonese 4.0 6.00 ... 345.0 \n", "Empoli 1.0 1.00 ... 384.0 \n", "Fiorentina 4.0 6.00 ... 460.0 \n", "Verona 1.0 1.00 ... 337.0 \n", "Inter 4.0 5.00 ... 368.0 \n", "Juventus 3.0 5.00 ... 348.0 \n", "Lazio 5.0 7.00 ... 421.0 \n", "Lecce 1.0 2.00 ... 378.0 \n", "Milan 3.0 3.00 ... 378.0 \n", "Monza 5.0 5.00 ... 437.0 \n", "Napoli 6.0 7.00 ... 405.0 \n", "Roma 6.0 9.00 ... 447.0 \n", "Salernitana 1.0 1.00 ... 375.0 \n", "Sampdoria 1.0 2.00 ... 449.0 \n", "Sassuolo 6.0 7.00 ... 384.0 \n", "Spezia 4.0 4.00 ... 321.0 \n", "Torino 2.0 2.00 ... 341.0 \n", "Udinese 1.0 2.00 ... 412.0 \n", "Avg 3.4 4.35 ... 385.2 \n", "\n", " vs_team_fouled vs_team_offsides vs_team_pens_won \\\n", "Atalanta 356.00 40.00 1.00 \n", "Bologna 365.00 52.00 5.00 \n", "Cremonese 372.00 52.00 4.00 \n", "Empoli 341.00 60.00 2.00 \n", "Fiorentina 371.00 78.00 2.00 \n", "Verona 438.00 32.00 1.00 \n", "Inter 336.00 29.00 3.00 \n", "Juventus 328.00 39.00 0.00 \n", "Lazio 304.00 55.00 1.00 \n", "Lecce 425.00 57.00 4.00 \n", "Milan 369.00 31.00 5.00 \n", "Monza 385.00 48.00 1.00 \n", "Napoli 287.00 39.00 1.00 \n", "Roma 344.00 21.00 2.00 \n", "Salernitana 357.00 64.00 10.00 \n", "Sampdoria 408.00 75.00 6.00 \n", "Sassuolo 307.00 94.00 2.00 \n", "Spezia 396.00 67.00 4.00 \n", "Torino 409.00 32.00 4.00 \n", "Udinese 357.00 50.00 3.00 \n", "Avg 362.75 50.75 3.05 \n", "\n", " vs_team_pens_conceded vs_team_own_goals \\\n", "Atalanta 8.0 1.00 \n", "Bologna 4.0 1.00 \n", "Cremonese 6.0 0.00 \n", "Empoli 1.0 0.00 \n", "Fiorentina 6.0 2.00 \n", "Verona 1.0 2.00 \n", "Inter 5.0 1.00 \n", "Juventus 5.0 0.00 \n", "Lazio 7.0 1.00 \n", "Lecce 2.0 2.00 \n", "Milan 3.0 3.00 \n", "Monza 5.0 2.00 \n", "Napoli 6.0 2.00 \n", "Roma 9.0 0.00 \n", "Salernitana 1.0 2.00 \n", "Sampdoria 2.0 0.00 \n", "Sassuolo 7.0 1.00 \n", "Spezia 4.0 2.00 \n", "Torino 2.0 0.00 \n", "Udinese 2.0 1.00 \n", "Avg 4.3 1.15 \n", "\n", " vs_team_ball_recoveries vs_team_aerials_won \\\n", "Atalanta 1865.0 389.0 \n", "Bologna 1687.0 379.0 \n", "Cremonese 1745.0 594.0 \n", "Empoli 1607.0 412.0 \n", "Fiorentina 1625.0 425.0 \n", "Verona 1728.0 619.0 \n", "Inter 1443.0 344.0 \n", "Juventus 1556.0 381.0 \n", "Lazio 1677.0 319.0 \n", "Lecce 1694.0 582.0 \n", "Milan 1617.0 387.0 \n", "Monza 1608.0 340.0 \n", "Napoli 1562.0 322.0 \n", "Roma 1621.0 331.0 \n", "Salernitana 1709.0 448.0 \n", "Sampdoria 1693.0 535.0 \n", "Sassuolo 1611.0 385.0 \n", "Spezia 1708.0 470.0 \n", "Torino 1597.0 508.0 \n", "Udinese 1577.0 326.0 \n", "Avg 1646.5 424.8 \n", "\n", " vs_team_aerials_lost vs_team_aerials_won_pct \n", "Atalanta 472.0 45.200 \n", "Bologna 306.0 55.300 \n", "Cremonese 462.0 56.300 \n", "Empoli 330.0 55.500 \n", "Fiorentina 504.0 45.700 \n", "Verona 615.0 50.200 \n", "Inter 443.0 43.700 \n", "Juventus 390.0 49.400 \n", "Lazio 319.0 50.000 \n", "Lecce 466.0 55.500 \n", "Milan 456.0 45.900 \n", "Monza 357.0 48.800 \n", "Napoli 389.0 45.300 \n", "Roma 426.0 43.700 \n", "Salernitana 427.0 51.200 \n", "Sampdoria 517.0 50.900 \n", "Sassuolo 329.0 53.900 \n", "Spezia 424.0 52.600 \n", "Torino 474.0 51.700 \n", "Udinese 390.0 45.500 \n", "Avg 424.8 49.815 \n", "\n", "[21 rows x 303 columns]" ] }, "execution_count": 7, "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": 8, "id": "32f56138", "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", " 'carries',\n", " 'progressive_carries',\n", " 'carries_into_final_third',\n", " 'carries_into_penalty_area']\n", "\n", "features_rel_gamecorr = [\n", " 'goals',\n", " 'assists',\n", " 'xg',\n", " 'npxg',\n", " 'cards_yellow',\n", " 'cards_red'\n", "]" ] }, { "cell_type": "code", "execution_count": 9, "id": "4001f3f8", "metadata": {}, "outputs": [], "source": [ "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", "]" ] }, { "cell_type": "code", "execution_count": 10, "id": "f4017b2f", "metadata": {}, "outputs": [], "source": [ "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", "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": 11, "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", "Sepe 1\n", "Milinkovic-Savic V. 1\n", "Musso 1\n", "Maignan 1\n", "Audero 1\n", "Montipo' 1\n", "Skorupski 1\n", "Consigli 1\n", "Dragowski 1\n", "Terracciano 1\n", "Tatarusanu 1\n", "Handanovic 0.7372677888806921\n", "Sportiello 1\n", "Perin 1\n", "Zoet 1\n", "Pegolo 1\n", "Mirante 0.0\n", "Ujkani 0.0\n", "Berisha 0.0\n", "Marchetti 1\n", "Padelli 0.0\n", "Bardi 1\n", "Cordaz 0.0\n", "Pinsoglio 0.0\n", "Fiorillo 0.0\n", "Cragno 0.07071960297766748\n", "Sirigu 0.0668969217356314\n", "Rossi F. 0.0\n", "Berardi A. 0.0\n", "Gemello 0.0\n", "Ravaglia 1\n", "Boer 0.0\n", "Adamonis 0.0\n", "Marfella 0.0\n", "Zovko 1\n", "Piana 0.0\n", "Dimarco 1\n", "Smalling 1\n", "Di Lorenzo 1\n", "Danilo 1\n", "Hernandez T. 1\n", "Udogie 0.9565331442750797\n", "Parisi 1\n", "Mario Rui 0.7658517004816814\n", "Romagnoli 1\n", "Bastoni S. 0.6399743856559673\n", "Mazzocchi 1\n", "Tomori 1\n", "Scalvini 1\n", "Toloi 1\n", "Demiral 1\n", "Maehle 1\n", "Dumfries 1\n", "Juan Jesus 0.649497814013943\n", "Depaoli 1\n", "Mancini 1\n", "Ibanez 0.9846664720478762\n", "Rodrigo Becao 0.8502516838000708\n", "Ebuehi 1\n", "Gosens 1\n", "Darmian 1\n", "Reca 1\n", "Bremer 0.9750733137829912\n", "Rrahmani 0.8642078351755771\n", "Vojvoda 0.9834089158894498\n", "Bastoni 0.9199631793804531\n", "Milenkovic 0.8387899576704131\n", "Kalulu 1\n", "Martinez Quarta 1\n", "Casale 0.756306865177833\n", "Perez N. 1\n", "Izzo 1\n", "Luperto 1\n", "Skriniar 0.743970223325062\n", "Rodriguez R. 1\n", "Marusic 1\n", "Lazzari 0.8799647802769551\n", "Kyriakopoulos 0.4694318473517583\n", "Ampadu 1\n", "Ismajli 1\n", "Llorente D. affine to Ibanez\n", "Llorente D. 0.2188147715661947\n", "Cambiaso 1\n", "Hysaj 1\n", "Biraghi 0.9718529944336394\n", "Medel 0.9017820888788629\n", "Bonucci 0.6716397849462366\n", "Calabria 0.858427180759687\n", "Acerbi 0.9900744416873448\n", "Spinazzola 1\n", "Lykogiannis 0.8397952853598015\n", "Pellegrini Lu. 0.13751033912324234\n", "Djidji 1\n", "Augello 1\n", "Singo 0.8856788372917405\n", "Mari' 1\n", "De Vrij 0.826633581472291\n", "Patric 0.8266335814722912\n", "Faraoni 0.658723635235732\n", "Ceccherini 0.6564443146985842\n", "Hateboer 1\n", "Rogerio 1\n", "Aina 0.9447240931111898\n", "Ferrari G. 0.8955197132616488\n", "Fazio 1\n", "Buongiorno 1\n", "Gunter 0.1650124069478908\n", "Troost-Ekong affine to Fazio\n", "Troost-Ekong 0.46498138957816376\n", "Soumaoro 0.9299627791563275\n", "Ceccaroni 0.03535980148883374\n", "Soppy 0.5303970223325062\n", "Ferrari A. 0.5918923292696083\n", "Zappacosta 0.510567800321121\n", "Gyomber 0.9199631793804531\n", "Alex Sandro 0.9742467210209147\n", "Pezzella Giu. 0.7071960297766748\n", "Bereszynski 0.5303970223325062\n", "Venuti 0.593019743230122\n", "Palomino 0.47409867172675524\n", "Nuytinck 0.6417149159084642\n", "Magnani 1\n", "Colley 0.6199751861042183\n", "Nikolaou 0.9988489109456851\n", "Terzic 1\n", "Igor 0.9092969396195203\n", "Toljan 1\n", "Zortea 0.2560537349191409\n", "Dawidowicz 1\n", "Bellanova 0.518990634755463\n", "Erlic 0.9075682382133995\n", "Ballo-Toure' affine to Calabria\n", "Ballo-Toure' 0.23845199465546857\n", "Stojanovic 0.8266335814722912\n", "Amian 0.9299627791563275\n", "Zima 0.5579776674937966\n", "De Winter 1\n", "Romagnoli S. 0.195409429280397\n", "Ghiglione 1\n", "Rugani 0.6199751861042183\n", "De Sciglio 0.9919602977667494\n", "Djimsiti 0.6799727847594653\n", "Caldara 0.7984471303930201\n", "Karsdorp 0.4477598566308244\n", "Marchizza 0.521091811414392\n", "Kjaer 1\n", "Ruggeri 1\n", "Zanoli 1\n", "Radovanovic 0.8856788372917405\n", "D'ambrosio 0.6199751861042183\n", "De Silvestri 0.39998399103497956\n", "Chiriches 0.4694318473517583\n", "Murru 0.901782088878863\n", "Bonifazi 0.39452966388450256\n", "Walukiewicz 1\n", "Ranieri L. 0.22918389853873725\n", "Gabbia 1\n", "Kumbulla 0.4376295431323894\n", "Lovato 0.9281947890818858\n", "Ferrer 0.13777226357871517\n", "Vasquez 0.7955955334987593\n", "Ruan 1\n", "Ostigard 1\n", "Coppola D. 1\n", "Cacace 1\n", "Conti 0.1771357674583481\n", "Conti 0.6679835812950357\n", "Marrone 0.11786600496277913\n", "Tonelli 0.08856788372917405\n", "Radu 1\n", "Florenzi 0.258322994210091\n", "Sala 0.4133167907361455\n", "Fares 0.0\n", "Fares 0.0\n", "Romagna 0.0\n", "Romagna 0.0\n", "Muldur 0.03999839910349796\n", "Amey 0.0\n", "Zaccagni 1\n", "Milinkovic-Savic 0.9718529944336394\n", "Barella 1\n", "Zielinski 1\n", "Luis Alberto 1\n", "Felipe Anderson 1\n", "Koopmeiners 1\n", "Calhanoglu 1\n", "Frattesi 1\n", "Diaz B. 1\n", "Zambo Anguissa 1\n", "Elmas 1\n", "Miranchuk 1\n", "Samardzic 1\n", "Pereyra 1\n", "Politano 0.9393563425821488\n", "Rabiot 1\n", "Lazovic 0.8752590862647788\n", "Lobotka 1\n", "Bonaventura 1\n", "Pessina 1\n", "Tonali 0.9299627791563276\n", "Pellegrini Lo. 1\n", "El Shaarawy 1\n", "Orsolini 1\n", "Ikone' 1\n", "Candreva 1\n", "Bennacer 0.9999599775874489\n", "Pasalic 0.8378043055462409\n", "Mkhitaryan 1\n", "Chiesa 1\n", "Bandinelli 1\n", "Fagioli affine to Henderson L.\n", "Fagioli 0.7178660049627792\n", "Messias 0.9538079786218743\n", "Arslan 1\n", "Ricci S. 1\n", "Verdi 1\n", "Sensi 1\n", "Barak 1\n", "Soriano 0.9565331442750797\n", "Dominguez 1\n", "Brozovic 0.743970223325062\n", "Cristante 1\n", "Saponara 1\n", "Vecino 1\n", "Locatelli 1\n", "Zaniolo 0.5756912442396314\n", "Maldini 1\n", "Marin 0.996949958643507\n", "Zalewski 1\n", "Bajrami 0.3889578163771712\n", "Coulibaly L. 1\n", "De Roon 1\n", "Mandragora 1\n", "Bourabia 1\n", "Sottil 0.6716397849462366\n", "Aebischer 1\n", "Ederson D.s. 1\n", "Miretti 1\n", "Cataldi 1\n", "Djuricic 1\n", "Linetty 1\n", "Haas 1\n", "Walace 1\n", "Agudelo 1\n", "Pobega 0.5625422964132641\n", "Rovella 1\n", "Amrabat 1\n", "Tameze 0.9789081885856079\n", "Gyasi 0.9644058450510063\n", "Ilic 0.27072348014888337\n", "Matheus Henrique 1\n", "Harroui 1\n", "Volpato 1\n", "Duncan 0.6763365666591473\n", "Cuadrado 0.9393563425821488\n", "Ekdal 1\n", "Schouten 1\n", "Obiang 1\n", "Kovalenko 0.7153559839664058\n", "Crnigoj 0.2547985695518902\n", "Basic 0.8551381877299562\n", "Asllani 0.8609342971194303\n", "Sabiri 1\n", "Grassi 0.7425558312655087\n", "Krunic 0.7528270116979794\n", "Rincon 1\n", "Miguel Veloso 1\n", "Henderson L. 0.6199751861042183\n", "Lopez M. 0.8502516838000708\n", "Cuisance 0.8567951899217408\n", "Saelemaekers 0.7921905155776124\n", "Maggiore 0.45967741935483875\n", "Akpa Akpro 0.0\n", "Akpa Akpro 0.0\n", "Maleh 0.5745967741935485\n", "Romero L. 0.9299627791563275\n", "Ceide 1\n", "Benassi 1\n", "Gagliardini 0.9644058450510063\n", "Vieira 0.08839950372208435\n", "Bianco 1\n", "Galdames 0.0\n", "Kastanos 0.9644058450510062\n", "Vignato 0.2062655086848635\n", "Askildsen 1\n", "Bove 1\n", "Bohinen 1\n", "Bakayoko 0.26570365118752215\n", "Zurkowski 0.21215880893300246\n", "Castrovilli 0.5391088574819289\n", "Demme 0.32630272952853595\n", "Darboe 0.0\n", "Darboe 0.24799007444168736\n", "Urbanski 0.0\n", "Yepes 1\n", "Osimhen 1\n", "Martinez L. 1\n", "Dybala 0.9815393171900401\n", "Rafael Leao 1\n", "Immobile 0.9599615784839509\n", "Vlahovic 1\n", "Arnautovic 0.6011880592525753\n", "Dzeko 1\n", "Nzola 1\n", "Beto 1\n", "Giroud 1\n", "Abraham 1\n", "Deulofeu 0.5835060575098525\n", "Simeone 0.6718362282878412\n", "Lozano 1\n", "Correa 1\n", "Berardi 0.7139108203624331\n", "Pedro 1\n", "Sanabria 1\n", "Thauvin affine to Deulofeu\n", "Thauvin 0.36469128594365785\n", "Cabral 1\n", "Caprari 1\n", "Piatek 1\n", "Rebic 1\n", "Bonazzoli 0.9299627791563275\n", "Zapata D. 1\n", "Gonzalez N. 0.7139108203624331\n", "Brekalo 0.15469913151364761\n", "Kean 0.9299627791563275\n", "Okereke 1\n", "Muriel 1\n", "Pinamonti 0.9281947890818859\n", "Di Francesco F. 1\n", "Caputo 0.5500413564929694\n", "Boga 1\n", "Alvarez A. affine to Raspadori\n", "Alvarez A. 0.688861317893576\n", "Petagna 1\n", "Barrow 0.9117282148591446\n", "Djuric 1\n", "Henry 0.6000451161741484\n", "Success 1\n", "Gabbiadini 1\n", "Kallon 1\n", "Nestorovski 1\n", "Raspadori 0.6531741108354012\n", "Lasagna 1\n", "Belotti 1\n", "Pellegri 1\n", "Verde 0.7514850740657192\n", "Destro 0.5500413564929694\n", "Seck 1\n", "Sansone 0.688861317893576\n", "Quagliarella 0.6763365666591473\n", "Defrel 0.6526054590570719\n", "Pjaca 0.6703629032258065\n", "Piccoli 1\n", "Shomurodov 0.44199751861042186\n", "Afena-Gyan 1\n", "Ibrahimovic 0.2156435429927716\n", "Pussetto 0.22099875930521093\n", "Cancellieri 1\n", "Oddei 0.0\n", "Oddei 0.4959801488833747\n", "Braaf 1\n", "Raimondo 1\n", "Kaio Jorge 0.0\n", "Players with low quantity of games:\n", "Aiwu 0.0\n", "Zeefuik 0.16666666666666663\n", "Dermaku 0.16666666666666663\n", "Ostigard 0.8333333333333334\n", "Gila 0.6666666666666667\n", "Bayeye 0.16666666666666663\n", "Moutinho J. 0.6666666666666667\n", "Paletta 0.0\n", "Romagna 0.0\n", "Cassandro 0.16666666666666663\n", "Amey 0.16666666666666663\n", "Zanotti 0.16666666666666663\n", "Buta 0.0\n", "Abankwah 0.16666666666666663\n", "Guessand A. 0.0\n", "Guarino 0.0\n", "Carboni F. 0.33333333333333337\n", "Pogba 0.5\n", "Machin 0.0\n", "Akpa Akpro 0.0\n", "Bianco 0.6666666666666667\n", "Galdames 0.0\n", "D'andrea 0.8333333333333334\n", "Cipot 0.8333333333333334\n", "Gaetano 0.8333333333333334\n", "Darboe 0.668006617038875\n", "Urbanski 0.16666666666666663\n", "Bertini 0.0\n", "Yepes 0.8333333333333334\n", "Pyyhtia 0.6666666666666667\n", "Trimboli 0.0\n", "Adli 0.8333333333333334\n", "Vignato S. 0.5\n", "Samek 0.0\n", "Ilkhan 0.5\n", "Degli Innocenti 0.0\n", "Acella 0.16666666666666663\n", "Carboni V. 0.8333333333333334\n", "Malagrida 0.6666666666666667\n", "Faticanti 0.0\n", "Oddei 0.5853432588916461\n", "Braaf 0.6666666666666667\n", "Raimondo 0.33333333333333337\n", "De Luca 0.33333333333333337\n", "Krollis 0.16666666666666663\n", "Vivaldo 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": 12, "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=151)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "players.columns[9:]" ] }, { "cell_type": "code", "execution_count": 13, "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 - aerials_won_pct\n", "19 - team_possession\n", "20 - team_goals_assists_per90\n", "21 - team_goals_pens_per90\n", "22 - team_goals_assists_pens_per90\n", "23 - team_xg_per90\n", "24 - team_gk_goals_against_per90\n", "25 - team_gk_save_pct\n", "26 - team_gk_clean_sheets_pct\n", "27 - team_passes_pct\n", "28 - team_passes_pct_medium\n", "29 - team_passes_pct_long\n", "30 - team_sca_per90\n", "31 - team_gca_per90\n", "32 - team_aerials_won_pct\n", "33 - vs_team_possession\n", "34 - vs_team_goals_per90\n", "35 - vs_team_assists_per90\n", "36 - vs_team_xg_per90\n", "37 - vs_team_gk_save_pct\n", "38 - vs_team_gk_clean_sheets_pct\n", "39 - vs_team_gk_pct_passes_launched\n", "40 - vs_team_gk_crosses_stopped_pct\n", "41 - vs_team_shots_on_target_per90\n", "42 - vs_team_passes_pct\n", "43 - vs_team_passes_pct_short\n", "44 - vs_team_passes_pct_medium\n", "45 - vs_team_passes_pct_long\n", "46 - vs_team_sca_per90\n", "47 - vs_team_gca_per90\n", "48 - vs_team_aerials_won_pct\n", "49 - opp_team_possession\n", "50 - opp_team_goals_assists_per90\n", "51 - opp_team_goals_pens_per90\n", "52 - opp_team_goals_assists_pens_per90\n", "53 - opp_team_xg_per90\n", "54 - opp_team_gk_goals_against_per90\n", "55 - opp_team_gk_save_pct\n", "56 - opp_team_gk_clean_sheets_pct\n", "57 - opp_team_passes_pct\n", "58 - opp_team_passes_pct_medium\n", "59 - opp_team_passes_pct_long\n", "60 - opp_team_sca_per90\n", "61 - opp_team_gca_per90\n", "62 - opp_team_aerials_won_pct\n", "63 - opp_vs_team_possession\n", "64 - opp_vs_team_goals_per90\n", "65 - opp_vs_team_assists_per90\n", "66 - opp_vs_team_xg_per90\n", "67 - opp_vs_team_gk_save_pct\n", "68 - opp_vs_team_gk_clean_sheets_pct\n", "69 - opp_vs_team_gk_pct_passes_launched\n", "70 - opp_vs_team_gk_crosses_stopped_pct\n", "71 - opp_vs_team_shots_on_target_per90\n", "72 - opp_vs_team_passes_pct\n", "73 - opp_vs_team_passes_pct_short\n", "74 - opp_vs_team_passes_pct_medium\n", "75 - opp_vs_team_passes_pct_long\n", "76 - opp_vs_team_sca_per90\n", "77 - opp_vs_team_gca_per90\n", "78 - opp_vs_team_aerials_won_pct\n", "79 - vote_avg\n", "80 - vote_std\n", "81 - goals.1\n", "82 - assists.1\n", "83 - cards_yellow\n", "84 - cards_red\n", "85 - xg\n", "86 - npxg\n", "87 - shots_on_target\n", "88 - passes_completed\n", "89 - passes_into_final_third\n", "90 - passes_into_penalty_area\n", "91 - progressive_passes\n", "92 - passes_live\n", "93 - passes_dead\n", "94 - through_balls\n", "95 - passes_switches\n", "96 - crosses\n", "97 - corner_kicks\n", "98 - blocks\n", "99 - blocked_shots\n", "100 - blocked_passes\n", "101 - interceptions\n", "102 - clearances\n", "103 - errors\n", "104 - touches\n", "105 - touches_def_pen_area\n", "106 - touches_def_3rd\n", "107 - touches_mid_3rd\n", "108 - touches_att_3rd\n", "109 - touches_att_pen_area\n", "110 - touches_live_ball\n", "111 - passes_received\n", "112 - miscontrols\n", "113 - dispossessed\n", "114 - fouls\n", "115 - fouled\n", "116 - aerials_won\n", "117 - aerials_lost\n", "118 - carries\n", "119 - progressive_carries\n", "120 - carries_into_final_third\n", "121 - carries_into_penalty_area\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": 14, "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": 15, "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": 16, "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_aerials_won_pct\n", "39 - vs_team_possession\n", "40 - vs_team_goals_per90\n", "41 - vs_team_assists_per90\n", "42 - vs_team_xg_per90\n", "43 - vs_team_gk_save_pct\n", "44 - vs_team_gk_clean_sheets_pct\n", "45 - vs_team_gk_pct_passes_launched\n", "46 - vs_team_gk_crosses_stopped_pct\n", "47 - vs_team_shots_on_target_per90\n", "48 - vs_team_passes_pct\n", "49 - vs_team_passes_pct_short\n", "50 - vs_team_passes_pct_medium\n", "51 - vs_team_passes_pct_long\n", "52 - vs_team_sca_per90\n", "53 - vs_team_gca_per90\n", "54 - vs_team_aerials_won_pct\n", "55 - opp_team_possession\n", "56 - opp_team_goals_assists_per90\n", "57 - opp_team_goals_pens_per90\n", "58 - opp_team_goals_assists_pens_per90\n", "59 - opp_team_xg_per90\n", "60 - opp_team_gk_goals_against_per90\n", "61 - opp_team_gk_save_pct\n", "62 - opp_team_gk_clean_sheets_pct\n", "63 - opp_team_passes_pct\n", "64 - opp_team_passes_pct_medium\n", "65 - opp_team_passes_pct_long\n", "66 - opp_team_sca_per90\n", "67 - opp_team_gca_per90\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_aerials_won_pct\n", "85 - vote_avg\n", "86 - vote_std\n", "87 - gk_shots_on_target_against\n", "88 - gk_saves\n", "89 - gk_free_kick_goals_against\n", "90 - gk_corner_kick_goals_against\n", "91 - gk_own_goals_against\n", "92 - gk_psxg\n", "93 - gk_psnpxg_per_shot_on_target_against\n", "94 - gk_psxg_net\n", "95 - gk_passes_completed_launched\n", "96 - gk_passes_launched\n", "97 - gk_passes\n", "98 - gk_passes_throws\n", "99 - gk_goal_kicks\n", "100 - gk_crosses\n", "101 - 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": 17, "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": 18, "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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", "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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", "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": 36, "id": "8aad9652", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/1000\n", "85/85 [==============================] - 4s 9ms/step - loss: 2.1506 - distribution_lambda_8_loss: 0.8422 - distribution_lambda_9_loss: 1.3084 - val_loss: 2.1163 - val_distribution_lambda_8_loss: 0.8236 - val_distribution_lambda_9_loss: 1.2926\n", "Epoch 2/1000\n", "85/85 [==============================] - 0s 2ms/step - loss: 2.1461 - distribution_lambda_8_loss: 0.8394 - distribution_lambda_9_loss: 1.3067 - val_loss: 2.1203 - val_distribution_lambda_8_loss: 0.8253 - val_distribution_lambda_9_loss: 1.2950\n", "Epoch 3/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1514 - distribution_lambda_8_loss: 0.8435 - distribution_lambda_9_loss: 1.3079 - val_loss: 2.1184 - val_distribution_lambda_8_loss: 0.8249 - val_distribution_lambda_9_loss: 1.2935\n", "Epoch 4/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1450 - distribution_lambda_8_loss: 0.8390 - distribution_lambda_9_loss: 1.3060 - val_loss: 2.1215 - val_distribution_lambda_8_loss: 0.8261 - val_distribution_lambda_9_loss: 1.2954\n", "Epoch 5/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1462 - distribution_lambda_8_loss: 0.8403 - distribution_lambda_9_loss: 1.3059 - val_loss: 2.1222 - val_distribution_lambda_8_loss: 0.8268 - val_distribution_lambda_9_loss: 1.2954\n", "Epoch 6/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1486 - distribution_lambda_8_loss: 0.8415 - distribution_lambda_9_loss: 1.3071 - val_loss: 2.1232 - val_distribution_lambda_8_loss: 0.8268 - val_distribution_lambda_9_loss: 1.2963\n", "Epoch 7/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1468 - distribution_lambda_8_loss: 0.8398 - distribution_lambda_9_loss: 1.3070 - val_loss: 2.1224 - val_distribution_lambda_8_loss: 0.8261 - val_distribution_lambda_9_loss: 1.2964\n", "Epoch 8/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1443 - distribution_lambda_8_loss: 0.8388 - distribution_lambda_9_loss: 1.3055 - val_loss: 2.1274 - val_distribution_lambda_8_loss: 0.8291 - val_distribution_lambda_9_loss: 1.2984\n", "Epoch 9/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1464 - distribution_lambda_8_loss: 0.8401 - distribution_lambda_9_loss: 1.3063 - val_loss: 2.1231 - val_distribution_lambda_8_loss: 0.8262 - val_distribution_lambda_9_loss: 1.2969\n", "Epoch 10/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1435 - distribution_lambda_8_loss: 0.8387 - distribution_lambda_9_loss: 1.3048 - val_loss: 2.1272 - val_distribution_lambda_8_loss: 0.8301 - val_distribution_lambda_9_loss: 1.2971\n", "Epoch 11/1000\n", "85/85 [==============================] - 0s 3ms/step - loss: 2.1467 - distribution_lambda_8_loss: 0.8405 - distribution_lambda_9_loss: 1.3061 - val_loss: 2.1255 - val_distribution_lambda_8_loss: 0.8280 - val_distribution_lambda_9_loss: 1.2975\n" ] } ], "source": [ "load_model_of = True# load scaler and model weights for outfield player predictor\n", "refit_model_of = False\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": 37, "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": 38, "id": "c2674211", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.13385223635677934\n", "0.1536831746216616\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.127508905428527\n", "0.147998716039207\n" ] }, { "data": { "image/png": "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\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": 30, "id": "41e7e1ee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:Detecting that an object or model or tf.train.Checkpoint is being deleted with unrestored values. See the following logs for the specific values in question. To silence these warnings, use `status.expect_partial()`. See https://www.tensorflow.org/api_docs/python/tf/train/Checkpoint#restorefor details about the status object returned by the restore function.\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.iter\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.beta_1\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.beta_2\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.decay\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.learning_rate\n", "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.momentum_cache\n", "Epoch 1/2500\n", "12/12 [==============================] - 4s 80ms/step - loss: 14.7604 - distribution_lambda_5_loss: 7.3535 - distribution_lambda_6_loss: 6.7090 - distribution_lambda_7_loss: 0.6979 - val_loss: 12.1101 - val_distribution_lambda_5_loss: 6.1507 - val_distribution_lambda_6_loss: 5.3170 - val_distribution_lambda_7_loss: 0.6425\n", "Epoch 2/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 11.1729 - distribution_lambda_5_loss: 5.3710 - distribution_lambda_6_loss: 5.1048 - distribution_lambda_7_loss: 0.6971 - val_loss: 9.4836 - val_distribution_lambda_5_loss: 4.5808 - val_distribution_lambda_6_loss: 4.2683 - val_distribution_lambda_7_loss: 0.6345\n", "Epoch 3/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 9.0293 - distribution_lambda_5_loss: 4.1805 - distribution_lambda_6_loss: 4.1700 - distribution_lambda_7_loss: 0.6787 - val_loss: 8.0017 - val_distribution_lambda_5_loss: 3.7385 - val_distribution_lambda_6_loss: 3.6386 - val_distribution_lambda_7_loss: 0.6246\n", "Epoch 4/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 7.8436 - distribution_lambda_5_loss: 3.5641 - distribution_lambda_6_loss: 3.6071 - distribution_lambda_7_loss: 0.6724 - val_loss: 7.2102 - val_distribution_lambda_5_loss: 3.2992 - val_distribution_lambda_6_loss: 3.2956 - val_distribution_lambda_7_loss: 0.6153\n", "Epoch 5/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 7.1980 - distribution_lambda_5_loss: 3.2289 - distribution_lambda_6_loss: 3.3129 - distribution_lambda_7_loss: 0.6562 - val_loss: 6.7861 - val_distribution_lambda_5_loss: 3.0710 - val_distribution_lambda_6_loss: 3.1081 - val_distribution_lambda_7_loss: 0.6070\n", "Epoch 6/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 6.8153 - distribution_lambda_5_loss: 3.0546 - distribution_lambda_6_loss: 3.1226 - distribution_lambda_7_loss: 0.6381 - val_loss: 6.5470 - val_distribution_lambda_5_loss: 2.9413 - val_distribution_lambda_6_loss: 3.0047 - val_distribution_lambda_7_loss: 0.6010\n", "Epoch 7/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.6171 - distribution_lambda_5_loss: 2.9480 - distribution_lambda_6_loss: 3.0307 - distribution_lambda_7_loss: 0.6384 - val_loss: 6.4026 - val_distribution_lambda_5_loss: 2.8636 - val_distribution_lambda_6_loss: 2.9427 - val_distribution_lambda_7_loss: 0.5962\n", "Epoch 8/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.4642 - distribution_lambda_5_loss: 2.8778 - distribution_lambda_6_loss: 2.9519 - distribution_lambda_7_loss: 0.6346 - val_loss: 6.3068 - val_distribution_lambda_5_loss: 2.8104 - val_distribution_lambda_6_loss: 2.9033 - val_distribution_lambda_7_loss: 0.5932\n", "Epoch 9/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.3437 - distribution_lambda_5_loss: 2.8189 - distribution_lambda_6_loss: 2.9033 - distribution_lambda_7_loss: 0.6216 - val_loss: 6.2352 - val_distribution_lambda_5_loss: 2.7723 - val_distribution_lambda_6_loss: 2.8734 - val_distribution_lambda_7_loss: 0.5895\n", "Epoch 10/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.2853 - distribution_lambda_5_loss: 2.7854 - distribution_lambda_6_loss: 2.8646 - distribution_lambda_7_loss: 0.6353 - val_loss: 6.1806 - val_distribution_lambda_5_loss: 2.7406 - val_distribution_lambda_6_loss: 2.8530 - val_distribution_lambda_7_loss: 0.5870\n", "Epoch 11/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.2554 - distribution_lambda_5_loss: 2.7582 - distribution_lambda_6_loss: 2.8710 - distribution_lambda_7_loss: 0.6262 - val_loss: 6.1310 - val_distribution_lambda_5_loss: 2.7127 - val_distribution_lambda_6_loss: 2.8340 - val_distribution_lambda_7_loss: 0.5844\n", "Epoch 12/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.1727 - distribution_lambda_5_loss: 2.7322 - distribution_lambda_6_loss: 2.8245 - distribution_lambda_7_loss: 0.6161 - val_loss: 6.0854 - val_distribution_lambda_5_loss: 2.6864 - val_distribution_lambda_6_loss: 2.8166 - val_distribution_lambda_7_loss: 0.5824\n", "Epoch 13/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 6.1178 - distribution_lambda_5_loss: 2.6953 - distribution_lambda_6_loss: 2.8064 - distribution_lambda_7_loss: 0.6161 - val_loss: 6.0368 - val_distribution_lambda_5_loss: 2.6614 - val_distribution_lambda_6_loss: 2.7951 - val_distribution_lambda_7_loss: 0.5803\n", "Epoch 14/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 6.0761 - distribution_lambda_5_loss: 2.6726 - distribution_lambda_6_loss: 2.7920 - distribution_lambda_7_loss: 0.6115 - val_loss: 5.9913 - val_distribution_lambda_5_loss: 2.6360 - val_distribution_lambda_6_loss: 2.7770 - val_distribution_lambda_7_loss: 0.5783\n", "Epoch 15/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 6.0046 - distribution_lambda_5_loss: 2.6427 - distribution_lambda_6_loss: 2.7585 - distribution_lambda_7_loss: 0.6034 - val_loss: 5.9446 - val_distribution_lambda_5_loss: 2.6104 - val_distribution_lambda_6_loss: 2.7579 - val_distribution_lambda_7_loss: 0.5763\n", "Epoch 16/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.9628 - distribution_lambda_5_loss: 2.6176 - distribution_lambda_6_loss: 2.7441 - distribution_lambda_7_loss: 0.6011 - val_loss: 5.8978 - val_distribution_lambda_5_loss: 2.5841 - val_distribution_lambda_6_loss: 2.7394 - val_distribution_lambda_7_loss: 0.5743\n", "Epoch 17/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.9200 - distribution_lambda_5_loss: 2.5898 - distribution_lambda_6_loss: 2.7272 - distribution_lambda_7_loss: 0.6029 - val_loss: 5.8483 - val_distribution_lambda_5_loss: 2.5567 - val_distribution_lambda_6_loss: 2.7191 - val_distribution_lambda_7_loss: 0.5725\n", "Epoch 18/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.8701 - distribution_lambda_5_loss: 2.5636 - distribution_lambda_6_loss: 2.7069 - distribution_lambda_7_loss: 0.5997 - val_loss: 5.7991 - val_distribution_lambda_5_loss: 2.5287 - val_distribution_lambda_6_loss: 2.6993 - val_distribution_lambda_7_loss: 0.5712\n", "Epoch 19/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.8382 - distribution_lambda_5_loss: 2.5305 - distribution_lambda_6_loss: 2.7015 - distribution_lambda_7_loss: 0.6062 - val_loss: 5.7486 - val_distribution_lambda_5_loss: 2.5000 - val_distribution_lambda_6_loss: 2.6789 - val_distribution_lambda_7_loss: 0.5697\n", "Epoch 20/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.7968 - distribution_lambda_5_loss: 2.5054 - distribution_lambda_6_loss: 2.6885 - distribution_lambda_7_loss: 0.6029 - val_loss: 5.6952 - val_distribution_lambda_5_loss: 2.4697 - val_distribution_lambda_6_loss: 2.6570 - val_distribution_lambda_7_loss: 0.5685\n", "Epoch 21/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.7312 - distribution_lambda_5_loss: 2.4749 - distribution_lambda_6_loss: 2.6586 - distribution_lambda_7_loss: 0.5977 - val_loss: 5.6417 - val_distribution_lambda_5_loss: 2.4376 - val_distribution_lambda_6_loss: 2.6370 - val_distribution_lambda_7_loss: 0.5672\n", "Epoch 22/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 5.6665 - distribution_lambda_5_loss: 2.4377 - distribution_lambda_6_loss: 2.6381 - distribution_lambda_7_loss: 0.5907 - val_loss: 5.5870 - val_distribution_lambda_5_loss: 2.4033 - val_distribution_lambda_6_loss: 2.6182 - val_distribution_lambda_7_loss: 0.5655\n", "Epoch 23/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.6108 - distribution_lambda_5_loss: 2.4040 - distribution_lambda_6_loss: 2.6132 - distribution_lambda_7_loss: 0.5936 - val_loss: 5.5293 - val_distribution_lambda_5_loss: 2.3659 - val_distribution_lambda_6_loss: 2.5985 - val_distribution_lambda_7_loss: 0.5649\n", "Epoch 24/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.5523 - distribution_lambda_5_loss: 2.3646 - distribution_lambda_6_loss: 2.5892 - distribution_lambda_7_loss: 0.5985 - val_loss: 5.4668 - val_distribution_lambda_5_loss: 2.3249 - val_distribution_lambda_6_loss: 2.5775 - val_distribution_lambda_7_loss: 0.5643\n", "Epoch 25/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.4853 - distribution_lambda_5_loss: 2.3234 - distribution_lambda_6_loss: 2.5736 - distribution_lambda_7_loss: 0.5882 - val_loss: 5.3986 - val_distribution_lambda_5_loss: 2.2792 - val_distribution_lambda_6_loss: 2.5569 - val_distribution_lambda_7_loss: 0.5626\n", "Epoch 26/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 5.4339 - distribution_lambda_5_loss: 2.2765 - distribution_lambda_6_loss: 2.5646 - distribution_lambda_7_loss: 0.5928 - val_loss: 5.3267 - val_distribution_lambda_5_loss: 2.2288 - val_distribution_lambda_6_loss: 2.5364 - val_distribution_lambda_7_loss: 0.5615\n", "Epoch 27/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.3537 - distribution_lambda_5_loss: 2.2266 - distribution_lambda_6_loss: 2.5348 - distribution_lambda_7_loss: 0.5923 - val_loss: 5.2489 - val_distribution_lambda_5_loss: 2.1735 - val_distribution_lambda_6_loss: 2.5146 - val_distribution_lambda_7_loss: 0.5609\n", "Epoch 28/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.2647 - distribution_lambda_5_loss: 2.1690 - distribution_lambda_6_loss: 2.5114 - distribution_lambda_7_loss: 0.5844 - val_loss: 5.1669 - val_distribution_lambda_5_loss: 2.1148 - val_distribution_lambda_6_loss: 2.4919 - val_distribution_lambda_7_loss: 0.5602\n", "Epoch 29/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.1959 - distribution_lambda_5_loss: 2.1094 - distribution_lambda_6_loss: 2.5009 - distribution_lambda_7_loss: 0.5856 - val_loss: 5.0822 - val_distribution_lambda_5_loss: 2.0536 - val_distribution_lambda_6_loss: 2.4675 - val_distribution_lambda_7_loss: 0.5611\n", "Epoch 30/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.1125 - distribution_lambda_5_loss: 2.0511 - distribution_lambda_6_loss: 2.4719 - distribution_lambda_7_loss: 0.5894 - val_loss: 4.9983 - val_distribution_lambda_5_loss: 1.9913 - val_distribution_lambda_6_loss: 2.4454 - val_distribution_lambda_7_loss: 0.5617\n", "Epoch 31/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 5.0260 - distribution_lambda_5_loss: 1.9909 - distribution_lambda_6_loss: 2.4509 - distribution_lambda_7_loss: 0.5842 - val_loss: 4.9159 - val_distribution_lambda_5_loss: 1.9304 - val_distribution_lambda_6_loss: 2.4237 - val_distribution_lambda_7_loss: 0.5618\n", "Epoch 32/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.9230 - distribution_lambda_5_loss: 1.9268 - distribution_lambda_6_loss: 2.4203 - distribution_lambda_7_loss: 0.5759 - val_loss: 4.8309 - val_distribution_lambda_5_loss: 1.8708 - val_distribution_lambda_6_loss: 2.3996 - val_distribution_lambda_7_loss: 0.5604\n", "Epoch 33/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.8393 - distribution_lambda_5_loss: 1.8677 - distribution_lambda_6_loss: 2.3975 - distribution_lambda_7_loss: 0.5741 - val_loss: 4.7490 - val_distribution_lambda_5_loss: 1.8131 - val_distribution_lambda_6_loss: 2.3761 - val_distribution_lambda_7_loss: 0.5598\n", "Epoch 34/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.7824 - distribution_lambda_5_loss: 1.8114 - distribution_lambda_6_loss: 2.3825 - distribution_lambda_7_loss: 0.5885 - val_loss: 4.6694 - val_distribution_lambda_5_loss: 1.7564 - val_distribution_lambda_6_loss: 2.3531 - val_distribution_lambda_7_loss: 0.5600\n", "Epoch 35/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.6961 - distribution_lambda_5_loss: 1.7560 - distribution_lambda_6_loss: 2.3599 - distribution_lambda_7_loss: 0.5802 - val_loss: 4.5908 - val_distribution_lambda_5_loss: 1.7009 - val_distribution_lambda_6_loss: 2.3298 - val_distribution_lambda_7_loss: 0.5600\n", "Epoch 36/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.6126 - distribution_lambda_5_loss: 1.6985 - distribution_lambda_6_loss: 2.3318 - distribution_lambda_7_loss: 0.5823 - val_loss: 4.5135 - val_distribution_lambda_5_loss: 1.6472 - val_distribution_lambda_6_loss: 2.3066 - val_distribution_lambda_7_loss: 0.5597\n", "Epoch 37/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.5339 - distribution_lambda_5_loss: 1.6479 - distribution_lambda_6_loss: 2.3165 - distribution_lambda_7_loss: 0.5695 - val_loss: 4.4370 - val_distribution_lambda_5_loss: 1.5947 - val_distribution_lambda_6_loss: 2.2835 - val_distribution_lambda_7_loss: 0.5588\n", "Epoch 38/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.4675 - distribution_lambda_5_loss: 1.5954 - distribution_lambda_6_loss: 2.2981 - distribution_lambda_7_loss: 0.5740 - val_loss: 4.3619 - val_distribution_lambda_5_loss: 1.5446 - val_distribution_lambda_6_loss: 2.2594 - val_distribution_lambda_7_loss: 0.5579\n", "Epoch 39/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.4010 - distribution_lambda_5_loss: 1.5424 - distribution_lambda_6_loss: 2.2754 - distribution_lambda_7_loss: 0.5831 - val_loss: 4.2914 - val_distribution_lambda_5_loss: 1.4958 - val_distribution_lambda_6_loss: 2.2374 - val_distribution_lambda_7_loss: 0.5582\n", "Epoch 40/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.3301 - distribution_lambda_5_loss: 1.4992 - distribution_lambda_6_loss: 2.2468 - distribution_lambda_7_loss: 0.5841 - val_loss: 4.2237 - val_distribution_lambda_5_loss: 1.4493 - val_distribution_lambda_6_loss: 2.2156 - val_distribution_lambda_7_loss: 0.5589\n", "Epoch 41/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.2535 - distribution_lambda_5_loss: 1.4513 - distribution_lambda_6_loss: 2.2275 - distribution_lambda_7_loss: 0.5747 - val_loss: 4.1582 - val_distribution_lambda_5_loss: 1.4041 - val_distribution_lambda_6_loss: 2.1957 - val_distribution_lambda_7_loss: 0.5585\n", "Epoch 42/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.1966 - distribution_lambda_5_loss: 1.4086 - distribution_lambda_6_loss: 2.2098 - distribution_lambda_7_loss: 0.5782 - val_loss: 4.0939 - val_distribution_lambda_5_loss: 1.3605 - val_distribution_lambda_6_loss: 2.1757 - val_distribution_lambda_7_loss: 0.5577\n", "Epoch 43/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.1313 - distribution_lambda_5_loss: 1.3670 - distribution_lambda_6_loss: 2.1916 - distribution_lambda_7_loss: 0.5727 - val_loss: 4.0329 - val_distribution_lambda_5_loss: 1.3191 - val_distribution_lambda_6_loss: 2.1568 - val_distribution_lambda_7_loss: 0.5571\n", "Epoch 44/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.0969 - distribution_lambda_5_loss: 1.3324 - distribution_lambda_6_loss: 2.1824 - distribution_lambda_7_loss: 0.5820 - val_loss: 3.9778 - val_distribution_lambda_5_loss: 1.2800 - val_distribution_lambda_6_loss: 2.1400 - val_distribution_lambda_7_loss: 0.5579\n", "Epoch 45/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 4.0388 - distribution_lambda_5_loss: 1.2894 - distribution_lambda_6_loss: 2.1766 - distribution_lambda_7_loss: 0.5728 - val_loss: 3.9233 - val_distribution_lambda_5_loss: 1.2419 - val_distribution_lambda_6_loss: 2.1233 - val_distribution_lambda_7_loss: 0.5581\n", "Epoch 46/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 3.9562 - distribution_lambda_5_loss: 1.2550 - distribution_lambda_6_loss: 2.1281 - distribution_lambda_7_loss: 0.5731 - val_loss: 3.8713 - val_distribution_lambda_5_loss: 1.2049 - val_distribution_lambda_6_loss: 2.1083 - val_distribution_lambda_7_loss: 0.5580\n", "Epoch 47/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.9115 - distribution_lambda_5_loss: 1.2199 - distribution_lambda_6_loss: 2.1140 - distribution_lambda_7_loss: 0.5776 - val_loss: 3.8218 - val_distribution_lambda_5_loss: 1.1688 - val_distribution_lambda_6_loss: 2.0952 - val_distribution_lambda_7_loss: 0.5578\n", "Epoch 48/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.8719 - distribution_lambda_5_loss: 1.1901 - distribution_lambda_6_loss: 2.1102 - distribution_lambda_7_loss: 0.5716 - val_loss: 3.7723 - val_distribution_lambda_5_loss: 1.1335 - val_distribution_lambda_6_loss: 2.0816 - val_distribution_lambda_7_loss: 0.5572\n", "Epoch 49/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.8225 - distribution_lambda_5_loss: 1.1527 - distribution_lambda_6_loss: 2.0901 - distribution_lambda_7_loss: 0.5797 - val_loss: 3.7242 - val_distribution_lambda_5_loss: 1.0991 - val_distribution_lambda_6_loss: 2.0680 - val_distribution_lambda_7_loss: 0.5570\n", "Epoch 50/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.7799 - distribution_lambda_5_loss: 1.1191 - distribution_lambda_6_loss: 2.0818 - distribution_lambda_7_loss: 0.5790 - val_loss: 3.6787 - val_distribution_lambda_5_loss: 1.0660 - val_distribution_lambda_6_loss: 2.0557 - val_distribution_lambda_7_loss: 0.5570\n", "Epoch 51/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.7149 - distribution_lambda_5_loss: 1.0828 - distribution_lambda_6_loss: 2.0570 - distribution_lambda_7_loss: 0.5752 - val_loss: 3.6349 - val_distribution_lambda_5_loss: 1.0334 - val_distribution_lambda_6_loss: 2.0448 - val_distribution_lambda_7_loss: 0.5567\n", "Epoch 52/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.6888 - distribution_lambda_5_loss: 1.0519 - distribution_lambda_6_loss: 2.0577 - distribution_lambda_7_loss: 0.5793 - val_loss: 3.5938 - val_distribution_lambda_5_loss: 1.0017 - val_distribution_lambda_6_loss: 2.0355 - val_distribution_lambda_7_loss: 0.5566\n", "Epoch 53/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.6366 - distribution_lambda_5_loss: 1.0202 - distribution_lambda_6_loss: 2.0430 - distribution_lambda_7_loss: 0.5734 - val_loss: 3.5555 - val_distribution_lambda_5_loss: 0.9715 - val_distribution_lambda_6_loss: 2.0275 - val_distribution_lambda_7_loss: 0.5565\n", "Epoch 54/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.6053 - distribution_lambda_5_loss: 0.9987 - distribution_lambda_6_loss: 2.0324 - distribution_lambda_7_loss: 0.5742 - val_loss: 3.5163 - val_distribution_lambda_5_loss: 0.9432 - val_distribution_lambda_6_loss: 2.0174 - val_distribution_lambda_7_loss: 0.5556\n", "Epoch 55/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.5597 - distribution_lambda_5_loss: 0.9746 - distribution_lambda_6_loss: 2.0217 - distribution_lambda_7_loss: 0.5634 - val_loss: 3.4795 - val_distribution_lambda_5_loss: 0.9163 - val_distribution_lambda_6_loss: 2.0088 - val_distribution_lambda_7_loss: 0.5545\n", "Epoch 56/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.5533 - distribution_lambda_5_loss: 0.9586 - distribution_lambda_6_loss: 2.0219 - distribution_lambda_7_loss: 0.5728 - val_loss: 3.4496 - val_distribution_lambda_5_loss: 0.8923 - val_distribution_lambda_6_loss: 2.0016 - val_distribution_lambda_7_loss: 0.5557\n", "Epoch 57/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.5218 - distribution_lambda_5_loss: 0.9309 - distribution_lambda_6_loss: 2.0212 - distribution_lambda_7_loss: 0.5697 - val_loss: 3.4177 - val_distribution_lambda_5_loss: 0.8698 - val_distribution_lambda_6_loss: 1.9931 - val_distribution_lambda_7_loss: 0.5548\n", "Epoch 58/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.4684 - distribution_lambda_5_loss: 0.9049 - distribution_lambda_6_loss: 2.0021 - distribution_lambda_7_loss: 0.5614 - val_loss: 3.3879 - val_distribution_lambda_5_loss: 0.8480 - val_distribution_lambda_6_loss: 1.9856 - val_distribution_lambda_7_loss: 0.5543\n", "Epoch 59/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.4592 - distribution_lambda_5_loss: 0.8903 - distribution_lambda_6_loss: 1.9961 - distribution_lambda_7_loss: 0.5728 - val_loss: 3.3603 - val_distribution_lambda_5_loss: 0.8268 - val_distribution_lambda_6_loss: 1.9783 - val_distribution_lambda_7_loss: 0.5552\n", "Epoch 60/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.4450 - distribution_lambda_5_loss: 0.8751 - distribution_lambda_6_loss: 1.9994 - distribution_lambda_7_loss: 0.5705 - val_loss: 3.3339 - val_distribution_lambda_5_loss: 0.8072 - val_distribution_lambda_6_loss: 1.9719 - val_distribution_lambda_7_loss: 0.5548\n", "Epoch 61/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.3990 - distribution_lambda_5_loss: 0.8569 - distribution_lambda_6_loss: 1.9742 - distribution_lambda_7_loss: 0.5680 - val_loss: 3.3080 - val_distribution_lambda_5_loss: 0.7881 - val_distribution_lambda_6_loss: 1.9655 - val_distribution_lambda_7_loss: 0.5545\n", "Epoch 62/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.3794 - distribution_lambda_5_loss: 0.8383 - distribution_lambda_6_loss: 1.9727 - distribution_lambda_7_loss: 0.5683 - val_loss: 3.2814 - val_distribution_lambda_5_loss: 0.7696 - val_distribution_lambda_6_loss: 1.9576 - val_distribution_lambda_7_loss: 0.5541\n", "Epoch 63/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.3512 - distribution_lambda_5_loss: 0.8154 - distribution_lambda_6_loss: 1.9638 - distribution_lambda_7_loss: 0.5720 - val_loss: 3.2563 - val_distribution_lambda_5_loss: 0.7510 - val_distribution_lambda_6_loss: 1.9516 - val_distribution_lambda_7_loss: 0.5537\n", "Epoch 64/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.3164 - distribution_lambda_5_loss: 0.7990 - distribution_lambda_6_loss: 1.9493 - distribution_lambda_7_loss: 0.5681 - val_loss: 3.2347 - val_distribution_lambda_5_loss: 0.7343 - val_distribution_lambda_6_loss: 1.9462 - val_distribution_lambda_7_loss: 0.5542\n", "Epoch 65/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.3119 - distribution_lambda_5_loss: 0.7921 - distribution_lambda_6_loss: 1.9490 - distribution_lambda_7_loss: 0.5708 - val_loss: 3.2165 - val_distribution_lambda_5_loss: 0.7217 - val_distribution_lambda_6_loss: 1.9404 - val_distribution_lambda_7_loss: 0.5544\n", "Epoch 66/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.2947 - distribution_lambda_5_loss: 0.7781 - distribution_lambda_6_loss: 1.9459 - distribution_lambda_7_loss: 0.5707 - val_loss: 3.1987 - val_distribution_lambda_5_loss: 0.7120 - val_distribution_lambda_6_loss: 1.9333 - val_distribution_lambda_7_loss: 0.5534\n", "Epoch 67/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.2752 - distribution_lambda_5_loss: 0.7618 - distribution_lambda_6_loss: 1.9411 - distribution_lambda_7_loss: 0.5724 - val_loss: 3.1808 - val_distribution_lambda_5_loss: 0.7026 - val_distribution_lambda_6_loss: 1.9252 - val_distribution_lambda_7_loss: 0.5530\n", "Epoch 68/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.2565 - distribution_lambda_5_loss: 0.7578 - distribution_lambda_6_loss: 1.9225 - distribution_lambda_7_loss: 0.5762 - val_loss: 3.1676 - val_distribution_lambda_5_loss: 0.6950 - val_distribution_lambda_6_loss: 1.9193 - val_distribution_lambda_7_loss: 0.5532\n", "Epoch 69/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.2277 - distribution_lambda_5_loss: 0.7400 - distribution_lambda_6_loss: 1.9256 - distribution_lambda_7_loss: 0.5621 - val_loss: 3.1515 - val_distribution_lambda_5_loss: 0.6880 - val_distribution_lambda_6_loss: 1.9116 - val_distribution_lambda_7_loss: 0.5519\n", "Epoch 70/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 3.2046 - distribution_lambda_5_loss: 0.7307 - distribution_lambda_6_loss: 1.9110 - distribution_lambda_7_loss: 0.5628 - val_loss: 3.1392 - val_distribution_lambda_5_loss: 0.6821 - val_distribution_lambda_6_loss: 1.9070 - val_distribution_lambda_7_loss: 0.5502\n", "Epoch 71/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.2007 - distribution_lambda_5_loss: 0.7315 - distribution_lambda_6_loss: 1.8950 - distribution_lambda_7_loss: 0.5743 - val_loss: 3.1303 - val_distribution_lambda_5_loss: 0.6774 - val_distribution_lambda_6_loss: 1.9029 - val_distribution_lambda_7_loss: 0.5500\n", "Epoch 72/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1805 - distribution_lambda_5_loss: 0.7238 - distribution_lambda_6_loss: 1.8897 - distribution_lambda_7_loss: 0.5670 - val_loss: 3.1215 - val_distribution_lambda_5_loss: 0.6730 - val_distribution_lambda_6_loss: 1.8983 - val_distribution_lambda_7_loss: 0.5502\n", "Epoch 73/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1985 - distribution_lambda_5_loss: 0.7268 - distribution_lambda_6_loss: 1.9092 - distribution_lambda_7_loss: 0.5626 - val_loss: 3.1100 - val_distribution_lambda_5_loss: 0.6695 - val_distribution_lambda_6_loss: 1.8896 - val_distribution_lambda_7_loss: 0.5509\n", "Epoch 74/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.1899 - distribution_lambda_5_loss: 0.7176 - distribution_lambda_6_loss: 1.9100 - distribution_lambda_7_loss: 0.5623 - val_loss: 3.0987 - val_distribution_lambda_5_loss: 0.6666 - val_distribution_lambda_6_loss: 1.8820 - val_distribution_lambda_7_loss: 0.5500\n", "Epoch 75/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.1621 - distribution_lambda_5_loss: 0.7223 - distribution_lambda_6_loss: 1.8752 - distribution_lambda_7_loss: 0.5646 - val_loss: 3.0892 - val_distribution_lambda_5_loss: 0.6641 - val_distribution_lambda_6_loss: 1.8752 - val_distribution_lambda_7_loss: 0.5500\n", "Epoch 76/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.1533 - distribution_lambda_5_loss: 0.7186 - distribution_lambda_6_loss: 1.8636 - distribution_lambda_7_loss: 0.5711 - val_loss: 3.0798 - val_distribution_lambda_5_loss: 0.6607 - val_distribution_lambda_6_loss: 1.8689 - val_distribution_lambda_7_loss: 0.5501\n", "Epoch 77/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1419 - distribution_lambda_5_loss: 0.7061 - distribution_lambda_6_loss: 1.8719 - distribution_lambda_7_loss: 0.5639 - val_loss: 3.0692 - val_distribution_lambda_5_loss: 0.6588 - val_distribution_lambda_6_loss: 1.8614 - val_distribution_lambda_7_loss: 0.5490\n", "Epoch 78/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1355 - distribution_lambda_5_loss: 0.6982 - distribution_lambda_6_loss: 1.8712 - distribution_lambda_7_loss: 0.5661 - val_loss: 3.0605 - val_distribution_lambda_5_loss: 0.6570 - val_distribution_lambda_6_loss: 1.8546 - val_distribution_lambda_7_loss: 0.5489\n", "Epoch 79/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1185 - distribution_lambda_5_loss: 0.6911 - distribution_lambda_6_loss: 1.8625 - distribution_lambda_7_loss: 0.5649 - val_loss: 3.0537 - val_distribution_lambda_5_loss: 0.6559 - val_distribution_lambda_6_loss: 1.8493 - val_distribution_lambda_7_loss: 0.5485\n", "Epoch 80/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.1031 - distribution_lambda_5_loss: 0.6918 - distribution_lambda_6_loss: 1.8472 - distribution_lambda_7_loss: 0.5641 - val_loss: 3.0477 - val_distribution_lambda_5_loss: 0.6548 - val_distribution_lambda_6_loss: 1.8451 - val_distribution_lambda_7_loss: 0.5478\n", "Epoch 81/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.1080 - distribution_lambda_5_loss: 0.6934 - distribution_lambda_6_loss: 1.8497 - distribution_lambda_7_loss: 0.5650 - val_loss: 3.0382 - val_distribution_lambda_5_loss: 0.6530 - val_distribution_lambda_6_loss: 1.8382 - val_distribution_lambda_7_loss: 0.5471\n", "Epoch 82/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0745 - distribution_lambda_5_loss: 0.6767 - distribution_lambda_6_loss: 1.8330 - distribution_lambda_7_loss: 0.5647 - val_loss: 3.0306 - val_distribution_lambda_5_loss: 0.6524 - val_distribution_lambda_6_loss: 1.8318 - val_distribution_lambda_7_loss: 0.5464\n", "Epoch 83/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0738 - distribution_lambda_5_loss: 0.6847 - distribution_lambda_6_loss: 1.8313 - distribution_lambda_7_loss: 0.5577 - val_loss: 3.0232 - val_distribution_lambda_5_loss: 0.6518 - val_distribution_lambda_6_loss: 1.8255 - val_distribution_lambda_7_loss: 0.5459\n", "Epoch 84/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0691 - distribution_lambda_5_loss: 0.6761 - distribution_lambda_6_loss: 1.8284 - distribution_lambda_7_loss: 0.5646 - val_loss: 3.0161 - val_distribution_lambda_5_loss: 0.6514 - val_distribution_lambda_6_loss: 1.8189 - val_distribution_lambda_7_loss: 0.5458\n", "Epoch 85/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0572 - distribution_lambda_5_loss: 0.6679 - distribution_lambda_6_loss: 1.8273 - distribution_lambda_7_loss: 0.5620 - val_loss: 3.0087 - val_distribution_lambda_5_loss: 0.6503 - val_distribution_lambda_6_loss: 1.8125 - val_distribution_lambda_7_loss: 0.5459\n", "Epoch 86/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0501 - distribution_lambda_5_loss: 0.6789 - distribution_lambda_6_loss: 1.8029 - distribution_lambda_7_loss: 0.5682 - val_loss: 2.9998 - val_distribution_lambda_5_loss: 0.6493 - val_distribution_lambda_6_loss: 1.8048 - val_distribution_lambda_7_loss: 0.5457\n", "Epoch 87/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 3.0360 - distribution_lambda_5_loss: 0.6659 - distribution_lambda_6_loss: 1.8017 - distribution_lambda_7_loss: 0.5684 - val_loss: 2.9940 - val_distribution_lambda_5_loss: 0.6478 - val_distribution_lambda_6_loss: 1.8006 - val_distribution_lambda_7_loss: 0.5456\n", "Epoch 88/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.0367 - distribution_lambda_5_loss: 0.6767 - distribution_lambda_6_loss: 1.8059 - distribution_lambda_7_loss: 0.5542 - val_loss: 2.9867 - val_distribution_lambda_5_loss: 0.6474 - val_distribution_lambda_6_loss: 1.7953 - val_distribution_lambda_7_loss: 0.5440\n", "Epoch 89/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.0315 - distribution_lambda_5_loss: 0.6738 - distribution_lambda_6_loss: 1.8010 - distribution_lambda_7_loss: 0.5567 - val_loss: 2.9821 - val_distribution_lambda_5_loss: 0.6463 - val_distribution_lambda_6_loss: 1.7924 - val_distribution_lambda_7_loss: 0.5434\n", "Epoch 90/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 3.0072 - distribution_lambda_5_loss: 0.6600 - distribution_lambda_6_loss: 1.7907 - distribution_lambda_7_loss: 0.5566 - val_loss: 2.9710 - val_distribution_lambda_5_loss: 0.6446 - val_distribution_lambda_6_loss: 1.7828 - val_distribution_lambda_7_loss: 0.5437\n", "Epoch 91/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.9924 - distribution_lambda_5_loss: 0.6572 - distribution_lambda_6_loss: 1.7812 - distribution_lambda_7_loss: 0.5540 - val_loss: 2.9657 - val_distribution_lambda_5_loss: 0.6443 - val_distribution_lambda_6_loss: 1.7787 - val_distribution_lambda_7_loss: 0.5427\n", "Epoch 92/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9960 - distribution_lambda_5_loss: 0.6586 - distribution_lambda_6_loss: 1.7838 - distribution_lambda_7_loss: 0.5537 - val_loss: 2.9602 - val_distribution_lambda_5_loss: 0.6433 - val_distribution_lambda_6_loss: 1.7749 - val_distribution_lambda_7_loss: 0.5420\n", "Epoch 93/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9987 - distribution_lambda_5_loss: 0.6607 - distribution_lambda_6_loss: 1.7735 - distribution_lambda_7_loss: 0.5645 - val_loss: 2.9564 - val_distribution_lambda_5_loss: 0.6420 - val_distribution_lambda_6_loss: 1.7719 - val_distribution_lambda_7_loss: 0.5425\n", "Epoch 94/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.9916 - distribution_lambda_5_loss: 0.6550 - distribution_lambda_6_loss: 1.7694 - distribution_lambda_7_loss: 0.5672 - val_loss: 2.9519 - val_distribution_lambda_5_loss: 0.6408 - val_distribution_lambda_6_loss: 1.7675 - val_distribution_lambda_7_loss: 0.5435\n", "Epoch 95/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9547 - distribution_lambda_5_loss: 0.6414 - distribution_lambda_6_loss: 1.7526 - distribution_lambda_7_loss: 0.5607 - val_loss: 2.9467 - val_distribution_lambda_5_loss: 0.6398 - val_distribution_lambda_6_loss: 1.7644 - val_distribution_lambda_7_loss: 0.5425\n", "Epoch 96/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9603 - distribution_lambda_5_loss: 0.6371 - distribution_lambda_6_loss: 1.7587 - distribution_lambda_7_loss: 0.5645 - val_loss: 2.9390 - val_distribution_lambda_5_loss: 0.6386 - val_distribution_lambda_6_loss: 1.7576 - val_distribution_lambda_7_loss: 0.5428\n", "Epoch 97/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9605 - distribution_lambda_5_loss: 0.6493 - distribution_lambda_6_loss: 1.7525 - distribution_lambda_7_loss: 0.5587 - val_loss: 2.9334 - val_distribution_lambda_5_loss: 0.6378 - val_distribution_lambda_6_loss: 1.7534 - val_distribution_lambda_7_loss: 0.5422\n", "Epoch 98/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9663 - distribution_lambda_5_loss: 0.6438 - distribution_lambda_6_loss: 1.7522 - distribution_lambda_7_loss: 0.5703 - val_loss: 2.9294 - val_distribution_lambda_5_loss: 0.6370 - val_distribution_lambda_6_loss: 1.7493 - val_distribution_lambda_7_loss: 0.5432\n", "Epoch 99/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9429 - distribution_lambda_5_loss: 0.6455 - distribution_lambda_6_loss: 1.7339 - distribution_lambda_7_loss: 0.5635 - val_loss: 2.9223 - val_distribution_lambda_5_loss: 0.6364 - val_distribution_lambda_6_loss: 1.7433 - val_distribution_lambda_7_loss: 0.5426\n", "Epoch 100/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9426 - distribution_lambda_5_loss: 0.6388 - distribution_lambda_6_loss: 1.7377 - distribution_lambda_7_loss: 0.5660 - val_loss: 2.9185 - val_distribution_lambda_5_loss: 0.6360 - val_distribution_lambda_6_loss: 1.7393 - val_distribution_lambda_7_loss: 0.5432\n", "Epoch 101/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9262 - distribution_lambda_5_loss: 0.6452 - distribution_lambda_6_loss: 1.7258 - distribution_lambda_7_loss: 0.5553 - val_loss: 2.9111 - val_distribution_lambda_5_loss: 0.6349 - val_distribution_lambda_6_loss: 1.7333 - val_distribution_lambda_7_loss: 0.5429\n", "Epoch 102/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9395 - distribution_lambda_5_loss: 0.6491 - distribution_lambda_6_loss: 1.7248 - distribution_lambda_7_loss: 0.5656 - val_loss: 2.9103 - val_distribution_lambda_5_loss: 0.6366 - val_distribution_lambda_6_loss: 1.7304 - val_distribution_lambda_7_loss: 0.5433\n", "Epoch 103/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9080 - distribution_lambda_5_loss: 0.6384 - distribution_lambda_6_loss: 1.7122 - distribution_lambda_7_loss: 0.5575 - val_loss: 2.9084 - val_distribution_lambda_5_loss: 0.6365 - val_distribution_lambda_6_loss: 1.7293 - val_distribution_lambda_7_loss: 0.5426\n", "Epoch 104/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.9211 - distribution_lambda_5_loss: 0.6383 - distribution_lambda_6_loss: 1.7238 - distribution_lambda_7_loss: 0.5590 - val_loss: 2.8948 - val_distribution_lambda_5_loss: 0.6339 - val_distribution_lambda_6_loss: 1.7192 - val_distribution_lambda_7_loss: 0.5417\n", "Epoch 105/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9020 - distribution_lambda_5_loss: 0.6437 - distribution_lambda_6_loss: 1.7061 - distribution_lambda_7_loss: 0.5522 - val_loss: 2.8854 - val_distribution_lambda_5_loss: 0.6333 - val_distribution_lambda_6_loss: 1.7119 - val_distribution_lambda_7_loss: 0.5402\n", "Epoch 106/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.9069 - distribution_lambda_5_loss: 0.6523 - distribution_lambda_6_loss: 1.6969 - distribution_lambda_7_loss: 0.5578 - val_loss: 2.8807 - val_distribution_lambda_5_loss: 0.6314 - val_distribution_lambda_6_loss: 1.7099 - val_distribution_lambda_7_loss: 0.5395\n", "Epoch 107/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8878 - distribution_lambda_5_loss: 0.6341 - distribution_lambda_6_loss: 1.6971 - distribution_lambda_7_loss: 0.5565 - val_loss: 2.8765 - val_distribution_lambda_5_loss: 0.6314 - val_distribution_lambda_6_loss: 1.7048 - val_distribution_lambda_7_loss: 0.5403\n", "Epoch 108/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8703 - distribution_lambda_5_loss: 0.6271 - distribution_lambda_6_loss: 1.6908 - distribution_lambda_7_loss: 0.5525 - val_loss: 2.8727 - val_distribution_lambda_5_loss: 0.6303 - val_distribution_lambda_6_loss: 1.7014 - val_distribution_lambda_7_loss: 0.5410\n", "Epoch 109/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8731 - distribution_lambda_5_loss: 0.6417 - distribution_lambda_6_loss: 1.6777 - distribution_lambda_7_loss: 0.5536 - val_loss: 2.8728 - val_distribution_lambda_5_loss: 0.6321 - val_distribution_lambda_6_loss: 1.6998 - val_distribution_lambda_7_loss: 0.5409\n", "Epoch 110/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8729 - distribution_lambda_5_loss: 0.6319 - distribution_lambda_6_loss: 1.6922 - distribution_lambda_7_loss: 0.5488 - val_loss: 2.8642 - val_distribution_lambda_5_loss: 0.6297 - val_distribution_lambda_6_loss: 1.6949 - val_distribution_lambda_7_loss: 0.5396\n", "Epoch 111/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8590 - distribution_lambda_5_loss: 0.6347 - distribution_lambda_6_loss: 1.6713 - distribution_lambda_7_loss: 0.5531 - val_loss: 2.8688 - val_distribution_lambda_5_loss: 0.6290 - val_distribution_lambda_6_loss: 1.7004 - val_distribution_lambda_7_loss: 0.5394\n", "Epoch 112/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8447 - distribution_lambda_5_loss: 0.6183 - distribution_lambda_6_loss: 1.6740 - distribution_lambda_7_loss: 0.5524 - val_loss: 2.8578 - val_distribution_lambda_5_loss: 0.6261 - val_distribution_lambda_6_loss: 1.6929 - val_distribution_lambda_7_loss: 0.5388\n", "Epoch 113/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8725 - distribution_lambda_5_loss: 0.6337 - distribution_lambda_6_loss: 1.6787 - distribution_lambda_7_loss: 0.5601 - val_loss: 2.8544 - val_distribution_lambda_5_loss: 0.6278 - val_distribution_lambda_6_loss: 1.6871 - val_distribution_lambda_7_loss: 0.5395\n", "Epoch 114/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8576 - distribution_lambda_5_loss: 0.6319 - distribution_lambda_6_loss: 1.6731 - distribution_lambda_7_loss: 0.5526 - val_loss: 2.8498 - val_distribution_lambda_5_loss: 0.6263 - val_distribution_lambda_6_loss: 1.6832 - val_distribution_lambda_7_loss: 0.5403\n", "Epoch 115/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8395 - distribution_lambda_5_loss: 0.6247 - distribution_lambda_6_loss: 1.6596 - distribution_lambda_7_loss: 0.5552 - val_loss: 2.8579 - val_distribution_lambda_5_loss: 0.6293 - val_distribution_lambda_6_loss: 1.6886 - val_distribution_lambda_7_loss: 0.5401\n", "Epoch 116/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8272 - distribution_lambda_5_loss: 0.6213 - distribution_lambda_6_loss: 1.6582 - distribution_lambda_7_loss: 0.5477 - val_loss: 2.8455 - val_distribution_lambda_5_loss: 0.6259 - val_distribution_lambda_6_loss: 1.6802 - val_distribution_lambda_7_loss: 0.5394\n", "Epoch 117/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8369 - distribution_lambda_5_loss: 0.6302 - distribution_lambda_6_loss: 1.6564 - distribution_lambda_7_loss: 0.5504 - val_loss: 2.8354 - val_distribution_lambda_5_loss: 0.6227 - val_distribution_lambda_6_loss: 1.6732 - val_distribution_lambda_7_loss: 0.5395\n", "Epoch 118/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.8547 - distribution_lambda_5_loss: 0.6273 - distribution_lambda_6_loss: 1.6663 - distribution_lambda_7_loss: 0.5611 - val_loss: 2.8411 - val_distribution_lambda_5_loss: 0.6233 - val_distribution_lambda_6_loss: 1.6775 - val_distribution_lambda_7_loss: 0.5403\n", "Epoch 119/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8207 - distribution_lambda_5_loss: 0.6149 - distribution_lambda_6_loss: 1.6550 - distribution_lambda_7_loss: 0.5508 - val_loss: 2.8273 - val_distribution_lambda_5_loss: 0.6230 - val_distribution_lambda_6_loss: 1.6650 - val_distribution_lambda_7_loss: 0.5393\n", "Epoch 120/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8210 - distribution_lambda_5_loss: 0.6295 - distribution_lambda_6_loss: 1.6406 - distribution_lambda_7_loss: 0.5508 - val_loss: 2.8314 - val_distribution_lambda_5_loss: 0.6232 - val_distribution_lambda_6_loss: 1.6692 - val_distribution_lambda_7_loss: 0.5390\n", "Epoch 121/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7992 - distribution_lambda_5_loss: 0.6161 - distribution_lambda_6_loss: 1.6357 - distribution_lambda_7_loss: 0.5474 - val_loss: 2.8313 - val_distribution_lambda_5_loss: 0.6227 - val_distribution_lambda_6_loss: 1.6695 - val_distribution_lambda_7_loss: 0.5391\n", "Epoch 122/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8297 - distribution_lambda_5_loss: 0.6242 - distribution_lambda_6_loss: 1.6511 - distribution_lambda_7_loss: 0.5544 - val_loss: 2.8355 - val_distribution_lambda_5_loss: 0.6266 - val_distribution_lambda_6_loss: 1.6693 - val_distribution_lambda_7_loss: 0.5396\n", "Epoch 123/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.8020 - distribution_lambda_5_loss: 0.6080 - distribution_lambda_6_loss: 1.6410 - distribution_lambda_7_loss: 0.5530 - val_loss: 2.8260 - val_distribution_lambda_5_loss: 0.6225 - val_distribution_lambda_6_loss: 1.6640 - val_distribution_lambda_7_loss: 0.5395\n", "Epoch 124/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7879 - distribution_lambda_5_loss: 0.6057 - distribution_lambda_6_loss: 1.6208 - distribution_lambda_7_loss: 0.5614 - val_loss: 2.8248 - val_distribution_lambda_5_loss: 0.6236 - val_distribution_lambda_6_loss: 1.6618 - val_distribution_lambda_7_loss: 0.5394\n", "Epoch 125/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.8028 - distribution_lambda_5_loss: 0.6138 - distribution_lambda_6_loss: 1.6311 - distribution_lambda_7_loss: 0.5578 - val_loss: 2.8144 - val_distribution_lambda_5_loss: 0.6196 - val_distribution_lambda_6_loss: 1.6555 - val_distribution_lambda_7_loss: 0.5393\n", "Epoch 126/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7840 - distribution_lambda_5_loss: 0.6074 - distribution_lambda_6_loss: 1.6242 - distribution_lambda_7_loss: 0.5525 - val_loss: 2.8126 - val_distribution_lambda_5_loss: 0.6208 - val_distribution_lambda_6_loss: 1.6535 - val_distribution_lambda_7_loss: 0.5383\n", "Epoch 127/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7804 - distribution_lambda_5_loss: 0.6056 - distribution_lambda_6_loss: 1.6281 - distribution_lambda_7_loss: 0.5467 - val_loss: 2.8056 - val_distribution_lambda_5_loss: 0.6190 - val_distribution_lambda_6_loss: 1.6496 - val_distribution_lambda_7_loss: 0.5370\n", "Epoch 128/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7843 - distribution_lambda_5_loss: 0.6185 - distribution_lambda_6_loss: 1.6160 - distribution_lambda_7_loss: 0.5498 - val_loss: 2.7969 - val_distribution_lambda_5_loss: 0.6180 - val_distribution_lambda_6_loss: 1.6431 - val_distribution_lambda_7_loss: 0.5358\n", "Epoch 129/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7802 - distribution_lambda_5_loss: 0.5962 - distribution_lambda_6_loss: 1.6208 - distribution_lambda_7_loss: 0.5633 - val_loss: 2.8009 - val_distribution_lambda_5_loss: 0.6181 - val_distribution_lambda_6_loss: 1.6469 - val_distribution_lambda_7_loss: 0.5360\n", "Epoch 130/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7755 - distribution_lambda_5_loss: 0.5955 - distribution_lambda_6_loss: 1.6279 - distribution_lambda_7_loss: 0.5521 - val_loss: 2.8003 - val_distribution_lambda_5_loss: 0.6216 - val_distribution_lambda_6_loss: 1.6425 - val_distribution_lambda_7_loss: 0.5363\n", "Epoch 131/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7762 - distribution_lambda_5_loss: 0.6055 - distribution_lambda_6_loss: 1.6128 - distribution_lambda_7_loss: 0.5578 - val_loss: 2.7917 - val_distribution_lambda_5_loss: 0.6166 - val_distribution_lambda_6_loss: 1.6382 - val_distribution_lambda_7_loss: 0.5370\n", "Epoch 132/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7924 - distribution_lambda_5_loss: 0.6140 - distribution_lambda_6_loss: 1.6246 - distribution_lambda_7_loss: 0.5538 - val_loss: 2.7918 - val_distribution_lambda_5_loss: 0.6149 - val_distribution_lambda_6_loss: 1.6389 - val_distribution_lambda_7_loss: 0.5380\n", "Epoch 133/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7754 - distribution_lambda_5_loss: 0.6011 - distribution_lambda_6_loss: 1.6263 - distribution_lambda_7_loss: 0.5480 - val_loss: 2.7816 - val_distribution_lambda_5_loss: 0.6134 - val_distribution_lambda_6_loss: 1.6316 - val_distribution_lambda_7_loss: 0.5366\n", "Epoch 134/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7774 - distribution_lambda_5_loss: 0.6003 - distribution_lambda_6_loss: 1.6167 - distribution_lambda_7_loss: 0.5605 - val_loss: 2.7879 - val_distribution_lambda_5_loss: 0.6162 - val_distribution_lambda_6_loss: 1.6352 - val_distribution_lambda_7_loss: 0.5364\n", "Epoch 135/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7549 - distribution_lambda_5_loss: 0.6018 - distribution_lambda_6_loss: 1.5988 - distribution_lambda_7_loss: 0.5543 - val_loss: 2.7920 - val_distribution_lambda_5_loss: 0.6144 - val_distribution_lambda_6_loss: 1.6417 - val_distribution_lambda_7_loss: 0.5359\n", "Epoch 136/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7517 - distribution_lambda_5_loss: 0.5994 - distribution_lambda_6_loss: 1.5996 - distribution_lambda_7_loss: 0.5527 - val_loss: 2.7949 - val_distribution_lambda_5_loss: 0.6155 - val_distribution_lambda_6_loss: 1.6438 - val_distribution_lambda_7_loss: 0.5356\n", "Epoch 137/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7176 - distribution_lambda_5_loss: 0.5893 - distribution_lambda_6_loss: 1.5877 - distribution_lambda_7_loss: 0.5406 - val_loss: 2.7821 - val_distribution_lambda_5_loss: 0.6150 - val_distribution_lambda_6_loss: 1.6321 - val_distribution_lambda_7_loss: 0.5350\n", "Epoch 138/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7369 - distribution_lambda_5_loss: 0.5894 - distribution_lambda_6_loss: 1.5984 - distribution_lambda_7_loss: 0.5491 - val_loss: 2.7740 - val_distribution_lambda_5_loss: 0.6129 - val_distribution_lambda_6_loss: 1.6263 - val_distribution_lambda_7_loss: 0.5347\n", "Epoch 139/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7628 - distribution_lambda_5_loss: 0.5868 - distribution_lambda_6_loss: 1.6181 - distribution_lambda_7_loss: 0.5579 - val_loss: 2.7682 - val_distribution_lambda_5_loss: 0.6108 - val_distribution_lambda_6_loss: 1.6231 - val_distribution_lambda_7_loss: 0.5343\n", "Epoch 140/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7354 - distribution_lambda_5_loss: 0.5906 - distribution_lambda_6_loss: 1.5918 - distribution_lambda_7_loss: 0.5530 - val_loss: 2.7777 - val_distribution_lambda_5_loss: 0.6117 - val_distribution_lambda_6_loss: 1.6308 - val_distribution_lambda_7_loss: 0.5352\n", "Epoch 141/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7343 - distribution_lambda_5_loss: 0.5913 - distribution_lambda_6_loss: 1.5897 - distribution_lambda_7_loss: 0.5533 - val_loss: 2.7737 - val_distribution_lambda_5_loss: 0.6107 - val_distribution_lambda_6_loss: 1.6281 - val_distribution_lambda_7_loss: 0.5349\n", "Epoch 142/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.7420 - distribution_lambda_5_loss: 0.5968 - distribution_lambda_6_loss: 1.5971 - distribution_lambda_7_loss: 0.5481 - val_loss: 2.7672 - val_distribution_lambda_5_loss: 0.6111 - val_distribution_lambda_6_loss: 1.6223 - val_distribution_lambda_7_loss: 0.5338\n", "Epoch 143/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.7179 - distribution_lambda_5_loss: 0.5893 - distribution_lambda_6_loss: 1.5837 - distribution_lambda_7_loss: 0.5449 - val_loss: 2.7670 - val_distribution_lambda_5_loss: 0.6102 - val_distribution_lambda_6_loss: 1.6246 - val_distribution_lambda_7_loss: 0.5322\n", "Epoch 144/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7136 - distribution_lambda_5_loss: 0.5849 - distribution_lambda_6_loss: 1.5833 - distribution_lambda_7_loss: 0.5454 - val_loss: 2.7682 - val_distribution_lambda_5_loss: 0.6119 - val_distribution_lambda_6_loss: 1.6239 - val_distribution_lambda_7_loss: 0.5325\n", "Epoch 145/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7409 - distribution_lambda_5_loss: 0.5900 - distribution_lambda_6_loss: 1.5968 - distribution_lambda_7_loss: 0.5541 - val_loss: 2.7591 - val_distribution_lambda_5_loss: 0.6107 - val_distribution_lambda_6_loss: 1.6156 - val_distribution_lambda_7_loss: 0.5328\n", "Epoch 146/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7038 - distribution_lambda_5_loss: 0.5883 - distribution_lambda_6_loss: 1.5733 - distribution_lambda_7_loss: 0.5422 - val_loss: 2.7632 - val_distribution_lambda_5_loss: 0.6096 - val_distribution_lambda_6_loss: 1.6213 - val_distribution_lambda_7_loss: 0.5323\n", "Epoch 147/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7251 - distribution_lambda_5_loss: 0.5893 - distribution_lambda_6_loss: 1.5817 - distribution_lambda_7_loss: 0.5541 - val_loss: 2.7593 - val_distribution_lambda_5_loss: 0.6109 - val_distribution_lambda_6_loss: 1.6160 - val_distribution_lambda_7_loss: 0.5325\n", "Epoch 148/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6991 - distribution_lambda_5_loss: 0.5838 - distribution_lambda_6_loss: 1.5672 - distribution_lambda_7_loss: 0.5481 - val_loss: 2.7570 - val_distribution_lambda_5_loss: 0.6091 - val_distribution_lambda_6_loss: 1.6153 - val_distribution_lambda_7_loss: 0.5326\n", "Epoch 149/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6928 - distribution_lambda_5_loss: 0.5727 - distribution_lambda_6_loss: 1.5733 - distribution_lambda_7_loss: 0.5468 - val_loss: 2.7488 - val_distribution_lambda_5_loss: 0.6085 - val_distribution_lambda_6_loss: 1.6081 - val_distribution_lambda_7_loss: 0.5322\n", "Epoch 150/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7083 - distribution_lambda_5_loss: 0.5786 - distribution_lambda_6_loss: 1.5820 - distribution_lambda_7_loss: 0.5477 - val_loss: 2.7482 - val_distribution_lambda_5_loss: 0.6058 - val_distribution_lambda_6_loss: 1.6101 - val_distribution_lambda_7_loss: 0.5322\n", "Epoch 151/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6844 - distribution_lambda_5_loss: 0.5777 - distribution_lambda_6_loss: 1.5674 - distribution_lambda_7_loss: 0.5393 - val_loss: 2.7450 - val_distribution_lambda_5_loss: 0.6052 - val_distribution_lambda_6_loss: 1.6086 - val_distribution_lambda_7_loss: 0.5312\n", "Epoch 152/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.7054 - distribution_lambda_5_loss: 0.5775 - distribution_lambda_6_loss: 1.5757 - distribution_lambda_7_loss: 0.5522 - val_loss: 2.7437 - val_distribution_lambda_5_loss: 0.6073 - val_distribution_lambda_6_loss: 1.6047 - val_distribution_lambda_7_loss: 0.5316\n", "Epoch 153/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6716 - distribution_lambda_5_loss: 0.5629 - distribution_lambda_6_loss: 1.5624 - distribution_lambda_7_loss: 0.5463 - val_loss: 2.7365 - val_distribution_lambda_5_loss: 0.6042 - val_distribution_lambda_6_loss: 1.6010 - val_distribution_lambda_7_loss: 0.5313\n", "Epoch 154/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6953 - distribution_lambda_5_loss: 0.5718 - distribution_lambda_6_loss: 1.5750 - distribution_lambda_7_loss: 0.5484 - val_loss: 2.7273 - val_distribution_lambda_5_loss: 0.6013 - val_distribution_lambda_6_loss: 1.5952 - val_distribution_lambda_7_loss: 0.5308\n", "Epoch 155/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.6825 - distribution_lambda_5_loss: 0.5721 - distribution_lambda_6_loss: 1.5677 - distribution_lambda_7_loss: 0.5427 - val_loss: 2.7295 - val_distribution_lambda_5_loss: 0.6001 - val_distribution_lambda_6_loss: 1.5998 - val_distribution_lambda_7_loss: 0.5296\n", "Epoch 156/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6692 - distribution_lambda_5_loss: 0.5696 - distribution_lambda_6_loss: 1.5525 - distribution_lambda_7_loss: 0.5471 - val_loss: 2.7371 - val_distribution_lambda_5_loss: 0.6037 - val_distribution_lambda_6_loss: 1.6044 - val_distribution_lambda_7_loss: 0.5290\n", "Epoch 157/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6808 - distribution_lambda_5_loss: 0.5772 - distribution_lambda_6_loss: 1.5649 - distribution_lambda_7_loss: 0.5387 - val_loss: 2.7361 - val_distribution_lambda_5_loss: 0.6049 - val_distribution_lambda_6_loss: 1.6027 - val_distribution_lambda_7_loss: 0.5286\n", "Epoch 158/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6872 - distribution_lambda_5_loss: 0.5799 - distribution_lambda_6_loss: 1.5637 - distribution_lambda_7_loss: 0.5437 - val_loss: 2.7395 - val_distribution_lambda_5_loss: 0.6098 - val_distribution_lambda_6_loss: 1.5997 - val_distribution_lambda_7_loss: 0.5300\n", "Epoch 159/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6887 - distribution_lambda_5_loss: 0.5786 - distribution_lambda_6_loss: 1.5640 - distribution_lambda_7_loss: 0.5461 - val_loss: 2.7353 - val_distribution_lambda_5_loss: 0.6004 - val_distribution_lambda_6_loss: 1.6043 - val_distribution_lambda_7_loss: 0.5306\n", "Epoch 160/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.6729 - distribution_lambda_5_loss: 0.5733 - distribution_lambda_6_loss: 1.5596 - distribution_lambda_7_loss: 0.5400 - val_loss: 2.7347 - val_distribution_lambda_5_loss: 0.5996 - val_distribution_lambda_6_loss: 1.6051 - val_distribution_lambda_7_loss: 0.5299\n", "Epoch 161/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6642 - distribution_lambda_5_loss: 0.5752 - distribution_lambda_6_loss: 1.5461 - distribution_lambda_7_loss: 0.5429 - val_loss: 2.7223 - val_distribution_lambda_5_loss: 0.5987 - val_distribution_lambda_6_loss: 1.5949 - val_distribution_lambda_7_loss: 0.5288\n", "Epoch 162/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6717 - distribution_lambda_5_loss: 0.5688 - distribution_lambda_6_loss: 1.5585 - distribution_lambda_7_loss: 0.5444 - val_loss: 2.7232 - val_distribution_lambda_5_loss: 0.6015 - val_distribution_lambda_6_loss: 1.5928 - val_distribution_lambda_7_loss: 0.5288\n", "Epoch 163/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6484 - distribution_lambda_5_loss: 0.5672 - distribution_lambda_6_loss: 1.5485 - distribution_lambda_7_loss: 0.5327 - val_loss: 2.7261 - val_distribution_lambda_5_loss: 0.5996 - val_distribution_lambda_6_loss: 1.5986 - val_distribution_lambda_7_loss: 0.5278\n", "Epoch 164/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6624 - distribution_lambda_5_loss: 0.5591 - distribution_lambda_6_loss: 1.5492 - distribution_lambda_7_loss: 0.5540 - val_loss: 2.7189 - val_distribution_lambda_5_loss: 0.5974 - val_distribution_lambda_6_loss: 1.5927 - val_distribution_lambda_7_loss: 0.5287\n", "Epoch 165/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6415 - distribution_lambda_5_loss: 0.5515 - distribution_lambda_6_loss: 1.5529 - distribution_lambda_7_loss: 0.5370 - val_loss: 2.7098 - val_distribution_lambda_5_loss: 0.5989 - val_distribution_lambda_6_loss: 1.5835 - val_distribution_lambda_7_loss: 0.5274\n", "Epoch 166/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.6461 - distribution_lambda_5_loss: 0.5582 - distribution_lambda_6_loss: 1.5393 - distribution_lambda_7_loss: 0.5486 - val_loss: 2.7176 - val_distribution_lambda_5_loss: 0.6009 - val_distribution_lambda_6_loss: 1.5891 - val_distribution_lambda_7_loss: 0.5275\n", "Epoch 167/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6715 - distribution_lambda_5_loss: 0.5683 - distribution_lambda_6_loss: 1.5478 - distribution_lambda_7_loss: 0.5554 - val_loss: 2.7165 - val_distribution_lambda_5_loss: 0.5963 - val_distribution_lambda_6_loss: 1.5918 - val_distribution_lambda_7_loss: 0.5284\n", "Epoch 168/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6432 - distribution_lambda_5_loss: 0.5545 - distribution_lambda_6_loss: 1.5424 - distribution_lambda_7_loss: 0.5463 - val_loss: 2.7249 - val_distribution_lambda_5_loss: 0.6011 - val_distribution_lambda_6_loss: 1.5947 - val_distribution_lambda_7_loss: 0.5292\n", "Epoch 169/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.6254 - distribution_lambda_5_loss: 0.5571 - distribution_lambda_6_loss: 1.5351 - distribution_lambda_7_loss: 0.5332 - val_loss: 2.7196 - val_distribution_lambda_5_loss: 0.6034 - val_distribution_lambda_6_loss: 1.5885 - val_distribution_lambda_7_loss: 0.5278\n", "Epoch 170/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.6360 - distribution_lambda_5_loss: 0.5496 - distribution_lambda_6_loss: 1.5439 - distribution_lambda_7_loss: 0.5426 - val_loss: 2.7219 - val_distribution_lambda_5_loss: 0.6011 - val_distribution_lambda_6_loss: 1.5935 - val_distribution_lambda_7_loss: 0.5274\n", "Epoch 171/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6483 - distribution_lambda_5_loss: 0.5649 - distribution_lambda_6_loss: 1.5433 - distribution_lambda_7_loss: 0.5402 - val_loss: 2.7081 - val_distribution_lambda_5_loss: 0.5986 - val_distribution_lambda_6_loss: 1.5841 - val_distribution_lambda_7_loss: 0.5254\n", "Epoch 172/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6358 - distribution_lambda_5_loss: 0.5508 - distribution_lambda_6_loss: 1.5357 - distribution_lambda_7_loss: 0.5493 - val_loss: 2.6936 - val_distribution_lambda_5_loss: 0.5941 - val_distribution_lambda_6_loss: 1.5746 - val_distribution_lambda_7_loss: 0.5248\n", "Epoch 173/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6253 - distribution_lambda_5_loss: 0.5466 - distribution_lambda_6_loss: 1.5290 - distribution_lambda_7_loss: 0.5496 - val_loss: 2.7004 - val_distribution_lambda_5_loss: 0.5947 - val_distribution_lambda_6_loss: 1.5804 - val_distribution_lambda_7_loss: 0.5254\n", "Epoch 174/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5879 - distribution_lambda_5_loss: 0.5343 - distribution_lambda_6_loss: 1.5196 - distribution_lambda_7_loss: 0.5339 - val_loss: 2.7038 - val_distribution_lambda_5_loss: 0.5944 - val_distribution_lambda_6_loss: 1.5861 - val_distribution_lambda_7_loss: 0.5232\n", "Epoch 175/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6351 - distribution_lambda_5_loss: 0.5607 - distribution_lambda_6_loss: 1.5407 - distribution_lambda_7_loss: 0.5337 - val_loss: 2.6986 - val_distribution_lambda_5_loss: 0.5982 - val_distribution_lambda_6_loss: 1.5785 - val_distribution_lambda_7_loss: 0.5220\n", "Epoch 176/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6163 - distribution_lambda_5_loss: 0.5457 - distribution_lambda_6_loss: 1.5322 - distribution_lambda_7_loss: 0.5383 - val_loss: 2.6986 - val_distribution_lambda_5_loss: 0.5949 - val_distribution_lambda_6_loss: 1.5812 - val_distribution_lambda_7_loss: 0.5225\n", "Epoch 177/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6246 - distribution_lambda_5_loss: 0.5515 - distribution_lambda_6_loss: 1.5295 - distribution_lambda_7_loss: 0.5437 - val_loss: 2.6929 - val_distribution_lambda_5_loss: 0.5965 - val_distribution_lambda_6_loss: 1.5750 - val_distribution_lambda_7_loss: 0.5215\n", "Epoch 178/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6128 - distribution_lambda_5_loss: 0.5492 - distribution_lambda_6_loss: 1.5286 - distribution_lambda_7_loss: 0.5350 - val_loss: 2.6871 - val_distribution_lambda_5_loss: 0.5962 - val_distribution_lambda_6_loss: 1.5701 - val_distribution_lambda_7_loss: 0.5208\n", "Epoch 179/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6149 - distribution_lambda_5_loss: 0.5488 - distribution_lambda_6_loss: 1.5283 - distribution_lambda_7_loss: 0.5378 - val_loss: 2.6864 - val_distribution_lambda_5_loss: 0.5890 - val_distribution_lambda_6_loss: 1.5759 - val_distribution_lambda_7_loss: 0.5215\n", "Epoch 180/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6082 - distribution_lambda_5_loss: 0.5360 - distribution_lambda_6_loss: 1.5307 - distribution_lambda_7_loss: 0.5416 - val_loss: 2.6849 - val_distribution_lambda_5_loss: 0.5891 - val_distribution_lambda_6_loss: 1.5737 - val_distribution_lambda_7_loss: 0.5221\n", "Epoch 181/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6029 - distribution_lambda_5_loss: 0.5437 - distribution_lambda_6_loss: 1.5256 - distribution_lambda_7_loss: 0.5337 - val_loss: 2.6857 - val_distribution_lambda_5_loss: 0.5928 - val_distribution_lambda_6_loss: 1.5719 - val_distribution_lambda_7_loss: 0.5210\n", "Epoch 182/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6190 - distribution_lambda_5_loss: 0.5478 - distribution_lambda_6_loss: 1.5200 - distribution_lambda_7_loss: 0.5511 - val_loss: 2.6964 - val_distribution_lambda_5_loss: 0.5943 - val_distribution_lambda_6_loss: 1.5806 - val_distribution_lambda_7_loss: 0.5215\n", "Epoch 183/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6277 - distribution_lambda_5_loss: 0.5365 - distribution_lambda_6_loss: 1.5375 - distribution_lambda_7_loss: 0.5537 - val_loss: 2.6796 - val_distribution_lambda_5_loss: 0.5888 - val_distribution_lambda_6_loss: 1.5707 - val_distribution_lambda_7_loss: 0.5202\n", "Epoch 184/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6040 - distribution_lambda_5_loss: 0.5385 - distribution_lambda_6_loss: 1.5246 - distribution_lambda_7_loss: 0.5409 - val_loss: 2.6796 - val_distribution_lambda_5_loss: 0.5899 - val_distribution_lambda_6_loss: 1.5699 - val_distribution_lambda_7_loss: 0.5199\n", "Epoch 185/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.6004 - distribution_lambda_5_loss: 0.5388 - distribution_lambda_6_loss: 1.5206 - distribution_lambda_7_loss: 0.5410 - val_loss: 2.6710 - val_distribution_lambda_5_loss: 0.5856 - val_distribution_lambda_6_loss: 1.5658 - val_distribution_lambda_7_loss: 0.5196\n", "Epoch 186/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5952 - distribution_lambda_5_loss: 0.5341 - distribution_lambda_6_loss: 1.5183 - distribution_lambda_7_loss: 0.5428 - val_loss: 2.6716 - val_distribution_lambda_5_loss: 0.5880 - val_distribution_lambda_6_loss: 1.5637 - val_distribution_lambda_7_loss: 0.5198\n", "Epoch 187/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5593 - distribution_lambda_5_loss: 0.5203 - distribution_lambda_6_loss: 1.5052 - distribution_lambda_7_loss: 0.5338 - val_loss: 2.6777 - val_distribution_lambda_5_loss: 0.5914 - val_distribution_lambda_6_loss: 1.5680 - val_distribution_lambda_7_loss: 0.5183\n", "Epoch 188/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5871 - distribution_lambda_5_loss: 0.5325 - distribution_lambda_6_loss: 1.5100 - distribution_lambda_7_loss: 0.5445 - val_loss: 2.6791 - val_distribution_lambda_5_loss: 0.5888 - val_distribution_lambda_6_loss: 1.5720 - val_distribution_lambda_7_loss: 0.5183\n", "Epoch 189/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5914 - distribution_lambda_5_loss: 0.5369 - distribution_lambda_6_loss: 1.5188 - distribution_lambda_7_loss: 0.5356 - val_loss: 2.6747 - val_distribution_lambda_5_loss: 0.5892 - val_distribution_lambda_6_loss: 1.5672 - val_distribution_lambda_7_loss: 0.5183\n", "Epoch 190/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.6018 - distribution_lambda_5_loss: 0.5390 - distribution_lambda_6_loss: 1.5259 - distribution_lambda_7_loss: 0.5369 - val_loss: 2.6742 - val_distribution_lambda_5_loss: 0.5893 - val_distribution_lambda_6_loss: 1.5665 - val_distribution_lambda_7_loss: 0.5185\n", "Epoch 191/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5887 - distribution_lambda_5_loss: 0.5358 - distribution_lambda_6_loss: 1.5134 - distribution_lambda_7_loss: 0.5395 - val_loss: 2.6778 - val_distribution_lambda_5_loss: 0.5884 - val_distribution_lambda_6_loss: 1.5716 - val_distribution_lambda_7_loss: 0.5178\n", "Epoch 192/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5790 - distribution_lambda_5_loss: 0.5269 - distribution_lambda_6_loss: 1.5182 - distribution_lambda_7_loss: 0.5339 - val_loss: 2.6761 - val_distribution_lambda_5_loss: 0.5863 - val_distribution_lambda_6_loss: 1.5716 - val_distribution_lambda_7_loss: 0.5182\n", "Epoch 193/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5667 - distribution_lambda_5_loss: 0.5263 - distribution_lambda_6_loss: 1.5097 - distribution_lambda_7_loss: 0.5306 - val_loss: 2.6778 - val_distribution_lambda_5_loss: 0.5887 - val_distribution_lambda_6_loss: 1.5714 - val_distribution_lambda_7_loss: 0.5177\n", "Epoch 194/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5782 - distribution_lambda_5_loss: 0.5226 - distribution_lambda_6_loss: 1.5163 - distribution_lambda_7_loss: 0.5393 - val_loss: 2.6633 - val_distribution_lambda_5_loss: 0.5834 - val_distribution_lambda_6_loss: 1.5631 - val_distribution_lambda_7_loss: 0.5167\n", "Epoch 195/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5606 - distribution_lambda_5_loss: 0.5177 - distribution_lambda_6_loss: 1.5108 - distribution_lambda_7_loss: 0.5321 - val_loss: 2.6627 - val_distribution_lambda_5_loss: 0.5835 - val_distribution_lambda_6_loss: 1.5628 - val_distribution_lambda_7_loss: 0.5165\n", "Epoch 196/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5644 - distribution_lambda_5_loss: 0.5179 - distribution_lambda_6_loss: 1.5103 - distribution_lambda_7_loss: 0.5362 - val_loss: 2.6698 - val_distribution_lambda_5_loss: 0.5859 - val_distribution_lambda_6_loss: 1.5682 - val_distribution_lambda_7_loss: 0.5157\n", "Epoch 197/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5503 - distribution_lambda_5_loss: 0.5154 - distribution_lambda_6_loss: 1.5022 - distribution_lambda_7_loss: 0.5328 - val_loss: 2.6652 - val_distribution_lambda_5_loss: 0.5801 - val_distribution_lambda_6_loss: 1.5703 - val_distribution_lambda_7_loss: 0.5148\n", "Epoch 198/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5635 - distribution_lambda_5_loss: 0.5226 - distribution_lambda_6_loss: 1.5073 - distribution_lambda_7_loss: 0.5336 - val_loss: 2.6640 - val_distribution_lambda_5_loss: 0.5792 - val_distribution_lambda_6_loss: 1.5700 - val_distribution_lambda_7_loss: 0.5148\n", "Epoch 199/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5452 - distribution_lambda_5_loss: 0.5162 - distribution_lambda_6_loss: 1.4952 - distribution_lambda_7_loss: 0.5338 - val_loss: 2.6636 - val_distribution_lambda_5_loss: 0.5814 - val_distribution_lambda_6_loss: 1.5666 - val_distribution_lambda_7_loss: 0.5155\n", "Epoch 200/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5337 - distribution_lambda_5_loss: 0.5235 - distribution_lambda_6_loss: 1.4931 - distribution_lambda_7_loss: 0.5171 - val_loss: 2.6632 - val_distribution_lambda_5_loss: 0.5783 - val_distribution_lambda_6_loss: 1.5693 - val_distribution_lambda_7_loss: 0.5156\n", "Epoch 201/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5433 - distribution_lambda_5_loss: 0.5054 - distribution_lambda_6_loss: 1.5004 - distribution_lambda_7_loss: 0.5375 - val_loss: 2.6632 - val_distribution_lambda_5_loss: 0.5860 - val_distribution_lambda_6_loss: 1.5616 - val_distribution_lambda_7_loss: 0.5156\n", "Epoch 202/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5355 - distribution_lambda_5_loss: 0.5086 - distribution_lambda_6_loss: 1.4940 - distribution_lambda_7_loss: 0.5330 - val_loss: 2.6532 - val_distribution_lambda_5_loss: 0.5800 - val_distribution_lambda_6_loss: 1.5598 - val_distribution_lambda_7_loss: 0.5135\n", "Epoch 203/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5468 - distribution_lambda_5_loss: 0.5144 - distribution_lambda_6_loss: 1.4981 - distribution_lambda_7_loss: 0.5342 - val_loss: 2.6519 - val_distribution_lambda_5_loss: 0.5740 - val_distribution_lambda_6_loss: 1.5644 - val_distribution_lambda_7_loss: 0.5134\n", "Epoch 204/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5321 - distribution_lambda_5_loss: 0.5038 - distribution_lambda_6_loss: 1.4883 - distribution_lambda_7_loss: 0.5400 - val_loss: 2.6474 - val_distribution_lambda_5_loss: 0.5762 - val_distribution_lambda_6_loss: 1.5578 - val_distribution_lambda_7_loss: 0.5134\n", "Epoch 205/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5264 - distribution_lambda_5_loss: 0.5126 - distribution_lambda_6_loss: 1.4850 - distribution_lambda_7_loss: 0.5289 - val_loss: 2.6533 - val_distribution_lambda_5_loss: 0.5818 - val_distribution_lambda_6_loss: 1.5586 - val_distribution_lambda_7_loss: 0.5130\n", "Epoch 206/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5143 - distribution_lambda_5_loss: 0.5049 - distribution_lambda_6_loss: 1.4831 - distribution_lambda_7_loss: 0.5263 - val_loss: 2.6425 - val_distribution_lambda_5_loss: 0.5764 - val_distribution_lambda_6_loss: 1.5541 - val_distribution_lambda_7_loss: 0.5121\n", "Epoch 207/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5251 - distribution_lambda_5_loss: 0.5087 - distribution_lambda_6_loss: 1.5009 - distribution_lambda_7_loss: 0.5155 - val_loss: 2.6473 - val_distribution_lambda_5_loss: 0.5793 - val_distribution_lambda_6_loss: 1.5578 - val_distribution_lambda_7_loss: 0.5103\n", "Epoch 208/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5123 - distribution_lambda_5_loss: 0.4896 - distribution_lambda_6_loss: 1.4986 - distribution_lambda_7_loss: 0.5241 - val_loss: 2.6327 - val_distribution_lambda_5_loss: 0.5709 - val_distribution_lambda_6_loss: 1.5524 - val_distribution_lambda_7_loss: 0.5094\n", "Epoch 209/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5118 - distribution_lambda_5_loss: 0.4929 - distribution_lambda_6_loss: 1.4880 - distribution_lambda_7_loss: 0.5309 - val_loss: 2.6252 - val_distribution_lambda_5_loss: 0.5672 - val_distribution_lambda_6_loss: 1.5481 - val_distribution_lambda_7_loss: 0.5099\n", "Epoch 210/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5195 - distribution_lambda_5_loss: 0.5015 - distribution_lambda_6_loss: 1.5004 - distribution_lambda_7_loss: 0.5177 - val_loss: 2.6379 - val_distribution_lambda_5_loss: 0.5764 - val_distribution_lambda_6_loss: 1.5513 - val_distribution_lambda_7_loss: 0.5102\n", "Epoch 211/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5048 - distribution_lambda_5_loss: 0.5029 - distribution_lambda_6_loss: 1.4854 - distribution_lambda_7_loss: 0.5165 - val_loss: 2.6460 - val_distribution_lambda_5_loss: 0.5737 - val_distribution_lambda_6_loss: 1.5620 - val_distribution_lambda_7_loss: 0.5104\n", "Epoch 212/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5310 - distribution_lambda_5_loss: 0.5148 - distribution_lambda_6_loss: 1.4902 - distribution_lambda_7_loss: 0.5260 - val_loss: 2.6250 - val_distribution_lambda_5_loss: 0.5629 - val_distribution_lambda_6_loss: 1.5519 - val_distribution_lambda_7_loss: 0.5103\n", "Epoch 213/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4843 - distribution_lambda_5_loss: 0.4819 - distribution_lambda_6_loss: 1.4865 - distribution_lambda_7_loss: 0.5158 - val_loss: 2.6220 - val_distribution_lambda_5_loss: 0.5663 - val_distribution_lambda_6_loss: 1.5457 - val_distribution_lambda_7_loss: 0.5100\n", "Epoch 214/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.5144 - distribution_lambda_5_loss: 0.5016 - distribution_lambda_6_loss: 1.4881 - distribution_lambda_7_loss: 0.5247 - val_loss: 2.6212 - val_distribution_lambda_5_loss: 0.5698 - val_distribution_lambda_6_loss: 1.5427 - val_distribution_lambda_7_loss: 0.5087\n", "Epoch 215/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4949 - distribution_lambda_5_loss: 0.4927 - distribution_lambda_6_loss: 1.4702 - distribution_lambda_7_loss: 0.5320 - val_loss: 2.6234 - val_distribution_lambda_5_loss: 0.5654 - val_distribution_lambda_6_loss: 1.5489 - val_distribution_lambda_7_loss: 0.5090\n", "Epoch 216/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4970 - distribution_lambda_5_loss: 0.4980 - distribution_lambda_6_loss: 1.4786 - distribution_lambda_7_loss: 0.5204 - val_loss: 2.6190 - val_distribution_lambda_5_loss: 0.5635 - val_distribution_lambda_6_loss: 1.5474 - val_distribution_lambda_7_loss: 0.5080\n", "Epoch 217/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4899 - distribution_lambda_5_loss: 0.4897 - distribution_lambda_6_loss: 1.4845 - distribution_lambda_7_loss: 0.5156 - val_loss: 2.6284 - val_distribution_lambda_5_loss: 0.5692 - val_distribution_lambda_6_loss: 1.5523 - val_distribution_lambda_7_loss: 0.5069\n", "Epoch 218/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4849 - distribution_lambda_5_loss: 0.4775 - distribution_lambda_6_loss: 1.4823 - distribution_lambda_7_loss: 0.5252 - val_loss: 2.6261 - val_distribution_lambda_5_loss: 0.5666 - val_distribution_lambda_6_loss: 1.5532 - val_distribution_lambda_7_loss: 0.5064\n", "Epoch 219/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4934 - distribution_lambda_5_loss: 0.4818 - distribution_lambda_6_loss: 1.4893 - distribution_lambda_7_loss: 0.5223 - val_loss: 2.6233 - val_distribution_lambda_5_loss: 0.5698 - val_distribution_lambda_6_loss: 1.5469 - val_distribution_lambda_7_loss: 0.5067\n", "Epoch 220/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4849 - distribution_lambda_5_loss: 0.4739 - distribution_lambda_6_loss: 1.4843 - distribution_lambda_7_loss: 0.5268 - val_loss: 2.6094 - val_distribution_lambda_5_loss: 0.5616 - val_distribution_lambda_6_loss: 1.5421 - val_distribution_lambda_7_loss: 0.5057\n", "Epoch 221/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4951 - distribution_lambda_5_loss: 0.4841 - distribution_lambda_6_loss: 1.4820 - distribution_lambda_7_loss: 0.5290 - val_loss: 2.5998 - val_distribution_lambda_5_loss: 0.5601 - val_distribution_lambda_6_loss: 1.5350 - val_distribution_lambda_7_loss: 0.5048\n", "Epoch 222/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.5088 - distribution_lambda_5_loss: 0.4976 - distribution_lambda_6_loss: 1.4805 - distribution_lambda_7_loss: 0.5308 - val_loss: 2.6040 - val_distribution_lambda_5_loss: 0.5591 - val_distribution_lambda_6_loss: 1.5392 - val_distribution_lambda_7_loss: 0.5057\n", "Epoch 223/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4734 - distribution_lambda_5_loss: 0.4818 - distribution_lambda_6_loss: 1.4730 - distribution_lambda_7_loss: 0.5186 - val_loss: 2.6039 - val_distribution_lambda_5_loss: 0.5565 - val_distribution_lambda_6_loss: 1.5415 - val_distribution_lambda_7_loss: 0.5058\n", "Epoch 224/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.5043 - distribution_lambda_5_loss: 0.4943 - distribution_lambda_6_loss: 1.4823 - distribution_lambda_7_loss: 0.5277 - val_loss: 2.6046 - val_distribution_lambda_5_loss: 0.5551 - val_distribution_lambda_6_loss: 1.5435 - val_distribution_lambda_7_loss: 0.5060\n", "Epoch 225/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4916 - distribution_lambda_5_loss: 0.4795 - distribution_lambda_6_loss: 1.4761 - distribution_lambda_7_loss: 0.5359 - val_loss: 2.5927 - val_distribution_lambda_5_loss: 0.5506 - val_distribution_lambda_6_loss: 1.5373 - val_distribution_lambda_7_loss: 0.5049\n", "Epoch 226/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4468 - distribution_lambda_5_loss: 0.4728 - distribution_lambda_6_loss: 1.4601 - distribution_lambda_7_loss: 0.5139 - val_loss: 2.5907 - val_distribution_lambda_5_loss: 0.5517 - val_distribution_lambda_6_loss: 1.5351 - val_distribution_lambda_7_loss: 0.5038\n", "Epoch 227/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4812 - distribution_lambda_5_loss: 0.4748 - distribution_lambda_6_loss: 1.4904 - distribution_lambda_7_loss: 0.5160 - val_loss: 2.5806 - val_distribution_lambda_5_loss: 0.5473 - val_distribution_lambda_6_loss: 1.5305 - val_distribution_lambda_7_loss: 0.5027\n", "Epoch 228/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4766 - distribution_lambda_5_loss: 0.4760 - distribution_lambda_6_loss: 1.4801 - distribution_lambda_7_loss: 0.5205 - val_loss: 2.5814 - val_distribution_lambda_5_loss: 0.5498 - val_distribution_lambda_6_loss: 1.5283 - val_distribution_lambda_7_loss: 0.5033\n", "Epoch 229/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4762 - distribution_lambda_5_loss: 0.4724 - distribution_lambda_6_loss: 1.4782 - distribution_lambda_7_loss: 0.5256 - val_loss: 2.5793 - val_distribution_lambda_5_loss: 0.5460 - val_distribution_lambda_6_loss: 1.5296 - val_distribution_lambda_7_loss: 0.5037\n", "Epoch 230/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4771 - distribution_lambda_5_loss: 0.4645 - distribution_lambda_6_loss: 1.4764 - distribution_lambda_7_loss: 0.5362 - val_loss: 2.5840 - val_distribution_lambda_5_loss: 0.5465 - val_distribution_lambda_6_loss: 1.5337 - val_distribution_lambda_7_loss: 0.5039\n", "Epoch 231/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4750 - distribution_lambda_5_loss: 0.4727 - distribution_lambda_6_loss: 1.4757 - distribution_lambda_7_loss: 0.5267 - val_loss: 2.5801 - val_distribution_lambda_5_loss: 0.5416 - val_distribution_lambda_6_loss: 1.5328 - val_distribution_lambda_7_loss: 0.5056\n", "Epoch 232/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4679 - distribution_lambda_5_loss: 0.4698 - distribution_lambda_6_loss: 1.4789 - distribution_lambda_7_loss: 0.5192 - val_loss: 2.5910 - val_distribution_lambda_5_loss: 0.5538 - val_distribution_lambda_6_loss: 1.5315 - val_distribution_lambda_7_loss: 0.5056\n", "Epoch 233/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4430 - distribution_lambda_5_loss: 0.4649 - distribution_lambda_6_loss: 1.4651 - distribution_lambda_7_loss: 0.5130 - val_loss: 2.5779 - val_distribution_lambda_5_loss: 0.5420 - val_distribution_lambda_6_loss: 1.5307 - val_distribution_lambda_7_loss: 0.5051\n", "Epoch 234/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4369 - distribution_lambda_5_loss: 0.4577 - distribution_lambda_6_loss: 1.4613 - distribution_lambda_7_loss: 0.5178 - val_loss: 2.5675 - val_distribution_lambda_5_loss: 0.5401 - val_distribution_lambda_6_loss: 1.5242 - val_distribution_lambda_7_loss: 0.5032\n", "Epoch 235/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4650 - distribution_lambda_5_loss: 0.4737 - distribution_lambda_6_loss: 1.4681 - distribution_lambda_7_loss: 0.5231 - val_loss: 2.5589 - val_distribution_lambda_5_loss: 0.5356 - val_distribution_lambda_6_loss: 1.5210 - val_distribution_lambda_7_loss: 0.5022\n", "Epoch 236/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4121 - distribution_lambda_5_loss: 0.4412 - distribution_lambda_6_loss: 1.4535 - distribution_lambda_7_loss: 0.5174 - val_loss: 2.5649 - val_distribution_lambda_5_loss: 0.5389 - val_distribution_lambda_6_loss: 1.5243 - val_distribution_lambda_7_loss: 0.5017\n", "Epoch 237/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4617 - distribution_lambda_5_loss: 0.4629 - distribution_lambda_6_loss: 1.4699 - distribution_lambda_7_loss: 0.5289 - val_loss: 2.5852 - val_distribution_lambda_5_loss: 0.5430 - val_distribution_lambda_6_loss: 1.5399 - val_distribution_lambda_7_loss: 0.5023\n", "Epoch 238/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.4233 - distribution_lambda_5_loss: 0.4529 - distribution_lambda_6_loss: 1.4546 - distribution_lambda_7_loss: 0.5157 - val_loss: 2.5787 - val_distribution_lambda_5_loss: 0.5475 - val_distribution_lambda_6_loss: 1.5305 - val_distribution_lambda_7_loss: 0.5006\n", "Epoch 239/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4040 - distribution_lambda_5_loss: 0.4450 - distribution_lambda_6_loss: 1.4476 - distribution_lambda_7_loss: 0.5114 - val_loss: 2.5727 - val_distribution_lambda_5_loss: 0.5447 - val_distribution_lambda_6_loss: 1.5290 - val_distribution_lambda_7_loss: 0.4990\n", "Epoch 240/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4080 - distribution_lambda_5_loss: 0.4457 - distribution_lambda_6_loss: 1.4459 - distribution_lambda_7_loss: 0.5164 - val_loss: 2.5724 - val_distribution_lambda_5_loss: 0.5447 - val_distribution_lambda_6_loss: 1.5286 - val_distribution_lambda_7_loss: 0.4990\n", "Epoch 241/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4421 - distribution_lambda_5_loss: 0.4523 - distribution_lambda_6_loss: 1.4694 - distribution_lambda_7_loss: 0.5204 - val_loss: 2.5651 - val_distribution_lambda_5_loss: 0.5365 - val_distribution_lambda_6_loss: 1.5284 - val_distribution_lambda_7_loss: 0.5002\n", "Epoch 242/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4092 - distribution_lambda_5_loss: 0.4482 - distribution_lambda_6_loss: 1.4387 - distribution_lambda_7_loss: 0.5223 - val_loss: 2.5614 - val_distribution_lambda_5_loss: 0.5293 - val_distribution_lambda_6_loss: 1.5310 - val_distribution_lambda_7_loss: 0.5010\n", "Epoch 243/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.4246 - distribution_lambda_5_loss: 0.4400 - distribution_lambda_6_loss: 1.4641 - distribution_lambda_7_loss: 0.5204 - val_loss: 2.5750 - val_distribution_lambda_5_loss: 0.5420 - val_distribution_lambda_6_loss: 1.5322 - val_distribution_lambda_7_loss: 0.5008\n", "Epoch 244/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3986 - distribution_lambda_5_loss: 0.4317 - distribution_lambda_6_loss: 1.4458 - distribution_lambda_7_loss: 0.5211 - val_loss: 2.5683 - val_distribution_lambda_5_loss: 0.5347 - val_distribution_lambda_6_loss: 1.5332 - val_distribution_lambda_7_loss: 0.5004\n", "Epoch 245/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4158 - distribution_lambda_5_loss: 0.4416 - distribution_lambda_6_loss: 1.4588 - distribution_lambda_7_loss: 0.5155 - val_loss: 2.5537 - val_distribution_lambda_5_loss: 0.5314 - val_distribution_lambda_6_loss: 1.5231 - val_distribution_lambda_7_loss: 0.4992\n", "Epoch 246/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4121 - distribution_lambda_5_loss: 0.4417 - distribution_lambda_6_loss: 1.4562 - distribution_lambda_7_loss: 0.5142 - val_loss: 2.5440 - val_distribution_lambda_5_loss: 0.5277 - val_distribution_lambda_6_loss: 1.5182 - val_distribution_lambda_7_loss: 0.4981\n", "Epoch 247/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4180 - distribution_lambda_5_loss: 0.4417 - distribution_lambda_6_loss: 1.4581 - distribution_lambda_7_loss: 0.5182 - val_loss: 2.5379 - val_distribution_lambda_5_loss: 0.5306 - val_distribution_lambda_6_loss: 1.5103 - val_distribution_lambda_7_loss: 0.4969\n", "Epoch 248/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4103 - distribution_lambda_5_loss: 0.4376 - distribution_lambda_6_loss: 1.4602 - distribution_lambda_7_loss: 0.5124 - val_loss: 2.5437 - val_distribution_lambda_5_loss: 0.5319 - val_distribution_lambda_6_loss: 1.5153 - val_distribution_lambda_7_loss: 0.4965\n", "Epoch 249/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4004 - distribution_lambda_5_loss: 0.4337 - distribution_lambda_6_loss: 1.4410 - distribution_lambda_7_loss: 0.5256 - val_loss: 2.5327 - val_distribution_lambda_5_loss: 0.5283 - val_distribution_lambda_6_loss: 1.5073 - val_distribution_lambda_7_loss: 0.4971\n", "Epoch 250/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4153 - distribution_lambda_5_loss: 0.4364 - distribution_lambda_6_loss: 1.4619 - distribution_lambda_7_loss: 0.5170 - val_loss: 2.5335 - val_distribution_lambda_5_loss: 0.5288 - val_distribution_lambda_6_loss: 1.5066 - val_distribution_lambda_7_loss: 0.4981\n", "Epoch 251/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4028 - distribution_lambda_5_loss: 0.4431 - distribution_lambda_6_loss: 1.4456 - distribution_lambda_7_loss: 0.5141 - val_loss: 2.5344 - val_distribution_lambda_5_loss: 0.5243 - val_distribution_lambda_6_loss: 1.5117 - val_distribution_lambda_7_loss: 0.4985\n", "Epoch 252/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3807 - distribution_lambda_5_loss: 0.4229 - distribution_lambda_6_loss: 1.4392 - distribution_lambda_7_loss: 0.5186 - val_loss: 2.5289 - val_distribution_lambda_5_loss: 0.5185 - val_distribution_lambda_6_loss: 1.5124 - val_distribution_lambda_7_loss: 0.4980\n", "Epoch 253/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4029 - distribution_lambda_5_loss: 0.4279 - distribution_lambda_6_loss: 1.4632 - distribution_lambda_7_loss: 0.5118 - val_loss: 2.5202 - val_distribution_lambda_5_loss: 0.5161 - val_distribution_lambda_6_loss: 1.5082 - val_distribution_lambda_7_loss: 0.4960\n", "Epoch 254/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3868 - distribution_lambda_5_loss: 0.4297 - distribution_lambda_6_loss: 1.4466 - distribution_lambda_7_loss: 0.5105 - val_loss: 2.5353 - val_distribution_lambda_5_loss: 0.5270 - val_distribution_lambda_6_loss: 1.5145 - val_distribution_lambda_7_loss: 0.4938\n", "Epoch 255/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3728 - distribution_lambda_5_loss: 0.4211 - distribution_lambda_6_loss: 1.4457 - distribution_lambda_7_loss: 0.5060 - val_loss: 2.5370 - val_distribution_lambda_5_loss: 0.5297 - val_distribution_lambda_6_loss: 1.5142 - val_distribution_lambda_7_loss: 0.4930\n", "Epoch 256/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3834 - distribution_lambda_5_loss: 0.4266 - distribution_lambda_6_loss: 1.4471 - distribution_lambda_7_loss: 0.5096 - val_loss: 2.5176 - val_distribution_lambda_5_loss: 0.5136 - val_distribution_lambda_6_loss: 1.5127 - val_distribution_lambda_7_loss: 0.4913\n", "Epoch 257/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.4128 - distribution_lambda_5_loss: 0.4301 - distribution_lambda_6_loss: 1.4617 - distribution_lambda_7_loss: 0.5209 - val_loss: 2.5187 - val_distribution_lambda_5_loss: 0.5185 - val_distribution_lambda_6_loss: 1.5086 - val_distribution_lambda_7_loss: 0.4916\n", "Epoch 258/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3599 - distribution_lambda_5_loss: 0.4190 - distribution_lambda_6_loss: 1.4403 - distribution_lambda_7_loss: 0.5006 - val_loss: 2.5126 - val_distribution_lambda_5_loss: 0.5173 - val_distribution_lambda_6_loss: 1.5047 - val_distribution_lambda_7_loss: 0.4907\n", "Epoch 259/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3786 - distribution_lambda_5_loss: 0.4203 - distribution_lambda_6_loss: 1.4461 - distribution_lambda_7_loss: 0.5122 - val_loss: 2.5232 - val_distribution_lambda_5_loss: 0.5190 - val_distribution_lambda_6_loss: 1.5121 - val_distribution_lambda_7_loss: 0.4922\n", "Epoch 260/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3594 - distribution_lambda_5_loss: 0.4119 - distribution_lambda_6_loss: 1.4401 - distribution_lambda_7_loss: 0.5073 - val_loss: 2.5158 - val_distribution_lambda_5_loss: 0.5213 - val_distribution_lambda_6_loss: 1.5022 - val_distribution_lambda_7_loss: 0.4923\n", "Epoch 261/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3868 - distribution_lambda_5_loss: 0.4163 - distribution_lambda_6_loss: 1.4555 - distribution_lambda_7_loss: 0.5151 - val_loss: 2.5079 - val_distribution_lambda_5_loss: 0.5205 - val_distribution_lambda_6_loss: 1.4961 - val_distribution_lambda_7_loss: 0.4913\n", "Epoch 262/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.3819 - distribution_lambda_5_loss: 0.4251 - distribution_lambda_6_loss: 1.4411 - distribution_lambda_7_loss: 0.5157 - val_loss: 2.5012 - val_distribution_lambda_5_loss: 0.5181 - val_distribution_lambda_6_loss: 1.4933 - val_distribution_lambda_7_loss: 0.4898\n", "Epoch 263/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3660 - distribution_lambda_5_loss: 0.4174 - distribution_lambda_6_loss: 1.4389 - distribution_lambda_7_loss: 0.5097 - val_loss: 2.5058 - val_distribution_lambda_5_loss: 0.5148 - val_distribution_lambda_6_loss: 1.5015 - val_distribution_lambda_7_loss: 0.4896\n", "Epoch 264/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3485 - distribution_lambda_5_loss: 0.4071 - distribution_lambda_6_loss: 1.4336 - distribution_lambda_7_loss: 0.5078 - val_loss: 2.5022 - val_distribution_lambda_5_loss: 0.5124 - val_distribution_lambda_6_loss: 1.5006 - val_distribution_lambda_7_loss: 0.4893\n", "Epoch 265/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3803 - distribution_lambda_5_loss: 0.4297 - distribution_lambda_6_loss: 1.4346 - distribution_lambda_7_loss: 0.5160 - val_loss: 2.5110 - val_distribution_lambda_5_loss: 0.5152 - val_distribution_lambda_6_loss: 1.5049 - val_distribution_lambda_7_loss: 0.4909\n", "Epoch 266/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3326 - distribution_lambda_5_loss: 0.3944 - distribution_lambda_6_loss: 1.4250 - distribution_lambda_7_loss: 0.5132 - val_loss: 2.5241 - val_distribution_lambda_5_loss: 0.5208 - val_distribution_lambda_6_loss: 1.5118 - val_distribution_lambda_7_loss: 0.4914\n", "Epoch 267/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3343 - distribution_lambda_5_loss: 0.4103 - distribution_lambda_6_loss: 1.4204 - distribution_lambda_7_loss: 0.5036 - val_loss: 2.5082 - val_distribution_lambda_5_loss: 0.5204 - val_distribution_lambda_6_loss: 1.4983 - val_distribution_lambda_7_loss: 0.4896\n", "Epoch 268/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3544 - distribution_lambda_5_loss: 0.4194 - distribution_lambda_6_loss: 1.4341 - distribution_lambda_7_loss: 0.5008 - val_loss: 2.5047 - val_distribution_lambda_5_loss: 0.5181 - val_distribution_lambda_6_loss: 1.4984 - val_distribution_lambda_7_loss: 0.4882\n", "Epoch 269/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3745 - distribution_lambda_5_loss: 0.4196 - distribution_lambda_6_loss: 1.4434 - distribution_lambda_7_loss: 0.5115 - val_loss: 2.4888 - val_distribution_lambda_5_loss: 0.5117 - val_distribution_lambda_6_loss: 1.4905 - val_distribution_lambda_7_loss: 0.4865\n", "Epoch 270/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3488 - distribution_lambda_5_loss: 0.3983 - distribution_lambda_6_loss: 1.4276 - distribution_lambda_7_loss: 0.5228 - val_loss: 2.5158 - val_distribution_lambda_5_loss: 0.5224 - val_distribution_lambda_6_loss: 1.5052 - val_distribution_lambda_7_loss: 0.4883\n", "Epoch 271/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3375 - distribution_lambda_5_loss: 0.3998 - distribution_lambda_6_loss: 1.4339 - distribution_lambda_7_loss: 0.5039 - val_loss: 2.4952 - val_distribution_lambda_5_loss: 0.5176 - val_distribution_lambda_6_loss: 1.4909 - val_distribution_lambda_7_loss: 0.4867\n", "Epoch 272/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3375 - distribution_lambda_5_loss: 0.4026 - distribution_lambda_6_loss: 1.4328 - distribution_lambda_7_loss: 0.5021 - val_loss: 2.4841 - val_distribution_lambda_5_loss: 0.5049 - val_distribution_lambda_6_loss: 1.4929 - val_distribution_lambda_7_loss: 0.4863\n", "Epoch 273/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3135 - distribution_lambda_5_loss: 0.3995 - distribution_lambda_6_loss: 1.4189 - distribution_lambda_7_loss: 0.4951 - val_loss: 2.4923 - val_distribution_lambda_5_loss: 0.5084 - val_distribution_lambda_6_loss: 1.4983 - val_distribution_lambda_7_loss: 0.4856\n", "Epoch 274/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3480 - distribution_lambda_5_loss: 0.3906 - distribution_lambda_6_loss: 1.4490 - distribution_lambda_7_loss: 0.5084 - val_loss: 2.5072 - val_distribution_lambda_5_loss: 0.5088 - val_distribution_lambda_6_loss: 1.5118 - val_distribution_lambda_7_loss: 0.4866\n", "Epoch 275/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3374 - distribution_lambda_5_loss: 0.3983 - distribution_lambda_6_loss: 1.4303 - distribution_lambda_7_loss: 0.5089 - val_loss: 2.5087 - val_distribution_lambda_5_loss: 0.5145 - val_distribution_lambda_6_loss: 1.5063 - val_distribution_lambda_7_loss: 0.4879\n", "Epoch 276/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3236 - distribution_lambda_5_loss: 0.3835 - distribution_lambda_6_loss: 1.4305 - distribution_lambda_7_loss: 0.5095 - val_loss: 2.5109 - val_distribution_lambda_5_loss: 0.5167 - val_distribution_lambda_6_loss: 1.5059 - val_distribution_lambda_7_loss: 0.4883\n", "Epoch 277/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3522 - distribution_lambda_5_loss: 0.4139 - distribution_lambda_6_loss: 1.4372 - distribution_lambda_7_loss: 0.5012 - val_loss: 2.4860 - val_distribution_lambda_5_loss: 0.5038 - val_distribution_lambda_6_loss: 1.4951 - val_distribution_lambda_7_loss: 0.4870\n", "Epoch 278/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3593 - distribution_lambda_5_loss: 0.4165 - distribution_lambda_6_loss: 1.4327 - distribution_lambda_7_loss: 0.5101 - val_loss: 2.4811 - val_distribution_lambda_5_loss: 0.5000 - val_distribution_lambda_6_loss: 1.4944 - val_distribution_lambda_7_loss: 0.4866\n", "Epoch 279/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3278 - distribution_lambda_5_loss: 0.3818 - distribution_lambda_6_loss: 1.4363 - distribution_lambda_7_loss: 0.5097 - val_loss: 2.4926 - val_distribution_lambda_5_loss: 0.5091 - val_distribution_lambda_6_loss: 1.4975 - val_distribution_lambda_7_loss: 0.4860\n", "Epoch 280/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3263 - distribution_lambda_5_loss: 0.4102 - distribution_lambda_6_loss: 1.4168 - distribution_lambda_7_loss: 0.4993 - val_loss: 2.4788 - val_distribution_lambda_5_loss: 0.5056 - val_distribution_lambda_6_loss: 1.4892 - val_distribution_lambda_7_loss: 0.4840\n", "Epoch 281/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3040 - distribution_lambda_5_loss: 0.3789 - distribution_lambda_6_loss: 1.4205 - distribution_lambda_7_loss: 0.5046 - val_loss: 2.4872 - val_distribution_lambda_5_loss: 0.5114 - val_distribution_lambda_6_loss: 1.4922 - val_distribution_lambda_7_loss: 0.4837\n", "Epoch 282/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3128 - distribution_lambda_5_loss: 0.3876 - distribution_lambda_6_loss: 1.4215 - distribution_lambda_7_loss: 0.5037 - val_loss: 2.4863 - val_distribution_lambda_5_loss: 0.5146 - val_distribution_lambda_6_loss: 1.4894 - val_distribution_lambda_7_loss: 0.4823\n", "Epoch 283/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3234 - distribution_lambda_5_loss: 0.3756 - distribution_lambda_6_loss: 1.4363 - distribution_lambda_7_loss: 0.5116 - val_loss: 2.4810 - val_distribution_lambda_5_loss: 0.5074 - val_distribution_lambda_6_loss: 1.4912 - val_distribution_lambda_7_loss: 0.4824\n", "Epoch 284/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3074 - distribution_lambda_5_loss: 0.3799 - distribution_lambda_6_loss: 1.4252 - distribution_lambda_7_loss: 0.5023 - val_loss: 2.4850 - val_distribution_lambda_5_loss: 0.5120 - val_distribution_lambda_6_loss: 1.4903 - val_distribution_lambda_7_loss: 0.4828\n", "Epoch 285/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3120 - distribution_lambda_5_loss: 0.3834 - distribution_lambda_6_loss: 1.4214 - distribution_lambda_7_loss: 0.5072 - val_loss: 2.4866 - val_distribution_lambda_5_loss: 0.5119 - val_distribution_lambda_6_loss: 1.4902 - val_distribution_lambda_7_loss: 0.4846\n", "Epoch 286/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 2.2920 - distribution_lambda_5_loss: 0.3640 - distribution_lambda_6_loss: 1.4132 - distribution_lambda_7_loss: 0.5148 - val_loss: 2.4701 - val_distribution_lambda_5_loss: 0.5064 - val_distribution_lambda_6_loss: 1.4801 - val_distribution_lambda_7_loss: 0.4835\n", "Epoch 287/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3071 - distribution_lambda_5_loss: 0.3701 - distribution_lambda_6_loss: 1.4231 - distribution_lambda_7_loss: 0.5139 - val_loss: 2.4826 - val_distribution_lambda_5_loss: 0.5157 - val_distribution_lambda_6_loss: 1.4835 - val_distribution_lambda_7_loss: 0.4834\n", "Epoch 288/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3236 - distribution_lambda_5_loss: 0.3809 - distribution_lambda_6_loss: 1.4312 - distribution_lambda_7_loss: 0.5115 - val_loss: 2.4833 - val_distribution_lambda_5_loss: 0.5112 - val_distribution_lambda_6_loss: 1.4877 - val_distribution_lambda_7_loss: 0.4845\n", "Epoch 289/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2939 - distribution_lambda_5_loss: 0.3788 - distribution_lambda_6_loss: 1.4141 - distribution_lambda_7_loss: 0.5010 - val_loss: 2.4711 - val_distribution_lambda_5_loss: 0.5074 - val_distribution_lambda_6_loss: 1.4802 - val_distribution_lambda_7_loss: 0.4836\n", "Epoch 290/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3099 - distribution_lambda_5_loss: 0.3727 - distribution_lambda_6_loss: 1.4264 - distribution_lambda_7_loss: 0.5108 - val_loss: 2.4665 - val_distribution_lambda_5_loss: 0.5047 - val_distribution_lambda_6_loss: 1.4777 - val_distribution_lambda_7_loss: 0.4841\n", "Epoch 291/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2828 - distribution_lambda_5_loss: 0.3697 - distribution_lambda_6_loss: 1.4186 - distribution_lambda_7_loss: 0.4944 - val_loss: 2.4656 - val_distribution_lambda_5_loss: 0.5034 - val_distribution_lambda_6_loss: 1.4803 - val_distribution_lambda_7_loss: 0.4819\n", "Epoch 292/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2922 - distribution_lambda_5_loss: 0.3724 - distribution_lambda_6_loss: 1.4207 - distribution_lambda_7_loss: 0.4991 - val_loss: 2.4717 - val_distribution_lambda_5_loss: 0.5084 - val_distribution_lambda_6_loss: 1.4815 - val_distribution_lambda_7_loss: 0.4819\n", "Epoch 293/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2978 - distribution_lambda_5_loss: 0.3628 - distribution_lambda_6_loss: 1.4273 - distribution_lambda_7_loss: 0.5076 - val_loss: 2.4738 - val_distribution_lambda_5_loss: 0.5103 - val_distribution_lambda_6_loss: 1.4815 - val_distribution_lambda_7_loss: 0.4820\n", "Epoch 294/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.2820 - distribution_lambda_5_loss: 0.3634 - distribution_lambda_6_loss: 1.4116 - distribution_lambda_7_loss: 0.5069 - val_loss: 2.4906 - val_distribution_lambda_5_loss: 0.5222 - val_distribution_lambda_6_loss: 1.4863 - val_distribution_lambda_7_loss: 0.4821\n", "Epoch 295/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3092 - distribution_lambda_5_loss: 0.3752 - distribution_lambda_6_loss: 1.4330 - distribution_lambda_7_loss: 0.5009 - val_loss: 2.4656 - val_distribution_lambda_5_loss: 0.5106 - val_distribution_lambda_6_loss: 1.4748 - val_distribution_lambda_7_loss: 0.4802\n", "Epoch 296/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3127 - distribution_lambda_5_loss: 0.3732 - distribution_lambda_6_loss: 1.4257 - distribution_lambda_7_loss: 0.5138 - val_loss: 2.4539 - val_distribution_lambda_5_loss: 0.4991 - val_distribution_lambda_6_loss: 1.4732 - val_distribution_lambda_7_loss: 0.4816\n", "Epoch 297/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2956 - distribution_lambda_5_loss: 0.3784 - distribution_lambda_6_loss: 1.4160 - distribution_lambda_7_loss: 0.5012 - val_loss: 2.4428 - val_distribution_lambda_5_loss: 0.4948 - val_distribution_lambda_6_loss: 1.4680 - val_distribution_lambda_7_loss: 0.4800\n", "Epoch 298/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2750 - distribution_lambda_5_loss: 0.3538 - distribution_lambda_6_loss: 1.4188 - distribution_lambda_7_loss: 0.5024 - val_loss: 2.4503 - val_distribution_lambda_5_loss: 0.5009 - val_distribution_lambda_6_loss: 1.4697 - val_distribution_lambda_7_loss: 0.4797\n", "Epoch 299/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2912 - distribution_lambda_5_loss: 0.3815 - distribution_lambda_6_loss: 1.4124 - distribution_lambda_7_loss: 0.4973 - val_loss: 2.4416 - val_distribution_lambda_5_loss: 0.4920 - val_distribution_lambda_6_loss: 1.4697 - val_distribution_lambda_7_loss: 0.4799\n", "Epoch 300/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3084 - distribution_lambda_5_loss: 0.3745 - distribution_lambda_6_loss: 1.4180 - distribution_lambda_7_loss: 0.5158 - val_loss: 2.4342 - val_distribution_lambda_5_loss: 0.4895 - val_distribution_lambda_6_loss: 1.4646 - val_distribution_lambda_7_loss: 0.4800\n", "Epoch 301/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.3088 - distribution_lambda_5_loss: 0.3766 - distribution_lambda_6_loss: 1.4187 - distribution_lambda_7_loss: 0.5134 - val_loss: 2.4396 - val_distribution_lambda_5_loss: 0.4919 - val_distribution_lambda_6_loss: 1.4677 - val_distribution_lambda_7_loss: 0.4800\n", "Epoch 302/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2637 - distribution_lambda_5_loss: 0.3459 - distribution_lambda_6_loss: 1.4089 - distribution_lambda_7_loss: 0.5089 - val_loss: 2.4604 - val_distribution_lambda_5_loss: 0.5082 - val_distribution_lambda_6_loss: 1.4713 - val_distribution_lambda_7_loss: 0.4809\n", "Epoch 303/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2657 - distribution_lambda_5_loss: 0.3542 - distribution_lambda_6_loss: 1.4122 - distribution_lambda_7_loss: 0.4993 - val_loss: 2.4496 - val_distribution_lambda_5_loss: 0.4981 - val_distribution_lambda_6_loss: 1.4718 - val_distribution_lambda_7_loss: 0.4797\n", "Epoch 304/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2495 - distribution_lambda_5_loss: 0.3442 - distribution_lambda_6_loss: 1.3991 - distribution_lambda_7_loss: 0.5061 - val_loss: 2.4650 - val_distribution_lambda_5_loss: 0.5075 - val_distribution_lambda_6_loss: 1.4778 - val_distribution_lambda_7_loss: 0.4798\n", "Epoch 305/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.3159 - distribution_lambda_5_loss: 0.3701 - distribution_lambda_6_loss: 1.4341 - distribution_lambda_7_loss: 0.5118 - val_loss: 2.4389 - val_distribution_lambda_5_loss: 0.4928 - val_distribution_lambda_6_loss: 1.4662 - val_distribution_lambda_7_loss: 0.4799\n", "Epoch 306/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2861 - distribution_lambda_5_loss: 0.3736 - distribution_lambda_6_loss: 1.4145 - distribution_lambda_7_loss: 0.4980 - val_loss: 2.4401 - val_distribution_lambda_5_loss: 0.4935 - val_distribution_lambda_6_loss: 1.4663 - val_distribution_lambda_7_loss: 0.4803\n", "Epoch 307/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2346 - distribution_lambda_5_loss: 0.3437 - distribution_lambda_6_loss: 1.4063 - distribution_lambda_7_loss: 0.4846 - val_loss: 2.4376 - val_distribution_lambda_5_loss: 0.4937 - val_distribution_lambda_6_loss: 1.4651 - val_distribution_lambda_7_loss: 0.4789\n", "Epoch 308/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2627 - distribution_lambda_5_loss: 0.3609 - distribution_lambda_6_loss: 