rams/fantabeto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
4dc3df3ec2c5a2addfeef123c32ecdd3a2ba3df5
fantabeto/6_neural_network_training_and_prediction.ipynb
T
Giuseppe Musicco 4dc3df3ec2 Matchdays 32 and 33 + notebook for Lineup simulation
2023-04-29 10:39:31 +02:00

7216 lines
768 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>miscontrols</th>\n",
" <th>dispossessed</th>\n",
" <th>fouls</th>\n",
" <th>fouled</th>\n",
" <th>aerials_won</th>\n",
" <th>aerials_lost</th>\n",
" <th>carries</th>\n",
" <th>progressive_carries</th>\n",
" <th>carries_into_final_third</th>\n",
" <th>carries_into_penalty_area</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Toloi</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.006906</td>\n",
" <td>0.001381</td>\n",
" <td>0.007597</td>\n",
" <td>0.006906</td>\n",
" <td>0.013812</td>\n",
" <td>0.010359</td>\n",
" <td>0.356354</td>\n",
" <td>0.008287</td>\n",
" <td>0.015884</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.003210</td>\n",
" <td>0.006421</td>\n",
" <td>0.004815</td>\n",
" <td>0.004815</td>\n",
" <td>0.022472</td>\n",
" <td>0.014446</td>\n",
" <td>0.462279</td>\n",
" <td>0.004815</td>\n",
" <td>0.004815</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Hateboer</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.005727</td>\n",
" <td>0.005011</td>\n",
" <td>0.013601</td>\n",
" <td>0.002147</td>\n",
" <td>0.017180</td>\n",
" <td>0.010021</td>\n",
" <td>0.282749</td>\n",
" <td>0.011453</td>\n",
" <td>0.009306</td>\n",
" <td>0.000716</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Okoli</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>0.013018</td>\n",
" <td>0.003550</td>\n",
" <td>0.015385</td>\n",
" <td>0.008284</td>\n",
" <td>0.047337</td>\n",
" <td>0.027219</td>\n",
" <td>0.269822</td>\n",
" <td>0.002367</td>\n",
" <td>0.004734</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Zortea</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.011111</td>\n",
" <td>0.005556</td>\n",
" <td>0.016667</td>\n",
" <td>0.022222</td>\n",
" <td>0.016667</td>\n",
" <td>0.027778</td>\n",
" <td>0.561111</td>\n",
" <td>0.072222</td>\n",
" <td>0.055556</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24806</th>\n",
" <td>38</td>\n",
" <td>Tameze</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.019814</td>\n",
" <td>0.010101</td>\n",
" <td>0.012821</td>\n",
" <td>0.013209</td>\n",
" <td>0.023699</td>\n",
" <td>0.021368</td>\n",
" <td>0.337218</td>\n",
" <td>0.021368</td>\n",
" <td>0.012821</td>\n",
" <td>0.003885</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24807</th>\n",
" <td>38</td>\n",
" <td>Hongla</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.018433</td>\n",
" <td>0.012289</td>\n",
" <td>0.023041</td>\n",
" <td>0.007680</td>\n",
" <td>0.023041</td>\n",
" <td>0.026114</td>\n",
" <td>0.341014</td>\n",
" <td>0.009217</td>\n",
" <td>0.015361</td>\n",
" <td>0.003072</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24808</th>\n",
" <td>38</td>\n",
" <td>Lasagna</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.046453</td>\n",
" <td>0.022804</td>\n",
" <td>0.016047</td>\n",
" <td>0.008446</td>\n",
" <td>0.026182</td>\n",
" <td>0.041385</td>\n",
" <td>0.190878</td>\n",
" <td>0.021959</td>\n",
" <td>0.010980</td>\n",