1.4063 - distribution_lambda_7_loss: 0.4955 - val_loss: 2.4479 - val_distribution_lambda_5_loss: 0.4997 - val_distribution_lambda_6_loss: 1.4693 - val_distribution_lambda_7_loss: 0.4789\n", "Epoch 309/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2726 - distribution_lambda_5_loss: 0.3686 - distribution_lambda_6_loss: 1.4024 - distribution_lambda_7_loss: 0.5016 - val_loss: 2.4309 - val_distribution_lambda_5_loss: 0.4899 - val_distribution_lambda_6_loss: 1.4624 - val_distribution_lambda_7_loss: 0.4787\n", "Epoch 310/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 2.2533 - distribution_lambda_5_loss: 0.3361 - distribution_lambda_6_loss: 1.4095 - distribution_lambda_7_loss: 0.5076 - val_loss: 2.4369 - val_distribution_lambda_5_loss: 0.4962 - val_distribution_lambda_6_loss: 1.4626 - val_distribution_lambda_7_loss: 0.4780\n", "Epoch 311/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2672 - distribution_lambda_5_loss: 0.3706 - distribution_lambda_6_loss: 1.4043 - distribution_lambda_7_loss: 0.4923 - val_loss: 2.4451 - val_distribution_lambda_5_loss: 0.5001 - val_distribution_lambda_6_loss: 1.4671 - val_distribution_lambda_7_loss: 0.4779\n", "Epoch 312/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2612 - distribution_lambda_5_loss: 0.3561 - distribution_lambda_6_loss: 1.4121 - distribution_lambda_7_loss: 0.4930 - val_loss: 2.4288 - val_distribution_lambda_5_loss: 0.4876 - val_distribution_lambda_6_loss: 1.4641 - val_distribution_lambda_7_loss: 0.4770\n", "Epoch 313/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2450 - distribution_lambda_5_loss: 0.3531 - distribution_lambda_6_loss: 1.3942 - distribution_lambda_7_loss: 0.4977 - val_loss: 2.4308 - val_distribution_lambda_5_loss: 0.4969 - val_distribution_lambda_6_loss: 1.4587 - val_distribution_lambda_7_loss: 0.4753\n", "Epoch 314/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2466 - distribution_lambda_5_loss: 0.3389 - distribution_lambda_6_loss: 1.4011 - distribution_lambda_7_loss: 0.5066 - val_loss: 2.4245 - val_distribution_lambda_5_loss: 0.4899 - val_distribution_lambda_6_loss: 1.4594 - val_distribution_lambda_7_loss: 0.4752\n", "Epoch 315/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2589 - distribution_lambda_5_loss: 0.3586 - distribution_lambda_6_loss: 1.4026 - distribution_lambda_7_loss: 0.4978 - val_loss: 2.4331 - val_distribution_lambda_5_loss: 0.4986 - val_distribution_lambda_6_loss: 1.4606 - val_distribution_lambda_7_loss: 0.4740\n", "Epoch 316/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2642 - distribution_lambda_5_loss: 0.3443 - distribution_lambda_6_loss: 1.4182 - distribution_lambda_7_loss: 0.5017 - val_loss: 2.4381 - val_distribution_lambda_5_loss: 0.4912 - val_distribution_lambda_6_loss: 1.4709 - val_distribution_lambda_7_loss: 0.4760\n", "Epoch 317/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2556 - distribution_lambda_5_loss: 0.3584 - distribution_lambda_6_loss: 1.3951 - distribution_lambda_7_loss: 0.5021 - val_loss: 2.4101 - val_distribution_lambda_5_loss: 0.4776 - val_distribution_lambda_6_loss: 1.4557 - val_distribution_lambda_7_loss: 0.4768\n", "Epoch 318/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2396 - distribution_lambda_5_loss: 0.3506 - distribution_lambda_6_loss: 1.3910 - distribution_lambda_7_loss: 0.4981 - val_loss: 2.4256 - val_distribution_lambda_5_loss: 0.4846 - val_distribution_lambda_6_loss: 1.4642 - val_distribution_lambda_7_loss: 0.4769\n", "Epoch 319/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2254 - distribution_lambda_5_loss: 0.3423 - distribution_lambda_6_loss: 1.3847 - distribution_lambda_7_loss: 0.4984 - val_loss: 2.4489 - val_distribution_lambda_5_loss: 0.4977 - val_distribution_lambda_6_loss: 1.4765 - val_distribution_lambda_7_loss: 0.4747\n", "Epoch 320/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2560 - distribution_lambda_5_loss: 0.3445 - distribution_lambda_6_loss: 1.4150 - distribution_lambda_7_loss: 0.4965 - val_loss: 2.4373 - val_distribution_lambda_5_loss: 0.4936 - val_distribution_lambda_6_loss: 1.4667 - val_distribution_lambda_7_loss: 0.4770\n", "Epoch 321/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2798 - distribution_lambda_5_loss: 0.3652 - distribution_lambda_6_loss: 1.4152 - distribution_lambda_7_loss: 0.4994 - val_loss: 2.4211 - val_distribution_lambda_5_loss: 0.4857 - val_distribution_lambda_6_loss: 1.4593 - val_distribution_lambda_7_loss: 0.4761\n", "Epoch 322/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2275 - distribution_lambda_5_loss: 0.3342 - distribution_lambda_6_loss: 1.3920 - distribution_lambda_7_loss: 0.5013 - val_loss: 2.4241 - val_distribution_lambda_5_loss: 0.4889 - val_distribution_lambda_6_loss: 1.4618 - val_distribution_lambda_7_loss: 0.4734\n", "Epoch 323/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2153 - distribution_lambda_5_loss: 0.3445 - distribution_lambda_6_loss: 1.3905 - distribution_lambda_7_loss: 0.4802 - val_loss: 2.4249 - val_distribution_lambda_5_loss: 0.4849 - val_distribution_lambda_6_loss: 1.4675 - val_distribution_lambda_7_loss: 0.4725\n", "Epoch 324/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2383 - distribution_lambda_5_loss: 0.3394 - distribution_lambda_6_loss: 1.3968 - distribution_lambda_7_loss: 0.5021 - val_loss: 2.4174 - val_distribution_lambda_5_loss: 0.4796 - val_distribution_lambda_6_loss: 1.4662 - val_distribution_lambda_7_loss: 0.4716\n", "Epoch 325/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2330 - distribution_lambda_5_loss: 0.3283 - distribution_lambda_6_loss: 1.4011 - distribution_lambda_7_loss: 0.5036 - val_loss: 2.4461 - val_distribution_lambda_5_loss: 0.5067 - val_distribution_lambda_6_loss: 1.4673 - val_distribution_lambda_7_loss: 0.4721\n", "Epoch 326/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2219 - distribution_lambda_5_loss: 0.3383 - distribution_lambda_6_loss: 1.3870 - distribution_lambda_7_loss: 0.4966 - val_loss: 2.4367 - val_distribution_lambda_5_loss: 0.4950 - val_distribution_lambda_6_loss: 1.4697 - val_distribution_lambda_7_loss: 0.4721\n", "Epoch 327/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2366 - distribution_lambda_5_loss: 0.3292 - distribution_lambda_6_loss: 1.4041 - distribution_lambda_7_loss: 0.5034 - val_loss: 2.4336 - val_distribution_lambda_5_loss: 0.4955 - val_distribution_lambda_6_loss: 1.4662 - val_distribution_lambda_7_loss: 0.4719\n", "Epoch 328/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2403 - distribution_lambda_5_loss: 0.3502 - distribution_lambda_6_loss: 1.3911 - distribution_lambda_7_loss: 0.4990 - val_loss: 2.4216 - val_distribution_lambda_5_loss: 0.4935 - val_distribution_lambda_6_loss: 1.4582 - val_distribution_lambda_7_loss: 0.4700\n", "Epoch 329/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2305 - distribution_lambda_5_loss: 0.3328 - distribution_lambda_6_loss: 1.3988 - distribution_lambda_7_loss: 0.4989 - val_loss: 2.4291 - val_distribution_lambda_5_loss: 0.4983 - val_distribution_lambda_6_loss: 1.4613 - val_distribution_lambda_7_loss: 0.4695\n", "Epoch 330/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2350 - distribution_lambda_5_loss: 0.3535 - distribution_lambda_6_loss: 1.4030 - distribution_lambda_7_loss: 0.4785 - val_loss: 2.4059 - val_distribution_lambda_5_loss: 0.4833 - val_distribution_lambda_6_loss: 1.4544 - val_distribution_lambda_7_loss: 0.4682\n", "Epoch 331/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2349 - distribution_lambda_5_loss: 0.3409 - distribution_lambda_6_loss: 1.3932 - distribution_lambda_7_loss: 0.5008 - val_loss: 2.4207 - val_distribution_lambda_5_loss: 0.4866 - val_distribution_lambda_6_loss: 1.4639 - val_distribution_lambda_7_loss: 0.4702\n", "Epoch 332/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2311 - distribution_lambda_5_loss: 0.3292 - distribution_lambda_6_loss: 1.3935 - distribution_lambda_7_loss: 0.5084 - val_loss: 2.4207 - val_distribution_lambda_5_loss: 0.4830 - val_distribution_lambda_6_loss: 1.4652 - val_distribution_lambda_7_loss: 0.4725\n", "Epoch 333/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2364 - distribution_lambda_5_loss: 0.3348 - distribution_lambda_6_loss: 1.3982 - distribution_lambda_7_loss: 0.5034 - val_loss: 2.4315 - val_distribution_lambda_5_loss: 0.4886 - val_distribution_lambda_6_loss: 1.4710 - val_distribution_lambda_7_loss: 0.4720\n", "Epoch 334/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.2214 - distribution_lambda_5_loss: 0.3313 - distribution_lambda_6_loss: 1.3907 - distribution_lambda_7_loss: 0.4993 - val_loss: 2.4135 - val_distribution_lambda_5_loss: 0.4800 - val_distribution_lambda_6_loss: 1.4621 - val_distribution_lambda_7_loss: 0.4714\n", "Epoch 335/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2190 - distribution_lambda_5_loss: 0.3245 - distribution_lambda_6_loss: 1.4018 - distribution_lambda_7_loss: 0.4927 - val_loss: 2.4057 - val_distribution_lambda_5_loss: 0.4812 - val_distribution_lambda_6_loss: 1.4545 - val_distribution_lambda_7_loss: 0.4701\n", "Epoch 336/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2281 - distribution_lambda_5_loss: 0.3252 - distribution_lambda_6_loss: 1.3981 - distribution_lambda_7_loss: 0.5048 - val_loss: 2.3902 - val_distribution_lambda_5_loss: 0.4716 - val_distribution_lambda_6_loss: 1.4483 - val_distribution_lambda_7_loss: 0.4703\n", "Epoch 337/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2096 - distribution_lambda_5_loss: 0.3188 - distribution_lambda_6_loss: 1.3949 - distribution_lambda_7_loss: 0.4959 - val_loss: 2.4197 - val_distribution_lambda_5_loss: 0.4890 - val_distribution_lambda_6_loss: 1.4612 - val_distribution_lambda_7_loss: 0.4695\n", "Epoch 338/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2122 - distribution_lambda_5_loss: 0.3329 - distribution_lambda_6_loss: 1.3957 - distribution_lambda_7_loss: 0.4836 - val_loss: 2.4062 - val_distribution_lambda_5_loss: 0.4824 - val_distribution_lambda_6_loss: 1.4553 - val_distribution_lambda_7_loss: 0.4685\n", "Epoch 339/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1853 - distribution_lambda_5_loss: 0.3129 - distribution_lambda_6_loss: 1.3766 - distribution_lambda_7_loss: 0.4958 - val_loss: 2.4005 - val_distribution_lambda_5_loss: 0.4789 - val_distribution_lambda_6_loss: 1.4525 - val_distribution_lambda_7_loss: 0.4691\n", "Epoch 340/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2039 - distribution_lambda_5_loss: 0.3147 - distribution_lambda_6_loss: 1.3930 - distribution_lambda_7_loss: 0.4962 - val_loss: 2.4121 - val_distribution_lambda_5_loss: 0.4882 - val_distribution_lambda_6_loss: 1.4536 - val_distribution_lambda_7_loss: 0.4702\n", "Epoch 341/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1907 - distribution_lambda_5_loss: 0.3101 - distribution_lambda_6_loss: 1.3816 - distribution_lambda_7_loss: 0.4990 - val_loss: 2.4365 - val_distribution_lambda_5_loss: 0.5044 - val_distribution_lambda_6_loss: 1.4634 - val_distribution_lambda_7_loss: 0.4687\n", "Epoch 342/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1984 - distribution_lambda_5_loss: 0.3158 - distribution_lambda_6_loss: 1.3958 - distribution_lambda_7_loss: 0.4869 - val_loss: 2.4419 - val_distribution_lambda_5_loss: 0.5141 - val_distribution_lambda_6_loss: 1.4602 - val_distribution_lambda_7_loss: 0.4676\n", "Epoch 343/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1631 - distribution_lambda_5_loss: 0.2983 - distribution_lambda_6_loss: 1.3890 - distribution_lambda_7_loss: 0.4759 - val_loss: 2.4206 - val_distribution_lambda_5_loss: 0.4940 - val_distribution_lambda_6_loss: 1.4590 - val_distribution_lambda_7_loss: 0.4675\n", "Epoch 344/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1870 - distribution_lambda_5_loss: 0.3391 - distribution_lambda_6_loss: 1.3737 - distribution_lambda_7_loss: 0.4742 - val_loss: 2.4087 - val_distribution_lambda_5_loss: 0.4800 - val_distribution_lambda_6_loss: 1.4613 - val_distribution_lambda_7_loss: 0.4673\n", "Epoch 345/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2041 - distribution_lambda_5_loss: 0.3139 - distribution_lambda_6_loss: 1.3980 - distribution_lambda_7_loss: 0.4922 - val_loss: 2.4052 - val_distribution_lambda_5_loss: 0.4774 - val_distribution_lambda_6_loss: 1.4612 - val_distribution_lambda_7_loss: 0.4666\n", "Epoch 346/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1870 - distribution_lambda_5_loss: 0.3169 - distribution_lambda_6_loss: 1.3738 - distribution_lambda_7_loss: 0.4963 - val_loss: 2.4082 - val_distribution_lambda_5_loss: 0.4850 - val_distribution_lambda_6_loss: 1.4567 - val_distribution_lambda_7_loss: 0.4666\n", "Epoch 347/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1704 - distribution_lambda_5_loss: 0.3078 - distribution_lambda_6_loss: 1.3838 - distribution_lambda_7_loss: 0.4788 - val_loss: 2.3957 - val_distribution_lambda_5_loss: 0.4767 - val_distribution_lambda_6_loss: 1.4534 - val_distribution_lambda_7_loss: 0.4656\n", "Epoch 348/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2337 - distribution_lambda_5_loss: 0.3183 - distribution_lambda_6_loss: 1.4069 - distribution_lambda_7_loss: 0.5084 - val_loss: 2.4172 - val_distribution_lambda_5_loss: 0.4869 - val_distribution_lambda_6_loss: 1.4618 - val_distribution_lambda_7_loss: 0.4684\n", "Epoch 349/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1784 - distribution_lambda_5_loss: 0.3071 - distribution_lambda_6_loss: 1.3810 - distribution_lambda_7_loss: 0.4902 - val_loss: 2.4049 - val_distribution_lambda_5_loss: 0.4815 - val_distribution_lambda_6_loss: 1.4537 - val_distribution_lambda_7_loss: 0.4697\n", "Epoch 350/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1833 - distribution_lambda_5_loss: 0.3084 - distribution_lambda_6_loss: 1.3874 - distribution_lambda_7_loss: 0.4874 - val_loss: 2.3928 - val_distribution_lambda_5_loss: 0.4749 - val_distribution_lambda_6_loss: 1.4493 - val_distribution_lambda_7_loss: 0.4686\n", "Epoch 351/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1668 - distribution_lambda_5_loss: 0.2953 - distribution_lambda_6_loss: 1.3815 - distribution_lambda_7_loss: 0.4900 - val_loss: 2.4036 - val_distribution_lambda_5_loss: 0.4833 - val_distribution_lambda_6_loss: 1.4520 - val_distribution_lambda_7_loss: 0.4683\n", "Epoch 352/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.1941 - distribution_lambda_5_loss: 0.3141 - distribution_lambda_6_loss: 1.3874 - distribution_lambda_7_loss: 0.4926 - val_loss: 2.4155 - val_distribution_lambda_5_loss: 0.4900 - val_distribution_lambda_6_loss: 1.4584 - val_distribution_lambda_7_loss: 0.4671\n", "Epoch 353/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.2082 - distribution_lambda_5_loss: 0.3259 - distribution_lambda_6_loss: 1.3999 - distribution_lambda_7_loss: 0.4824 - val_loss: 2.4073 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.4625 - val_distribution_lambda_7_loss: 0.4692\n", "Epoch 354/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1655 - distribution_lambda_5_loss: 0.2740 - distribution_lambda_6_loss: 1.3920 - distribution_lambda_7_loss: 0.4996 - val_loss: 2.4095 - val_distribution_lambda_5_loss: 0.4920 - val_distribution_lambda_6_loss: 1.4506 - val_distribution_lambda_7_loss: 0.4669\n", "Epoch 355/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1584 - distribution_lambda_5_loss: 0.2856 - distribution_lambda_6_loss: 1.3732 - distribution_lambda_7_loss: 0.4996 - val_loss: 2.4297 - val_distribution_lambda_5_loss: 0.5023 - val_distribution_lambda_6_loss: 1.4614 - val_distribution_lambda_7_loss: 0.4660\n", "Epoch 356/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1877 - distribution_lambda_5_loss: 0.3190 - distribution_lambda_6_loss: 1.3828 - distribution_lambda_7_loss: 0.4860 - val_loss: 2.4147 - val_distribution_lambda_5_loss: 0.4936 - val_distribution_lambda_6_loss: 1.4550 - val_distribution_lambda_7_loss: 0.4661\n", "Epoch 357/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1569 - distribution_lambda_5_loss: 0.3037 - distribution_lambda_6_loss: 1.3673 - distribution_lambda_7_loss: 0.4860 - val_loss: 2.4015 - val_distribution_lambda_5_loss: 0.4809 - val_distribution_lambda_6_loss: 1.4554 - val_distribution_lambda_7_loss: 0.4653\n", "Epoch 358/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.1474 - distribution_lambda_5_loss: 0.2818 - distribution_lambda_6_loss: 1.3756 - distribution_lambda_7_loss: 0.4899 - val_loss: 2.4208 - val_distribution_lambda_5_loss: 0.4902 - val_distribution_lambda_6_loss: 1.4646 - val_distribution_lambda_7_loss: 0.4661\n", "Epoch 359/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1437 - distribution_lambda_5_loss: 0.2969 - distribution_lambda_6_loss: 1.3673 - distribution_lambda_7_loss: 0.4796 - val_loss: 2.3889 - val_distribution_lambda_5_loss: 0.4758 - val_distribution_lambda_6_loss: 1.4491 - val_distribution_lambda_7_loss: 0.4640\n", "Epoch 360/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1526 - distribution_lambda_5_loss: 0.2882 - distribution_lambda_6_loss: 1.3788 - distribution_lambda_7_loss: 0.4856 - val_loss: 2.3941 - val_distribution_lambda_5_loss: 0.4860 - val_distribution_lambda_6_loss: 1.4457 - val_distribution_lambda_7_loss: 0.4624\n", "Epoch 361/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1476 - distribution_lambda_5_loss: 0.2927 - distribution_lambda_6_loss: 1.3738 - distribution_lambda_7_loss: 0.4811 - val_loss: 2.4105 - val_distribution_lambda_5_loss: 0.4805 - val_distribution_lambda_6_loss: 1.4669 - val_distribution_lambda_7_loss: 0.4632\n", "Epoch 362/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1740 - distribution_lambda_5_loss: 0.2991 - distribution_lambda_6_loss: 1.3717 - distribution_lambda_7_loss: 0.5032 - val_loss: 2.4221 - val_distribution_lambda_5_loss: 0.4974 - val_distribution_lambda_6_loss: 1.4618 - val_distribution_lambda_7_loss: 0.4630\n", "Epoch 363/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1977 - distribution_lambda_5_loss: 0.3121 - distribution_lambda_6_loss: 1.3890 - distribution_lambda_7_loss: 0.4966 - val_loss: 2.3943 - val_distribution_lambda_5_loss: 0.4770 - val_distribution_lambda_6_loss: 1.4532 - val_distribution_lambda_7_loss: 0.4641\n", "Epoch 364/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1261 - distribution_lambda_5_loss: 0.2670 - distribution_lambda_6_loss: 1.3818 - distribution_lambda_7_loss: 0.4773 - val_loss: 2.4153 - val_distribution_lambda_5_loss: 0.4936 - val_distribution_lambda_6_loss: 1.4571 - val_distribution_lambda_7_loss: 0.4646\n", "Epoch 365/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1501 - distribution_lambda_5_loss: 0.2985 - distribution_lambda_6_loss: 1.3749 - distribution_lambda_7_loss: 0.4767 - val_loss: 2.3976 - val_distribution_lambda_5_loss: 0.4801 - val_distribution_lambda_6_loss: 1.4539 - val_distribution_lambda_7_loss: 0.4636\n", "Epoch 366/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1537 - distribution_lambda_5_loss: 0.2909 - distribution_lambda_6_loss: 1.3700 - distribution_lambda_7_loss: 0.4929 - val_loss: 2.4007 - val_distribution_lambda_5_loss: 0.4863 - val_distribution_lambda_6_loss: 1.4507 - val_distribution_lambda_7_loss: 0.4637\n", "Epoch 367/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1552 - distribution_lambda_5_loss: 0.2936 - distribution_lambda_6_loss: 1.3755 - distribution_lambda_7_loss: 0.4861 - val_loss: 2.4036 - val_distribution_lambda_5_loss: 0.4898 - val_distribution_lambda_6_loss: 1.4510 - val_distribution_lambda_7_loss: 0.4628\n", "Epoch 368/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1545 - distribution_lambda_5_loss: 0.3018 - distribution_lambda_6_loss: 1.3762 - distribution_lambda_7_loss: 0.4765 - val_loss: 2.3846 - val_distribution_lambda_5_loss: 0.4791 - val_distribution_lambda_6_loss: 1.4430 - val_distribution_lambda_7_loss: 0.4625\n", "Epoch 369/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1224 - distribution_lambda_5_loss: 0.2839 - distribution_lambda_6_loss: 1.3594 - distribution_lambda_7_loss: 0.4792 - val_loss: 2.3855 - val_distribution_lambda_5_loss: 0.4795 - val_distribution_lambda_6_loss: 1.4436 - val_distribution_lambda_7_loss: 0.4623\n", "Epoch 370/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.2060 - distribution_lambda_5_loss: 0.2999 - distribution_lambda_6_loss: 1.4112 - distribution_lambda_7_loss: 0.4949 - val_loss: 2.3915 - val_distribution_lambda_5_loss: 0.4809 - val_distribution_lambda_6_loss: 1.4475 - val_distribution_lambda_7_loss: 0.4631\n", "Epoch 371/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1402 - distribution_lambda_5_loss: 0.2844 - distribution_lambda_6_loss: 1.3748 - distribution_lambda_7_loss: 0.4810 - val_loss: 2.3904 - val_distribution_lambda_5_loss: 0.4818 - val_distribution_lambda_6_loss: 1.4454 - val_distribution_lambda_7_loss: 0.4632\n", "Epoch 372/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1481 - distribution_lambda_5_loss: 0.2781 - distribution_lambda_6_loss: 1.3785 - distribution_lambda_7_loss: 0.4915 - val_loss: 2.3937 - val_distribution_lambda_5_loss: 0.4821 - val_distribution_lambda_6_loss: 1.4488 - val_distribution_lambda_7_loss: 0.4628\n", "Epoch 373/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1514 - distribution_lambda_5_loss: 0.3058 - distribution_lambda_6_loss: 1.3663 - distribution_lambda_7_loss: 0.4793 - val_loss: 2.3900 - val_distribution_lambda_5_loss: 0.4728 - val_distribution_lambda_6_loss: 1.4539 - val_distribution_lambda_7_loss: 0.4633\n", "Epoch 374/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1451 - distribution_lambda_5_loss: 0.2877 - distribution_lambda_6_loss: 1.3733 - distribution_lambda_7_loss: 0.4841 - val_loss: 2.3995 - val_distribution_lambda_5_loss: 0.4851 - val_distribution_lambda_6_loss: 1.4511 - val_distribution_lambda_7_loss: 0.4634\n", "Epoch 375/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0984 - distribution_lambda_5_loss: 0.2662 - distribution_lambda_6_loss: 1.3649 - distribution_lambda_7_loss: 0.4672 - val_loss: 2.4194 - val_distribution_lambda_5_loss: 0.5033 - val_distribution_lambda_6_loss: 1.4537 - val_distribution_lambda_7_loss: 0.4624\n", "Epoch 376/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1499 - distribution_lambda_5_loss: 0.2964 - distribution_lambda_6_loss: 1.3641 - distribution_lambda_7_loss: 0.4894 - val_loss: 2.3851 - val_distribution_lambda_5_loss: 0.4813 - val_distribution_lambda_6_loss: 1.4432 - val_distribution_lambda_7_loss: 0.4605\n", "Epoch 377/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1152 - distribution_lambda_5_loss: 0.2753 - distribution_lambda_6_loss: 1.3615 - distribution_lambda_7_loss: 0.4784 - val_loss: 2.3912 - val_distribution_lambda_5_loss: 0.4833 - val_distribution_lambda_6_loss: 1.4469 - val_distribution_lambda_7_loss: 0.4610\n", "Epoch 378/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1785 - distribution_lambda_5_loss: 0.2992 - distribution_lambda_6_loss: 1.3749 - distribution_lambda_7_loss: 0.5044 - val_loss: 2.3947 - val_distribution_lambda_5_loss: 0.4863 - val_distribution_lambda_6_loss: 1.4472 - val_distribution_lambda_7_loss: 0.4612\n", "Epoch 379/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1853 - distribution_lambda_5_loss: 0.3163 - distribution_lambda_6_loss: 1.3801 - distribution_lambda_7_loss: 0.4889 - val_loss: 2.3974 - val_distribution_lambda_5_loss: 0.4897 - val_distribution_lambda_6_loss: 1.4491 - val_distribution_lambda_7_loss: 0.4586\n", "Epoch 380/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1360 - distribution_lambda_5_loss: 0.2852 - distribution_lambda_6_loss: 1.3704 - distribution_lambda_7_loss: 0.4804 - val_loss: 2.3583 - val_distribution_lambda_5_loss: 0.4694 - val_distribution_lambda_6_loss: 1.4317 - val_distribution_lambda_7_loss: 0.4572\n", "Epoch 381/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1674 - distribution_lambda_5_loss: 0.2867 - distribution_lambda_6_loss: 1.3841 - distribution_lambda_7_loss: 0.4965 - val_loss: 2.3721 - val_distribution_lambda_5_loss: 0.4738 - val_distribution_lambda_6_loss: 1.4392 - val_distribution_lambda_7_loss: 0.4591\n", "Epoch 382/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.1481 - distribution_lambda_5_loss: 0.2910 - distribution_lambda_6_loss: 1.3706 - distribution_lambda_7_loss: 0.4865 - val_loss: 2.3726 - val_distribution_lambda_5_loss: 0.4750 - val_distribution_lambda_6_loss: 1.4403 - val_distribution_lambda_7_loss: 0.4573\n", "Epoch 383/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1746 - distribution_lambda_5_loss: 0.3016 - distribution_lambda_6_loss: 1.3827 - distribution_lambda_7_loss: 0.4904 - val_loss: 2.3884 - val_distribution_lambda_5_loss: 0.4799 - val_distribution_lambda_6_loss: 1.4486 - val_distribution_lambda_7_loss: 0.4599\n", "Epoch 384/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1323 - distribution_lambda_5_loss: 0.2967 - distribution_lambda_6_loss: 1.3574 - distribution_lambda_7_loss: 0.4782 - val_loss: 2.3668 - val_distribution_lambda_5_loss: 0.4707 - val_distribution_lambda_6_loss: 1.4387 - val_distribution_lambda_7_loss: 0.4575\n", "Epoch 385/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1514 - distribution_lambda_5_loss: 0.2934 - distribution_lambda_6_loss: 1.3761 - distribution_lambda_7_loss: 0.4819 - val_loss: 2.3705 - val_distribution_lambda_5_loss: 0.4708 - val_distribution_lambda_6_loss: 1.4410 - val_distribution_lambda_7_loss: 0.4587\n", "Epoch 386/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1144 - distribution_lambda_5_loss: 0.2797 - distribution_lambda_6_loss: 1.3577 - distribution_lambda_7_loss: 0.4771 - val_loss: 2.3684 - val_distribution_lambda_5_loss: 0.4708 - val_distribution_lambda_6_loss: 1.4403 - val_distribution_lambda_7_loss: 0.4573\n", "Epoch 387/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1181 - distribution_lambda_5_loss: 0.2836 - distribution_lambda_6_loss: 1.3516 - distribution_lambda_7_loss: 0.4830 - val_loss: 2.3812 - val_distribution_lambda_5_loss: 0.4791 - val_distribution_lambda_6_loss: 1.4449 - val_distribution_lambda_7_loss: 0.4572\n", "Epoch 388/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1340 - distribution_lambda_5_loss: 0.2867 - distribution_lambda_6_loss: 1.3622 - distribution_lambda_7_loss: 0.4851 - val_loss: 2.3660 - val_distribution_lambda_5_loss: 0.4789 - val_distribution_lambda_6_loss: 1.4310 - val_distribution_lambda_7_loss: 0.4561\n", "Epoch 389/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0988 - distribution_lambda_5_loss: 0.2760 - distribution_lambda_6_loss: 1.3547 - distribution_lambda_7_loss: 0.4681 - val_loss: 2.4047 - val_distribution_lambda_5_loss: 0.5025 - val_distribution_lambda_6_loss: 1.4471 - val_distribution_lambda_7_loss: 0.4551\n", "Epoch 390/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1608 - distribution_lambda_5_loss: 0.2996 - distribution_lambda_6_loss: 1.3737 - distribution_lambda_7_loss: 0.4875 - val_loss: 2.3878 - val_distribution_lambda_5_loss: 0.4806 - val_distribution_lambda_6_loss: 1.4505 - val_distribution_lambda_7_loss: 0.4567\n", "Epoch 391/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1224 - distribution_lambda_5_loss: 0.2841 - distribution_lambda_6_loss: 1.3637 - distribution_lambda_7_loss: 0.4746 - val_loss: 2.3761 - val_distribution_lambda_5_loss: 0.4770 - val_distribution_lambda_6_loss: 1.4438 - val_distribution_lambda_7_loss: 0.4552\n", "Epoch 392/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0839 - distribution_lambda_5_loss: 0.2745 - distribution_lambda_6_loss: 1.3452 - distribution_lambda_7_loss: 0.4642 - val_loss: 2.3692 - val_distribution_lambda_5_loss: 0.4831 - val_distribution_lambda_6_loss: 1.4340 - val_distribution_lambda_7_loss: 0.4521\n", "Epoch 393/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1419 - distribution_lambda_5_loss: 0.2981 - distribution_lambda_6_loss: 1.3600 - distribution_lambda_7_loss: 0.4838 - val_loss: 2.3681 - val_distribution_lambda_5_loss: 0.4720 - val_distribution_lambda_6_loss: 1.4438 - val_distribution_lambda_7_loss: 0.4523\n", "Epoch 394/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1050 - distribution_lambda_5_loss: 0.2722 - distribution_lambda_6_loss: 1.3630 - distribution_lambda_7_loss: 0.4698 - val_loss: 2.3723 - val_distribution_lambda_5_loss: 0.4821 - val_distribution_lambda_6_loss: 1.4382 - val_distribution_lambda_7_loss: 0.4520\n", "Epoch 395/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1050 - distribution_lambda_5_loss: 0.2677 - distribution_lambda_6_loss: 1.3575 - distribution_lambda_7_loss: 0.4797 - val_loss: 2.3887 - val_distribution_lambda_5_loss: 0.4886 - val_distribution_lambda_6_loss: 1.4443 - val_distribution_lambda_7_loss: 0.4558\n", "Epoch 396/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1201 - distribution_lambda_5_loss: 0.2799 - distribution_lambda_6_loss: 1.3587 - distribution_lambda_7_loss: 0.4815 - val_loss: 2.3676 - val_distribution_lambda_5_loss: 0.4763 - val_distribution_lambda_6_loss: 1.4366 - val_distribution_lambda_7_loss: 0.4547\n", "Epoch 397/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1074 - distribution_lambda_5_loss: 0.2821 - distribution_lambda_6_loss: 1.3569 - distribution_lambda_7_loss: 0.4685 - val_loss: 2.3547 - val_distribution_lambda_5_loss: 0.4670 - val_distribution_lambda_6_loss: 1.4331 - val_distribution_lambda_7_loss: 0.4546\n", "Epoch 398/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1322 - distribution_lambda_5_loss: 0.2839 - distribution_lambda_6_loss: 1.3637 - distribution_lambda_7_loss: 0.4847 - val_loss: 2.3543 - val_distribution_lambda_5_loss: 0.4678 - val_distribution_lambda_6_loss: 1.4315 - val_distribution_lambda_7_loss: 0.4549\n", "Epoch 399/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1300 - distribution_lambda_5_loss: 0.2757 - distribution_lambda_6_loss: 1.3691 - distribution_lambda_7_loss: 0.4852 - val_loss: 2.3759 - val_distribution_lambda_5_loss: 0.4778 - val_distribution_lambda_6_loss: 1.4417 - val_distribution_lambda_7_loss: 0.4563\n", "Epoch 400/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0980 - distribution_lambda_5_loss: 0.2766 - distribution_lambda_6_loss: 1.3510 - distribution_lambda_7_loss: 0.4704 - val_loss: 2.3687 - val_distribution_lambda_5_loss: 0.4726 - val_distribution_lambda_6_loss: 1.4398 - val_distribution_lambda_7_loss: 0.4562\n", "Epoch 401/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1195 - distribution_lambda_5_loss: 0.2738 - distribution_lambda_6_loss: 1.3611 - distribution_lambda_7_loss: 0.4846 - val_loss: 2.3690 - val_distribution_lambda_5_loss: 0.4710 - val_distribution_lambda_6_loss: 1.4426 - val_distribution_lambda_7_loss: 0.4554\n", "Epoch 402/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1029 - distribution_lambda_5_loss: 0.2731 - distribution_lambda_6_loss: 1.3544 - distribution_lambda_7_loss: 0.4754 - val_loss: 2.3568 - val_distribution_lambda_5_loss: 0.4709 - val_distribution_lambda_6_loss: 1.4325 - val_distribution_lambda_7_loss: 0.4535\n", "Epoch 403/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1420 - distribution_lambda_5_loss: 0.2969 - distribution_lambda_6_loss: 1.3683 - distribution_lambda_7_loss: 0.4768 - val_loss: 2.3488 - val_distribution_lambda_5_loss: 0.4602 - val_distribution_lambda_6_loss: 1.4362 - val_distribution_lambda_7_loss: 0.4525\n", "Epoch 404/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1159 - distribution_lambda_5_loss: 0.2805 - distribution_lambda_6_loss: 1.3629 - distribution_lambda_7_loss: 0.4725 - val_loss: 2.3456 - val_distribution_lambda_5_loss: 0.4679 - val_distribution_lambda_6_loss: 1.4287 - val_distribution_lambda_7_loss: 0.4490\n", "Epoch 405/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0666 - distribution_lambda_5_loss: 0.2608 - distribution_lambda_6_loss: 1.3408 - distribution_lambda_7_loss: 0.4651 - val_loss: 2.3581 - val_distribution_lambda_5_loss: 0.4772 - val_distribution_lambda_6_loss: 1.4330 - val_distribution_lambda_7_loss: 0.4479\n", "Epoch 406/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.1223 - distribution_lambda_5_loss: 0.2989 - distribution_lambda_6_loss: 1.3464 - distribution_lambda_7_loss: 0.4771 - val_loss: 2.3516 - val_distribution_lambda_5_loss: 0.4690 - val_distribution_lambda_6_loss: 1.4342 - val_distribution_lambda_7_loss: 0.4484\n", "Epoch 407/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0931 - distribution_lambda_5_loss: 0.2572 - distribution_lambda_6_loss: 1.3541 - distribution_lambda_7_loss: 0.4818 - val_loss: 2.3655 - val_distribution_lambda_5_loss: 0.4807 - val_distribution_lambda_6_loss: 1.4353 - val_distribution_lambda_7_loss: 0.4495\n", "Epoch 408/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1160 - distribution_lambda_5_loss: 0.2838 - distribution_lambda_6_loss: 1.3503 - distribution_lambda_7_loss: 0.4819 - val_loss: 2.3839 - val_distribution_lambda_5_loss: 0.4885 - val_distribution_lambda_6_loss: 1.4447 - val_distribution_lambda_7_loss: 0.4507\n", "Epoch 409/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1335 - distribution_lambda_5_loss: 0.2801 - distribution_lambda_6_loss: 1.3611 - distribution_lambda_7_loss: 0.4923 - val_loss: 2.3725 - val_distribution_lambda_5_loss: 0.4899 - val_distribution_lambda_6_loss: 1.4318 - val_distribution_lambda_7_loss: 0.4508\n", "Epoch 410/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1066 - distribution_lambda_5_loss: 0.2628 - distribution_lambda_6_loss: 1.3535 - distribution_lambda_7_loss: 0.4903 - val_loss: 2.3575 - val_distribution_lambda_5_loss: 0.4845 - val_distribution_lambda_6_loss: 1.4231 - val_distribution_lambda_7_loss: 0.4499\n", "Epoch 411/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1334 - distribution_lambda_5_loss: 0.2798 - distribution_lambda_6_loss: 1.3579 - distribution_lambda_7_loss: 0.4958 - val_loss: 2.3661 - val_distribution_lambda_5_loss: 0.4874 - val_distribution_lambda_6_loss: 1.4275 - val_distribution_lambda_7_loss: 0.4512\n", "Epoch 412/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1305 - distribution_lambda_5_loss: 0.2923 - distribution_lambda_6_loss: 1.3556 - distribution_lambda_7_loss: 0.4827 - val_loss: 2.3546 - val_distribution_lambda_5_loss: 0.4809 - val_distribution_lambda_6_loss: 1.4241 - val_distribution_lambda_7_loss: 0.4496\n", "Epoch 413/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1048 - distribution_lambda_5_loss: 0.2637 - distribution_lambda_6_loss: 1.3638 - distribution_lambda_7_loss: 0.4772 - val_loss: 2.3511 - val_distribution_lambda_5_loss: 0.4742 - val_distribution_lambda_6_loss: 1.4285 - val_distribution_lambda_7_loss: 0.4484\n", "Epoch 414/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1081 - distribution_lambda_5_loss: 0.2665 - distribution_lambda_6_loss: 1.3697 - distribution_lambda_7_loss: 0.4719 - val_loss: 2.3482 - val_distribution_lambda_5_loss: 0.4742 - val_distribution_lambda_6_loss: 1.4273 - val_distribution_lambda_7_loss: 0.4467\n", "Epoch 415/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1149 - distribution_lambda_5_loss: 0.2824 - distribution_lambda_6_loss: 1.3564 - distribution_lambda_7_loss: 0.4761 - val_loss: 2.3602 - val_distribution_lambda_5_loss: 0.4859 - val_distribution_lambda_6_loss: 1.4284 - val_distribution_lambda_7_loss: 0.4460\n", "Epoch 416/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0991 - distribution_lambda_5_loss: 0.2863 - distribution_lambda_6_loss: 1.3582 - distribution_lambda_7_loss: 0.4546 - val_loss: 2.3494 - val_distribution_lambda_5_loss: 0.4791 - val_distribution_lambda_6_loss: 1.4255 - val_distribution_lambda_7_loss: 0.4448\n", "Epoch 417/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0993 - distribution_lambda_5_loss: 0.2688 - distribution_lambda_6_loss: 1.3539 - distribution_lambda_7_loss: 0.4766 - val_loss: 2.3367 - val_distribution_lambda_5_loss: 0.4650 - val_distribution_lambda_6_loss: 1.4253 - val_distribution_lambda_7_loss: 0.4465\n", "Epoch 418/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0951 - distribution_lambda_5_loss: 0.2782 - distribution_lambda_6_loss: 1.3464 - distribution_lambda_7_loss: 0.4704 - val_loss: 2.3456 - val_distribution_lambda_5_loss: 0.4708 - val_distribution_lambda_6_loss: 1.4278 - val_distribution_lambda_7_loss: 0.4470\n", "Epoch 419/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1039 - distribution_lambda_5_loss: 0.2772 - distribution_lambda_6_loss: 1.3527 - distribution_lambda_7_loss: 0.4740 - val_loss: 2.3538 - val_distribution_lambda_5_loss: 0.4709 - val_distribution_lambda_6_loss: 1.4358 - val_distribution_lambda_7_loss: 0.4470\n", "Epoch 420/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0883 - distribution_lambda_5_loss: 0.2632 - distribution_lambda_6_loss: 1.3447 - distribution_lambda_7_loss: 0.4804 - val_loss: 2.3426 - val_distribution_lambda_5_loss: 0.4671 - val_distribution_lambda_6_loss: 1.4278 - val_distribution_lambda_7_loss: 0.4477\n", "Epoch 421/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0683 - distribution_lambda_5_loss: 0.2516 - distribution_lambda_6_loss: 1.3440 - distribution_lambda_7_loss: 0.4727 - val_loss: 2.3445 - val_distribution_lambda_5_loss: 0.4715 - val_distribution_lambda_6_loss: 1.4250 - val_distribution_lambda_7_loss: 0.4480\n", "Epoch 422/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0702 - distribution_lambda_5_loss: 0.2834 - distribution_lambda_6_loss: 1.3322 - distribution_lambda_7_loss: 0.4546 - val_loss: 2.3486 - val_distribution_lambda_5_loss: 0.4638 - val_distribution_lambda_6_loss: 1.4380 - val_distribution_lambda_7_loss: 0.4468\n", "Epoch 423/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1017 - distribution_lambda_5_loss: 0.2761 - distribution_lambda_6_loss: 1.3472 - distribution_lambda_7_loss: 0.4784 - val_loss: 2.3726 - val_distribution_lambda_5_loss: 0.4779 - val_distribution_lambda_6_loss: 1.4471 - val_distribution_lambda_7_loss: 0.4475\n", "Epoch 424/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0641 - distribution_lambda_5_loss: 0.2580 - distribution_lambda_6_loss: 1.3408 - distribution_lambda_7_loss: 0.4652 - val_loss: 2.3574 - val_distribution_lambda_5_loss: 0.4787 - val_distribution_lambda_6_loss: 1.4316 - val_distribution_lambda_7_loss: 0.4472\n", "Epoch 425/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1048 - distribution_lambda_5_loss: 0.2847 - distribution_lambda_6_loss: 1.3456 - distribution_lambda_7_loss: 0.4745 - val_loss: 2.3576 - val_distribution_lambda_5_loss: 0.4766 - val_distribution_lambda_6_loss: 1.4367 - val_distribution_lambda_7_loss: 0.4444\n", "Epoch 426/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.1030 - distribution_lambda_5_loss: 0.2749 - distribution_lambda_6_loss: 1.3522 - distribution_lambda_7_loss: 0.4759 - val_loss: 2.3395 - val_distribution_lambda_5_loss: 0.4664 - val_distribution_lambda_6_loss: 1.4305 - val_distribution_lambda_7_loss: 0.4426\n", "Epoch 427/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0567 - distribution_lambda_5_loss: 0.2519 - distribution_lambda_6_loss: 1.3293 - distribution_lambda_7_loss: 0.4754 - val_loss: 2.3482 - val_distribution_lambda_5_loss: 0.4771 - val_distribution_lambda_6_loss: 1.4289 - val_distribution_lambda_7_loss: 0.4423\n", "Epoch 428/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0681 - distribution_lambda_5_loss: 0.2628 - distribution_lambda_6_loss: 1.3350 - distribution_lambda_7_loss: 0.4703 - val_loss: 2.3471 - val_distribution_lambda_5_loss: 0.4809 - val_distribution_lambda_6_loss: 1.4225 - val_distribution_lambda_7_loss: 0.4438\n", "Epoch 429/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0821 - distribution_lambda_5_loss: 0.2696 - distribution_lambda_6_loss: 1.3380 - distribution_lambda_7_loss: 0.4745 - val_loss: 2.3640 - val_distribution_lambda_5_loss: 0.4841 - val_distribution_lambda_6_loss: 1.4346 - val_distribution_lambda_7_loss: 0.4452\n", "Epoch 430/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 2.0885 - distribution_lambda_5_loss: 0.2697 - distribution_lambda_6_loss: 1.3541 - distribution_lambda_7_loss: 0.4646 - val_loss: 2.3558 - val_distribution_lambda_5_loss: 0.4773 - val_distribution_lambda_6_loss: 1.4295 - val_distribution_lambda_7_loss: 0.4490\n", "Epoch 431/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0724 - distribution_lambda_5_loss: 0.2544 - distribution_lambda_6_loss: 1.3519 - distribution_lambda_7_loss: 0.4661 - val_loss: 2.3535 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.4321 - val_distribution_lambda_7_loss: 0.4459\n", "Epoch 432/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1039 - distribution_lambda_5_loss: 0.2594 - distribution_lambda_6_loss: 1.3522 - distribution_lambda_7_loss: 0.4922 - val_loss: 2.3623 - val_distribution_lambda_5_loss: 0.4777 - val_distribution_lambda_6_loss: 1.4382 - val_distribution_lambda_7_loss: 0.4464\n", "Epoch 433/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0437 - distribution_lambda_5_loss: 0.2538 - distribution_lambda_6_loss: 1.3175 - distribution_lambda_7_loss: 0.4724 - val_loss: 2.3539 - val_distribution_lambda_5_loss: 0.4835 - val_distribution_lambda_6_loss: 1.4256 - val_distribution_lambda_7_loss: 0.4448\n", "Epoch 434/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0938 - distribution_lambda_5_loss: 0.2600 - distribution_lambda_6_loss: 1.3535 - distribution_lambda_7_loss: 0.4803 - val_loss: 2.3583 - val_distribution_lambda_5_loss: 0.4745 - val_distribution_lambda_6_loss: 1.4372 - val_distribution_lambda_7_loss: 0.4466\n", "Epoch 