" <td>0.005912</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24809</th>\n",
" <td>38</td>\n",
" <td>Caprari</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.033954</td>\n",
" <td>0.019715</td>\n",
" <td>0.015334</td>\n",
" <td>0.027017</td>\n",
" <td>0.002921</td>\n",
" <td>0.009858</td>\n",
" <td>0.391384</td>\n",
" <td>0.042716</td>\n",
" <td>0.027747</td>\n",
" <td>0.018620</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24810</th>\n",
" <td>38</td>\n",
" <td>Simeone</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.051263</td>\n",
" <td>0.030155</td>\n",
" <td>0.021108</td>\n",
" <td>0.021862</td>\n",
" <td>0.022616</td>\n",
" <td>0.040709</td>\n",
" <td>0.246136</td>\n",
" <td>0.015077</td>\n",
" <td>0.012816</td>\n",
" <td>0.006031</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>24811 rows × 122 columns</p>\n",
"</div>"
],
"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",
"24806 38 Tameze Verona Lazio 0 5.5 0 0 \n",
"24807 38 Hongla Verona Lazio 0 7.0 1 0 \n",
"24808 38 Lasagna Verona Lazio 0 7.0 1 0 \n",
"24809 38 Caprari Verona Lazio 0 6.0 0 0 \n",
"24810 38 Simeone Verona Lazio 0 7.0 1 0 \n",
"\n",
" cards_malus fantavote ... miscontrols dispossessed fouls \\\n",
"0 0.0 10.0 ... 0.006906 0.001381 0.007597 \n",
"1 0.0 6.0 ... 0.003210 0.006421 0.004815 \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 ... 0.011111 0.005556 0.016667 \n",
"... ... ... ... ... ... ... \n",
"24806 0.0 5.5 ... 0.019814 0.010101 0.012821 \n",
"24807 0.5 9.5 ... 0.018433 0.012289 0.023041 \n",
"24808 0.5 9.5 ... 0.046453 0.022804 0.016047 \n",
"24809 0.0 6.0 ... 0.033954 0.019715 0.015334 \n",
"24810 0.0 10.0 ... 0.051263 0.030155 0.021108 \n",
"\n",
" fouled aerials_won aerials_lost carries progressive_carries \\\n",
"0 0.006906 0.013812 0.010359 0.356354 0.008287 \n",
"1 0.004815 0.022472 0.014446 0.462279 0.004815 \n",
"2 0.002147 0.017180 0.010021 0.282749 0.011453 \n",
"3 0.008284 0.047337 0.027219 0.269822 0.002367 \n",
"4 0.022222 0.016667 0.027778 0.561111 0.072222 \n",
"... ... ... ... ... ... \n",
"24806 0.013209 0.023699 0.021368 0.337218 0.021368 \n",
"24807 0.007680 0.023041 0.026114 0.341014 0.009217 \n",
"24808 0.008446 0.026182 0.041385 0.190878 0.021959 \n",
"24809 0.027017 0.002921 0.009858 0.391384 0.042716 \n",
"24810 0.021862 0.022616 0.040709 0.246136 0.015077 \n",
"\n",
" carries_into_final_third carries_into_penalty_area \n",
"0 0.015884 0.000000 \n",
"1 0.004815 0.000000 \n",
"2 0.009306 0.000716 \n",
"3 0.004734 0.000000 \n",
"4 0.055556 0.000000 \n",
"... ... ... \n",
"24806 0.012821 0.003885 \n",
"24807 0.015361 0.003072 \n",
"24808 0.010980 0.005912 \n",
"24809 0.027747 0.018620 \n",
"24810 0.012816 0.006031 \n",
"\n",
"[24811 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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>gk_psxg</th>\n",
" <th>gk_psnpxg_per_shot_on_target_against</th>\n",
" <th>gk_psxg_net</th>\n",
" <th>gk_passes_completed_launched</th>\n",
" <th>gk_passes_launched</th>\n",
" <th>gk_passes</th>\n",
" <th>gk_passes_throws</th>\n",
" <th>gk_goal_kicks</th>\n",
" <th>gk_crosses</th>\n",
" <th>gk_crosses_stopped</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Musso</td>\n",
" <td>Atalanta</td>\n",
" <td>Sampdoria</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>13.00</td>\n",
" <td>0.20</td>\n",
" <td>-1.00</td>\n",
" <td>88.0</td>\n",
" <td>201.0</td>\n",
" <td>397.0</td>\n",
" <td>112.0</td>\n",
" <td>101.0</td>\n",
" <td>186.0</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Skorupski</td>\n",
" <td>Bologna</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.5</td>\n",
" <td>...</td>\n",
" <td>32.50</td>\n",
" <td>0.29</td>\n",
" <td>2.50</td>\n",
" <td>101.0</td>\n",
" <td>242.0</td>\n",
" <td>576.0</td>\n",
" <td>117.0</td>\n",
" <td>159.0</td>\n",
" <td>304.0</td>\n",
" <td>18.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Vicario</td>\n",
" <td>Empoli</td>\n",
" <td>Spezia</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.5</td>\n",
" <td>...</td>\n",
" <td>27.80</td>\n",
" <td>0.26</td>\n",
" <td>-0.20</td>\n",
" <td>102.0</td>\n",
" <td>313.0</td>\n",
" <td>806.0</td>\n",
" <td>117.0</td>\n",
" <td>114.0</td>\n",
" <td>431.0</td>\n",
" <td>25.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Gollini</td>\n",
" <td>Fiorentina</td>\n",
" <td>Cremonese</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>9.45</td>\n",
" <td>0.24</td>\n",
" <td>0.95</td>\n",
" <td>24.0</td>\n",
" <td>68.0</td>\n",
" <td>299.5</td>\n",
" <td>48.5</td>\n",
" <td>72.5</td>\n",
" <td>128.0</td>\n",
" <td>3.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Handanovic</td>\n",
" <td>Inter</td>\n",
" <td>Lecce</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>10.60</td>\n",
" <td>0.30</td>\n",
" <td>-1.40</td>\n",
" <td>27.0</td>\n",
" <td>52.0</td>\n",
" <td>266.0</td>\n",
" <td>46.0</td>\n",
" <td>45.0</td>\n",
" <td>79.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1300</th>\n",
" <td>22</td>\n",
" <td>Consigli</td>\n",
" <td>Sassuolo</td>\n",
" <td>Udinese</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>24.40</td>\n",
" <td>0.33</td>\n",
" <td>-5.60</td>\n",
" <td>113.0</td>\n",
" <td>277.0</td>\n",
" <td>711.0</td>\n",
" <td>108.0</td>\n",
" <td>179.0</td>\n",
" <td>276.0</td>\n",
" <td>17.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1301</th>\n",
" <td>22</td>\n",
" <td>Dragowski</td>\n",
" <td>Spezia</td>\n",
" <td>Empoli</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.5</td>\n",
" <td>...</td>\n",
" <td>29.50</td>\n",
" <td>0.27</td>\n",
" <td>-4.50</td>\n",
" <td>93.0</td>\n",
" <td>285.0</td>\n",
" <td>528.0</td>\n",
" <td>97.0</td>\n",
" <td>122.0</td>\n",
" <td>270.0</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1302</th>\n",
" <td>22</td>\n",
" <td>Milinkovic-Savic V.</td>\n",
" <td>Torino</td>\n",
" <td>Milan</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>23.10</td>\n",
" <td>0.24</td>\n",
" <td>0.10</td>\n",
" <td>150.0</td>\n",
" <td>540.0</td>\n",
" <td>817.0</td>\n",
" <td>97.0</td>\n",
" <td>160.0</td>\n",
" <td>271.0</td>\n",
" <td>19.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1303</th>\n",
" <td>22</td>\n",
" <td>Silvestri</td>\n",
" <td>Udinese</td>\n",
" <td>Sassuolo</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>24.00</td>\n",
" <td>0.31</td>\n",
" <td>1.00</td>\n",
" <td>91.0</td>\n",
" <td>227.0</td>\n",
" <td>470.0</td>\n",
" <td>80.0</td>\n",
" <td>175.0</td>\n",
" <td>293.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1304</th>\n",