435/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0856 - distribution_lambda_5_loss: 0.2706 - distribution_lambda_6_loss: 1.3450 - distribution_lambda_7_loss: 0.4700 - val_loss: 2.3496 - val_distribution_lambda_5_loss: 0.4778 - val_distribution_lambda_6_loss: 1.4271 - val_distribution_lambda_7_loss: 0.4447\n", "Epoch 436/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0956 - distribution_lambda_5_loss: 0.2780 - distribution_lambda_6_loss: 1.3453 - distribution_lambda_7_loss: 0.4723 - val_loss: 2.3458 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.4251 - val_distribution_lambda_7_loss: 0.4451\n", "Epoch 437/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0748 - distribution_lambda_5_loss: 0.2605 - distribution_lambda_6_loss: 1.3442 - distribution_lambda_7_loss: 0.4701 - val_loss: 2.3403 - val_distribution_lambda_5_loss: 0.4691 - val_distribution_lambda_6_loss: 1.4271 - val_distribution_lambda_7_loss: 0.4440\n", "Epoch 438/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0840 - distribution_lambda_5_loss: 0.2709 - distribution_lambda_6_loss: 1.3424 - distribution_lambda_7_loss: 0.4708 - val_loss: 2.3224 - val_distribution_lambda_5_loss: 0.4552 - val_distribution_lambda_6_loss: 1.4246 - val_distribution_lambda_7_loss: 0.4426\n", "Epoch 439/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0691 - distribution_lambda_5_loss: 0.2502 - distribution_lambda_6_loss: 1.3398 - distribution_lambda_7_loss: 0.4791 - val_loss: 2.3255 - val_distribution_lambda_5_loss: 0.4562 - val_distribution_lambda_6_loss: 1.4274 - val_distribution_lambda_7_loss: 0.4420\n", "Epoch 440/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0678 - distribution_lambda_5_loss: 0.2495 - distribution_lambda_6_loss: 1.3372 - distribution_lambda_7_loss: 0.4810 - val_loss: 2.3382 - val_distribution_lambda_5_loss: 0.4584 - val_distribution_lambda_6_loss: 1.4369 - val_distribution_lambda_7_loss: 0.4429\n", "Epoch 441/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0867 - distribution_lambda_5_loss: 0.2547 - distribution_lambda_6_loss: 1.3576 - distribution_lambda_7_loss: 0.4744 - val_loss: 2.3458 - val_distribution_lambda_5_loss: 0.4666 - val_distribution_lambda_6_loss: 1.4356 - val_distribution_lambda_7_loss: 0.4436\n", "Epoch 442/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.1124 - distribution_lambda_5_loss: 0.2889 - distribution_lambda_6_loss: 1.3508 - distribution_lambda_7_loss: 0.4728 - val_loss: 2.3460 - val_distribution_lambda_5_loss: 0.4606 - val_distribution_lambda_6_loss: 1.4420 - val_distribution_lambda_7_loss: 0.4434\n", "Epoch 443/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0422 - distribution_lambda_5_loss: 0.2677 - distribution_lambda_6_loss: 1.3208 - distribution_lambda_7_loss: 0.4537 - val_loss: 2.3380 - val_distribution_lambda_5_loss: 0.4639 - val_distribution_lambda_6_loss: 1.4320 - val_distribution_lambda_7_loss: 0.4420\n", "Epoch 444/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0751 - distribution_lambda_5_loss: 0.2608 - distribution_lambda_6_loss: 1.3433 - distribution_lambda_7_loss: 0.4710 - val_loss: 2.3414 - val_distribution_lambda_5_loss: 0.4628 - val_distribution_lambda_6_loss: 1.4368 - val_distribution_lambda_7_loss: 0.4419\n", "Epoch 445/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0656 - distribution_lambda_5_loss: 0.2696 - distribution_lambda_6_loss: 1.3320 - distribution_lambda_7_loss: 0.4641 - val_loss: 2.3313 - val_distribution_lambda_5_loss: 0.4641 - val_distribution_lambda_6_loss: 1.4267 - val_distribution_lambda_7_loss: 0.4405\n", "Epoch 446/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0618 - distribution_lambda_5_loss: 0.2572 - distribution_lambda_6_loss: 1.3484 - distribution_lambda_7_loss: 0.4561 - val_loss: 2.3413 - val_distribution_lambda_5_loss: 0.4693 - val_distribution_lambda_6_loss: 1.4316 - val_distribution_lambda_7_loss: 0.4404\n", "Epoch 447/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0626 - distribution_lambda_5_loss: 0.2617 - distribution_lambda_6_loss: 1.3406 - distribution_lambda_7_loss: 0.4604 - val_loss: 2.3473 - val_distribution_lambda_5_loss: 0.4655 - val_distribution_lambda_6_loss: 1.4413 - val_distribution_lambda_7_loss: 0.4405\n", "Epoch 448/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0257 - distribution_lambda_5_loss: 0.2459 - distribution_lambda_6_loss: 1.3236 - distribution_lambda_7_loss: 0.4563 - val_loss: 2.3226 - val_distribution_lambda_5_loss: 0.4587 - val_distribution_lambda_6_loss: 1.4236 - val_distribution_lambda_7_loss: 0.4403\n", "Epoch 449/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0531 - distribution_lambda_5_loss: 0.2417 - distribution_lambda_6_loss: 1.3481 - distribution_lambda_7_loss: 0.4633 - val_loss: 2.3533 - val_distribution_lambda_5_loss: 0.4680 - val_distribution_lambda_6_loss: 1.4441 - val_distribution_lambda_7_loss: 0.4412\n", "Epoch 450/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0513 - distribution_lambda_5_loss: 0.2572 - distribution_lambda_6_loss: 1.3365 - distribution_lambda_7_loss: 0.4577 - val_loss: 2.3351 - val_distribution_lambda_5_loss: 0.4651 - val_distribution_lambda_6_loss: 1.4276 - val_distribution_lambda_7_loss: 0.4424\n", "Epoch 451/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0253 - distribution_lambda_5_loss: 0.2416 - distribution_lambda_6_loss: 1.3247 - distribution_lambda_7_loss: 0.4589 - val_loss: 2.3326 - val_distribution_lambda_5_loss: 0.4662 - val_distribution_lambda_6_loss: 1.4256 - val_distribution_lambda_7_loss: 0.4408\n", "Epoch 452/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0724 - distribution_lambda_5_loss: 0.2737 - distribution_lambda_6_loss: 1.3279 - distribution_lambda_7_loss: 0.4708 - val_loss: 2.3437 - val_distribution_lambda_5_loss: 0.4693 - val_distribution_lambda_6_loss: 1.4318 - val_distribution_lambda_7_loss: 0.4426\n", "Epoch 453/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0296 - distribution_lambda_5_loss: 0.2335 - distribution_lambda_6_loss: 1.3310 - distribution_lambda_7_loss: 0.4652 - val_loss: 2.3429 - val_distribution_lambda_5_loss: 0.4786 - val_distribution_lambda_6_loss: 1.4258 - val_distribution_lambda_7_loss: 0.4385\n", "Epoch 454/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.0335 - distribution_lambda_5_loss: 0.2312 - distribution_lambda_6_loss: 1.3290 - distribution_lambda_7_loss: 0.4734 - val_loss: 2.3692 - val_distribution_lambda_5_loss: 0.4970 - val_distribution_lambda_6_loss: 1.4319 - val_distribution_lambda_7_loss: 0.4404\n", "Epoch 455/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0615 - distribution_lambda_5_loss: 0.2599 - distribution_lambda_6_loss: 1.3323 - distribution_lambda_7_loss: 0.4692 - val_loss: 2.3564 - val_distribution_lambda_5_loss: 0.4793 - val_distribution_lambda_6_loss: 1.4360 - val_distribution_lambda_7_loss: 0.4410\n", "Epoch 456/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0841 - distribution_lambda_5_loss: 0.2642 - distribution_lambda_6_loss: 1.3436 - distribution_lambda_7_loss: 0.4763 - val_loss: 2.3366 - val_distribution_lambda_5_loss: 0.4656 - val_distribution_lambda_6_loss: 1.4297 - val_distribution_lambda_7_loss: 0.4413\n", "Epoch 457/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0314 - distribution_lambda_5_loss: 0.2478 - distribution_lambda_6_loss: 1.3155 - distribution_lambda_7_loss: 0.4682 - val_loss: 2.3499 - val_distribution_lambda_5_loss: 0.4742 - val_distribution_lambda_6_loss: 1.4336 - val_distribution_lambda_7_loss: 0.4421\n", "Epoch 458/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0597 - distribution_lambda_5_loss: 0.2662 - distribution_lambda_6_loss: 1.3293 - distribution_lambda_7_loss: 0.4642 - val_loss: 2.3361 - val_distribution_lambda_5_loss: 0.4677 - val_distribution_lambda_6_loss: 1.4258 - val_distribution_lambda_7_loss: 0.4425\n", "Epoch 459/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0425 - distribution_lambda_5_loss: 0.2484 - distribution_lambda_6_loss: 1.3302 - distribution_lambda_7_loss: 0.4638 - val_loss: 2.3632 - val_distribution_lambda_5_loss: 0.4779 - val_distribution_lambda_6_loss: 1.4404 - val_distribution_lambda_7_loss: 0.4450\n", "Epoch 460/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0805 - distribution_lambda_5_loss: 0.2534 - distribution_lambda_6_loss: 1.3410 - distribution_lambda_7_loss: 0.4861 - val_loss: 2.3397 - val_distribution_lambda_5_loss: 0.4712 - val_distribution_lambda_6_loss: 1.4256 - val_distribution_lambda_7_loss: 0.4429\n", "Epoch 461/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0454 - distribution_lambda_5_loss: 0.2475 - distribution_lambda_6_loss: 1.3312 - distribution_lambda_7_loss: 0.4667 - val_loss: 2.3389 - val_distribution_lambda_5_loss: 0.4759 - val_distribution_lambda_6_loss: 1.4214 - val_distribution_lambda_7_loss: 0.4416\n", "Epoch 462/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0806 - distribution_lambda_5_loss: 0.2754 - distribution_lambda_6_loss: 1.3360 - distribution_lambda_7_loss: 0.4691 - val_loss: 2.3291 - val_distribution_lambda_5_loss: 0.4656 - val_distribution_lambda_6_loss: 1.4257 - val_distribution_lambda_7_loss: 0.4377\n", "Epoch 463/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0693 - distribution_lambda_5_loss: 0.2600 - distribution_lambda_6_loss: 1.3348 - distribution_lambda_7_loss: 0.4746 - val_loss: 2.3163 - val_distribution_lambda_5_loss: 0.4599 - val_distribution_lambda_6_loss: 1.4187 - val_distribution_lambda_7_loss: 0.4377\n", "Epoch 464/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0222 - distribution_lambda_5_loss: 0.2394 - distribution_lambda_6_loss: 1.3169 - distribution_lambda_7_loss: 0.4660 - val_loss: 2.3192 - val_distribution_lambda_5_loss: 0.4578 - val_distribution_lambda_6_loss: 1.4229 - val_distribution_lambda_7_loss: 0.4386\n", "Epoch 465/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0584 - distribution_lambda_5_loss: 0.2435 - distribution_lambda_6_loss: 1.3403 - distribution_lambda_7_loss: 0.4745 - val_loss: 2.3338 - val_distribution_lambda_5_loss: 0.4773 - val_distribution_lambda_6_loss: 1.4193 - val_distribution_lambda_7_loss: 0.4372\n", "Epoch 466/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0691 - distribution_lambda_5_loss: 0.2517 - distribution_lambda_6_loss: 1.3383 - distribution_lambda_7_loss: 0.4791 - val_loss: 2.3490 - val_distribution_lambda_5_loss: 0.4830 - val_distribution_lambda_6_loss: 1.4282 - val_distribution_lambda_7_loss: 0.4379\n", "Epoch 467/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0622 - distribution_lambda_5_loss: 0.2670 - distribution_lambda_6_loss: 1.3301 - distribution_lambda_7_loss: 0.4651 - val_loss: 2.3433 - val_distribution_lambda_5_loss: 0.4739 - val_distribution_lambda_6_loss: 1.4303 - val_distribution_lambda_7_loss: 0.4392\n", "Epoch 468/2500\n", "12/12 [==============================] - 0s 7ms/step - loss: 2.0125 - distribution_lambda_5_loss: 0.2543 - distribution_lambda_6_loss: 1.3136 - distribution_lambda_7_loss: 0.4446 - val_loss: 2.3355 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.4235 - val_distribution_lambda_7_loss: 0.4364\n", "Epoch 469/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0023 - distribution_lambda_5_loss: 0.2258 - distribution_lambda_6_loss: 1.3214 - distribution_lambda_7_loss: 0.4551 - val_loss: 2.3378 - val_distribution_lambda_5_loss: 0.4775 - val_distribution_lambda_6_loss: 1.4253 - val_distribution_lambda_7_loss: 0.4351\n", "Epoch 470/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0383 - distribution_lambda_5_loss: 0.2468 - distribution_lambda_6_loss: 1.3240 - distribution_lambda_7_loss: 0.4675 - val_loss: 2.3412 - val_distribution_lambda_5_loss: 0.4830 - val_distribution_lambda_6_loss: 1.4238 - val_distribution_lambda_7_loss: 0.4344\n", "Epoch 471/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0331 - distribution_lambda_5_loss: 0.2382 - distribution_lambda_6_loss: 1.3316 - distribution_lambda_7_loss: 0.4633 - val_loss: 2.3598 - val_distribution_lambda_5_loss: 0.4964 - val_distribution_lambda_6_loss: 1.4262 - val_distribution_lambda_7_loss: 0.4372\n", "Epoch 472/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0631 - distribution_lambda_5_loss: 0.2570 - distribution_lambda_6_loss: 1.3395 - distribution_lambda_7_loss: 0.4667 - val_loss: 2.3469 - val_distribution_lambda_5_loss: 0.4843 - val_distribution_lambda_6_loss: 1.4265 - val_distribution_lambda_7_loss: 0.4361\n", "Epoch 473/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0588 - distribution_lambda_5_loss: 0.2443 - distribution_lambda_6_loss: 1.3419 - distribution_lambda_7_loss: 0.4727 - val_loss: 2.3395 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.4262 - val_distribution_lambda_7_loss: 0.4377\n", "Epoch 474/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0228 - distribution_lambda_5_loss: 0.2274 - distribution_lambda_6_loss: 1.3271 - distribution_lambda_7_loss: 0.4682 - val_loss: 2.3470 - val_distribution_lambda_5_loss: 0.4855 - val_distribution_lambda_6_loss: 1.4237 - val_distribution_lambda_7_loss: 0.4378\n", "Epoch 475/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0541 - distribution_lambda_5_loss: 0.2497 - distribution_lambda_6_loss: 1.3324 - distribution_lambda_7_loss: 0.4719 - val_loss: 2.3554 - val_distribution_lambda_5_loss: 0.4863 - val_distribution_lambda_6_loss: 1.4292 - val_distribution_lambda_7_loss: 0.4399\n", "Epoch 476/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0595 - distribution_lambda_5_loss: 0.2620 - distribution_lambda_6_loss: 1.3384 - distribution_lambda_7_loss: 0.4592 - val_loss: 2.3332 - val_distribution_lambda_5_loss: 0.4719 - val_distribution_lambda_6_loss: 1.4206 - val_distribution_lambda_7_loss: 0.4407\n", "Epoch 477/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0305 - distribution_lambda_5_loss: 0.2297 - distribution_lambda_6_loss: 1.3285 - distribution_lambda_7_loss: 0.4723 - val_loss: 2.3347 - val_distribution_lambda_5_loss: 0.4710 - val_distribution_lambda_6_loss: 1.4236 - val_distribution_lambda_7_loss: 0.4400\n", "Epoch 478/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.0507 - distribution_lambda_5_loss: 0.2491 - distribution_lambda_6_loss: 1.3247 - distribution_lambda_7_loss: 0.4769 - val_loss: 2.3506 - val_distribution_lambda_5_loss: 0.4771 - val_distribution_lambda_6_loss: 1.4321 - val_distribution_lambda_7_loss: 0.4413\n", "Epoch 479/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0675 - distribution_lambda_5_loss: 0.2601 - distribution_lambda_6_loss: 1.3312 - distribution_lambda_7_loss: 0.4762 - val_loss: 2.3417 - val_distribution_lambda_5_loss: 0.4752 - val_distribution_lambda_6_loss: 1.4255 - val_distribution_lambda_7_loss: 0.4410\n", "Epoch 480/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0049 - distribution_lambda_5_loss: 0.2559 - distribution_lambda_6_loss: 1.3116 - distribution_lambda_7_loss: 0.4374 - val_loss: 2.3257 - val_distribution_lambda_5_loss: 0.4644 - val_distribution_lambda_6_loss: 1.4242 - val_distribution_lambda_7_loss: 0.4370\n", "Epoch 481/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0471 - distribution_lambda_5_loss: 0.2551 - distribution_lambda_6_loss: 1.3215 - distribution_lambda_7_loss: 0.4705 - val_loss: 2.3311 - val_distribution_lambda_5_loss: 0.4701 - val_distribution_lambda_6_loss: 1.4234 - val_distribution_lambda_7_loss: 0.4376\n", "Epoch 482/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0208 - distribution_lambda_5_loss: 0.2372 - distribution_lambda_6_loss: 1.3206 - distribution_lambda_7_loss: 0.4630 - val_loss: 2.3371 - val_distribution_lambda_5_loss: 0.4793 - val_distribution_lambda_6_loss: 1.4189 - val_distribution_lambda_7_loss: 0.4389\n", "Epoch 483/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0323 - distribution_lambda_5_loss: 0.2478 - distribution_lambda_6_loss: 1.3241 - distribution_lambda_7_loss: 0.4604 - val_loss: 2.3268 - val_distribution_lambda_5_loss: 0.4687 - val_distribution_lambda_6_loss: 1.4203 - val_distribution_lambda_7_loss: 0.4378\n", "Epoch 484/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9960 - distribution_lambda_5_loss: 0.2260 - distribution_lambda_6_loss: 1.3051 - distribution_lambda_7_loss: 0.4649 - val_loss: 2.3457 - val_distribution_lambda_5_loss: 0.4763 - val_distribution_lambda_6_loss: 1.4330 - val_distribution_lambda_7_loss: 0.4364\n", "Epoch 485/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0781 - distribution_lambda_5_loss: 0.2654 - distribution_lambda_6_loss: 1.3325 - distribution_lambda_7_loss: 0.4802 - val_loss: 2.3397 - val_distribution_lambda_5_loss: 0.4812 - val_distribution_lambda_6_loss: 1.4212 - val_distribution_lambda_7_loss: 0.4373\n", "Epoch 486/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9882 - distribution_lambda_5_loss: 0.2200 - distribution_lambda_6_loss: 1.3031 - distribution_lambda_7_loss: 0.4650 - val_loss: 2.3532 - val_distribution_lambda_5_loss: 0.4993 - val_distribution_lambda_6_loss: 1.4151 - val_distribution_lambda_7_loss: 0.4388\n", "Epoch 487/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0206 - distribution_lambda_5_loss: 0.2367 - distribution_lambda_6_loss: 1.3208 - distribution_lambda_7_loss: 0.4632 - val_loss: 2.3546 - val_distribution_lambda_5_loss: 0.4983 - val_distribution_lambda_6_loss: 1.4167 - val_distribution_lambda_7_loss: 0.4397\n", "Epoch 488/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0608 - distribution_lambda_5_loss: 0.2338 - distribution_lambda_6_loss: 1.3522 - distribution_lambda_7_loss: 0.4748 - val_loss: 2.3855 - val_distribution_lambda_5_loss: 0.5085 - val_distribution_lambda_6_loss: 1.4362 - val_distribution_lambda_7_loss: 0.4407\n", "Epoch 489/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0389 - distribution_lambda_5_loss: 0.2444 - distribution_lambda_6_loss: 1.3309 - distribution_lambda_7_loss: 0.4636 - val_loss: 2.3552 - val_distribution_lambda_5_loss: 0.4976 - val_distribution_lambda_6_loss: 1.4213 - val_distribution_lambda_7_loss: 0.4363\n", "Epoch 490/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0811 - distribution_lambda_5_loss: 0.2819 - distribution_lambda_6_loss: 1.3360 - distribution_lambda_7_loss: 0.4631 - val_loss: 2.3497 - val_distribution_lambda_5_loss: 0.4864 - val_distribution_lambda_6_loss: 1.4280 - val_distribution_lambda_7_loss: 0.4352\n", "Epoch 491/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0194 - distribution_lambda_5_loss: 0.2448 - distribution_lambda_6_loss: 1.3190 - distribution_lambda_7_loss: 0.4556 - val_loss: 2.3419 - val_distribution_lambda_5_loss: 0.4687 - val_distribution_lambda_6_loss: 1.4364 - val_distribution_lambda_7_loss: 0.4368\n", "Epoch 492/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0105 - distribution_lambda_5_loss: 0.2378 - distribution_lambda_6_loss: 1.3206 - distribution_lambda_7_loss: 0.4521 - val_loss: 2.3371 - val_distribution_lambda_5_loss: 0.4654 - val_distribution_lambda_6_loss: 1.4353 - val_distribution_lambda_7_loss: 0.4365\n", "Epoch 493/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0333 - distribution_lambda_5_loss: 0.2349 - distribution_lambda_6_loss: 1.3257 - distribution_lambda_7_loss: 0.4727 - val_loss: 2.3185 - val_distribution_lambda_5_loss: 0.4699 - val_distribution_lambda_6_loss: 1.4122 - val_distribution_lambda_7_loss: 0.4364\n", "Epoch 494/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9622 - distribution_lambda_5_loss: 0.2175 - distribution_lambda_6_loss: 1.2950 - distribution_lambda_7_loss: 0.4497 - val_loss: 2.3315 - val_distribution_lambda_5_loss: 0.4830 - val_distribution_lambda_6_loss: 1.4149 - val_distribution_lambda_7_loss: 0.4336\n", "Epoch 495/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0488 - distribution_lambda_5_loss: 0.2540 - distribution_lambda_6_loss: 1.3252 - distribution_lambda_7_loss: 0.4697 - val_loss: 2.3458 - val_distribution_lambda_5_loss: 0.4840 - val_distribution_lambda_6_loss: 1.4265 - val_distribution_lambda_7_loss: 0.4353\n", "Epoch 496/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0291 - distribution_lambda_5_loss: 0.2482 - distribution_lambda_6_loss: 1.3258 - distribution_lambda_7_loss: 0.4551 - val_loss: 2.3310 - val_distribution_lambda_5_loss: 0.4812 - val_distribution_lambda_6_loss: 1.4158 - val_distribution_lambda_7_loss: 0.4340\n", "Epoch 497/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0272 - distribution_lambda_5_loss: 0.2397 - distribution_lambda_6_loss: 1.3265 - distribution_lambda_7_loss: 0.4611 - val_loss: 2.3339 - val_distribution_lambda_5_loss: 0.4771 - val_distribution_lambda_6_loss: 1.4235 - val_distribution_lambda_7_loss: 0.4333\n", "Epoch 498/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0105 - distribution_lambda_5_loss: 0.2280 - distribution_lambda_6_loss: 1.3127 - distribution_lambda_7_loss: 0.4698 - val_loss: 2.3564 - val_distribution_lambda_5_loss: 0.4949 - val_distribution_lambda_6_loss: 1.4272 - val_distribution_lambda_7_loss: 0.4343\n", "Epoch 499/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0044 - distribution_lambda_5_loss: 0.2218 - distribution_lambda_6_loss: 1.3189 - distribution_lambda_7_loss: 0.4637 - val_loss: 2.3724 - val_distribution_lambda_5_loss: 0.4990 - val_distribution_lambda_6_loss: 1.4362 - val_distribution_lambda_7_loss: 0.4372\n", "Epoch 500/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0165 - distribution_lambda_5_loss: 0.2398 - distribution_lambda_6_loss: 1.3145 - distribution_lambda_7_loss: 0.4622 - val_loss: 2.3531 - val_distribution_lambda_5_loss: 0.4945 - val_distribution_lambda_6_loss: 1.4240 - val_distribution_lambda_7_loss: 0.4346\n", "Epoch 501/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0279 - distribution_lambda_5_loss: 0.2458 - distribution_lambda_6_loss: 1.3256 - distribution_lambda_7_loss: 0.4565 - val_loss: 2.3347 - val_distribution_lambda_5_loss: 0.4852 - val_distribution_lambda_6_loss: 1.4168 - val_distribution_lambda_7_loss: 0.4327\n", "Epoch 502/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 2.0409 - distribution_lambda_5_loss: 0.2640 - distribution_lambda_6_loss: 1.3251 - distribution_lambda_7_loss: 0.4517 - val_loss: 2.3300 - val_distribution_lambda_5_loss: 0.4780 - val_distribution_lambda_6_loss: 1.4199 - val_distribution_lambda_7_loss: 0.4321\n", "Epoch 503/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9908 - distribution_lambda_5_loss: 0.2296 - distribution_lambda_6_loss: 1.3025 - distribution_lambda_7_loss: 0.4586 - val_loss: 2.3147 - val_distribution_lambda_5_loss: 0.4683 - val_distribution_lambda_6_loss: 1.4148 - val_distribution_lambda_7_loss: 0.4315\n", "Epoch 504/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9658 - distribution_lambda_5_loss: 0.2190 - distribution_lambda_6_loss: 1.3048 - distribution_lambda_7_loss: 0.4420 - val_loss: 2.3476 - val_distribution_lambda_5_loss: 0.4954 - val_distribution_lambda_6_loss: 1.4203 - val_distribution_lambda_7_loss: 0.4319\n", "Epoch 505/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0471 - distribution_lambda_5_loss: 0.2401 - distribution_lambda_6_loss: 1.3308 - distribution_lambda_7_loss: 0.4761 - val_loss: 2.3462 - val_distribution_lambda_5_loss: 0.4953 - val_distribution_lambda_6_loss: 1.4176 - val_distribution_lambda_7_loss: 0.4333\n", "Epoch 506/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 2.0057 - distribution_lambda_5_loss: 0.2411 - distribution_lambda_6_loss: 1.3067 - distribution_lambda_7_loss: 0.4579 - val_loss: 2.3300 - val_distribution_lambda_5_loss: 0.4834 - val_distribution_lambda_6_loss: 1.4139 - val_distribution_lambda_7_loss: 0.4327\n", "Epoch 507/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9924 - distribution_lambda_5_loss: 0.2280 - distribution_lambda_6_loss: 1.3063 - distribution_lambda_7_loss: 0.4581 - val_loss: 2.3455 - val_distribution_lambda_5_loss: 0.4868 - val_distribution_lambda_6_loss: 1.4237 - val_distribution_lambda_7_loss: 0.4349\n", "Epoch 508/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0524 - distribution_lambda_5_loss: 0.2529 - distribution_lambda_6_loss: 1.3323 - distribution_lambda_7_loss: 0.4671 - val_loss: 2.3547 - val_distribution_lambda_5_loss: 0.4802 - val_distribution_lambda_6_loss: 1.4398 - val_distribution_lambda_7_loss: 0.4348\n", "Epoch 509/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9654 - distribution_lambda_5_loss: 0.2150 - distribution_lambda_6_loss: 1.2940 - distribution_lambda_7_loss: 0.4564 - val_loss: 2.3374 - val_distribution_lambda_5_loss: 0.4855 - val_distribution_lambda_6_loss: 1.4201 - val_distribution_lambda_7_loss: 0.4319\n", "Epoch 510/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0070 - distribution_lambda_5_loss: 0.2051 - distribution_lambda_6_loss: 1.3229 - distribution_lambda_7_loss: 0.4790 - val_loss: 2.3523 - val_distribution_lambda_5_loss: 0.5013 - val_distribution_lambda_6_loss: 1.4169 - val_distribution_lambda_7_loss: 0.4341\n", "Epoch 511/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0236 - distribution_lambda_5_loss: 0.2418 - distribution_lambda_6_loss: 1.3108 - distribution_lambda_7_loss: 0.4710 - val_loss: 2.3317 - val_distribution_lambda_5_loss: 0.4946 - val_distribution_lambda_6_loss: 1.4046 - val_distribution_lambda_7_loss: 0.4325\n", "Epoch 512/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9956 - distribution_lambda_5_loss: 0.2172 - distribution_lambda_6_loss: 1.3171 - distribution_lambda_7_loss: 0.4613 - val_loss: 2.3420 - val_distribution_lambda_5_loss: 0.4964 - val_distribution_lambda_6_loss: 1.4138 - val_distribution_lambda_7_loss: 0.4318\n", "Epoch 513/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9858 - distribution_lambda_5_loss: 0.2271 - distribution_lambda_6_loss: 1.3042 - distribution_lambda_7_loss: 0.4545 - val_loss: 2.3438 - val_distribution_lambda_5_loss: 0.4972 - val_distribution_lambda_6_loss: 1.4151 - val_distribution_lambda_7_loss: 0.4315\n", "Epoch 514/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0063 - distribution_lambda_5_loss: 0.2405 - distribution_lambda_6_loss: 1.3043 - distribution_lambda_7_loss: 0.4614 - val_loss: 2.3513 - val_distribution_lambda_5_loss: 0.4960 - val_distribution_lambda_6_loss: 1.4232 - val_distribution_lambda_7_loss: 0.4320\n", "Epoch 515/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0304 - distribution_lambda_5_loss: 0.2441 - distribution_lambda_6_loss: 1.3153 - distribution_lambda_7_loss: 0.4710 - val_loss: 2.3495 - val_distribution_lambda_5_loss: 0.4813 - val_distribution_lambda_6_loss: 1.4316 - val_distribution_lambda_7_loss: 0.4366\n", "Epoch 516/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0117 - distribution_lambda_5_loss: 0.2409 - distribution_lambda_6_loss: 1.3104 - distribution_lambda_7_loss: 0.4603 - val_loss: 2.3505 - val_distribution_lambda_5_loss: 0.4842 - val_distribution_lambda_6_loss: 1.4283 - val_distribution_lambda_7_loss: 0.4381\n", "Epoch 517/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0120 - distribution_lambda_5_loss: 0.2346 - distribution_lambda_6_loss: 1.3156 - distribution_lambda_7_loss: 0.4619 - val_loss: 2.3392 - val_distribution_lambda_5_loss: 0.4817 - val_distribution_lambda_6_loss: 1.4205 - val_distribution_lambda_7_loss: 0.4370\n", "Epoch 518/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0360 - distribution_lambda_5_loss: 0.2407 - distribution_lambda_6_loss: 1.3259 - distribution_lambda_7_loss: 0.4694 - val_loss: 2.3223 - val_distribution_lambda_5_loss: 0.4745 - val_distribution_lambda_6_loss: 1.4111 - val_distribution_lambda_7_loss: 0.4367\n", "Epoch 519/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0114 - distribution_lambda_5_loss: 0.2552 - distribution_lambda_6_loss: 1.3057 - distribution_lambda_7_loss: 0.4506 - val_loss: 2.3100 - val_distribution_lambda_5_loss: 0.4644 - val_distribution_lambda_6_loss: 1.4112 - val_distribution_lambda_7_loss: 0.4343\n", "Epoch 520/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9725 - distribution_lambda_5_loss: 0.2212 - distribution_lambda_6_loss: 1.2938 - distribution_lambda_7_loss: 0.4575 - val_loss: 2.3119 - val_distribution_lambda_5_loss: 0.4611 - val_distribution_lambda_6_loss: 1.4202 - val_distribution_lambda_7_loss: 0.4306\n", "Epoch 521/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9964 - distribution_lambda_5_loss: 0.2169 - distribution_lambda_6_loss: 1.3238 - distribution_lambda_7_loss: 0.4557 - val_loss: 2.3214 - val_distribution_lambda_5_loss: 0.4674 - val_distribution_lambda_6_loss: 1.4224 - val_distribution_lambda_7_loss: 0.4315\n", "Epoch 522/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0004 - distribution_lambda_5_loss: 0.2089 - distribution_lambda_6_loss: 1.3209 - distribution_lambda_7_loss: 0.4705 - val_loss: 2.3349 - val_distribution_lambda_5_loss: 0.4950 - val_distribution_lambda_6_loss: 1.4080 - val_distribution_lambda_7_loss: 0.4319\n", "Epoch 523/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0379 - distribution_lambda_5_loss: 0.2556 - distribution_lambda_6_loss: 1.3136 - distribution_lambda_7_loss: 0.4688 - val_loss: 2.3409 - val_distribution_lambda_5_loss: 0.4905 - val_distribution_lambda_6_loss: 1.4150 - val_distribution_lambda_7_loss: 0.4354\n", "Epoch 524/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9921 - distribution_lambda_5_loss: 0.2370 - distribution_lambda_6_loss: 1.3110 - distribution_lambda_7_loss: 0.4440 - val_loss: 2.3397 - val_distribution_lambda_5_loss: 0.4905 - val_distribution_lambda_6_loss: 1.4152 - val_distribution_lambda_7_loss: 0.4340\n", "Epoch 525/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0079 - distribution_lambda_5_loss: 0.2384 - distribution_lambda_6_loss: 1.2991 - distribution_lambda_7_loss: 0.4704 - val_loss: 2.3550 - val_distribution_lambda_5_loss: 0.5022 - val_distribution_lambda_6_loss: 1.4202 - val_distribution_lambda_7_loss: 0.4326\n", "Epoch 526/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 2.0150 - distribution_lambda_5_loss: 0.2311 - distribution_lambda_6_loss: 1.3242 - distribution_lambda_7_loss: 0.4597 - val_loss: 2.3280 - val_distribution_lambda_5_loss: 0.4874 - val_distribution_lambda_6_loss: 1.4089 - val_distribution_lambda_7_loss: 0.4318\n", "Epoch 527/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9377 - distribution_lambda_5_loss: 0.2235 - distribution_lambda_6_loss: 1.2795 - distribution_lambda_7_loss: 0.4347 - val_loss: 2.3380 - val_distribution_lambda_5_loss: 0.4951 - val_distribution_lambda_6_loss: 1.4137 - val_distribution_lambda_7_loss: 0.4291\n", "Epoch 528/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9824 - distribution_lambda_5_loss: 0.2141 - distribution_lambda_6_loss: 1.3164 - distribution_lambda_7_loss: 0.4519 - val_loss: 2.3712 - val_distribution_lambda_5_loss: 0.5014 - val_distribution_lambda_6_loss: 1.4366 - val_distribution_lambda_7_loss: 0.4333\n", "Epoch 529/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9796 - distribution_lambda_5_loss: 0.2351 - distribution_lambda_6_loss: 1.2957 - distribution_lambda_7_loss: 0.4488 - val_loss: 2.3400 - val_distribution_lambda_5_loss: 0.4855 - val_distribution_lambda_6_loss: 1.4220 - val_distribution_lambda_7_loss: 0.4324\n", "Epoch 530/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0217 - distribution_lambda_5_loss: 0.2396 - distribution_lambda_6_loss: 1.3312 - distribution_lambda_7_loss: 0.4509 - val_loss: 2.3306 - val_distribution_lambda_5_loss: 0.4879 - val_distribution_lambda_6_loss: 1.4117 - val_distribution_lambda_7_loss: 0.4310\n", "Epoch 531/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0156 - distribution_lambda_5_loss: 0.2440 - distribution_lambda_6_loss: 1.3001 - distribution_lambda_7_loss: 0.4715 - val_loss: 2.3083 - val_distribution_lambda_5_loss: 0.4722 - val_distribution_lambda_6_loss: 1.4034 - val_distribution_lambda_7_loss: 0.4328\n", "Epoch 532/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9538 - distribution_lambda_5_loss: 0.2117 - distribution_lambda_6_loss: 1.2974 - distribution_lambda_7_loss: 0.4446 - val_loss: 2.3290 - val_distribution_lambda_5_loss: 0.4843 - val_distribution_lambda_6_loss: 1.4123 - val_distribution_lambda_7_loss: 0.4324\n", "Epoch 533/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0194 - distribution_lambda_5_loss: 0.2253 - distribution_lambda_6_loss: 1.3307 - distribution_lambda_7_loss: 0.4634 - val_loss: 2.3295 - val_distribution_lambda_5_loss: 0.4851 - val_distribution_lambda_6_loss: 1.4144 - val_distribution_lambda_7_loss: 0.4300\n", "Epoch 534/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9643 - distribution_lambda_5_loss: 0.2312 - distribution_lambda_6_loss: 1.2807 - distribution_lambda_7_loss: 0.4525 - val_loss: 2.3201 - val_distribution_lambda_5_loss: 0.4810 - val_distribution_lambda_6_loss: 1.4109 - val_distribution_lambda_7_loss: 0.4283\n", "Epoch 535/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9607 - distribution_lambda_5_loss: 0.2067 - distribution_lambda_6_loss: 1.3018 - distribution_lambda_7_loss: 0.4522 - val_loss: 2.3239 - val_distribution_lambda_5_loss: 0.4827 - val_distribution_lambda_6_loss: 1.4123 - val_distribution_lambda_7_loss: 0.4289\n", "Epoch 536/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9933 - distribution_lambda_5_loss: 0.2157 - distribution_lambda_6_loss: 1.3115 - distribution_lambda_7_loss: 0.4661 - val_loss: 2.3381 - val_distribution_lambda_5_loss: 0.4955 - val_distribution_lambda_6_loss: 1.4132 - val_distribution_lambda_7_loss: 0.4294\n", "Epoch 537/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9954 - distribution_lambda_5_loss: 0.2485 - distribution_lambda_6_loss: 1.2994 - distribution_lambda_7_loss: 0.4475 - val_loss: 2.3357 - val_distribution_lambda_5_loss: 0.4929 - val_distribution_lambda_6_loss: 1.4136 - val_distribution_lambda_7_loss: 0.4292\n", "Epoch 538/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0124 - distribution_lambda_5_loss: 0.2525 - distribution_lambda_6_loss: 1.3002 - distribution_lambda_7_loss: 0.4597 - val_loss: 2.3295 - val_distribution_lambda_5_loss: 0.4881 - val_distribution_lambda_6_loss: 1.4118 - val_distribution_lambda_7_loss: 0.4296\n", "Epoch 539/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0187 - distribution_lambda_5_loss: 0.2236 - distribution_lambda_6_loss: 1.3213 - distribution_lambda_7_loss: 0.4738 - val_loss: 2.3453 - val_distribution_lambda_5_loss: 0.4910 - val_distribution_lambda_6_loss: 1.4219 - val_distribution_lambda_7_loss: 0.4324\n", "Epoch 540/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9707 - distribution_lambda_5_loss: 0.2391 - distribution_lambda_6_loss: 1.2977 - distribution_lambda_7_loss: 0.4339 - val_loss: 2.3321 - val_distribution_lambda_5_loss: 0.4841 - val_distribution_lambda_6_loss: 1.4175 - val_distribution_lambda_7_loss: 0.4304\n", "Epoch 541/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9988 - distribution_lambda_5_loss: 0.2389 - distribution_lambda_6_loss: 1.3040 - distribution_lambda_7_loss: 0.4559 - val_loss: 2.3261 - val_distribution_lambda_5_loss: 0.4818 - val_distribution_lambda_6_loss: 1.4158 - val_distribution_lambda_7_loss: 0.4286\n", "Epoch 542/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9644 - distribution_lambda_5_loss: 0.1959 - distribution_lambda_6_loss: 1.3032 - distribution_lambda_7_loss: 0.4654 - val_loss: 2.3376 - val_distribution_lambda_5_loss: 0.4932 - val_distribution_lambda_6_loss: 1.4153 - val_distribution_lambda_7_loss: 0.4291\n", "Epoch 543/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9808 - distribution_lambda_5_loss: 0.2144 - distribution_lambda_6_loss: 1.3020 - distribution_lambda_7_loss: 0.4644 - val_loss: 2.3637 - val_distribution_lambda_5_loss: 0.5120 - val_distribution_lambda_6_loss: 1.4202 - val_distribution_lambda_7_loss: 0.4315\n", "Epoch 544/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0245 - distribution_lambda_5_loss: 0.2387 - distribution_lambda_6_loss: 1.3178 - distribution_lambda_7_loss: 0.4679 - val_loss: 2.3306 - val_distribution_lambda_5_loss: 0.4872 - val_distribution_lambda_6_loss: 1.4109 - val_distribution_lambda_7_loss: 0.4325\n", "Epoch 545/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0015 - distribution_lambda_5_loss: 0.2321 - distribution_lambda_6_loss: 1.3115 - distribution_lambda_7_loss: 0.4580 - val_loss: 2.3486 - val_distribution_lambda_5_loss: 0.4949 - val_distribution_lambda_6_loss: 1.4209 - val_distribution_lambda_7_loss: 0.4329\n", "Epoch 546/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0205 - distribution_lambda_5_loss: 0.2479 - distribution_lambda_6_loss: 1.3131 - distribution_lambda_7_loss: 0.4595 - val_loss: 2.3244 - val_distribution_lambda_5_loss: 0.4760 - val_distribution_lambda_6_loss: 1.4165 - val_distribution_lambda_7_loss: 0.4319\n", "Epoch 547/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9526 - distribution_lambda_5_loss: 0.2112 - distribution_lambda_6_loss: 1.2923 - distribution_lambda_7_loss: 0.4492 - val_loss: 2.3211 - val_distribution_lambda_5_loss: 0.4813 - val_distribution_lambda_6_loss: 1.4130 - val_distribution_lambda_7_loss: 0.4268\n", "Epoch 548/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9554 - distribution_lambda_5_loss: 0.2289 - distribution_lambda_6_loss: 1.2773 - distribution_lambda_7_loss: 0.4493 - val_loss: 2.3431 - val_distribution_lambda_5_loss: 0.5000 - val_distribution_lambda_6_loss: 1.4173 - val_distribution_lambda_7_loss: 0.4259\n", "Epoch 549/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9722 - distribution_lambda_5_loss: 0.2195 - distribution_lambda_6_loss: 1.3048 - distribution_lambda_7_loss: 0.4479 - val_loss: 2.3267 - val_distribution_lambda_5_loss: 0.4926 - val_distribution_lambda_6_loss: 1.4074 - val_distribution_lambda_7_loss: 0.4267\n", "Epoch 550/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 1.9713 - distribution_lambda_5_loss: 0.2096 - distribution_lambda_6_loss: 1.3070 - distribution_lambda_7_loss: 0.4548 - val_loss: 2.3512 - val_distribution_lambda_5_loss: 0.5061 - val_distribution_lambda_6_loss: 1.4164 - val_distribution_lambda_7_loss: 0.4287\n", "Epoch 551/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9608 - distribution_lambda_5_loss: 0.2271 - distribution_lambda_6_loss: 1.2918 - distribution_lambda_7_loss: 0.4418 - val_loss: 2.3343 - val_distribution_lambda_5_loss: 0.4952 - val_distribution_lambda_6_loss: 1.4119 - val_distribution_lambda_7_loss: 0.4271\n", "Epoch 552/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0004 - distribution_lambda_5_loss: 0.2409 - distribution_lambda_6_loss: 1.3008 - distribution_lambda_7_loss: 0.4587 - val_loss: 2.3308 - val_distribution_lambda_5_loss: 0.4912 - val_distribution_lambda_6_loss: 1.4137 - val_distribution_lambda_7_loss: 0.4259\n", "Epoch 553/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9798 - distribution_lambda_5_loss: 0.2211 - distribution_lambda_6_loss: 1.3028 - distribution_lambda_7_loss: 0.4559 - val_loss: 2.3257 - val_distribution_lambda_5_loss: 0.4948 - val_distribution_lambda_6_loss: 1.4042 - val_distribution_lambda_7_loss: 0.4266\n", "Epoch 554/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0190 - distribution_lambda_5_loss: 0.2446 - distribution_lambda_6_loss: 1.3168 - distribution_lambda_7_loss: 0.4576 - val_loss: 2.3278 - val_distribution_lambda_5_loss: 0.4867 - val_distribution_lambda_6_loss: 1.4143 - val_distribution_lambda_7_loss: 0.4267\n", "Epoch 555/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9678 - distribution_lambda_5_loss: 0.2128 - distribution_lambda_6_loss: 1.3076 - distribution_lambda_7_loss: 0.4474 - val_loss: 2.3085 - val_distribution_lambda_5_loss: 0.4773 - val_distribution_lambda_6_loss: 1.4035 - val_distribution_lambda_7_loss: 0.4277\n", "Epoch 556/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9652 - distribution_lambda_5_loss: 0.2315 - distribution_lambda_6_loss: 1.2876 - distribution_lambda_7_loss: 0.4461 - val_loss: 2.3248 - val_distribution_lambda_5_loss: 0.4820 - val_distribution_lambda_6_loss: 1.4154 - val_distribution_lambda_7_loss: 0.4274\n", "Epoch 557/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9883 - distribution_lambda_5_loss: 0.2553 - distribution_lambda_6_loss: 1.2827 - distribution_lambda_7_loss: 0.4503 - val_loss: 2.3290 - val_distribution_lambda_5_loss: 0.4797 - val_distribution_lambda_6_loss: 1.4215 - val_distribution_lambda_7_loss: 0.4278\n", "Epoch 558/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9487 - distribution_lambda_5_loss: 0.2227 - distribution_lambda_6_loss: 1.2825 - distribution_lambda_7_loss: 0.4435 - val_loss: 2.3174 - val_distribution_lambda_5_loss: 0.4768 - val_distribution_lambda_6_loss: 1.4142 - val_distribution_lambda_7_loss: 0.4264\n", "Epoch 559/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9653 - distribution_lambda_5_loss: 0.2116 - distribution_lambda_6_loss: 1.3069 - distribution_lambda_7_loss: 0.4469 - val_loss: 2.3055 - val_distribution_lambda_5_loss: 0.4823 - val_distribution_lambda_6_loss: 1.3976 - val_distribution_lambda_7_loss: 0.4257\n", "Epoch 560/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9725 - distribution_lambda_5_loss: 0.2172 - distribution_lambda_6_loss: 1.3007 - distribution_lambda_7_loss: 0.4545 - val_loss: 2.3288 - val_distribution_lambda_5_loss: 0.4887 - val_distribution_lambda_6_loss: 1.4128 - val_distribution_lambda_7_loss: 0.4273\n", "Epoch 561/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0010 - distribution_lambda_5_loss: 0.2369 - distribution_lambda_6_loss: 1.3120 - distribution_lambda_7_loss: 0.4521 - val_loss: 2.3005 - val_distribution_lambda_5_loss: 0.4715 - val_distribution_lambda_6_loss: 1.4022 - val_distribution_lambda_7_loss: 0.4268\n", "Epoch 562/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9726 - distribution_lambda_5_loss: 0.2216 - distribution_lambda_6_loss: 1.3048 - distribution_lambda_7_loss: 0.4462 - val_loss: 2.3223 - val_distribution_lambda_5_loss: 0.4808 - val_distribution_lambda_6_loss: 1.4121 - val_distribution_lambda_7_loss: 0.4293\n", "Epoch 563/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0458 - distribution_lambda_5_loss: 0.2564 - distribution_lambda_6_loss: 1.3175 - distribution_lambda_7_loss: 0.4718 - val_loss: 2.2854 - val_distribution_lambda_5_loss: 0.4591 - val_distribution_lambda_6_loss: 1.3982 - val_distribution_lambda_7_loss: 0.4282\n", "Epoch 564/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9886 - distribution_lambda_5_loss: 0.2199 - distribution_lambda_6_loss: 1.3056 - distribution_lambda_7_loss: 0.4632 - val_loss: 2.2938 - val_distribution_lambda_5_loss: 0.4707 - val_distribution_lambda_6_loss: 1.3945 - val_distribution_lambda_7_loss: 0.4286\n", "Epoch 565/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0163 - distribution_lambda_5_loss: 0.2532 - distribution_lambda_6_loss: 1.3041 - distribution_lambda_7_loss: 0.4590 - val_loss: 2.3071 - val_distribution_lambda_5_loss: 0.4737 - val_distribution_lambda_6_loss: 1.4050 - val_distribution_lambda_7_loss: 0.4284\n", "Epoch 566/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9860 - distribution_lambda_5_loss: 0.2378 - distribution_lambda_6_loss: 1.2933 - distribution_lambda_7_loss: 0.4549 - val_loss: 2.2919 - val_distribution_lambda_5_loss: 0.4643 - val_distribution_lambda_6_loss: 1.3998 - val_distribution_lambda_7_loss: 0.4277\n", "Epoch 567/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9343 - distribution_lambda_5_loss: 0.2124 - distribution_lambda_6_loss: 1.2766 - distribution_lambda_7_loss: 0.4453 - val_loss: 2.2950 - val_distribution_lambda_5_loss: 0.4699 - val_distribution_lambda_6_loss: 1.3988 - val_distribution_lambda_7_loss: 0.4263\n", "Epoch 568/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9333 - distribution_lambda_5_loss: 0.2197 - distribution_lambda_6_loss: 1.2682 - distribution_lambda_7_loss: 0.4454 - val_loss: 2.2969 - val_distribution_lambda_5_loss: 0.4758 - val_distribution_lambda_6_loss: 1.3957 - val_distribution_lambda_7_loss: 0.4253\n", "Epoch 569/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9603 - distribution_lambda_5_loss: 0.2213 - distribution_lambda_6_loss: 1.2799 - distribution_lambda_7_loss: 0.4592 - val_loss: 2.3024 - val_distribution_lambda_5_loss: 0.4786 - val_distribution_lambda_6_loss: 1.3997 - val_distribution_lambda_7_loss: 0.4241\n", "Epoch 570/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9983 - distribution_lambda_5_loss: 0.2410 - distribution_lambda_6_loss: 1.3043 - distribution_lambda_7_loss: 0.4531 - val_loss: 2.2874 - val_distribution_lambda_5_loss: 0.4702 - val_distribution_lambda_6_loss: 1.3920 - val_distribution_lambda_7_loss: 0.4253\n", "Epoch 571/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9990 - distribution_lambda_5_loss: 0.2549 - distribution_lambda_6_loss: 1.2984 - distribution_lambda_7_loss: 0.4457 - val_loss: 2.3014 - val_distribution_lambda_5_loss: 0.4662 - val_distribution_lambda_6_loss: 1.4102 - val_distribution_lambda_7_loss: 0.4250\n", "Epoch 572/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9877 - distribution_lambda_5_loss: 0.2286 - distribution_lambda_6_loss: 1.2973 - distribution_lambda_7_loss: 0.4618 - val_loss: 2.2853 - val_distribution_lambda_5_loss: 0.4563 - val_distribution_lambda_6_loss: 1.4020 - val_distribution_lambda_7_loss: 0.4270\n", "Epoch 573/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9539 - distribution_lambda_5_loss: 0.2111 - distribution_lambda_6_loss: 1.2982 - distribution_lambda_7_loss: 0.4446 - val_loss: 2.2824 - val_distribution_lambda_5_loss: 0.4647 - val_distribution_lambda_6_loss: 1.3930 - val_distribution_lambda_7_loss: 0.4247\n", "Epoch 574/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 1.9779 - distribution_lambda_5_loss: 0.2397 - distribution_lambda_6_loss: 1.2859 - distribution_lambda_7_loss: 0.4523 - val_loss: 2.2960 - val_distribution_lambda_5_loss: 0.4710 - val_distribution_lambda_6_loss: 1.4012 - val_distribution_lambda_7_loss: 0.4239\n", "Epoch 575/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9813 - distribution_lambda_5_loss: 0.2101 - distribution_lambda_6_loss: 1.3007 - distribution_lambda_7_loss: 0.4705 - val_loss: 2.2940 - val_distribution_lambda_5_loss: 0.4760 - val_distribution_lambda_6_loss: 1.3949 - val_distribution_lambda_7_loss: 0.4231\n", "Epoch 576/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9350 - distribution_lambda_5_loss: 0.1998 - distribution_lambda_6_loss: 1.2797 - distribution_lambda_7_loss: 0.4555 - val_loss: 2.2927 - val_distribution_lambda_5_loss: 0.4783 - val_distribution_lambda_6_loss: 1.3914 - val_distribution_lambda_7_loss: 0.4230\n", "Epoch 577/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9755 - distribution_lambda_5_loss: 0.2292 - distribution_lambda_6_loss: 1.2909 - distribution_lambda_7_loss: 0.4553 - val_loss: 2.2893 - val_distribution_lambda_5_loss: 0.4824 - val_distribution_lambda_6_loss: 1.3846 - val_distribution_lambda_7_loss: 0.4222\n", "Epoch 578/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9944 - distribution_lambda_5_loss: 0.2305 - distribution_lambda_6_loss: 1.3046 - distribution_lambda_7_loss: 0.4592 - val_loss: 2.2880 - val_distribution_lambda_5_loss: 0.4805 - val_distribution_lambda_6_loss: 1.3848 - val_distribution_lambda_7_loss: 0.4226\n", "Epoch 579/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9526 - distribution_lambda_5_loss: 0.2187 - distribution_lambda_6_loss: 1.2914 - distribution_lambda_7_loss: 0.4426 - val_loss: 2.3006 - val_distribution_lambda_5_loss: 0.4831 - val_distribution_lambda_6_loss: 1.3967 - val_distribution_lambda_7_loss: 0.4208\n", "Epoch 580/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9622 - distribution_lambda_5_loss: 0.2236 - distribution_lambda_6_loss: 1.2837 - distribution_lambda_7_loss: 0.4549 - val_loss: 2.2999 - val_distribution_lambda_5_loss: 0.4794 - val_distribution_lambda_6_loss: 1.4007 - val_distribution_lambda_7_loss: 0.4198\n", "Epoch 581/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9669 - distribution_lambda_5_loss: 0.2253 - distribution_lambda_6_loss: 1.2821 - distribution_lambda_7_loss: 0.4594 - val_loss: 2.3118 - val_distribution_lambda_5_loss: 0.4836 - val_distribution_lambda_6_loss: 1.4065 - val_distribution_lambda_7_loss: 0.4217\n", "Epoch 582/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9857 - distribution_lambda_5_loss: 0.2319 - distribution_lambda_6_loss: 1.3086 - distribution_lambda_7_loss: 0.4452 - val_loss: 2.2932 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.3974 - val_distribution_lambda_7_loss: 0.4202\n", "Epoch 583/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9804 - distribution_lambda_5_loss: 0.2204 - distribution_lambda_6_loss: 1.3078 - distribution_lambda_7_loss: 0.4523 - val_loss: 2.2908 - val_distribution_lambda_5_loss: 0.4774 - val_distribution_lambda_6_loss: 1.3934 - val_distribution_lambda_7_loss: 0.4200\n", "Epoch 584/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9278 - distribution_lambda_5_loss: 0.2172 - distribution_lambda_6_loss: 1.2815 - distribution_lambda_7_loss: 0.4292 - val_loss: 2.2868 - val_distribution_lambda_5_loss: 0.4758 - val_distribution_lambda_6_loss: 1.3922 - val_distribution_lambda_7_loss: 0.4188\n", "Epoch 585/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9798 - distribution_lambda_5_loss: 0.2248 - distribution_lambda_6_loss: 1.2956 - distribution_lambda_7_loss: 0.4594 - val_loss: 2.2994 - val_distribution_lambda_5_loss: 0.4755 - val_distribution_lambda_6_loss: 1.4023 - val_distribution_lambda_7_loss: 0.4215\n", "Epoch 586/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9860 - distribution_lambda_5_loss: 0.2375 - distribution_lambda_6_loss: 1.2913 - distribution_lambda_7_loss: 0.4572 - val_loss: 2.2916 - val_distribution_lambda_5_loss: 0.4655 - val_distribution_lambda_6_loss: 1.4019 - val_distribution_lambda_7_loss: 0.4242\n", "Epoch 587/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9300 - distribution_lambda_5_loss: 0.2131 - distribution_lambda_6_loss: 1.2757 - distribution_lambda_7_loss: 0.4413 - val_loss: 2.2723 - val_distribution_lambda_5_loss: 0.4594 - val_distribution_lambda_6_loss: 1.3919 - val_distribution_lambda_7_loss: 0.4209\n", "Epoch 588/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0033 - distribution_lambda_5_loss: 0.2416 - distribution_lambda_6_loss: 1.3087 - distribution_lambda_7_loss: 0.4530 - val_loss: 2.2755 - val_distribution_lambda_5_loss: 0.4600 - val_distribution_lambda_6_loss: 1.3970 - val_distribution_lambda_7_loss: 0.4185\n", "Epoch 589/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9495 - distribution_lambda_5_loss: 0.2269 - distribution_lambda_6_loss: 1.2803 - distribution_lambda_7_loss: 0.4424 - val_loss: 2.2725 - val_distribution_lambda_5_loss: 0.4660 - val_distribution_lambda_6_loss: 1.3893 - val_distribution_lambda_7_loss: 0.4172\n", "Epoch 590/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9692 - distribution_lambda_5_loss: 0.2173 - distribution_lambda_6_loss: 1.2940 - distribution_lambda_7_loss: 0.4580 - val_loss: 2.2853 - val_distribution_lambda_5_loss: 0.4784 - val_distribution_lambda_6_loss: 1.3888 - val_distribution_lambda_7_loss: 0.4181\n", "Epoch 591/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9388 - distribution_lambda_5_loss: 0.2310 - distribution_lambda_6_loss: 1.2682 - distribution_lambda_7_loss: 0.4396 - val_loss: 2.2713 - val_distribution_lambda_5_loss: 0.4674 - val_distribution_lambda_6_loss: 1.3867 - val_distribution_lambda_7_loss: 0.4172\n", "Epoch 592/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9783 - distribution_lambda_5_loss: 0.2335 - distribution_lambda_6_loss: 1.2891 - distribution_lambda_7_loss: 0.4557 - val_loss: 2.2783 - val_distribution_lambda_5_loss: 0.4614 - val_distribution_lambda_6_loss: 1.3997 - val_distribution_lambda_7_loss: 0.4172\n", "Epoch 593/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9700 - distribution_lambda_5_loss: 0.2405 - distribution_lambda_6_loss: 1.2817 - distribution_lambda_7_loss: 0.4477 - val_loss: 2.2726 - val_distribution_lambda_5_loss: 0.4548 - val_distribution_lambda_6_loss: 1.3992 - val_distribution_lambda_7_loss: 0.4186\n", "Epoch 594/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9844 - distribution_lambda_5_loss: 0.2391 - distribution_lambda_6_loss: 1.2980 - distribution_lambda_7_loss: 0.4473 - val_loss: 2.2546 - val_distribution_lambda_5_loss: 0.4470 - val_distribution_lambda_6_loss: 1.3898 - val_distribution_lambda_7_loss: 0.4178\n", "Epoch 595/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9809 - distribution_lambda_5_loss: 0.2328 - distribution_lambda_6_loss: 1.2951 - distribution_lambda_7_loss: 0.4530 - val_loss: 2.2773 - val_distribution_lambda_5_loss: 0.4515 - val_distribution_lambda_6_loss: 1.4061 - val_distribution_lambda_7_loss: 0.4198\n", "Epoch 596/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9223 - distribution_lambda_5_loss: 0.2067 - distribution_lambda_6_loss: 1.2826 - distribution_lambda_7_loss: 0.4330 - val_loss: 2.2670 - val_distribution_lambda_5_loss: 0.4593 - val_distribution_lambda_6_loss: 1.3896 - val_distribution_lambda_7_loss: 0.4180\n", "Epoch 597/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9466 - distribution_lambda_5_loss: 0.2312 - distribution_lambda_6_loss: 1.2740 - distribution_lambda_7_loss: 0.4414 - val_loss: 2.2773 - val_distribution_lambda_5_loss: 0.4659 - val_distribution_lambda_6_loss: 1.3930 - val_distribution_lambda_7_loss: 0.4184\n", "Epoch 598/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 1.9207 - distribution_lambda_5_loss: 0.1974 - distribution_lambda_6_loss: 1.2728 - distribution_lambda_7_loss: 0.4504 - val_loss: 2.2903 - val_distribution_lambda_5_loss: 0.4723 - val_distribution_lambda_6_loss: 1.3991 - val_distribution_lambda_7_loss: 0.4190\n", "Epoch 599/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9118 - distribution_lambda_5_loss: 0.1735 - distribution_lambda_6_loss: 1.2890 - distribution_lambda_7_loss: 0.4493 - val_loss: 2.2983 - val_distribution_lambda_5_loss: 0.4883 - val_distribution_lambda_6_loss: 1.3887 - val_distribution_lambda_7_loss: 0.4213\n", "Epoch 600/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 2.0029 - distribution_lambda_5_loss: 0.2502 - distribution_lambda_6_loss: 1.2847 - distribution_lambda_7_loss: 0.4680 - val_loss: 2.3006 - val_distribution_lambda_5_loss: 0.4934 - val_distribution_lambda_6_loss: 1.3866 - val_distribution_lambda_7_loss: 0.4206\n", "Epoch 601/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9299 - distribution_lambda_5_loss: 0.2066 - distribution_lambda_6_loss: 1.2825 - distribution_lambda_7_loss: 0.4407 - val_loss: 2.3113 - val_distribution_lambda_5_loss: 0.4972 - val_distribution_lambda_6_loss: 1.3943 - val_distribution_lambda_7_loss: 0.4198\n", "Epoch 602/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9600 - distribution_lambda_5_loss: 0.2166 - distribution_lambda_6_loss: 1.2915 - distribution_lambda_7_loss: 0.4519 - val_loss: 2.3047 - val_distribution_lambda_5_loss: 0.4900 - val_distribution_lambda_6_loss: 1.3947 - val_distribution_lambda_7_loss: 0.4201\n", "Epoch 603/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9987 - distribution_lambda_5_loss: 0.2532 - distribution_lambda_6_loss: 1.2947 - distribution_lambda_7_loss: 0.4508 - val_loss: 2.3080 - val_distribution_lambda_5_loss: 0.4836 - val_distribution_lambda_6_loss: 1.4057 - val_distribution_lambda_7_loss: 0.4188\n", "Epoch 604/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9468 - distribution_lambda_5_loss: 0.2314 - distribution_lambda_6_loss: 1.2728 - distribution_lambda_7_loss: 0.4426 - val_loss: 2.3056 - val_distribution_lambda_5_loss: 0.4733 - val_distribution_lambda_6_loss: 1.4125 - val_distribution_lambda_7_loss: 0.4198\n", "Epoch 605/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9711 - distribution_lambda_5_loss: 0.2326 - distribution_lambda_6_loss: 1.2857 - distribution_lambda_7_loss: 0.4528 - val_loss: 2.2892 - val_distribution_lambda_5_loss: 0.4651 - val_distribution_lambda_6_loss: 1.4065 - val_distribution_lambda_7_loss: 0.4176\n", "Epoch 606/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9440 - distribution_lambda_5_loss: 0.2240 - distribution_lambda_6_loss: 1.2737 - distribution_lambda_7_loss: 0.4462 - val_loss: 2.2826 - val_distribution_lambda_5_loss: 0.4620 - val_distribution_lambda_6_loss: 1.4035 - val_distribution_lambda_7_loss: 0.4171\n", "Epoch 607/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9412 - distribution_lambda_5_loss: 0.2147 - distribution_lambda_6_loss: 1.2787 - distribution_lambda_7_loss: 0.4477 - val_loss: 2.2960 - val_distribution_lambda_5_loss: 0.4725 - val_distribution_lambda_6_loss: 1.4036 - val_distribution_lambda_7_loss: 0.4199\n", "Epoch 608/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9515 - distribution_lambda_5_loss: 0.2083 - distribution_lambda_6_loss: 1.2851 - distribution_lambda_7_loss: 0.4581 - val_loss: 2.2845 - val_distribution_lambda_5_loss: 0.4741 - val_distribution_lambda_6_loss: 1.3934 - val_distribution_lambda_7_loss: 0.4170\n", "Epoch 609/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9517 - distribution_lambda_5_loss: 0.1841 - distribution_lambda_6_loss: 1.3090 - distribution_lambda_7_loss: 0.4586 - val_loss: 2.3140 - val_distribution_lambda_5_loss: 0.4900 - val_distribution_lambda_6_loss: 1.4032 - val_distribution_lambda_7_loss: 0.4208\n", "Epoch 610/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9623 - distribution_lambda_5_loss: 0.2130 - distribution_lambda_6_loss: 1.2953 - distribution_lambda_7_loss: 0.4541 - val_loss: 2.3160 - val_distribution_lambda_5_loss: 0.5017 - val_distribution_lambda_6_loss: 1.3913 - val_distribution_lambda_7_loss: 0.4229\n", "Epoch 611/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9933 - distribution_lambda_5_loss: 0.2304 - distribution_lambda_6_loss: 1.2924 - distribution_lambda_7_loss: 0.4705 - val_loss: 2.3145 - val_distribution_lambda_5_loss: 0.5013 - val_distribution_lambda_6_loss: 1.3933 - val_distribution_lambda_7_loss: 0.4199\n", "Epoch 612/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9474 - distribution_lambda_5_loss: 0.2275 - distribution_lambda_6_loss: 1.2658 - distribution_lambda_7_loss: 0.4540 - val_loss: 2.3192 - val_distribution_lambda_5_loss: 0.4989 - val_distribution_lambda_6_loss: 1.3989 - val_distribution_lambda_7_loss: 0.4214\n", "Epoch 613/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9657 - distribution_lambda_5_loss: 0.2373 - distribution_lambda_6_loss: 1.2805 - distribution_lambda_7_loss: 0.4480 - val_loss: 2.2967 - val_distribution_lambda_5_loss: 0.4792 - val_distribution_lambda_6_loss: 1.3979 - val_distribution_lambda_7_loss: 0.4196\n", "Epoch 614/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9466 - distribution_lambda_5_loss: 0.2042 - distribution_lambda_6_loss: 1.2882 - distribution_lambda_7_loss: 0.4542 - val_loss: 2.2873 - val_distribution_lambda_5_loss: 0.4800 - val_distribution_lambda_6_loss: 1.3907 - val_distribution_lambda_7_loss: 0.4166\n", "Epoch 615/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9328 - distribution_lambda_5_loss: 0.2235 - distribution_lambda_6_loss: 1.2664 - distribution_lambda_7_loss: 0.4429 - val_loss: 2.2727 - val_distribution_lambda_5_loss: 0.4706 - val_distribution_lambda_6_loss: 1.3840 - val_distribution_lambda_7_loss: 0.4181\n", "Epoch 616/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9918 - distribution_lambda_5_loss: 0.2315 - distribution_lambda_6_loss: 1.2978 - distribution_lambda_7_loss: 0.4625 - val_loss: 2.2797 - val_distribution_lambda_5_loss: 0.4667 - val_distribution_lambda_6_loss: 1.3934 - val_distribution_lambda_7_loss: 0.4196\n", "Epoch 617/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9057 - distribution_lambda_5_loss: 0.2068 - distribution_lambda_6_loss: 1.2627 - distribution_lambda_7_loss: 0.4362 - val_loss: 2.2639 - val_distribution_lambda_5_loss: 0.4570 - val_distribution_lambda_6_loss: 1.3884 - val_distribution_lambda_7_loss: 0.4185\n", "Epoch 618/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9548 - distribution_lambda_5_loss: 0.2105 - distribution_lambda_6_loss: 1.2948 - distribution_lambda_7_loss: 0.4495 - val_loss: 2.2714 - val_distribution_lambda_5_loss: 0.4607 - val_distribution_lambda_6_loss: 1.3919 - val_distribution_lambda_7_loss: 0.4188\n", "Epoch 619/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9224 - distribution_lambda_5_loss: 0.2309 - distribution_lambda_6_loss: 1.2633 - distribution_lambda_7_loss: 0.4282 - val_loss: 2.2958 - val_distribution_lambda_5_loss: 0.4751 - val_distribution_lambda_6_loss: 1.4032 - val_distribution_lambda_7_loss: 0.4176\n", "Epoch 620/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9426 - distribution_lambda_5_loss: 0.2224 - distribution_lambda_6_loss: 1.2784 - distribution_lambda_7_loss: 0.4417 - val_loss: 2.2902 - val_distribution_lambda_5_loss: 0.4759 - val_distribution_lambda_6_loss: 1.3992 - val_distribution_lambda_7_loss: 0.4151\n", "Epoch 621/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9688 - distribution_lambda_5_loss: 0.2148 - distribution_lambda_6_loss: 1.2830 - distribution_lambda_7_loss: 0.4710 - val_loss: 2.2945 - val_distribution_lambda_5_loss: 0.4758 - val_distribution_lambda_6_loss: 1.4015 - val_distribution_lambda_7_loss: 0.4172\n", "Epoch 622/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 4ms/step - loss: 1.9683 - distribution_lambda_5_loss: 0.2216 - distribution_lambda_6_loss: 1.3007 - distribution_lambda_7_loss: 0.4460 - val_loss: 2.2849 - val_distribution_lambda_5_loss: 0.4759 - val_distribution_lambda_6_loss: 1.3894 - val_distribution_lambda_7_loss: 0.4196\n", "Epoch 623/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9459 - distribution_lambda_5_loss: 0.2174 - distribution_lambda_6_loss: 1.2816 - distribution_lambda_7_loss: 0.4469 - val_loss: 2.2717 - val_distribution_lambda_5_loss: 0.4696 - val_distribution_lambda_6_loss: 1.3852 - val_distribution_lambda_7_loss: 0.4169\n", "Epoch 624/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9310 - distribution_lambda_5_loss: 0.2257 - distribution_lambda_6_loss: 1.2741 - distribution_lambda_7_loss: 0.4312 - val_loss: 2.2760 - val_distribution_lambda_5_loss: 0.4657 - val_distribution_lambda_6_loss: 1.3923 - val_distribution_lambda_7_loss: 0.4180\n", "Epoch 625/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9278 - distribution_lambda_5_loss: 0.2301 - distribution_lambda_6_loss: 1.2574 - distribution_lambda_7_loss: 0.4403 - val_loss: 2.2760 - val_distribution_lambda_5_loss: 0.4563 - val_distribution_lambda_6_loss: 1.4027 - val_distribution_lambda_7_loss: 0.4169\n", "Epoch 626/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9317 - distribution_lambda_5_loss: 0.2153 - distribution_lambda_6_loss: 1.2749 - distribution_lambda_7_loss: 0.4415 - val_loss: 2.2656 - val_distribution_lambda_5_loss: 0.4572 - val_distribution_lambda_6_loss: 1.3921 - val_distribution_lambda_7_loss: 0.4163\n", "Epoch 627/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9378 - distribution_lambda_5_loss: 0.2054 - distribution_lambda_6_loss: 1.2752 - distribution_lambda_7_loss: 0.4572 - val_loss: 2.2645 - val_distribution_lambda_5_loss: 0.4554 - val_distribution_lambda_6_loss: 1.3906 - val_distribution_lambda_7_loss: 0.4185\n", "Epoch 628/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 1.9339 - distribution_lambda_5_loss: 0.2068 - distribution_lambda_6_loss: 1.2838 - distribution_lambda_7_loss: 0.4433 - val_loss: 2.2710 - val_distribution_lambda_5_loss: 0.4618 - val_distribution_lambda_6_loss: 1.3885 - val_distribution_lambda_7_loss: 0.4208\n", "Epoch 629/2500\n", "12/12 [==============================] - 0s 6ms/step - loss: 1.9383 - distribution_lambda_5_loss: 0.2217 - distribution_lambda_6_loss: 1.2797 - distribution_lambda_7_loss: 0.4370 - val_loss: 2.2688 - val_distribution_lambda_5_loss: 0.4572 - val_distribution_lambda_6_loss: 1.3930 - val_distribution_lambda_7_loss: 0.4187\n", "Epoch 630/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9474 - distribution_lambda_5_loss: 0.2422 - distribution_lambda_6_loss: 1.2650 - distribution_lambda_7_loss: 0.4402 - val_loss: 2.2619 - val_distribution_lambda_5_loss: 0.4490 - val_distribution_lambda_6_loss: 1.3969 - val_distribution_lambda_7_loss: 0.4160\n", "Epoch 631/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9581 - distribution_lambda_5_loss: 0.2187 - distribution_lambda_6_loss: 1.2909 - distribution_lambda_7_loss: 0.4484 - val_loss: 2.2467 - val_distribution_lambda_5_loss: 0.4432 - val_distribution_lambda_6_loss: 1.3900 - val_distribution_lambda_7_loss: 0.4135\n", "Epoch 632/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9842 - distribution_lambda_5_loss: 0.2408 - distribution_lambda_6_loss: 1.2886 - distribution_lambda_7_loss: 0.4547 - val_loss: 2.2597 - val_distribution_lambda_5_loss: 0.4458 - val_distribution_lambda_6_loss: 1.3995 - val_distribution_lambda_7_loss: 0.4144\n", "Epoch 633/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9129 - distribution_lambda_5_loss: 0.2080 - distribution_lambda_6_loss: 1.2752 - distribution_lambda_7_loss: 0.4297 - val_loss: 2.2551 - val_distribution_lambda_5_loss: 0.4475 - val_distribution_lambda_6_loss: 1.3926 - val_distribution_lambda_7_loss: 0.4149\n", "Epoch 634/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 2.0062 - distribution_lambda_5_loss: 0.2315 - distribution_lambda_6_loss: 1.2987 - distribution_lambda_7_loss: 0.4760 - val_loss: 2.2595 - val_distribution_lambda_5_loss: 0.4490 - val_distribution_lambda_6_loss: 1.3944 - val_distribution_lambda_7_loss: 0.4161\n", "Epoch 635/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8907 - distribution_lambda_5_loss: 0.1959 - distribution_lambda_6_loss: 1.2600 - distribution_lambda_7_loss: 0.4348 - val_loss: 2.2665 - val_distribution_lambda_5_loss: 0.4655 - val_distribution_lambda_6_loss: 1.3893 - val_distribution_lambda_7_loss: 0.4118\n", "Epoch 636/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9428 - distribution_lambda_5_loss: 0.2136 - distribution_lambda_6_loss: 1.2839 - distribution_lambda_7_loss: 0.4453 - val_loss: 2.2680 - val_distribution_lambda_5_loss: 0.4637 - val_distribution_lambda_6_loss: 1.3921 - val_distribution_lambda_7_loss: 0.4121\n", "Epoch 637/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9431 - distribution_lambda_5_loss: 0.2203 - distribution_lambda_6_loss: 1.2652 - distribution_lambda_7_loss: 0.4576 - val_loss: 2.2678 - val_distribution_lambda_5_loss: 0.4690 - val_distribution_lambda_6_loss: 1.3844 - val_distribution_lambda_7_loss: 0.4143\n", "Epoch 638/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9405 - distribution_lambda_5_loss: 0.2273 - distribution_lambda_6_loss: 1.2727 - distribution_lambda_7_loss: 0.4404 - val_loss: 2.2798 - val_distribution_lambda_5_loss: 0.4739 - val_distribution_lambda_6_loss: 1.3900 - val_distribution_lambda_7_loss: 0.4158\n", "Epoch 639/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9192 - distribution_lambda_5_loss: 0.2012 - distribution_lambda_6_loss: 1.2737 - distribution_lambda_7_loss: 0.4443 - val_loss: 2.2961 - val_distribution_lambda_5_loss: 0.4804 - val_distribution_lambda_6_loss: 1.3978 - val_distribution_lambda_7_loss: 0.4178\n", "Epoch 640/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9429 - distribution_lambda_5_loss: 0.2176 - distribution_lambda_6_loss: 1.2843 - distribution_lambda_7_loss: 0.4410 - val_loss: 2.2839 - val_distribution_lambda_5_loss: 0.4715 - val_distribution_lambda_6_loss: 1.3951 - val_distribution_lambda_7_loss: 0.4174\n", "Epoch 641/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9281 - distribution_lambda_5_loss: 0.2198 - distribution_lambda_6_loss: 1.2713 - distribution_lambda_7_loss: 0.4370 - val_loss: 2.2859 - val_distribution_lambda_5_loss: 0.4653 - val_distribution_lambda_6_loss: 1.4040 - val_distribution_lambda_7_loss: 0.4167\n", "Epoch 642/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9353 - distribution_lambda_5_loss: 0.2167 - distribution_lambda_6_loss: 1.2720 - distribution_lambda_7_loss: 0.4466 - val_loss: 2.2626 - val_distribution_lambda_5_loss: 0.4555 - val_distribution_lambda_6_loss: 1.3920 - val_distribution_lambda_7_loss: 0.4151\n", "Epoch 643/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9225 - distribution_lambda_5_loss: 0.2164 - distribution_lambda_6_loss: 1.2742 - distribution_lambda_7_loss: 0.4319 - val_loss: 2.2593 - val_distribution_lambda_5_loss: 0.4507 - val_distribution_lambda_6_loss: 1.3971 - val_distribution_lambda_7_loss: 0.4115\n", "Epoch 644/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9519 - distribution_lambda_5_loss: 0.2289 - distribution_lambda_6_loss: 1.2753 - distribution_lambda_7_loss: 0.4477 - val_loss: 2.2659 - val_distribution_lambda_5_loss: 0.4554 - val_distribution_lambda_6_loss: 1.3984 - val_distribution_lambda_7_loss: 0.4121\n", "Epoch 645/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9335 - distribution_lambda_5_loss: 0.2173 - distribution_lambda_6_loss: 1.2720 - distribution_lambda_7_loss: 0.4442 - val_loss: 2.2608 - val_distribution_lambda_5_loss: 0.4526 - val_distribution_lambda_6_loss: 1.3928 - val_distribution_lambda_7_loss: 0.4154\n", "Epoch 646/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 1.8951 - distribution_lambda_5_loss: 0.1648 - distribution_lambda_6_loss: 1.2773 - distribution_lambda_7_loss: 0.4531 - val_loss: 2.2799 - val_distribution_lambda_5_loss: 0.4637 - val_distribution_lambda_6_loss: 1.3995 - val_distribution_lambda_7_loss: 0.4167\n", "Epoch 647/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8930 - distribution_lambda_5_loss: 0.1877 - distribution_lambda_6_loss: 1.2660 - distribution_lambda_7_loss: 0.4393 - val_loss: 2.2951 - val_distribution_lambda_5_loss: 0.4821 - val_distribution_lambda_6_loss: 1.3970 - val_distribution_lambda_7_loss: 0.4161\n", "Epoch 648/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8876 - distribution_lambda_5_loss: 0.1943 - distribution_lambda_6_loss: 1.2612 - distribution_lambda_7_loss: 0.4320 - val_loss: 2.3011 - val_distribution_lambda_5_loss: 0.4868 - val_distribution_lambda_6_loss: 1.4018 - val_distribution_lambda_7_loss: 0.4125\n", "Epoch 649/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9351 - distribution_lambda_5_loss: 0.2082 - distribution_lambda_6_loss: 1.2745 - distribution_lambda_7_loss: 0.4525 - val_loss: 2.3114 - val_distribution_lambda_5_loss: 0.4936 - val_distribution_lambda_6_loss: 1.4041 - val_distribution_lambda_7_loss: 0.4137\n", "Epoch 650/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9063 - distribution_lambda_5_loss: 0.1997 - distribution_lambda_6_loss: 1.2728 - distribution_lambda_7_loss: 0.4339 - val_loss: 2.2986 - val_distribution_lambda_5_loss: 0.4875 - val_distribution_lambda_6_loss: 1.3993 - val_distribution_lambda_7_loss: 0.4119\n", "Epoch 651/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9628 - distribution_lambda_5_loss: 0.2177 - distribution_lambda_6_loss: 1.2883 - distribution_lambda_7_loss: 0.4567 - val_loss: 2.2949 - val_distribution_lambda_5_loss: 0.4928 - val_distribution_lambda_6_loss: 1.3886 - val_distribution_lambda_7_loss: 0.4134\n", "Epoch 652/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9506 - distribution_lambda_5_loss: 0.2129 - distribution_lambda_6_loss: 1.2752 - distribution_lambda_7_loss: 0.4625 - val_loss: 2.2836 - val_distribution_lambda_5_loss: 0.4717 - val_distribution_lambda_6_loss: 1.3986 - val_distribution_lambda_7_loss: 0.4133\n", "Epoch 653/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9600 - distribution_lambda_5_loss: 0.2253 - distribution_lambda_6_loss: 1.2690 - distribution_lambda_7_loss: 0.4657 - val_loss: 2.2880 - val_distribution_lambda_5_loss: 0.4683 - val_distribution_lambda_6_loss: 1.4036 - val_distribution_lambda_7_loss: 0.4161\n", "Epoch 654/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9214 - distribution_lambda_5_loss: 0.2168 - distribution_lambda_6_loss: 1.2663 - distribution_lambda_7_loss: 0.4382 - val_loss: 2.2673 - val_distribution_lambda_5_loss: 0.4546 - val_distribution_lambda_6_loss: 1.3974 - val_distribution_lambda_7_loss: 0.4153\n", "Epoch 655/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9456 - distribution_lambda_5_loss: 0.2262 - distribution_lambda_6_loss: 1.2767 - distribution_lambda_7_loss: 0.4427 - val_loss: 2.2521 - val_distribution_lambda_5_loss: 0.4458 - val_distribution_lambda_6_loss: 1.3925 - val_distribution_lambda_7_loss: 0.4139\n", "Epoch 656/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9405 - distribution_lambda_5_loss: 0.2099 - distribution_lambda_6_loss: 1.2769 - distribution_lambda_7_loss: 0.4537 - val_loss: 2.2619 - val_distribution_lambda_5_loss: 0.4434 - val_distribution_lambda_6_loss: 1.4044 - val_distribution_lambda_7_loss: 0.4141\n", "Epoch 657/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9214 - distribution_lambda_5_loss: 0.2066 - distribution_lambda_6_loss: 1.2734 - distribution_lambda_7_loss: 0.4414 - val_loss: 2.2487 - val_distribution_lambda_5_loss: 0.4450 - val_distribution_lambda_6_loss: 1.3895 - val_distribution_lambda_7_loss: 0.4142\n", "Epoch 658/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9281 - distribution_lambda_5_loss: 0.2008 - distribution_lambda_6_loss: 1.2817 - distribution_lambda_7_loss: 0.4456 - val_loss: 2.2611 - val_distribution_lambda_5_loss: 0.4573 - val_distribution_lambda_6_loss: 1.3908 - val_distribution_lambda_7_loss: 0.4131\n", "Epoch 659/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9226 - distribution_lambda_5_loss: 0.2158 - distribution_lambda_6_loss: 1.2744 - distribution_lambda_7_loss: 0.4324 - val_loss: 2.2594 - val_distribution_lambda_5_loss: 0.4498 - val_distribution_lambda_6_loss: 1.3979 - val_distribution_lambda_7_loss: 0.4118\n", "Epoch 660/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9482 - distribution_lambda_5_loss: 0.2194 - distribution_lambda_6_loss: 1.2666 - distribution_lambda_7_loss: 0.4621 - val_loss: 2.2727 - val_distribution_lambda_5_loss: 0.4607 - val_distribution_lambda_6_loss: 1.3965 - val_distribution_lambda_7_loss: 0.4155\n", "Epoch 661/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9496 - distribution_lambda_5_loss: 0.2248 - distribution_lambda_6_loss: 1.2734 - distribution_lambda_7_loss: 0.4514 - val_loss: 2.2721 - val_distribution_lambda_5_loss: 0.4647 - val_distribution_lambda_6_loss: 1.3900 - val_distribution_lambda_7_loss: 0.4174\n", "Epoch 662/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9289 - distribution_lambda_5_loss: 0.2085 - distribution_lambda_6_loss: 1.2727 - distribution_lambda_7_loss: 0.4478 - val_loss: 2.2921 - val_distribution_lambda_5_loss: 0.4720 - val_distribution_lambda_6_loss: 1.4010 - val_distribution_lambda_7_loss: 0.4190\n", "Epoch 663/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9416 - distribution_lambda_5_loss: 0.2082 - distribution_lambda_6_loss: 1.2783 - distribution_lambda_7_loss: 0.4551 - val_loss: 2.2806 - val_distribution_lambda_5_loss: 0.4769 - val_distribution_lambda_6_loss: 1.3859 - val_distribution_lambda_7_loss: 0.4177\n", "Epoch 664/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9204 - distribution_lambda_5_loss: 0.2322 - distribution_lambda_6_loss: 1.2593 - distribution_lambda_7_loss: 0.4288 - val_loss: 2.2614 - val_distribution_lambda_5_loss: 0.4633 - val_distribution_lambda_6_loss: 1.3823 - val_distribution_lambda_7_loss: 0.4157\n", "Epoch 665/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9082 - distribution_lambda_5_loss: 0.1986 - distribution_lambda_6_loss: 1.2667 - distribution_lambda_7_loss: 0.4429 - val_loss: 2.2763 - val_distribution_lambda_5_loss: 0.4731 - val_distribution_lambda_6_loss: 1.3892 - val_distribution_lambda_7_loss: 0.4141\n", "Epoch 666/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8931 - distribution_lambda_5_loss: 0.1872 - distribution_lambda_6_loss: 1.2627 - distribution_lambda_7_loss: 0.4431 - val_loss: 2.3031 - val_distribution_lambda_5_loss: 0.4955 - val_distribution_lambda_6_loss: 1.3944 - val_distribution_lambda_7_loss: 0.4133\n", "Epoch 667/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9870 - distribution_lambda_5_loss: 0.2537 - distribution_lambda_6_loss: 1.2868 - distribution_lambda_7_loss: 0.4464 - val_loss: 2.2770 - val_distribution_lambda_5_loss: 0.4779 - val_distribution_lambda_6_loss: 1.3859 - val_distribution_lambda_7_loss: 0.4133\n", "Epoch 668/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9337 - distribution_lambda_5_loss: 0.2141 - distribution_lambda_6_loss: 1.2704 - distribution_lambda_7_loss: 0.4492 - val_loss: 2.2995 - val_distribution_lambda_5_loss: 0.4804 - val_distribution_lambda_6_loss: 1.4026 - val_distribution_lambda_7_loss: 0.4165\n", "Epoch 669/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9700 - distribution_lambda_5_loss: 0.2267 - distribution_lambda_6_loss: 1.2905 - distribution_lambda_7_loss: 0.4528 - val_loss: 2.2831 - val_distribution_lambda_5_loss: 0.4676 - val_distribution_lambda_6_loss: 1.4030 - val_distribution_lambda_7_loss: 0.4125\n", "Epoch 670/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "12/12 [==============================] - 0s 5ms/step - loss: 1.9584 - distribution_lambda_5_loss: 0.2327 - distribution_lambda_6_loss: 1.2815 - distribution_lambda_7_loss: 0.4442 - val_loss: 2.2705 - val_distribution_lambda_5_loss: 0.4592 - val_distribution_lambda_6_loss: 1.3967 - val_distribution_lambda_7_loss: 0.4146\n", "Epoch 671/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9363 - distribution_lambda_5_loss: 0.2149 - distribution_lambda_6_loss: 1.2810 - distribution_lambda_7_loss: 0.4404 - val_loss: 2.2704 - val_distribution_lambda_5_loss: 0.4595 - val_distribution_lambda_6_loss: 1.3967 - val_distribution_lambda_7_loss: 0.4142\n", "Epoch 672/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8835 - distribution_lambda_5_loss: 0.1810 - distribution_lambda_6_loss: 1.2625 - distribution_lambda_7_loss: 0.4400 - val_loss: 2.2817 - val_distribution_lambda_5_loss: 0.4749 - val_distribution_lambda_6_loss: 1.3926 - val_distribution_lambda_7_loss: 0.4142\n", "Epoch 673/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9283 - distribution_lambda_5_loss: 0.2089 - distribution_lambda_6_loss: 1.2697 - distribution_lambda_7_loss: 0.4497 - val_loss: 2.2701 - val_distribution_lambda_5_loss: 0.4699 - val_distribution_lambda_6_loss: 1.3879 - val_distribution_lambda_7_loss: 0.4123\n", "Epoch 674/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9700 - distribution_lambda_5_loss: 0.2350 - distribution_lambda_6_loss: 1.2865 - distribution_lambda_7_loss: 0.4485 - val_loss: 2.2670 - val_distribution_lambda_5_loss: 0.4601 - val_distribution_lambda_6_loss: 1.3933 - val_distribution_lambda_7_loss: 0.4135\n", "Epoch 675/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9008 - distribution_lambda_5_loss: 0.1846 - distribution_lambda_6_loss: 1.2706 - distribution_lambda_7_loss: 0.4456 - val_loss: 2.2797 - val_distribution_lambda_5_loss: 0.4766 - val_distribution_lambda_6_loss: 1.3900 - val_distribution_lambda_7_loss: 0.4130\n", "Epoch 676/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.9209 - distribution_lambda_5_loss: 0.1978 - distribution_lambda_6_loss: 1.2818 - distribution_lambda_7_loss: 0.4413 - val_loss: 2.2873 - val_distribution_lambda_5_loss: 0.4817 - val_distribution_lambda_6_loss: 1.3917 - val_distribution_lambda_7_loss: 0.4140\n", "Epoch 677/2500\n", "12/12 [==============================] - 0s 4ms/step - loss: 1.8906 - distribution_lambda_5_loss: 0.1910 - distribution_lambda_6_loss: 1.2681 - distribution_lambda_7_loss: 0.4315 - val_loss: 2.2865 - val_distribution_lambda_5_loss: 0.4815 - val_distribution_lambda_6_loss: 1.3915 - val_distribution_lambda_7_loss: 0.4136\n", "Epoch 678/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9242 - distribution_lambda_5_loss: 0.1985 - distribution_lambda_6_loss: 1.2796 - distribution_lambda_7_loss: 0.4461 - val_loss: 2.2903 - val_distribution_lambda_5_loss: 0.4848 - val_distribution_lambda_6_loss: 1.3901 - val_distribution_lambda_7_loss: 0.4154\n", "Epoch 679/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8873 - distribution_lambda_5_loss: 0.1908 - distribution_lambda_6_loss: 1.2673 - distribution_lambda_7_loss: 0.4292 - val_loss: 2.2924 - val_distribution_lambda_5_loss: 0.4902 - val_distribution_lambda_6_loss: 1.3877 - val_distribution_lambda_7_loss: 0.4145\n", "Epoch 680/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.8469 - distribution_lambda_5_loss: 0.1919 - distribution_lambda_6_loss: 1.2299 - distribution_lambda_7_loss: 0.4251 - val_loss: 2.2952 - val_distribution_lambda_5_loss: 0.4871 - val_distribution_lambda_6_loss: 1.3949 - val_distribution_lambda_7_loss: 0.4133\n", "Epoch 681/2500\n", "12/12 [==============================] - 0s 5ms/step - loss: 1.9011 - distribution_lambda_5_loss: 0.2214 - distribution_lambda_6_loss: 1.2549 - distribution_lambda_7_loss: 0.4247 - val_loss: 2.2815 - val_distribution_lambda_5_loss: 0.4756 - val_distribution_lambda_6_loss: 1.3958 - val_distribution_lambda_7_loss: 0.4101\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 = 2500\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 = 1.1\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 50)\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=\"relu\") (inputs)\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", "\n", "x2 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x2)\n", "\n", "x3 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x3 = tfk.layers.Dropout(0.5)(x3)\n", "x3 = tfk.layers.Dense(1, activation=\"sigmoid\")(x3)\n", "out_3 = tfp.layers.DistributionLambda(lambda t: tfp.distributions.Bernoulli(probs = t[..., 0]))(x3)\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": 23, "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": 31, "id": "c41cf448", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.32776719099564455\n", "0.5589799999938707\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.24975080840924535\n", "0.4193440300864497\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": 39, "id": "cecf5392", "metadata": {}, "outputs": [], "source": [ "save_model_of = False\n", "save_model_gk = False\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": 25, "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": 26, "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": 27, "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": 27, "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": 28, "id": "c58ba41d", "metadata": {}, "outputs": [], "source": [ "def PlayerMatch(player, match = 0):\n", " team = players.loc[player]['team']\n", " \n", " if(match == 0):\n", " oppteam = 'Avg'\n", " home = 1\n", " else:\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 = 0, 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": 29, "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
Falcone1.0090
Gendrey1.0090
Baschirotto1.0090
Umtiti1.0090
Gallo0.6565
.........
Barrenechea0.0020
Pogba0.0050
Chiesa0.4055
Soule'0.0020
Milik0.4060
\n", "

474 rows × 2 columns

\n", "
" ], "text/plain": [ " starter percentage\n", "player \n", "Falcone 1.00 90\n", "Gendrey 1.00 90\n", "Baschirotto 1.00 90\n", "Umtiti 1.00 90\n", "Gallo 0.65 65\n", "... ... ...\n", "Barrenechea 0.00 20\n", "Pogba 0.00 50\n", "Chiesa 0.40 55\n", "Soule' 0.00 20\n", "Milik 0.40 60\n", "\n", "[474 rows x 2 columns]" ] }, "execution_count": 29, "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": 45, "id": "5e63c2b7", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 6.26 ± 0.89; FV 5.91 + 0.93 (67.6% cs)\n", "Provedel: MV 6.26 ± 0.89; FV 5.88 + 0.98 (65.8% cs)\n", "Vicario: MV 6.26 ± 0.89; FV 6.02 + 0.89 (44.7% cs)\n", "Szczesny: MV 6.26 ± 0.89; FV 6.02 + 0.95 (67.6% cs)\n", "Falcone: MV 6.26 ± 0.89; FV 5.06 + 1.13 (10.0% cs)\n", "Silvestri: MV 6.26 ± 0.89; FV 5.85 + 0.95 (43.4% cs)\n", "Rui Patricio: MV 6.26 ± 0.89; FV 5.74 + 1.11 (47.3% cs)\n", "Onana: MV 6.26 ± 0.89; FV 6.07 + 0.95 (71.6% cs)\n", "Sepe: MV 6.25 ± 0.91; FV 3.07 + 2.17 (1.4% cs)\n", "Milinkovic-Savic V.: MV 6.15 ± 0.74; FV 4.91 + 1.52 (34.4% cs)\n", "Musso: MV 6.26 ± 0.88; FV 5.11 + 0.77 (6.7% cs)\n", "Maignan: MV 6.26 ± 0.89; FV 5.85 + 0.97 (39.0% cs)\n", "Carnesecchi: MV 6.26 ± 0.89; FV 5.28 + 0.59 (8.4% cs)\n", "Di Gregorio: MV 6.26 ± 0.89; FV 5.29 + 1.39 (31.4% cs)\n", "Audero: MV 6.26 ± 0.89; FV 4.64 + 1.09 (1.2% cs)\n", "Montipo': MV 6.04 ± 0.70; FV 5.09 + 1.34 (18.1% cs)\n", "Skorupski: MV 6.26 ± 0.89; FV 6.03 + 0.99 (69.8% cs)\n", "Consigli: MV 6.26 ± 0.89; FV 4.88 + 0.97 (10.5% cs)\n", "Dragowski: MV 6.26 ± 0.89; FV 4.80 + 1.22 (3.8% cs)\n", "Terracciano: MV 6.26 ± 0.89; FV 5.96 + 0.92 (68.3% cs)\n", "Tatarusanu: MV 6.24 ± 0.89; FV 3.47 + 2.77 (1.2% cs)\n", "Handanovic: MV 6.26 ± 0.89; FV 5.52 + 1.20 (33.3% cs)\n", "Sportiello: MV 6.26 ± 0.89; FV 5.04 + 0.65 (12.9% cs)\n", "Perin: MV 6.26 ± 0.89; FV 5.94 + 0.94 (61.3% cs)\n", "Zoet: MV 6.26 ± 0.89; FV 5.10 + 1.55 (36.4% cs)\n", "Ochoa: MV 6.26 ± 0.89; FV 2.62 + 2.40 (0.6% cs)\n", "Pegolo: MV 6.26 ± 0.89; FV 4.89 + 1.01 (9.1% cs)\n", "Gollini: MV 6.26 ± 0.89; FV 5.94 + 0.90 (74.0% cs)\n", "Mirante no data\n", "Sarr M. no data\n", "Lamanna no data\n", "Ujkani no data\n", "Berisha: MV 6.26 ± 0.89; FV 5.66 + 1.07 (21.0% cs)\n", "Marchetti: MV 6.26 ± 0.89; FV 4.70 + 1.12 (2.3% cs)\n", "Perilli: MV 6.25 ± 0.87; FV 5.82 + 0.96 (44.5% cs)\n", "Padelli: MV 6.19 ± 0.77; FV 4.54 + 1.63 (1.8% cs)\n", "Perisan: MV 6.26 ± 0.89; FV 6.04 + 0.98 (40.3% cs)\n", "Bardi: MV 6.26 ± 0.89; FV 5.95 + 0.91 (74.1% cs)\n", "Cordaz no data\n", "Pinsoglio: MV 5.21 ± 1.13; FV 3.01 + 1.33 (1.6% cs)\n", "Fiorillo: MV 6.26 ± 0.89; FV 3.64 + 1.17 (0.7% cs)\n", "Cragno: MV 6.26 ± 0.89; FV 5.07 + 1.66 (32.1% cs)\n", "Sirigu: MV 6.26 ± 0.89; FV 5.29 + 1.41 (40.6% cs)\n", "Cerofolini no data\n", "Rossi F.: MV 6.12 ± 0.77; FV 4.51 + 1.02 (1.7% cs)\n", "Ravaglia F.: MV 6.26 ± 0.89; FV 4.58 + 1.03 (5.2% cs)\n", "Brancolini no data\n", "Bleve no data\n", "Berardi A.: MV 6.26 ± 0.89; FV 5.20 + 0.96 (16.3% cs)\n", "Russo A. no data\n", "Gemello: MV 6.26 ± 0.89; FV 5.95 + 0.90 (73.1% cs)\n", "Ravaglia: MV 6.26 ± 0.89; FV 4.87 + 1.22 (2.5% cs)\n", "Boer no data\n", "Adamonis no data\n", "Marfella: MV 6.26 ± 0.89; FV 5.94 + 0.90 (71.6% cs)\n", "Zovko: MV 6.26 ± 0.89; FV 4.61 + 1.08 (1.5% cs)\n", "Piana no data\n", "Bagnolini no data\n", "Luis Maximiano: MV 6.26 ± 0.89; FV 5.94 + 0.91 (74.1% cs)\n", "Svilar no data\n", "Sorrentino A. no data\n", "Ciezkowski no data\n", "Saro no data\n", "Vasquez D. no data\n", "Turk: MV 6.26 ± 0.89; FV 4.81 + 1.21 (1.8% cs)\n", "Dimarco: MV 6.04 ± 0.82; FV 6.32 + 1.20\n", "Smalling: MV 6.20 ± 0.95; FV 6.56 + 1.57\n", "Doig: MV 6.15 ± 1.13; FV 6.71 + 2.14\n", "Carlos Augusto: MV 6.15 ± 1.03; FV 6.68 + 1.99\n", "Kim: MV 6.29 ± 0.99; FV 6.70 + 1.75\n", "Posch: MV 6.11 ± 1.06; FV 6.48 + 1.76\n", "Di Lorenzo: MV 6.24 ± 0.92; FV 6.58 + 1.56\n", "Danilo: MV 6.20 ± 0.93; FV 6.57 + 1.52\n", "Hernandez T.: MV 6.03 ± 1.08; FV 6.34 + 1.72\n", "Udogie: MV 6.01 ± 1.03; FV 6.42 + 1.82\n", "Parisi: MV 6.10 ± 0.93; FV 6.48 + 1.62\n", "Mario Rui: MV 6.18 ± 0.92; FV 6.30 + 1.21\n", "Romagnoli: MV 6.11 ± 0.93; FV 6.28 + 1.22\n", "Bastoni S.: MV 6.12 ± 0.92; FV 6.55 + 1.72\n", "Mazzocchi: MV 5.88 ± 0.92; FV 6.04 + 1.24\n", "Valeri: MV 6.11 ± 0.68; FV 6.36 + 1.08\n", "Tomori: MV 6.05 ± 0.92; FV 6.23 + 1.20\n", "Scalvini: MV 5.96 ± 0.98; FV 6.14 + 1.35\n", "Toloi: MV 5.97 ± 0.96; FV 6.14 + 1.26\n", "Demiral: MV 5.99 ± 0.91; FV 6.21 + 1.27\n", "Maehle: MV 5.92 ± 0.97; FV 6.11 + 1.50\n", "Dumfries: MV 5.84 ± 0.81; FV 5.92 + 1.01\n", "Baschirotto: MV 6.16 ± 0.99; FV 6.53 + 1.63\n", "Bijol: MV 5.94 ± 0.97; FV 6.10 + 1.38\n", "Schuurs: MV 6.12 ± 0.80; FV 6.19 + 0.94\n", "Juan Jesus: MV 6.18 ± 0.73; FV 6.45 + 1.23\n", "Depaoli: MV 6.07 ± 0.89; FV 6.40 + 1.43\n", "Mancini: MV 6.10 ± 0.83; FV 6.27 + 1.09\n", "Ibanez: MV 5.78 ± 1.13; FV 5.86 + 1.43\n", "Rodrigo Becao: MV 6.03 ± 0.95; FV 6.28 + 1.37\n", "Ebuehi: MV 6.06 ± 0.85; FV 6.36 + 1.37\n", "Gosens: MV 5.83 ± 0.66; FV 5.89 + 0.64\n", "Darmian: MV 5.98 ± 0.71; FV 6.11 + 0.85\n", "Reca: MV 5.99 ± 0.91; FV 6.18 + 1.35\n", "Bremer: MV 6.00 ± 1.07; FV 6.32 + 1.65\n", "Sernicola: MV 6.00 ± 0.95; FV 6.27 + 1.54\n", "Rrahmani: MV 6.28 ± 1.00; FV 6.71 + 1.78\n", "Vojvoda: MV 5.89 ± 0.83; FV 5.95 + 1.03\n", "Holm: MV 6.00 ± 0.84; FV 6.22 + 1.28\n", "Bastoni: MV 6.01 ± 0.79; FV 6.01 + 0.77\n", "Milenkovic: MV 6.11 ± 0.78; FV 6.31 + 1.11\n", "Kalulu: MV 5.75 ± 1.10; FV 5.79 + 1.31\n", "Martinez Quarta: MV 6.12 ± 0.81; FV 6.22 + 1.00\n", "Casale: MV 5.97 ± 0.89; FV 6.08 + 1.17\n", "Perez N.: MV 6.03 ± 0.87; FV 6.22 + 1.13\n", "Olivera: MV 6.14 ± 0.67; FV 6.44 + 1.18\n", "Izzo: MV 6.10 ± 0.82; FV 6.33 + 1.15\n", "Luperto: MV 5.80 ± 1.02; FV 5.79 + 0.96\n", "Skriniar: MV 5.83 ± 0.84; FV 5.82 + 0.78\n", "Rodriguez R.: MV 6.03 ± 0.72; FV 6.01 + 0.68\n", "Marusic: MV 6.00 ± 0.84; FV 6.07 + 0.93\n", "Lazzari: MV 6.00 ± 0.85; FV 6.11 + 1.08\n", "Kyriakopoulos: MV 5.96 ± 0.80; FV 5.96 + 0.82\n", "Ampadu: MV 5.85 ± 0.87; FV 5.84 + 0.88\n", "Ismajli: MV 5.84 ± 0.87; FV 5.80 + 0.79\n", "Llorente D.: MV 5.86 ± 1.01; FV 5.92 + 1.27\n", "Cambiaso: MV 5.98 ± 0.71; FV 5.96 + 0.66\n", "Hysaj: MV 5.94 ± 0.66; FV 5.95 + 0.60\n", "Biraghi: MV 6.15 ± 0.73; FV 6.37 + 1.11\n", "Medel: MV 6.00 ± 0.65; FV 5.93 + 0.54\n", "Bonucci: MV 6.00 ± 0.91; FV 6.28 + 1.38\n", "Calabria: MV 5.88 ± 1.03; FV 6.03 + 1.47\n", "Acerbi: MV 5.98 ± 0.66; FV 5.93 + 0.54\n", "Spinazzola: MV 6.12 ± 0.85; FV 6.41 + 1.33\n", "Lykogiannis: MV 5.97 ± 0.71; FV 6.05 + 0.76\n", "Pellegrini Lu.: MV 5.96 ± 0.79; FV 6.04 + 0.98\n", "Djidji: MV 5.85 ± 0.84; FV 5.86 + 1.01\n", "Lazaro: MV 6.02 ± 0.88; FV 6.15 + 1.11\n", "Augello: MV 5.91 ± 0.90; FV 6.16 + 1.45\n", "Gallo: MV 5.87 ± 0.78; FV 5.85 + 0.78\n", "Singo: MV 5.94 ± 0.87; FV 6.09 + 1.23\n", "Mari': MV 5.96 ± 0.90; FV 6.09 + 1.08\n", "Caldirola: MV 5.98 ± 0.88; FV 6.16 + 1.19\n", "Dodo': MV 5.99 ± 0.79; FV 6.00 + 0.78\n", "De Vrij: MV 5.82 ± 0.77; FV 5.85 + 0.69\n", "Patric: MV 5.97 ± 0.92; FV 6.01 + 0.98\n", "Faraoni: MV 6.08 ± 0.91; FV 6.42 + 1.51\n", "Ceccherini: MV 5.98 ± 0.94; FV 6.17 + 1.32\n", "Hateboer: MV 5.86 ± 0.96; FV 5.97 + 1.35\n", "Rogerio: MV 5.89 ± 0.70; FV 5.87 + 0.61\n", "Umtiti: MV 5.89 ± 0.91; FV 5.91 + 0.99\n", "Aina: MV 6.01 ± 0.91; FV 6.19 + 1.31\n", "Birindelli: MV 5.92 ± 0.69; FV 5.94 + 0.73\n", "Lucumi': MV 5.94 ± 0.77; FV 5.90 + 0.71\n", "Ehizibue: MV 5.86 ± 0.89; FV 6.01 + 1.32\n", "Bianchetti: MV 5.85 ± 0.82; FV 5.83 + 0.89\n", "Ferrari G.: MV 6.01 ± 0.91; FV 6.17 + 1.15\n", "Fazio: MV 5.45 ± 1.36; FV 5.50 + 1.29\n", "Gravillon: MV 6.00 ± 0.83; FV 6.01 + 0.86\n", "Buongiorno: MV 6.02 ± 0.79; FV 6.03 + 0.81\n", "Gunter: MV 5.74 ± 1.06; FV 5.71 + 1.08\n", "Troost-Ekong: MV 5.62 ± 1.09; FV 5.57 + 1.10\n", "Soumaoro: MV 5.87 ± 0.88; FV 5.82 + 0.81\n", "Ceccaroni: MV 5.89 ± 1.00; FV 5.99 + 1.23\n", "Pongracic: MV 5.97 ± 0.76; FV 5.95 + 0.73\n", "Soppy: MV 5.82 ± 0.76; FV 5.83 + 0.77\n", "Gendrey: MV 5.89 ± 0.65; FV 5.88 + 0.56\n", "Hien: MV 5.92 ± 0.77; FV 5.92 + 0.71\n", "Ferrari A.: MV 5.90 ± 0.82; FV 5.90 + 0.82\n", "Masina: MV 5.97 ± 0.75; FV 6.38 + 1.45\n", "Zappacosta: MV 6.00 ± 0.88; FV 6.23 + 1.31\n", "Gyomber: MV 5.70 ± 1.05; FV 5.65 + 1.05\n", "Alex Sandro: MV 5.77 ± 0.98; FV 5.71 + 0.89\n", "Pezzella Giu.: MV 5.88 ± 0.67; FV 5.88 + 0.57\n", "Bereszynski: MV 5.98 ± 0.67; FV 5.94 + 0.61\n", "Venuti: MV 5.98 ± 0.67; FV 5.97 + 0.60\n", "Palomino: MV 5.99 ± 0.92; FV 6.12 + 1.07\n", "Nuytinck: MV 5.79 ± 1.01; FV 5.80 + 1.09\n", "Marlon: MV 5.86 ± 0.68; FV 5.85 + 0.60\n", "Magnani: MV 5.91 ± 0.76; FV 5.89 + 0.69\n", "Colley: MV 5.73 ± 1.12; FV 5.78 + 1.30\n", "Nikolaou: MV 5.73 ± 0.75; FV 5.65 + 0.70\n", "Terzic: MV 6.07 ± 0.54; FV 6.00 + 0.47\n", "Igor: MV 5.99 ± 0.76; FV 5.94 + 0.70\n", "Toljan: MV 5.83 ± 0.72; FV 5.80 + 0.63\n", "Zortea: MV 5.93 ± 0.76; FV 5.97 + 0.81\n", "Dawidowicz: MV 5.93 ± 0.86; FV 6.00 + 1.04\n", "Celik: MV 5.78 ± 0.77; FV 5.74 + 0.79\n", "Bellanova: MV 5.87 ± 0.75; FV 5.90 + 0.77\n", "Erlic: MV 5.90 ± 0.77; FV 5.83 + 0.68\n", "Ballo-Toure': MV 6.01 ± 0.75; FV 6.21 + 1.00\n", "Dest: MV 5.70 ± 0.82; FV 5.71 + 0.86\n", "Stojanovic: MV 5.72 ± 0.80; FV 5.66 + 0.79\n", "Amian: MV 5.81 ± 0.75; FV 5.75 + 0.73\n", "Bradaric: MV 5.60 ± 1.02; FV 5.59 + 1.08\n", "Daniliuc: MV 5.60 ± 1.14; FV 5.58 + 1.18\n", "Zima: MV 5.94 ± 0.77; FV 5.95 + 0.78\n", "De Winter: MV 5.73 ± 0.88; FV 5.68 + 0.82\n", "Quagliata: MV 6.01 ± 0.58; FV 5.98 + 0.48\n", "Ebosse: MV 5.81 ± 0.64; FV 5.80 + 0.53\n", "Aiwu: MV 5.98 ± 0.78; FV 6.06 + 0.86\n", "Lochoshvili: MV 5.95 ± 0.81; FV 6.04 + 1.02\n", "Bronn: MV 5.57 ± 0.98; FV 5.46 + 0.93\n", "Thiaw: MV 5.81 ± 1.06; FV 5.84 + 1.17\n", "Zeefuik: MV 6.02 ± 0.79; FV 6.12 + 0.90\n", "Romagnoli S.: MV 5.96 ± 1.12; FV 6.25 + 1.76\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Ghiglione: MV 5.97 ± 0.85; FV 6.19 + 1.31\n", "Rugani: MV 5.99 ± 0.57; FV 5.94 + 0.43\n", "De Sciglio: MV 5.81 ± 0.61; FV 5.85 + 0.46\n", "Djimsiti: MV 5.90 ± 0.74; FV 5.91 + 0.66\n", "Caldara: MV 5.72 ± 0.98; FV 5.65 + 0.98\n", "Karsdorp: MV 5.86 ± 0.78; FV 5.87 + 0.78\n", "Marchizza: MV 6.01 ± 0.64; FV 5.99 + 0.56\n", "Kjaer: MV 5.90 ± 0.75; FV 5.87 + 0.69\n", "Okoli: MV 5.73 ± 0.91; FV 5.72 + 0.84\n", "Amione: MV 5.79 ± 0.95; FV 5.86 + 1.26\n", "Ruggeri: MV 5.89 ± 0.70; FV 5.90 + 0.61\n", "Zanoli: MV 6.01 ± 0.88; FV 6.28 + 1.41\n", "Wisniewski: MV 5.82 ± 0.68; FV 5.77 + 0.60\n", "Radovanovic: MV 5.49 ± 0.91; FV 5.38 + 0.86\n", "Dermaku: MV 6.02 ± 0.85; FV 6.15 + 1.04\n", "D'ambrosio: MV 5.99 ± 0.71; FV 5.95 + 0.65\n", "De Silvestri: MV 5.88 ± 0.88; FV 5.99 + 1.19\n", "Chiriches: MV 5.86 ± 0.78; FV 5.81 + 0.69\n", "Murru: MV 5.68 ± 0.78; FV 5.61 + 0.81\n", "Bonifazi: MV 5.79 ± 0.80; FV 5.70 + 0.73\n", "Donati: MV 5.92 ± 1.08; FV 6.18 + 1.72\n", "Walukiewicz: MV 6.07 ± 0.70; FV 6.03 + 0.64\n", "Ranieri L.: MV 6.01 ± 0.69; FV 6.09 + 0.77\n", "Gabbia: MV 5.65 ± 0.90; FV 5.56 + 0.89\n", "Kumbulla: MV 5.74 ± 1.02; FV 5.69 + 1.04\n", "Adopo: MV 6.01 ± 0.67; FV 5.99 + 0.61\n", "Pirola: MV 5.60 ± 1.24; FV 5.66 + 1.43\n", "Lovato: MV 5.50 ± 1.17; FV 5.43 + 1.01\n", "Tuia: MV 6.04 ± 0.58; FV 5.98 + 0.48\n", "Ferrer: MV 5.89 ± 0.84; FV 5.88 + 0.86\n", "Antov: MV 5.72 ± 0.93; FV 5.67 + 0.90\n", "Vasquez: MV 5.88 ± 0.69; FV 5.85 + 0.59\n", "Ruan: MV 5.90 ± 0.79; FV 5.81 + 0.70\n", "Ostigard: MV 6.11 ± 0.69; FV 6.03 + 0.67\n", "Coppola D.: MV 5.91 ± 0.69; FV 5.87 + 0.61\n", "Cacace: MV 5.82 ± 0.64; FV 5.78 + 0.53\n", "Gatti: MV 5.99 ± 0.81; FV 5.99 + 0.77\n", "Gila: MV 5.90 ± 1.02; FV 5.99 + 1.19\n", "Bayeye: MV 5.94 ± 0.88; FV 6.02 + 1.07\n", "Sambia: MV 5.66 ± 0.88; FV 5.66 + 0.89\n", "Moutinho J.: MV 5.90 ± 0.73; FV 5.89 + 0.71\n", "Conti: MV 5.85 ± 0.85; FV 5.98 + 1.24\n", "Marrone: MV 5.73 ± 0.78; FV 5.66 + 0.80\n", "Tonelli: MV 5.69 ± 0.89; FV 5.61 + 0.82\n", "Murillo: MV 5.64 ± 0.80; FV 5.54 + 0.79\n", "Radu: MV 5.95 ± 0.86; FV 5.89 + 0.78\n", "Paletta: MV 5.98 ± 0.83; FV 6.10 + 1.00\n", "Florenzi: MV 6.01 ± 0.75; FV 6.14 + 0.86\n", "Sala: MV 5.98 ± 0.76; FV 6.07 + 0.91\n", "Fares: MV 5.76 ± 0.80; FV 5.79 + 0.98\n", "Romagna: MV 6.00 ± 0.79; FV 6.05 + 0.81\n", "Cassandro: MV 6.01 ± 0.82; FV 6.10 + 0.96\n", "Muldur: MV 5.82 ± 0.71; FV 5.79 + 0.62\n", "Amey: MV 6.02 ± 0.78; FV 6.05 + 0.82\n", "Zanotti: MV 5.85 ± 0.83; FV 5.86 + 0.84\n", "Ebosele: MV 5.88 ± 0.63; FV 5.92 + 0.54\n", "Buta: MV 5.91 ± 0.83; FV 5.98 + 0.87\n", "Abankwah: MV 5.89 ± 0.78; FV 5.94 + 0.79\n", "Guessand A.: MV 5.91 ± 0.83; FV 5.98 + 0.87\n", "Cabal: MV 5.98 ± 0.61; FV 5.93 + 0.49\n", "Sosa: MV 5.60 ± 0.88; FV 5.49 + 0.83\n", "Guarino: MV 5.87 ± 0.92; FV 5.92 + 1.04\n", "Carboni F.: MV 6.00 ± 0.79; FV 6.09 + 0.88\n", "Zaccagni: MV 6.35 ± 1.16; FV 7.13 + 2.61\n", "Kvaratskhelia: MV 6.56 ± 1.38; FV 7.51 + 3.23\n", "Milinkovic-Savic: MV 6.13 ± 1.13; FV 6.68 + 2.21\n", "Barella: MV 6.12 ± 0.97; FV 6.61 + 1.82\n", "Zielinski: MV 6.31 ± 1.01; FV 6.92 + 2.05\n", "Luis Alberto: MV 6.22 ± 1.03; FV 6.78 + 2.02\n", "Strefezza: MV 6.27 ± 1.04; FV 6.99 + 2.30\n", "Felipe Anderson: MV 6.11 ± 1.07; FV 6.72 + 2.18\n", "Koopmeiners: MV 6.14 ± 1.10; FV 6.76 + 2.31\n", "Calhanoglu: MV 6.14 ± 0.78; FV 6.35 + 1.10\n", "Frattesi: MV 6.25 ± 1.08; FV 6.88 + 2.21\n", "Diaz B.: MV 6.06 ± 1.14; FV 6.61 + 2.18\n", "Vlasic: MV 6.14 ± 1.04; FV 6.68 + 1.94\n", "Zambo Anguissa: MV 6.27 ± 0.98; FV 6.76 + 1.82\n", "Elmas: MV 6.28 ± 1.03; FV 6.94 + 2.14\n", "Miranchuk: MV 6.21 ± 1.07; FV 6.80 + 2.07\n", "Samardzic: MV 6.06 ± 1.05; FV 6.63 + 2.04\n", "Pereyra: MV 6.05 ± 1.17; FV 6.68 + 2.42\n", "Politano: MV 6.23 ± 0.81; FV 6.77 + 1.75\n", "Rabiot: MV 6.16 ± 1.15; FV 6.91 + 2.63\n", "Ciurria: MV 6.09 ± 1.11; FV 6.71 + 2.32\n", "Lazovic: MV 6.24 ± 1.12; FV 6.86 + 2.15\n", "Lobotka: MV 6.21 ± 0.78; FV 6.51 + 1.34\n", "Radonjic: MV 6.17 ± 1.00; FV 6.68 + 1.85\n", "Ferguson: MV 6.08 ± 0.82; FV 6.34 + 1.24\n", "Bonaventura: MV 6.21 ± 0.85; FV 6.74 + 1.72\n", "Pessina: MV 6.11 ± 0.94; FV 6.51 + 1.59\n", "Tonali: MV 6.03 ± 1.07; FV 6.33 + 1.68\n", "Kostic: MV 6.05 ± 0.96; FV 6.48 + 1.77\n", "Baldanzi: MV 6.14 ± 0.98; FV 6.66 + 1.93\n", "Lovric: MV 6.04 ± 0.85; FV 6.44 + 1.46\n", "Pellegrini Lo.: MV 6.06 ± 1.16; FV 6.59 + 2.24\n", "El Shaarawy: MV 6.17 ± 0.87; FV 6.66 + 1.69\n", "Orsolini: MV 6.14 ± 1.23; FV 6.82 + 2.59\n", "Ikone': MV 6.08 ± 0.96; FV 6.50 + 1.73\n", "Candreva: MV 5.85 ± 1.04; FV 5.96 + 1.46\n", "Bennacer: MV 6.08 ± 0.84; FV 6.31 + 1.18\n", "Pasalic: MV 5.96 ± 1.05; FV 6.42 + 1.96\n", "Mkhitaryan: MV 5.94 ± 0.83; FV 6.08 + 1.12\n", "Colpani: MV 6.04 ± 0.80; FV 6.41 + 1.46\n", "Pogba: MV 6.03 ± 0.83; FV 6.12 + 0.91\n", "Chiesa: MV 5.99 ± 0.87; FV 6.19 + 1.26\n", "Bandinelli: MV 5.94 ± 0.82; FV 6.08 + 1.20\n", "Matic: MV 6.11 ± 0.80; FV 6.35 + 1.16\n", "Fagioli: MV 6.00 ± 0.95; FV 6.28 + 1.52\n", "Messias: MV 5.93 ± 0.99; FV 6.30 + 1.71\n", "Arslan: MV 5.87 ± 0.67; FV 5.95 + 0.65\n", "Ricci S.: MV 6.09 ± 0.86; FV 6.30 + 1.21\n", "Ranocchia F.: MV 6.09 ± 0.79; FV 6.44 + 1.35\n", "Verdi: MV 6.21 ± 1.25; FV 7.05 + 2.94\n", "Sensi: MV 6.08 ± 1.02; FV 6.58 + 1.96\n", "Barak: MV 6.00 ± 0.84; FV 6.27 + 1.30\n", "Soriano: MV 6.02 ± 0.74; FV 6.14 + 0.95\n", "Dominguez: MV 6.12 ± 0.86; FV 6.37 + 1.30\n", "Vilhena: MV 5.77 ± 1.01; FV 6.03 + 1.51\n", "Brozovic: MV 6.02 ± 0.84; FV 6.17 + 1.08\n", "Cristante: MV 5.96 ± 0.83; FV 6.07 + 1.09\n", "Thorstvedt: MV 6.02 ± 0.84; FV 6.23 + 1.17\n", "De Ketelaere: MV 5.80 ± 0.71; FV 5.84 + 0.83\n", "Saponara: MV 6.18 ± 0.99; FV 6.73 + 1.93\n", "Vecino: MV 5.94 ± 0.90; FV 6.10 + 1.31\n", "Locatelli: MV 6.03 ± 0.84; FV 6.14 + 0.95\n", "Zaniolo: MV 5.88 ± 0.99; FV 6.10 + 1.56\n", "Duda: MV 5.91 ± 0.66; FV 5.93 + 0.65\n", "Maldini: MV 6.00 ± 0.84; FV 6.37 + 1.53\n", "Marin: MV 5.92 ± 0.95; FV 6.07 + 1.35\n", "Zalewski: MV 6.01 ± 0.77; FV 6.14 + 1.00\n", "Bajrami: MV 6.18 ± 1.05; FV 6.75 + 2.10\n", "Coulibaly L.: MV 5.78 ± 1.10; FV 5.91 + 1.52\n", "Gonzalez J.: MV 5.97 ± 0.82; FV 6.13 + 1.18\n", "De Roon: MV 6.01 ± 0.93; FV 6.23 + 1.30\n", "Mandragora: MV 6.11 ± 0.84; FV 6.46 + 1.39\n", "Wijnaldum: MV 6.12 ± 1.09; FV 6.71 + 2.19\n", "Bourabia: MV 5.92 ± 0.71; FV 5.93 + 0.72\n", "Sottil: MV 6.15 ± 0.95; FV 6.57 + 1.69\n", "Aebischer: MV 5.90 ± 0.73; FV 5.96 + 0.89\n", "Ederson D.s.: MV 5.87 ± 0.90; FV 5.95 + 1.14\n", "Miretti: MV 5.89 ± 0.74; FV 5.99 + 0.80\n", "Blin: MV 5.95 ± 0.75; FV 6.02 + 0.93\n", "Hjulmand: MV 5.95 ± 0.83; FV 5.97 + 0.88\n", "Cataldi: MV 5.96 ± 0.76; FV 6.00 + 0.84\n", "Djuricic: MV 5.78 ± 0.96; FV 5.98 + 1.40\n", "Linetty: MV 5.94 ± 0.85; FV 5.99 + 1.10\n", "Haas: MV 5.90 ± 0.78; FV 5.99 + 1.05\n", "Walace: MV 5.88 ± 0.75; FV 5.91 + 0.70\n", "Agudelo: MV 5.93 ± 0.69; FV 5.96 + 0.78\n", "Pobega: MV 5.97 ± 0.88; FV 6.19 + 1.33\n", "Camara Ma.: MV 6.06 ± 0.85; FV 6.16 + 0.99\n", "Paredes: MV 5.80 ± 0.67; FV 5.80 + 0.55\n", "Ndombele': MV 6.07 ± 0.73; FV 6.23 + 0.96\n", "Nicolussi Caviglia: MV 5.65 ± 1.08; FV 5.75 + 1.37\n", "Rovella: MV 6.04 ± 0.87; FV 6.21 + 1.10\n", "Amrabat: MV 6.03 ± 0.76; FV 6.07 + 0.79\n", "Tameze: MV 5.92 ± 0.72; FV 5.96 + 0.67\n", "Gyasi: MV 5.90 ± 0.89; FV 5.98 + 1.23\n", "Ilic: MV 6.04 ± 0.86; FV 6.20 + 1.19\n", "Matheus Henrique: MV 5.95 ± 0.88; FV 6.11 + 1.21\n", "Harroui: MV 6.07 ± 0.85; FV 6.40 + 1.40\n", "Volpato: MV 6.06 ± 1.17; FV 6.60 + 2.24\n", "Pickel: MV 5.83 ± 0.73; FV 5.79 + 0.76\n", "Moro N.: MV 6.05 ± 0.76; FV 6.17 + 0.96\n", "Duncan: MV 5.99 ± 0.71; FV 6.13 + 0.87\n", "Machin: MV 5.96 ± 0.83; FV 6.08 + 1.04\n", "Cuadrado: MV 5.89 ± 0.94; FV 5.97 + 1.13\n", "Ekdal: MV 5.88 ± 0.74; FV 5.86 + 0.76\n", "Meite': MV 5.89 ± 0.74; FV 5.89 + 0.72\n", "Schouten: MV 5.97 ± 0.75; FV 5.94 + 0.73\n", "Obiang: MV 5.97 ± 0.59; FV 5.93 + 0.47\n", "Kovalenko: MV 5.95 ± 0.74; FV 6.00 + 0.86\n", "Crnigoj: MV 5.82 ± 0.78; FV 5.91 + 0.97\n", "Basic: MV 5.92 ± 0.65; FV 5.98 + 0.71\n", "Asllani: MV 5.95 ± 0.61; FV 5.94 + 0.51\n", "Sabiri: MV 5.87 ± 0.91; FV 6.05 + 1.34\n", "Terracciano F.: MV 6.04 ± 0.64; FV 6.08 + 0.65\n", "Castagnetti: MV 5.94 ± 0.62; FV 5.94 + 0.51\n", "Oudin: MV 5.91 ± 0.62; FV 5.96 + 0.57\n", "Grassi: MV 5.88 ± 0.66; FV 5.86 + 0.55\n", "Krunic: MV 5.90 ± 0.72; FV 5.92 + 0.83\n", "Rincon: MV 5.79 ± 0.75; FV 5.77 + 0.87\n", "Miguel Veloso: MV 5.99 ± 0.67; FV 6.02 + 0.65\n", "Leris: MV 5.87 ± 0.88; FV 5.97 + 1.23\n", "Esposito Sa.: MV 5.79 ± 0.81; FV 5.70 + 0.78\n", "Henderson L.: MV 5.88 ± 0.76; FV 5.91 + 0.91\n", "Lopez M.: MV 5.98 ± 0.72; FV 5.97 + 0.67\n", "Cuisance: MV 5.81 ± 0.62; FV 5.76 + 0.63\n", "Saelemaekers: MV 5.84 ± 0.75; FV 5.97 + 1.06\n", "Maggiore: MV 5.83 ± 0.78; FV 5.87 + 0.92\n", "Akpa Akpro: MV 5.85 ± 0.92; FV 5.89 + 1.07\n", "Maleh: MV 5.91 ± 0.68; FV 5.98 + 0.84\n", "Romero L.: MV 5.95 ± 0.92; FV 6.42 + 1.75\n", "Ceide: MV 5.91 ± 0.65; FV 5.91 + 0.55\n", "D'alessandro: MV 6.09 ± 0.63; FV 6.22 + 0.84\n", "Benassi: MV 5.89 ± 0.68; FV 5.93 + 0.66\n", "Gagliardini: MV 5.78 ± 0.56; FV 5.77 + 0.44\n", "Vieira: MV 5.86 ± 0.68; FV 5.82 + 0.79\n", "Bianco: MV 6.11 ± 0.66; FV 6.17 + 0.80\n", "Vranckx: MV 5.82 ± 0.66; FV 5.77 + 0.70\n", "Galdames: MV 5.98 ± 0.79; FV 6.07 + 0.91\n", "Marcos Antonio: MV 5.93 ± 0.81; FV 6.22 + 1.33\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fazzini: MV 5.81 ± 0.63; FV 5.76 + 0.56\n", "Sulemana I.: MV 5.94 ± 0.61; FV 5.94 + 0.52\n", "Tahirovic: MV 6.02 ± 0.64; FV 6.03 + 0.64\n", "Abildgaard: MV 5.97 ± 0.58; FV 5.96 + 0.47\n", "Barberis: MV 5.81 ± 0.75; FV 5.78 + 0.76\n", "Kastanos: MV 5.84 ± 0.84; FV 5.89 + 1.00\n", "Vignato: MV 5.97 ± 0.75; FV 6.06 + 0.90\n", "Valoti: MV 5.80 ± 0.69; FV 5.81 + 0.67\n", "Winks: MV 5.85 ± 0.83; FV 5.85 + 0.86\n", "Askildsen: MV 5.79 ± 0.62; FV 5.74 + 0.56\n", "Bove: MV 5.91 ± 0.88; FV 6.04 + 1.26\n", "Bohinen: MV 5.74 ± 0.62; FV 5.70 + 0.52\n", "D'andrea: MV 6.05 ± 0.66; FV 6.09 + 0.69\n", "Iling-Junior: MV 5.91 ± 0.66; FV 5.93 + 0.62\n", "Cipot: MV 6.00 ± 0.70; FV 6.06 + 0.76\n", "Bakayoko: MV 5.73 ± 0.77; FV 5.70 + 0.74\n", "Gaetano: MV 6.15 ± 0.66; FV 6.27 + 0.95\n", "Zurkowski: MV 6.06 ± 0.92; FV 6.47 + 1.72\n", "Castrovilli: MV 6.06 ± 0.69; FV 6.27 + 1.00\n", "Demme: MV 6.01 ± 0.77; FV 6.18 + 1.05\n", "Darboe: MV 5.90 ± 0.93; FV 5.97 + 1.03\n", "Urbanski: MV 5.98 ± 0.79; FV 6.00 + 0.85\n", "Bertini: MV 5.92 ± 0.93; FV 6.04 + 1.29\n", "Yepes: MV 5.75 ± 0.90; FV 5.72 + 1.03\n", "Pyyhtia: MV 5.84 ± 0.78; FV 5.81 + 0.77\n", "Trimboli: MV 5.88 ± 0.94; FV 5.96 + 1.29\n", "Pafundi: MV 6.03 ± 0.72; FV 6.05 + 0.69\n", "Helgason: MV 5.88 ± 0.61; FV 5.88 + 0.51\n", "Adli: MV 5.85 ± 0.70; FV 5.87 + 0.84\n", "Vignato S.: MV 5.99 ± 0.80; FV 6.08 + 0.89\n", "Hrustic: MV 5.80 ± 0.62; FV 5.82 + 0.52\n", "Samek: MV 5.98 ± 0.86; FV 6.09 + 1.11\n", "Zerbin: MV 5.94 ± 0.67; FV 5.99 + 0.74\n", "Ilkhan: MV 5.87 ± 0.80; FV 5.89 + 0.93\n", "Degli Innocenti: MV 5.85 ± 0.92; FV 5.89 + 1.07\n", "Acella: MV 6.02 ± 0.77; FV 6.13 + 0.90\n", "Carboni V.: MV 5.97 ± 0.72; FV 5.96 + 0.68\n", "Paoletti: MV 5.87 ± 0.58; FV 5.86 + 0.44\n", "Malagrida: MV 5.91 ± 1.02; FV 6.09 + 1.47\n", "Faticanti: MV 5.91 ± 0.91; FV 6.03 + 1.20\n", "Osimhen: MV 6.54 ± 1.47; FV 7.84 + 4.27\n", "Martinez L.: MV 6.12 ± 1.32; FV 7.31 + 3.56\n", "Dybala: MV 6.42 ± 1.33; FV 7.47 + 3.45\n", "Rafael Leao: MV 6.20 ± 1.34; FV 7.20 + 3.31\n", "Lookman: MV 6.22 ± 1.33; FV 7.38 + 3.64\n", "Immobile: MV 6.08 ± 1.33; FV 7.26 + 3.52\n", "Vlahovic: MV 6.03 ± 1.26; FV 7.01 + 3.09\n", "Arnautovic: MV 6.15 ± 1.22; FV 7.02 + 2.88\n", "Dia: MV 5.86 ± 1.27; FV 6.61 + 2.56\n", "Dzeko: MV 6.01 ± 1.12; FV 6.69 + 2.36\n", "Milik: MV 6.04 ± 1.10; FV 6.69 + 2.35\n", "Nzola: MV 6.20 ± 1.34; FV 7.35 + 3.62\n", "Beto: MV 5.99 ± 1.16; FV 6.83 + 2.73\n", "Giroud: MV 6.03 ± 1.16; FV 6.68 + 2.38\n", "Abraham: MV 6.08 ± 1.17; FV 6.83 + 2.60\n", "Deulofeu: MV 6.22 ± 1.23; FV 7.16 + 3.06\n", "Lauriente': MV 6.38 ± 1.32; FV 7.30 + 3.20\n", "Simeone: MV 6.25 ± 1.31; FV 7.25 + 3.24\n", "Lozano: MV 6.18 ± 1.08; FV 6.77 + 2.12\n", "Correa: MV 5.91 ± 0.87; FV 6.25 + 1.48\n", "Berardi: MV 6.33 ± 1.37; FV 7.58 + 3.96\n", "Pedro: MV 6.05 ± 0.96; FV 6.41 + 1.63\n", "Lukaku: MV 5.93 ± 1.13; FV 6.52 + 2.22\n", "Sanabria: MV 6.08 ± 1.23; FV 6.87 + 2.69\n", "Thauvin: MV 6.12 ± 1.13; FV 6.95 + 2.73\n", "Cabral: MV 6.26 ± 1.19; FV 7.13 + 2.85\n", "Hojlund: MV 6.00 ± 1.18; FV 6.74 + 2.58\n", "Caprari: MV 6.00 ± 0.98; FV 6.46 + 1.88\n", "Di Maria: MV 6.12 ± 1.20; FV 6.86 + 2.71\n", "Piatek: MV 5.70 ± 0.96; FV 6.13 + 1.63\n", "Rebic: MV 5.91 ± 1.07; FV 6.36 + 1.91\n", "Bonazzoli: MV 5.83 ± 0.99; FV 6.15 + 1.55\n", "Zapata D.: MV 5.85 ± 0.93; FV 6.07 + 1.38\n", "Kouame': MV 6.20 ± 1.18; FV 6.96 + 2.65\n", "Gonzalez N.: MV 6.30 ± 1.18; FV 7.10 + 2.71\n", "Brekalo: MV 6.24 ± 1.10; FV 6.93 + 2.32\n", "Mota: MV 6.02 ± 1.18; FV 6.79 + 2.64\n", "Kean: MV 5.97 ± 1.22; FV 6.66 + 2.51\n", "Okereke: MV 5.97 ± 1.06; FV 6.41 + 1.91\n", "Ceesay: MV 5.97 ± 1.00; FV 6.46 + 1.88\n", "Colombo: MV 5.97 ± 1.09; FV 6.48 + 2.05\n", "Dessers: MV 6.08 ± 1.20; FV 6.94 + 2.85\n", "Muriel: MV 5.83 ± 0.94; FV 5.84 + 1.11\n", "Pinamonti: MV 5.88 ± 0.98; FV 6.18 + 1.56\n", "Di Francesco F.: MV 6.01 ± 0.99; FV 6.39 + 1.72\n", "Jovic: MV 6.03 ± 1.09; FV 6.57 + 2.10\n", "Origi: MV 5.82 ± 0.93; FV 6.12 + 1.49\n", "Caputo: MV 5.98 ± 1.12; FV 6.56 + 2.23\n", "Boga: MV 6.16 ± 1.12; FV 6.83 + 2.39\n", "Cambiaghi: MV 6.11 ± 1.01; FV 6.68 + 2.09\n", "Alvarez A.: MV 6.07 ± 1.09; FV 6.57 + 2.11\n", "Banda: MV 5.92 ± 0.77; FV 6.06 + 0.98\n", "Ciofani D.: MV 6.08 ± 1.17; FV 6.87 + 2.68\n", "Petagna: MV 5.97 ± 1.09; FV 6.52 + 2.13\n", "Barrow: MV 5.98 ± 1.08; FV 6.34 + 1.84\n", "Djuric: MV 6.01 ± 0.73; FV 6.22 + 0.95\n", "Henry: MV 6.03 ± 1.19; FV 6.74 + 2.56\n", "Success: MV 5.89 ± 0.93; FV 6.23 + 1.58\n", "Gabbiadini: MV 5.89 ± 1.12; FV 6.35 + 1.98\n", "Zirkzee: MV 5.95 ± 0.92; FV 6.28 + 1.50\n", "Lammers: MV 5.81 ± 0.87; FV 6.01 + 1.28\n", "Satriano: MV 5.89 ± 0.93; FV 6.08 + 1.36\n", "Kallon: MV 5.88 ± 0.84; FV 6.11 + 1.27\n", "Nestorovski: MV 6.08 ± 0.80; FV 6.67 + 1.84\n", "Raspadori: MV 6.13 ± 1.09; FV 6.73 + 2.20\n", "Botheim: MV 5.83 ± 0.97; FV 6.20 + 1.61\n", "Gytkjaer: MV 5.82 ± 0.83; FV 5.98 + 1.19\n", "Solbakken: MV 5.90 ± 0.97; FV 6.20 + 1.55\n", "Lasagna: MV 5.78 ± 0.79; FV 5.85 + 0.99\n", "Belotti: MV 5.84 ± 0.84; FV 6.00 + 1.19\n", "Pellegri: MV 5.92 ± 0.90; FV 6.17 + 1.42\n", "Buonaiuto: MV 5.97 ± 0.69; FV 6.07 + 0.76\n", "Verde: MV 6.06 ± 1.11; FV 6.75 + 2.46\n", "Destro: MV 5.98 ± 1.20; FV 6.52 + 2.27\n", "Seck: MV 6.07 ± 0.69; FV 6.25 + 0.95\n", "Sansone: MV 6.04 ± 0.98; FV 6.41 + 1.68\n", "Quagliarella: MV 5.84 ± 0.78; FV 5.96 + 1.06\n", "Defrel: MV 5.85 ± 0.87; FV 5.99 + 1.19\n", "Pjaca: MV 5.85 ± 0.78; FV 5.92 + 0.88\n", "Gaich: MV 5.91 ± 0.95; FV 6.19 + 1.43\n", "Soule': MV 6.08 ± 0.76; FV 6.42 + 1.25\n", "Tsadjout: MV 5.90 ± 0.92; FV 6.17 + 1.42\n", "Piccoli: MV 5.79 ± 0.70; FV 5.82 + 0.69\n", "Shomurodov: MV 5.98 ± 1.01; FV 6.48 + 1.93\n", "Afena-Gyan: MV 5.76 ± 0.67; FV 5.71 + 0.62\n", "Ngonge: MV 6.14 ± 1.29; FV 7.02 + 3.01\n", "Karamoh: MV 6.03 ± 1.01; FV 6.53 + 1.91\n", "Ibrahimovic: MV 6.09 ± 1.13; FV 6.84 + 2.54\n", "Pussetto: MV 5.90 ± 1.01; FV 6.30 + 1.76\n", "Cancellieri: MV 5.78 ± 0.64; FV 5.78 + 0.67\n", "Valencia D.: MV 5.72 ± 0.59; FV 5.67 + 0.65\n", "Oddei: MV 6.10 ± 0.75; FV 6.19 + 0.88\n", "Braaf: MV 5.89 ± 0.78; FV 5.94 + 0.90\n", "Raimondo: MV 5.99 ± 0.82; FV 6.05 + 0.90\n", "Kaio Jorge: MV 5.82 ± 0.59; FV 5.87 + 0.49\n", "De Luca: MV 5.89 ± 0.86; FV 5.99 + 1.15\n", "Voelkerling Persson: MV 5.91 ± 0.63; FV 5.99 + 0.64\n", "Montevago: MV 5.72 ± 0.64; FV 5.69 + 0.70\n", "Krollis: MV 5.99 ± 0.88; FV 6.16 + 1.23\n", "Vivaldo: MV 5.90 ± 0.84; FV 6.00 + 0.95\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
MussoPAtalantaTorino00.0056.2583190.4402285.1072130.3870965.9844610.1739020.8498411.6992025.1973730.573992-0.1153770.8963856.705408
SportielloPAtalantaTorino01.00756.2639430.4454475.0361920.3238435.9849980.1684020.8765801.6992095.0820210.486595-0.0692780.90569312.926556
Rossi F.PAtalantaTorino00.0016.1159400.3861454.5055350.5108535.9219840.2781130.4699451.6990084.6213540.759368-0.1120680.9047051.720399
ZappacostaDAtalantaTorino01.00906.0043140.4397416.2255550.6538445.9521940.5079220.0758951.0991355.7503520.9035630.3686581.6999100.000000
DemiralDAtalantaTorino00.00355.9910590.4544796.2059470.6343705.9550220.5307630.0502221.0793875.7828250.9234670.3257191.6999140.000000
............................................................
DjuricAVeronaCremonese00.45606.0052100.3674036.2163720.4750225.9448700.4190860.1066101.1964805.9051150.6979840.3177761.6999330.000000
GaichAVeronaCremonese00.55555.9095270.4754706.1916960.7172665.8027480.5281310.1489881.0818665.5939960.8815330.4589951.6998930.000000
KallonAVeronaCremonese00.00405.8845970.4178376.1069650.6353585.8053580.4709290.1243381.1466355.5888470.7985430.4423061.6999050.000000
BraafAVeronaCremonese00.00355.8919280.3875555.9424290.4509165.8713070.4597070.0332681.1649315.7343910.7489570.2036171.6999380.000000
LasagnaAVeronaCremonese01.00805.7823440.3961765.8541430.4965085.7223910.4539680.0977861.1771115.5040450.6998530.3525761.6999220.000000
\n", "

525 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Musso P Atalanta Torino 0 0.00 5 6.258319 0.440228 \n", "Sportiello P Atalanta Torino 0 1.00 75 6.263943 0.445447 \n", "Rossi F. P Atalanta Torino 0 0.00 1 6.115940 0.386145 \n", "Zappacosta D Atalanta Torino 0 1.00 90 6.004314 0.439741 \n", "Demiral D Atalanta Torino 0 0.00 35 5.991059 0.454479 \n", "... ... ... ... ... ... ... ... ... \n", "Djuric A Verona Cremonese 0 0.45 60 6.005210 0.367403 \n", "Gaich A Verona Cremonese 0 0.55 55 5.909527 0.475470 \n", "Kallon A Verona Cremonese 0 0.00 40 5.884597 0.417837 \n", "Braaf A Verona Cremonese 0 0.00 35 5.891928 0.387555 \n", "Lasagna A Verona Cremonese 0 1.00 80 5.782344 0.396176 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Musso 5.107213 0.387096 5.984461 0.173902 0.849841 \n", "Sportiello 5.036192 0.323843 5.984998 0.168402 0.876580 \n", "Rossi F. 4.505535 0.510853 5.921984 0.278113 0.469945 \n", "Zappacosta 6.225555 0.653844 5.952194 0.507922 0.075895 \n", "Demiral 6.205947 0.634370 5.955022 0.530763 0.050222 \n", "... ... ... ... ... ... \n", "Djuric 6.216372 0.475022 5.944870 0.419086 0.106610 \n", "Gaich 6.191696 0.717266 5.802748 0.528131 0.148988 \n", "Kallon 6.106965 0.635358 5.805358 0.470929 0.124338 \n", "Braaf 5.942429 0.450916 5.871307 0.459707 0.033268 \n", "Lasagna 5.854143 0.496508 5.722391 0.453968 0.097786 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Musso 1.699202 5.197373 0.573992 -0.115377 0.896385 \n", "Sportiello 1.699209 5.082021 0.486595 -0.069278 0.905693 \n", "Rossi F. 1.699008 4.621354 0.759368 -0.112068 0.904705 \n", "Zappacosta 1.099135 5.750352 0.903563 0.368658 1.699910 \n", "Demiral 1.079387 5.782825 0.923467 0.325719 1.699914 \n", "... ... ... ... ... ... \n", "Djuric 1.196480 5.905115 0.697984 0.317776 1.699933 \n", "Gaich 1.081866 5.593996 0.881533 0.458995 1.699893 \n", "Kallon 1.146635 5.588847 0.798543 0.442306 1.699905 \n", "Braaf 1.164931 5.734391 0.748957 0.203617 1.699938 \n", "Lasagna 1.177111 5.504045 0.699853 0.352576 1.699922 \n", "\n", " Clean Sheet % \n", "player \n", "Musso 6.705408 \n", "Sportiello 12.926556 \n", "Rossi F. 1.720399 \n", "Zappacosta 0.000000 \n", "Demiral 0.000000 \n", "... ... \n", "Djuric 0.000000 \n", "Gaich 0.000000 \n", "Kallon 0.000000 \n", "Braaf 0.000000 \n", "Lasagna 0.000000 \n", "\n", "[525 rows x 19 columns]" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matchday_out = 33\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": 46, "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": 42, "id": "2b637a15", "metadata": {}, "outputs": [], "source": [ "gk_starters = ['Maignan', 'Ochoa', 'Silvestri', 'Consigli', 'Provedel', 'Di Gregorio', 'Meret', 'Milinkovic-Savic V.',\n", " 'Terracciano', 'Onana', 'Szczesny', 'Skorupski', 'Vicario', 'Musso', 'Carnesecchi', 'Rui Patricio',\n", " 'Montipo\\'', 'Falcone', 'Dragowski', 'Audero']" ] }, { "cell_type": "code", "execution_count": 43, "id": "60d73507", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret (6.26, 0.45); (5.81, 0.51)\n", "Provedel (6.26, 0.44); (5.84, 0.48)\n", "Vicario (6.26, 0.45); (5.20, 0.58)\n", "Szczesny (6.26, 0.45); (5.99, 0.47)\n", "Falcone (6.19, 0.40); (4.59, 0.47)\n", "Silvestri (6.26, 0.45); (5.53, 0.59)\n", "Rui Patricio (6.20, 0.43); (5.48, 0.61)\n", "Onana (6.15, 0.40); (5.14, 0.58)\n", "Sepe (6.22, 0.42); (4.99, 0.54)\n", "Milinkovic-Savic V. (6.09, 0.36); (5.02, 0.71)\n", "Musso (6.26, 0.44); (5.58, 0.50)\n", "Maignan (6.26, 0.44); (5.02, 0.47)\n", "Carnesecchi (6.26, 0.44); (4.84, 0.58)\n", "Di Gregorio (6.26, 0.45); (5.26, 0.64)\n", "Audero (6.26, 0.45); (4.96, 0.53)\n", "Montipo' (6.25, 0.43); (4.78, 0.40)\n", "Skorupski (6.25, 0.43); (5.51, 0.58)\n", "Consigli (6.26, 0.44); (5.48, 0.62)\n", "Dragowski (6.26, 0.45); (5.46, 0.62)\n", "Terracciano (6.13, 0.40); (4.75, 0.68)\n", "Tatarusanu (6.26, 0.45); (4.93, 0.80)\n", "Handanovic (6.26, 0.45); (5.96, 0.53)\n", "Sportiello (6.23, 0.42); (4.51, 0.40)\n", "Perin (6.26, 0.45); (5.97, 0.45)\n", "Zoet (6.26, 0.45); (6.07, 0.50)\n", "Ochoa (6.26, 0.45); (5.96, 0.52)\n", "Pegolo (6.26, 0.45); (4.87, 0.56)\n", "Gollini (6.26, 0.45); (5.91, 0.46)\n", "Mirante no data\n", "Sarr M. no data\n", "Lamanna no data\n", "Ujkani no data\n", "Berisha (6.26, 0.45); (5.85, 0.50)\n", "Marchetti (6.08, 0.47); (3.75, 0.71)\n", "Perilli (6.26, 0.45); (5.78, 0.52)\n", "Padelli (6.15, 0.41); (4.19, 0.63)\n", "Perisan (6.26, 0.45); (5.26, 0.64)\n", "Bardi (6.26, 0.45); (5.92, 0.46)\n", "Cordaz no data\n", "Pinsoglio (6.10, 0.43); (4.30, 0.68)\n", "Fiorillo (6.23, 0.42); (3.50, 0.56)\n", "Cragno (6.26, 0.45); (5.36, 0.81)\n", "Sirigu (6.26, 0.45); (5.69, 0.59)\n", "Cerofolini no data\n", "Rossi F. (5.91, 0.39); (4.05, 0.56)\n", "Ravaglia F. (6.26, 0.45); (4.86, 0.60)\n", "Brancolini no data\n", "Bleve no data\n", "Berardi A. (6.26, 0.45); (4.88, 0.53)\n", "Russo A. no data\n", "Gemello (6.26, 0.45); (5.95, 0.45)\n", "Ravaglia (6.26, 0.45); (4.59, 0.59)\n", "Boer no data\n", "Adamonis no data\n", "Marfella (6.26, 0.45); (5.79, 0.47)\n", "Zovko (6.13, 0.46); (3.89, 0.67)\n", "Piana no data\n", "Bagnolini no data\n", "Luis Maximiano (5.81, 0.46); (5.58, 0.55)\n", "Svilar no data\n", "Sorrentino A. no data\n", "Ciezkowski no data\n", "Saro no data\n", "Vasquez D. no data\n", "Turk (6.26, 0.45); (4.65, 0.59)\n", "Dimarco (6.14, 0.45); (6.55, 0.78)\n", "Smalling (6.21, 0.47); (6.57, 0.77)\n", "Doig (6.05, 0.52); (6.42, 0.89)\n", "Carlos Augusto (6.06, 0.52); (6.48, 0.93)\n", "Kim (6.26, 0.49); (6.59, 0.79)\n", "Posch (6.14, 0.55); (6.68, 1.07)\n", "Di Lorenzo (6.21, 0.47); (6.50, 0.72)\n", "Danilo (6.24, 0.47); (6.64, 0.81)\n", "Hernandez T. (6.12, 0.55); (6.54, 0.96)\n", "Udogie (6.06, 0.53); (6.45, 0.92)\n", "Parisi (6.12, 0.48); (6.47, 0.78)\n", "Mario Rui (6.13, 0.48); (6.23, 0.57)\n", "Romagnoli (6.19, 0.45); (6.46, 0.68)\n", "Bastoni S. (6.07, 0.46); (6.41, 0.77)\n", "Mazzocchi (6.13, 0.45); (6.51, 0.75)\n", "Valeri (6.08, 0.37); (6.34, 0.57)\n", "Tomori (6.10, 0.44); (6.27, 0.57)\n", "Scalvini (6.03, 0.51); (6.27, 0.73)\n", "Toloi (6.03, 0.49); (6.23, 0.66)\n", "Demiral (6.02, 0.44); (6.21, 0.59)\n", "Maehle (5.93, 0.50); (6.12, 0.73)\n", "Dumfries (5.92, 0.46); (6.08, 0.66)\n", "Baschirotto (6.15, 0.50); (6.50, 0.80)\n", "Bijol (5.93, 0.53); (6.14, 0.78)\n", "Schuurs (6.11, 0.40); (6.17, 0.45)\n", "Juan Jesus (6.16, 0.36); (6.40, 0.57)\n", "Depaoli (5.98, 0.44); (6.18, 0.64)\n", "Mancini (6.11, 0.41); (6.31, 0.55)\n", "Ibanez (5.84, 0.54); (5.97, 0.71)\n", "Rodrigo Becao (6.06, 0.49); (6.34, 0.74)\n", "Ebuehi (6.05, 0.41); (6.33, 0.62)\n", "Gosens (5.96, 0.36); (6.14, 0.49)\n", "Darmian (6.05, 0.38); (6.24, 0.53)\n", "Reca (5.95, 0.48); (6.09, 0.65)\n", "Bremer (6.07, 0.51); (6.39, 0.80)\n", "Sernicola (5.93, 0.49); (6.13, 0.75)\n", "Rrahmani (6.24, 0.50); (6.58, 0.80)\n", "Vojvoda (5.89, 0.41); (5.93, 0.47)\n", "Holm (5.98, 0.43); (6.14, 0.59)\n", "Bastoni (6.07, 0.41); (6.15, 0.46)\n", "Milenkovic (5.97, 0.46); (6.13, 0.64)\n", "Kalulu (5.83, 0.51); (5.87, 0.59)\n", "Martinez Quarta (5.99, 0.45); (6.09, 0.53)\n", "Casale (6.05, 0.41); (6.19, 0.51)\n", "Perez N. (6.06, 0.48); (6.30, 0.69)\n", "Olivera (6.12, 0.35); (6.39, 0.56)\n", "Izzo (6.04, 0.44); (6.21, 0.57)\n", "Luperto (5.86, 0.48); (5.87, 0.47)\n", "Skriniar (5.91, 0.40); (5.92, 0.39)\n", "Rodriguez R. (6.02, 0.35); (5.99, 0.33)\n", "Marusic (6.05, 0.38); (6.06, 0.38)\n", "Lazzari (6.05, 0.38); (6.11, 0.42)\n", "Kyriakopoulos (5.98, 0.43); (6.06, 0.49)\n", "Ampadu (5.85, 0.45); (5.83, 0.47)\n", "Ismajli (5.92, 0.41); (5.89, 0.38)\n", "Llorente D. (5.95, 0.48); (6.10, 0.64)\n", "Cambiaso (5.99, 0.37); (6.01, 0.37)\n", "Hysaj (6.00, 0.31); (5.98, 0.26)\n", "Biraghi (6.07, 0.40); (6.22, 0.49)\n", "Medel (6.01, 0.34); (5.96, 0.30)\n", "Bonucci (6.12, 0.47); (6.45, 0.76)\n", "Calabria (5.95, 0.51); (6.16, 0.76)\n", "Acerbi (6.02, 0.35); (6.01, 0.32)\n", "Spinazzola (6.13, 0.42); (6.46, 0.68)\n", "Lykogiannis (6.00, 0.37); (6.12, 0.45)\n", "Pellegrini Lu. (6.02, 0.36); (6.07, 0.38)\n", "Djidji (5.89, 0.40); (5.94, 0.47)\n", "Lazaro (6.01, 0.44); (6.13, 0.53)\n", "Augello (5.94, 0.44); (6.14, 0.67)\n", "Gallo (5.85, 0.39); (5.83, 0.38)\n", "Singo (5.94, 0.44); (6.09, 0.62)\n", "Mari' (5.86, 0.50); (5.94, 0.58)\n", "Caldirola (5.90, 0.48); (6.00, 0.61)\n", "Dodo' (5.86, 0.46); (5.88, 0.51)\n", "De Vrij (5.96, 0.40); (6.00, 0.41)\n", "Patric (6.07, 0.39); (6.06, 0.39)\n", "Faraoni (6.00, 0.44); (6.20, 0.65)\n", "Ceccherini (5.89, 0.51); (6.03, 0.71)\n", "Hateboer (5.88, 0.47); (5.98, 0.66)\n", "Rogerio (5.82, 0.40); (5.79, 0.40)\n", "Umtiti (5.87, 0.46); (5.87, 0.47)\n", "Aina (6.00, 0.47); (6.20, 0.69)\n", "Birindelli (5.84, 0.35); (5.82, 0.36)\n", "Lucumi' (5.98, 0.39); (5.97, 0.38)\n", "Ehizibue (5.88, 0.46); (5.99, 0.66)\n", "Bianchetti (5.76, 0.47); (5.75, 0.56)\n", "Ferrari G. (5.84, 0.53); (5.92, 0.65)\n", "Fazio (5.66, 0.60); (5.71, 0.66)\n", "Gravillon (5.98, 0.40); (5.95, 0.38)\n", "Buongiorno (6.01, 0.39); (6.00, 0.38)\n", "Gunter (5.79, 0.49); (5.74, 0.48)\n", "Troost-Ekong (5.83, 0.44); (5.82, 0.43)\n", "Soumaoro (5.93, 0.45); (5.93, 0.44)\n", "Ceccaroni (5.86, 0.52); (5.95, 0.61)\n", "Pongracic (5.94, 0.38); (5.91, 0.35)\n", "Soppy (5.86, 0.37); (5.88, 0.38)\n", "Gendrey (5.88, 0.33); (5.87, 0.28)\n", "Hien (5.87, 0.41); (5.83, 0.40)\n", "Ferrari A. (5.76, 0.49); (5.73, 0.54)\n", "Masina (5.99, 0.38); (6.37, 0.71)\n", "Zappacosta (6.04, 0.43); (6.28, 0.66)\n", "Gyomber (5.91, 0.40); (5.88, 0.37)\n", "Alex Sandro (5.84, 0.47); (5.78, 0.44)\n", "Pezzella Giu. (5.89, 0.34); (5.89, 0.29)\n", "Bereszynski (5.87, 0.34); (5.85, 0.31)\n", "Venuti (5.82, 0.36); (5.82, 0.35)\n", "Palomino (6.02, 0.45); (6.14, 0.52)\n", "Nuytinck (5.84, 0.46); (5.84, 0.47)\n", "Marlon (5.80, 0.36); (5.77, 0.33)\n", "Magnani (5.85, 0.42); (5.82, 0.40)\n", "Colley (5.79, 0.52); (5.81, 0.57)\n", "Nikolaou (5.74, 0.38); (5.66, 0.36)\n", "Terzic (5.99, 0.28); (5.94, 0.21)\n", "Igor (5.84, 0.45); (5.79, 0.45)\n", "Toljan (5.75, 0.41); (5.70, 0.40)\n", "Zortea (5.86, 0.41); (5.91, 0.51)\n", "Dawidowicz (5.84, 0.46); (5.87, 0.57)\n", "Celik (5.84, 0.36); (5.82, 0.34)\n", "Bellanova (5.93, 0.42); (6.01, 0.51)\n", "Erlic (5.83, 0.46); (5.79, 0.43)\n", "Ballo-Toure' (6.09, 0.38); (6.37, 0.57)\n", "Dest (5.77, 0.41); (5.77, 0.41)\n", "Stojanovic (5.78, 0.39); (5.74, 0.40)\n", "Amian (5.81, 0.38); (5.76, 0.38)\n", "Bradaric (5.82, 0.43); (5.79, 0.46)\n", "Daniliuc (5.80, 0.49); (5.79, 0.53)\n", "Zima (5.92, 0.38); (5.93, 0.36)\n", "De Winter (5.79, 0.42); (5.73, 0.38)\n", "Quagliata (5.95, 0.30); (5.96, 0.25)\n", "Ebosse (5.79, 0.33); (5.74, 0.29)\n", "Aiwu (5.91, 0.45); (5.96, 0.54)\n", "Lochoshvili (5.87, 0.45); (5.91, 0.59)\n", "Bronn (5.76, 0.38); (5.72, 0.34)\n", "Thiaw (5.88, 0.48); (5.91, 0.49)\n", "Zeefuik (5.94, 0.41); (5.98, 0.44)\n", "Romagnoli S. (5.93, 0.56); (6.21, 0.85)\n", "Ghiglione (5.91, 0.43); (6.08, 0.65)\n", "Rugani (6.04, 0.28); (5.96, 0.22)\n", "De Sciglio (5.88, 0.31); (5.88, 0.24)\n", "Djimsiti (5.94, 0.37); (5.94, 0.33)\n", "Caldara (5.73, 0.48); (5.67, 0.49)\n", "Karsdorp (5.92, 0.37); (5.93, 0.35)\n", "Marchizza (5.93, 0.34); (5.92, 0.30)\n", "Kjaer (5.96, 0.36); (5.92, 0.31)\n", "Okoli (5.77, 0.44); (5.75, 0.41)\n", "Amione (5.81, 0.46); (5.82, 0.56)\n", "Ruggeri (5.91, 0.34); (5.91, 0.30)\n", "Zanoli (6.04, 0.43); (6.29, 0.65)\n", "Wisniewski (5.82, 0.34); (5.77, 0.30)\n", "Radovanovic (5.69, 0.37); (5.64, 0.35)\n", "Dermaku (6.01, 0.43); (6.12, 0.51)\n", "D'ambrosio (6.03, 0.37); (6.04, 0.37)\n", "De Silvestri (5.93, 0.47); (6.08, 0.67)\n", "Chiriches (5.77, 0.47); (5.73, 0.45)\n", "Murru (5.72, 0.37); (5.65, 0.36)\n", "Bonifazi (5.84, 0.39); (5.78, 0.37)\n", "Donati (5.76, 0.59); (5.93, 0.83)\n", "Walukiewicz (6.09, 0.35); (6.07, 0.34)\n", "Ranieri L. (5.88, 0.38); (5.90, 0.46)\n", "Gabbia (5.72, 0.44); (5.65, 0.42)\n", "Kumbulla (5.81, 0.48); (5.78, 0.49)\n", "Adopo (6.01, 0.33); (5.99, 0.30)\n", "Pirola (5.81, 0.56); (5.93, 0.74)\n", "Lovato (5.72, 0.49); (5.67, 0.44)\n", "Tuia (6.03, 0.29); (5.97, 0.24)\n", "Ferrer (5.88, 0.44); (5.88, 0.46)\n", "Antov (5.66, 0.52); (5.58, 0.49)\n", "Vasquez (5.82, 0.39); (5.76, 0.36)\n", "Ruan (5.83, 0.47); (5.76, 0.44)\n", "Ostigard (6.08, 0.34); (6.04, 0.33)\n", "Coppola D. (5.86, 0.35); (5.81, 0.31)\n", "Cacace (5.84, 0.31); (5.81, 0.25)\n", "Gatti (6.06, 0.39); (6.05, 0.39)\n", "Gila (6.01, 0.44); (6.05, 0.47)\n", "Bayeye (5.96, 0.43); (6.04, 0.51)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Sambia (5.86, 0.39); (5.87, 0.36)\n", "Moutinho J. (5.87, 0.37); (5.85, 0.36)\n", "Conti (5.87, 0.41); (5.95, 0.54)\n", "Marrone (5.63, 0.43); (5.56, 0.43)\n", "Tonelli (5.79, 0.42); (5.73, 0.39)\n", "Murillo (5.71, 0.38); (5.62, 0.36)\n", "Radu (6.06, 0.38); (5.93, 0.34)\n", "Paletta (5.92, 0.44); (6.00, 0.54)\n", "Florenzi (6.09, 0.38); (6.25, 0.49)\n", "Sala (5.95, 0.39); (6.03, 0.44)\n", "Fares (5.84, 0.37); (5.84, 0.39)\n", "Romagna (5.91, 0.44); (5.94, 0.50)\n", "Cassandro (6.00, 0.42); (6.07, 0.46)\n", "Muldur (5.77, 0.40); (5.71, 0.40)\n", "Amey (6.05, 0.42); (6.16, 0.50)\n", "Zanotti (5.94, 0.42); (6.01, 0.48)\n", "Ebosele (5.92, 0.32); (5.92, 0.29)\n", "Buta (5.94, 0.43); (6.01, 0.50)\n", "Abankwah (5.90, 0.41); (5.93, 0.44)\n", "Guessand A. (5.94, 0.43); (6.01, 0.50)\n", "Cabal (5.94, 0.31); (5.90, 0.24)\n", "Sosa (5.61, 0.44); (5.54, 0.44)\n", "Guarino (5.92, 0.44); (5.97, 0.50)\n", "Carboni F. (5.92, 0.42); (5.97, 0.46)\n", "Zaccagni (6.39, 0.59); (7.26, 1.40)\n", "Kvaratskhelia (6.51, 0.68); (7.46, 1.60)\n", "Milinkovic-Savic (6.18, 0.58); (6.92, 1.31)\n", "Barella (6.19, 0.52); (6.78, 1.06)\n", "Zielinski (6.25, 0.49); (6.77, 0.92)\n", "Luis Alberto (6.28, 0.51); (6.93, 1.06)\n", "Strefezza (6.25, 0.51); (6.94, 1.12)\n", "Felipe Anderson (6.20, 0.55); (6.92, 1.23)\n", "Koopmeiners (6.20, 0.57); (6.88, 1.21)\n", "Calhanoglu (6.20, 0.43); (6.61, 0.76)\n", "Frattesi (6.18, 0.55); (6.78, 1.11)\n", "Diaz B. (6.15, 0.61); (6.82, 1.24)\n", "Vlasic (6.13, 0.53); (6.67, 1.00)\n", "Zambo Anguissa (6.22, 0.49); (6.63, 0.83)\n", "Elmas (6.20, 0.49); (6.78, 0.98)\n", "Miranchuk (6.20, 0.53); (6.80, 1.05)\n", "Samardzic (6.12, 0.53); (6.67, 1.04)\n", "Pereyra (6.09, 0.58); (6.68, 1.16)\n", "Politano (6.20, 0.40); (6.70, 0.82)\n", "Rabiot (6.26, 0.60); (7.05, 1.37)\n", "Ciurria (6.03, 0.54); (6.50, 1.00)\n", "Lazovic (6.16, 0.51); (6.68, 0.95)\n", "Lobotka (6.19, 0.40); (6.46, 0.63)\n", "Radonjic (6.14, 0.49); (6.64, 0.90)\n", "Ferguson (6.14, 0.45); (6.55, 0.80)\n", "Bonaventura (6.13, 0.46); (6.54, 0.80)\n", "Pessina (6.09, 0.50); (6.46, 0.85)\n", "Tonali (6.10, 0.54); (6.51, 0.93)\n", "Kostic (6.14, 0.49); (6.63, 0.93)\n", "Baldanzi (6.14, 0.49); (6.64, 0.93)\n", "Lovric (6.11, 0.46); (6.56, 0.83)\n", "Pellegrini Lo. (6.07, 0.58); (6.63, 1.15)\n", "El Shaarawy (6.17, 0.43); (6.69, 0.86)\n", "Orsolini (6.21, 0.64); (7.05, 1.48)\n", "Ikone' (5.98, 0.51); (6.33, 0.87)\n", "Candreva (6.07, 0.51); (6.45, 0.86)\n", "Bennacer (6.12, 0.41); (6.38, 0.61)\n", "Pasalic (6.03, 0.56); (6.56, 1.08)\n", "Mkhitaryan (6.03, 0.46); (6.40, 0.79)\n", "Colpani (6.00, 0.40); (6.37, 0.74)\n", "Pogba (6.09, 0.41); (6.20, 0.48)\n", "Chiesa (6.07, 0.41); (6.32, 0.63)\n", "Bandinelli (5.94, 0.40); (6.07, 0.56)\n", "Matic (6.12, 0.39); (6.39, 0.60)\n", "Fagioli (6.06, 0.48); (6.41, 0.81)\n", "Messias (5.98, 0.53); (6.42, 0.96)\n", "Arslan (5.92, 0.35); (5.98, 0.37)\n", "Ricci S. (6.09, 0.43); (6.32, 0.61)\n", "Ranocchia F. (6.05, 0.40); (6.35, 0.65)\n", "Verdi (6.13, 0.57); (6.77, 1.20)\n", "Sensi (6.04, 0.52); (6.43, 0.93)\n", "Barak (5.91, 0.46); (6.12, 0.71)\n", "Soriano (6.04, 0.40); (6.30, 0.62)\n", "Dominguez (6.17, 0.49); (6.61, 0.88)\n", "Vilhena (5.91, 0.49); (6.10, 0.73)\n", "Brozovic (6.08, 0.43); (6.36, 0.65)\n", "Cristante (5.98, 0.41); (6.10, 0.51)\n", "Thorstvedt (5.97, 0.46); (6.24, 0.72)\n", "De Ketelaere (5.81, 0.36); (5.83, 0.40)\n", "Saponara (6.04, 0.51); (6.48, 0.91)\n", "Vecino (6.01, 0.45); (6.21, 0.64)\n", "Locatelli (6.09, 0.40); (6.21, 0.49)\n", "Zaniolo (5.91, 0.50); (6.12, 0.77)\n", "Duda (5.88, 0.33); (5.87, 0.33)\n", "Maldini (5.97, 0.44); (6.31, 0.75)\n", "Marin (5.93, 0.47); (6.05, 0.66)\n", "Zalewski (6.02, 0.37); (6.16, 0.47)\n", "Bajrami (6.09, 0.53); (6.63, 1.04)\n", "Coulibaly L. (5.86, 0.55); (6.08, 0.78)\n", "Gonzalez J. (5.99, 0.44); (6.18, 0.66)\n", "De Roon (6.05, 0.45); (6.28, 0.64)\n", "Mandragora (5.97, 0.46); (6.15, 0.68)\n", "Wijnaldum (6.13, 0.54); (6.74, 1.09)\n", "Bourabia (5.91, 0.36); (5.92, 0.37)\n", "Sottil (6.02, 0.49); (6.33, 0.80)\n", "Aebischer (5.93, 0.39); (6.09, 0.56)\n", "Ederson D.s. (5.91, 0.44); (6.03, 0.57)\n", "Miretti (5.97, 0.36); (6.07, 0.42)\n", "Blin (5.95, 0.39); (6.03, 0.46)\n", "Hjulmand (5.94, 0.44); (5.97, 0.46)\n", "Cataldi (6.01, 0.36); (6.02, 0.35)\n", "Djuricic (5.83, 0.46); (5.98, 0.66)\n", "Linetty (5.95, 0.43); (6.07, 0.60)\n", "Haas (5.91, 0.38); (6.02, 0.51)\n", "Walace (5.94, 0.38); (5.95, 0.39)\n", "Agudelo (5.92, 0.35); (5.96, 0.40)\n", "Pobega (6.03, 0.46); (6.36, 0.76)\n", "Camara Ma. (6.07, 0.42); (6.18, 0.48)\n", "Paredes (5.84, 0.33); (5.82, 0.27)\n", "Ndombele' (6.01, 0.38); (6.16, 0.47)\n", "Nicolussi Caviglia (5.85, 0.51); (5.99, 0.73)\n", "Rovella (5.94, 0.48); (6.04, 0.58)\n", "Amrabat (5.91, 0.43); (5.96, 0.50)\n", "Tameze (5.91, 0.37); (5.90, 0.36)\n", "Gyasi (5.89, 0.46); (6.04, 0.67)\n", "Ilic (6.04, 0.44); (6.24, 0.62)\n", "Matheus Henrique (5.94, 0.46); (6.13, 0.70)\n", "Harroui (5.98, 0.45); (6.31, 0.75)\n", "Volpato (6.03, 0.56); (6.59, 1.10)\n", "Pickel (5.82, 0.37); (5.78, 0.42)\n", "Moro N. (6.10, 0.43); (6.39, 0.67)\n", "Duncan (5.90, 0.39); (6.01, 0.54)\n", "Machin (5.92, 0.44); (6.02, 0.58)\n", "Cuadrado (5.92, 0.46); (6.00, 0.55)\n", "Ekdal (5.88, 0.37); (5.87, 0.39)\n", "Meite' (5.87, 0.41); (5.86, 0.46)\n", "Schouten (5.99, 0.40); (6.03, 0.43)\n", "Obiang (5.93, 0.31); (5.91, 0.27)\n", "Kovalenko (5.92, 0.38); (5.98, 0.45)\n", "Crnigoj (5.91, 0.37); (6.02, 0.45)\n", "Basic (5.98, 0.31); (6.02, 0.30)\n", "Asllani (5.98, 0.32); (5.99, 0.29)\n", "Sabiri (5.88, 0.45); (6.07, 0.68)\n", "Terracciano F. (6.01, 0.32); (6.04, 0.30)\n", "Castagnetti (5.90, 0.33); (5.90, 0.29)\n", "Oudin (5.92, 0.31); (5.95, 0.27)\n", "Grassi (5.93, 0.32); (5.91, 0.27)\n", "Krunic (5.94, 0.36); (5.97, 0.38)\n", "Rincon (5.81, 0.36); (5.76, 0.38)\n", "Miguel Veloso (5.95, 0.34); (5.94, 0.32)\n", "Leris (5.88, 0.42); (5.95, 0.57)\n", "Esposito Sa. (5.79, 0.40); (5.70, 0.38)\n", "Henderson L. (5.91, 0.38); (5.99, 0.48)\n", "Lopez M. (5.93, 0.39); (5.92, 0.40)\n", "Cuisance (5.82, 0.30); (5.77, 0.28)\n", "Saelemaekers (5.88, 0.39); (6.02, 0.53)\n", "Maggiore (5.93, 0.38); (6.02, 0.45)\n", "Akpa Akpro (5.92, 0.45); (5.99, 0.54)\n", "Maleh (5.91, 0.35); (5.98, 0.42)\n", "Romero L. (6.05, 0.48); (6.63, 1.03)\n", "Ceide (5.88, 0.34); (5.90, 0.34)\n", "D'alessandro (6.04, 0.32); (6.13, 0.37)\n", "Benassi (5.85, 0.35); (5.86, 0.38)\n", "Gagliardini (5.81, 0.30); (5.79, 0.26)\n", "Vieira (5.86, 0.34); (5.83, 0.40)\n", "Bianco (6.06, 0.38); (6.16, 0.45)\n", "Vranckx (5.81, 0.33); (5.77, 0.33)\n", "Galdames (5.92, 0.44); (5.98, 0.55)\n", "Marcos Antonio (6.04, 0.40); (6.50, 0.83)\n", "Fazzini (5.85, 0.31); (5.80, 0.29)\n", "Sulemana I. (5.91, 0.30); (5.90, 0.26)\n", "Tahirovic (6.03, 0.32); (6.03, 0.31)\n", "Abildgaard (5.94, 0.29); (5.93, 0.22)\n", "Barberis (5.77, 0.39); (5.74, 0.42)\n", "Kastanos (5.95, 0.42); (6.08, 0.55)\n", "Vignato (5.98, 0.37); (6.06, 0.43)\n", "Valoti (5.82, 0.34); (5.80, 0.34)\n", "Winks (5.89, 0.39); (5.88, 0.37)\n", "Askildsen (5.79, 0.31); (5.75, 0.27)\n", "Bove (5.95, 0.43); (6.19, 0.68)\n", "Bohinen (5.86, 0.29); (5.86, 0.23)\n", "D'andrea (6.01, 0.36); (6.12, 0.43)\n", "Iling-Junior (5.97, 0.33); (6.00, 0.32)\n", "Cipot (5.98, 0.36); (6.03, 0.38)\n", "Bakayoko (5.80, 0.38); (5.77, 0.35)\n", "Gaetano (6.15, 0.35); (6.28, 0.48)\n", "Zurkowski (6.04, 0.48); (6.42, 0.86)\n", "Castrovilli (5.96, 0.38); (6.11, 0.55)\n", "Demme (5.94, 0.41); (6.06, 0.54)\n", "Darboe (5.94, 0.44); (5.98, 0.46)\n", "Urbanski (6.00, 0.42); (6.11, 0.52)\n", "Bertini (5.98, 0.43); (6.09, 0.51)\n", "Yepes (5.79, 0.43); (5.74, 0.46)\n", "Pyyhtia (5.90, 0.39); (5.89, 0.41)\n", "Trimboli (5.91, 0.44); (5.96, 0.53)\n", "Pafundi (6.04, 0.35); (6.03, 0.33)\n", "Helgason (5.88, 0.31); (5.88, 0.25)\n", "Adli (5.88, 0.35); (5.88, 0.39)\n", "Vignato S. (5.93, 0.42); (5.99, 0.48)\n", "Hrustic (5.76, 0.31); (5.74, 0.27)\n", "Samek (5.97, 0.44); (6.07, 0.53)\n", "Zerbin (5.87, 0.35); (5.89, 0.39)\n", "Ilkhan (5.90, 0.39); (5.90, 0.41)\n", "Degli Innocenti (5.92, 0.45); (5.99, 0.54)\n", "Acella (5.96, 0.43); (6.04, 0.53)\n", "Carboni V. (5.99, 0.37); (6.02, 0.37)\n", "Paoletti (5.92, 0.29); (5.89, 0.21)\n", "Malagrida (5.96, 0.47); (6.10, 0.63)\n", "Faticanti (5.96, 0.43); (6.07, 0.53)\n", "Osimhen (6.48, 0.73); (7.85, 2.20)\n", "Martinez L. (6.20, 0.69); (7.49, 1.94)\n", "Dybala (6.43, 0.67); (7.48, 1.74)\n", "Rafael Leao (6.29, 0.68); (7.37, 1.77)\n", "Lookman (6.28, 0.67); (7.45, 1.84)\n", "Immobile (6.23, 0.66); (7.37, 1.79)\n", "Vlahovic (6.11, 0.64); (7.10, 1.59)\n", "Arnautovic (6.18, 0.63); (7.20, 1.62)\n", "Dia (6.13, 0.64); (7.11, 1.59)\n", "Dzeko (6.09, 0.61); (6.92, 1.39)\n", "Milik (6.14, 0.57); (6.85, 1.26)\n", "Nzola (6.10, 0.66); (7.20, 1.70)\n", "Beto (6.02, 0.58); (6.83, 1.34)\n", "Giroud (6.11, 0.60); (6.88, 1.34)\n", "Abraham (6.09, 0.59); (6.92, 1.39)\n", "Deulofeu (6.29, 0.61); (7.15, 1.44)\n", "Lauriente' (6.29, 0.66); (7.22, 1.60)\n", "Simeone (6.15, 0.63); (7.08, 1.52)\n", "Lozano (6.09, 0.53); (6.65, 1.04)\n", "Correa (5.95, 0.46); (6.38, 0.86)\n", "Berardi (6.29, 0.68); (7.46, 1.87)\n", "Pedro (6.13, 0.49); (6.64, 0.97)\n", "Lukaku (6.05, 0.61); (6.80, 1.32)\n", "Sanabria (6.08, 0.61); (6.90, 1.38)\n", "Thauvin (6.20, 0.56); (6.96, 1.28)\n", "Cabral (6.07, 0.58); (6.78, 1.25)\n", "Hojlund (6.06, 0.62); (6.87, 1.40)\n", "Caprari (5.96, 0.48); (6.32, 0.83)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Di Maria (6.19, 0.62); (7.02, 1.45)\n", "Piatek (5.84, 0.49); (6.24, 0.84)\n", "Rebic (6.00, 0.57); (6.54, 1.10)\n", "Bonazzoli (5.96, 0.47); (6.29, 0.78)\n", "Zapata D. (5.88, 0.46); (6.13, 0.70)\n", "Kouame' (6.01, 0.56); (6.53, 1.07)\n", "Gonzalez N. (6.12, 0.58); (6.81, 1.23)\n", "Brekalo (6.04, 0.54); (6.56, 1.03)\n", "Mota (5.99, 0.57); (6.58, 1.13)\n", "Kean (6.05, 0.62); (6.75, 1.31)\n", "Okereke (5.92, 0.51); (6.31, 0.88)\n", "Ceesay (5.95, 0.50); (6.42, 0.93)\n", "Colombo (5.94, 0.55); (6.49, 1.06)\n", "Dessers (6.01, 0.56); (6.68, 1.19)\n", "Muriel (5.92, 0.49); (6.06, 0.67)\n", "Pinamonti (5.80, 0.48); (6.19, 0.82)\n", "Di Francesco F. (5.97, 0.50); (6.26, 0.81)\n", "Jovic (5.90, 0.52); (6.29, 0.90)\n", "Origi (5.84, 0.48); (6.14, 0.76)\n", "Caputo (5.95, 0.54); (6.46, 1.02)\n", "Boga (6.23, 0.58); (6.94, 1.24)\n", "Cambiaghi (6.10, 0.50); (6.65, 1.00)\n", "Alvarez A. (6.00, 0.52); (6.40, 0.92)\n", "Banda (5.93, 0.39); (6.07, 0.50)\n", "Ciofani D. (6.02, 0.54); (6.59, 1.09)\n", "Petagna (5.95, 0.52); (6.33, 0.88)\n", "Barrow (6.03, 0.57); (6.53, 1.07)\n", "Djuric (5.95, 0.35); (6.11, 0.44)\n", "Henry (5.92, 0.53); (6.33, 0.92)\n", "Success (5.92, 0.45); (6.20, 0.72)\n", "Gabbiadini (5.93, 0.55); (6.41, 1.01)\n", "Zirkzee (5.98, 0.50); (6.36, 0.85)\n", "Lammers (5.82, 0.42); (5.99, 0.59)\n", "Satriano (5.88, 0.45); (6.08, 0.66)\n", "Kallon (5.88, 0.41); (6.06, 0.58)\n", "Nestorovski (6.09, 0.39); (6.64, 0.86)\n", "Raspadori (6.02, 0.51); (6.48, 0.95)\n", "Botheim (5.92, 0.48); (6.30, 0.83)\n", "Gytkjaer (5.83, 0.42); (6.01, 0.61)\n", "Solbakken (5.91, 0.49); (6.27, 0.84)\n", "Lasagna (5.80, 0.39); (5.88, 0.48)\n", "Belotti (5.81, 0.40); (5.95, 0.53)\n", "Pellegri (5.91, 0.45); (6.16, 0.70)\n", "Buonaiuto (5.94, 0.36); (6.04, 0.43)\n", "Verde (6.03, 0.54); (6.53, 1.04)\n", "Destro (5.96, 0.57); (6.45, 1.05)\n", "Seck (6.04, 0.34); (6.15, 0.40)\n", "Sansone (6.07, 0.53); (6.57, 1.01)\n", "Quagliarella (5.85, 0.37); (5.94, 0.47)\n", "Defrel (5.85, 0.45); (6.07, 0.68)\n", "Pjaca (5.88, 0.40); (6.02, 0.52)\n", "Gaich (5.88, 0.46); (6.12, 0.68)\n", "Soule' (6.15, 0.39); (6.56, 0.71)\n", "Tsadjout (5.90, 0.48); (6.24, 0.79)\n", "Piccoli (5.81, 0.35); (5.86, 0.37)\n", "Shomurodov (5.95, 0.51); (6.39, 0.91)\n", "Afena-Gyan (5.77, 0.34); (5.74, 0.35)\n", "Ngonge (6.07, 0.57); (6.66, 1.14)\n", "Karamoh (6.04, 0.51); (6.62, 1.04)\n", "Ibrahimovic (6.16, 0.59); (7.06, 1.43)\n", "Pussetto (5.93, 0.52); (6.37, 0.95)\n", "Cancellieri (5.81, 0.30); (5.81, 0.26)\n", "Valencia D. (5.75, 0.29); (5.70, 0.30)\n", "Oddei (6.08, 0.42); (6.28, 0.57)\n", "Braaf (5.85, 0.40); (5.86, 0.46)\n", "Raimondo (6.03, 0.45); (6.18, 0.57)\n", "Kaio Jorge (5.86, 0.29); (5.90, 0.25)\n", "De Luca (5.92, 0.41); (5.99, 0.49)\n", "Voelkerling Persson (5.91, 0.32); (5.99, 0.31)\n", "Montevago (5.71, 0.31); (5.67, 0.30)\n", "Krollis (5.95, 0.47); (6.07, 0.62)\n", "Vivaldo (5.93, 0.45); (6.02, 0.57)\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
MussoPAtalantaAvg111006.2577700.4395965.5812510.5034855.9845720.1746250.8465551.6992015.8172010.714061-0.2454710.89703832.650129
SportielloPAtalantaAvg1006.2307670.4166184.5108410.3954335.9839570.2043800.7198761.6991674.4425640.6059520.0665080.9101694.898746
Rossi F.PAtalantaAvg1005.9117650.3878684.0496070.5602375.7470250.3297880.3573711.6987204.1635190.842991-0.1011380.9484582.865818
ZappacostaDAtalantaAvg10456.0386450.4348126.2845630.6568255.9852190.5015800.0788221.1024195.8016890.9004340.3751641.6999110.000000
ScalviniDAtalantaAvg11806.0261120.5053726.2744830.7263926.0045540.5935500.0270201.0273745.7789561.0438460.3358841.6998990.000000
............................................................
GaichAVeronaAvg10355.8807700.4566676.1174210.6828085.7979060.5158570.1185751.0996875.5600610.8570370.4429351.6998910.000000
DjuricAVeronaAvg10675.9520050.3549486.1106910.4382205.9002950.4083800.0938541.2152575.8401180.6622850.2930501.6999360.000000
KallonAVeronaAvg10675.8773790.4061006.0585970.5754735.8060830.4605030.1144711.1596905.6137870.7589940.4050531.6999120.000000
LasagnaAVeronaAvg11835.8035220.3860735.8812030.4790495.7467760.4433770.0947441.1874905.5504260.6833930.3415981.6999250.000000
BraafAVeronaAvg10125.8476330.3986975.8602360.4649335.8273980.4727670.0317501.1547095.6383020.7641480.2117991.6999330.000000
\n", "

525 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 6.257770 0.439596 \n", "Sportiello P Atalanta Avg 1 0 0 6.230767 0.416618 \n", "Rossi F. P Atalanta Avg 1 0 0 5.911765 0.387868 \n", "Zappacosta D Atalanta Avg 1 0 45 6.038645 0.434812 \n", "Scalvini D Atalanta Avg 1 1 80 6.026112 0.505372 \n", "... ... ... ... ... ... ... ... ... \n", "Gaich A Verona Avg 1 0 35 5.880770 0.456667 \n", "Djuric A Verona Avg 1 0 67 5.952005 0.354948 \n", "Kallon A Verona Avg 1 0 67 5.877379 0.406100 \n", "Lasagna A Verona Avg 1 1 83 5.803522 0.386073 \n", "Braaf A Verona Avg 1 0 12 5.847633 0.398697 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Musso 5.581251 0.503485 5.984572 0.174625 0.846555 \n", "Sportiello 4.510841 0.395433 5.983957 0.204380 0.719876 \n", "Rossi F. 4.049607 0.560237 5.747025 0.329788 0.357371 \n", "Zappacosta 6.284563 0.656825 5.985219 0.501580 0.078822 \n", "Scalvini 6.274483 0.726392 6.004554 0.593550 0.027020 \n", "... ... ... ... ... ... \n", "Gaich 6.117421 0.682808 5.797906 0.515857 0.118575 \n", "Djuric 6.110691 0.438220 5.900295 0.408380 0.093854 \n", "Kallon 6.058597 0.575473 5.806083 0.460503 0.114471 \n", "Lasagna 5.881203 0.479049 5.746776 0.443377 0.094744 \n", "Braaf 5.860236 0.464933 5.827398 0.472767 0.031750 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Musso 1.699201 5.817201 0.714061 -0.245471 0.897038 \n", "Sportiello 1.699167 4.442564 0.605952 0.066508 0.910169 \n", "Rossi F. 1.698720 4.163519 0.842991 -0.101138 0.948458 \n", "Zappacosta 1.102419 5.801689 0.900434 0.375164 1.699911 \n", "Scalvini 1.027374 5.778956 1.043846 0.335884 1.699899 \n", "... ... ... ... ... ... \n", "Gaich 1.099687 5.560061 0.857037 0.442935 1.699891 \n", "Djuric 1.215257 5.840118 0.662285 0.293050 1.699936 \n", "Kallon 1.159690 5.613787 0.758994 0.405053 1.699912 \n", "Lasagna 1.187490 5.550426 0.683393 0.341598 1.699925 \n", "Braaf 1.154709 5.638302 0.764148 0.211799 1.699933 \n", "\n", " Clean Sheet % \n", "player \n", "Musso 32.650129 \n", "Sportiello 4.898746 \n", "Rossi F. 2.865818 \n", "Zappacosta 0.000000 \n", "Scalvini 0.000000 \n", "... ... \n", "Gaich 0.000000 \n", "Djuric 0.000000 \n", "Kallon 0.000000 \n", "Lasagna 0.000000 \n", "Braaf 0.000000 \n", "\n", "[525 rows x 19 columns]" ] }, "execution_count": 43, "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", " try:\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", " except:\n", " print(players.index[i] + ' no data')\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": 44, "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": "cf9df3bb", "metadata": {}, "source": [ "Various predictions." ] }, { "cell_type": "code", "execution_count": 36, "id": "7300f3c2", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 6.08 ± 0.61; FV 5.48 + 1.00 (64.3% cs)\n", "Szczesny: MV 6.12 ± 0.63; FV 5.79 + 0.88 (87.3% cs)\n", "Provedel: MV 6.18 ± 0.65; FV 5.49 + 1.00 (55.3% cs)\n", "Maignan: MV 6.50 ± 0.78; FV 5.78 + 0.88 (47.3% cs)\n", "Rui Patricio: MV 6.36 ± 0.72; FV 6.14 + 0.74 (82.2% cs)\n", "Onana: MV 6.11 ± 0.62; FV 5.88 + 0.85 (82.9% cs)\n", "Milinkovic-Savic V.: MV 6.09 ± 0.62; FV 4.87 + 1.25 (6.9% cs)\n", "Musso: MV 6.56 ± 0.81; FV 6.04 + 0.79 (72.9% cs)\n", "Vicario: MV 6.68 ± 0.87; FV 5.75 + 0.88 (37.2% cs)\n", "Silvestri: MV 6.11 ± 1.17; FV 4.85 + 0.64 (13.9% cs)\n", "Terracciano: MV 6.12 ± 0.63; FV 5.38 + 1.01 (29.3% cs)\n", "Skorupski: MV 6.27 ± 0.68; FV 5.46 + 1.00 (47.3% cs)\n", "Falcone: MV 6.42 ± 0.75; FV 5.29 + 1.02 (2.8% cs)\n", "Di Gregorio: MV 6.39 ± 0.75; FV 5.73 + 0.89 (61.6% cs)\n", "Consigli: MV 6.16 ± 0.64; FV 5.22 + 1.11 (45.3% cs)\n", "Carnesecchi: MV 6.27 ± 0.77; FV 5.12 + 0.93 (7.8% cs)\n", "Montipo': MV 6.47 ± 0.77; FV 5.20 + 1.05 (6.4% cs)\n", "Audero: MV 6.48 ± 0.77; FV 5.26 + 0.95 (7.2% cs)\n", "Dragowski: MV 6.52 ± 0.80; FV 6.02 + 0.79 (76.4% cs)\n", "Ochoa: MV 6.46 ± 0.78; FV 5.69 + 0.79 (23.2% cs)\n", "Tatarusanu: MV 6.04 ± 0.69; FV 4.11 + 1.16 (3.0% cs)\n", "Handanovic: MV 6.41 ± 0.74; FV 6.19 + 0.74 (92.1% cs)\n", "Sportiello: MV 6.39 ± 0.75; FV 5.18 + 0.93 (15.2% cs)\n", "Sepe: MV 6.21 ± 0.71; FV 4.87 + 1.05 (4.9% cs)\n" ] }, { "data": { "text/plain": [ "[array([6.21465971, 4.86660706]),\n", " array([0.35387683, 0.5225544 ], dtype=float32),\n", " [,\n", " ,\n", " ]]" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Meret', log = 1, plot = 0)\n", "predict_player('Szczesny', log = 1, plot = 0)\n", "predict_player('Provedel', log = 1, plot = 0)\n", "predict_player('Maignan', log = 1, plot = 0)\n", "predict_player('Rui Patricio', log = 1, plot = 0)\n", "predict_player('Onana', log = 1, plot = 0)\n", "predict_player('Milinkovic-Savic V.', log = 1, plot = 0)\n", "predict_player('Musso', log = 1, plot = 0)\n", "predict_player('Vicario', log = 1, plot = 0)\n", "predict_player('Silvestri', log = 1, plot = 0)\n", "predict_player('Terracciano', log = 1, plot = 0)\n", "predict_player('Skorupski', log = 1, plot = 0)\n", "predict_player('Falcone', log = 1, plot = 0)\n", "predict_player('Di Gregorio', log = 1, plot = 0)\n", "predict_player('Consigli', log = 1, plot = 0)\n", "predict_player('Carnesecchi', log = 1, plot = 0)\n", "predict_player('Montipo\\'', log = 1, plot = 0)\n", "predict_player('Audero', log = 1, plot = 0)\n", "predict_player('Dragowski', log = 1, plot = 0)\n", "predict_player('Ochoa', log = 1, plot = 0)\n", "predict_player('Tatarusanu', log = 1, plot = 0)\n", "predict_player('Handanovic', log = 1, plot = 0)\n", "predict_player('Sportiello', log = 1, plot = 0)\n", "predict_player('Sepe', 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": 37, "id": "4b9f5a7d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Skriniar: MV 6.14 ± 0.82; FV 6.38 + 1.13\n", "Cuadrado: MV 6.29 ± 0.96; FV 6.83 + 1.94\n", "Bastoni: MV 6.13 ± 0.73; FV 6.32 + 0.98\n", "Barak: MV 6.31 ± 1.41; FV 7.50 + 3.97\n", "Politano: MV 6.18 ± 0.82; FV 6.57 + 1.55\n", "Smalling: MV 6.17 ± 0.86; FV 6.56 + 1.43\n", "Gosens: MV 6.05 ± 0.54; FV 6.11 + 0.66\n" ] }, { "data": { "text/plain": [ "[array([6.04807256, 6.10812885]),\n", " array([0.27137518, 0.32888246], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 37, "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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", "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": "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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", "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 }