" <td>22</td>\n",
" <td>Montipo'</td>\n",
" <td>Verona</td>\n",
" <td>Salernitana</td>\n",
" <td>1</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>28.70</td>\n",
" <td>0.26</td>\n",
" <td>-3.30</td>\n",
" <td>208.0</td>\n",
" <td>433.0</td>\n",
" <td>513.0</td>\n",
" <td>67.0</td>\n",
" <td>175.0</td>\n",
" <td>305.0</td>\n",
" <td>15.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1305 rows × 102 columns</p>\n",
"</div>"
],
"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",
"1300 22 Consigli Sassuolo Udinese 0 7.0 \n",
"1301 22 Dragowski Spezia Empoli 0 6.5 \n",
"1302 22 Milinkovic-Savic V. Torino Milan 0 6.5 \n",
"1303 22 Silvestri Udinese Sassuolo 1 6.0 \n",
"1304 22 Montipo' Verona Salernitana 1 6.5 \n",
"\n",
" goals assists cards_malus fantavote ... gk_psxg \\\n",
"0 0 0 0.5 5.5 ... 13.00 \n",
"1 -2 0 0.0 4.5 ... 32.50 \n",
"2 -1 0 0.0 4.5 ... 27.80 \n",
"3 -2 0 0.0 3.0 ... 9.45 \n",
"4 -1 0 0.0 5.5 ... 10.60 \n",
"... ... ... ... ... ... ... \n",
"1300 -2 0 0.0 5.0 ... 24.40 \n",
"1301 -2 0 0.0 4.5 ... 29.50 \n",
"1302 -1 0 0.0 5.5 ... 23.10 \n",
"1303 -2 0 0.0 4.0 ... 24.00 \n",
"1304 0 0 0.0 6.5 ... 28.70 \n",
"\n",
" gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n",
"0 0.20 -1.00 \n",
"1 0.29 2.50 \n",
"2 0.26 -0.20 \n",
"3 0.24 0.95 \n",
"4 0.30 -1.40 \n",
"... ... ... \n",
"1300 0.33 -5.60 \n",
"1301 0.27 -4.50 \n",
"1302 0.24 0.10 \n",
"1303 0.31 1.00 \n",
"1304 0.26 -3.30 \n",
"\n",
" gk_passes_completed_launched gk_passes_launched gk_passes \\\n",
"0 88.0 201.0 397.0 \n",
"1 101.0 242.0 576.0 \n",
"2 102.0 313.0 806.0 \n",
"3 24.0 68.0 299.5 \n",
"4 27.0 52.0 266.0 \n",
"... ... ... ... \n",
"1300 113.0 277.0 711.0 \n",
"1301 93.0 285.0 528.0 \n",
"1302 150.0 540.0 817.0 \n",
"1303 91.0 227.0 470.0 \n",
"1304 208.0 433.0 513.0 \n",
"\n",
" gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n",
"0 112.0 101.0 186.0 10.0 \n",
"1 117.0 159.0 304.0 18.0 \n",
"2 117.0 114.0 431.0 25.0 \n",
"3 48.5 72.5 128.0 3.5 \n",
"4 46.0 45.0 79.0 2.0 \n",
"... ... ... ... ... \n",
"1300 108.0 179.0 276.0 17.0 \n",
"1301 97.0 122.0 270.0 9.0 \n",
"1302 97.0 160.0 271.0 19.0 \n",
"1303 80.0 175.0 293.0 5.0 \n",
"1304 67.0 175.0 305.0 15.0 \n",
"\n",
"[1305 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_1568\\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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>team</th>\n",
" <th>team_players_used</th>\n",
" <th>team_possession</th>\n",
" <th>team_games</th>\n",
" <th>team_games_starts</th>\n",
" <th>team_minutes</th>\n",
" <th>team_goals</th>\n",
" <th>team_assists</th>\n",
" <th>team_pens_made</th>\n",
" <th>team_pens_att</th>\n",
" <th>...</th>\n",
" <th>vs_team_fouls</th>\n",
" <th>vs_team_fouled</th>\n",
" <th>vs_team_offsides</th>\n",
" <th>vs_team_pens_won</th>\n",
" <th>vs_team_pens_conceded</th>\n",
" <th>vs_team_own_goals</th>\n",
" <th>vs_team_ball_recoveries</th>\n",
" <th>vs_team_aerials_won</th>\n",
" <th>vs_team_aerials_lost</th>\n",
" <th>vs_team_aerials_won_pct</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Atalanta</th>\n",
" <td>Atalanta</td>\n",
" <td>24.00</td>\n",
" <td>48.600</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>40.00</td>\n",
" <td>28.00</td>\n",
" <td>6.00</td>\n",
" <td>8.0</td>\n",
" <td>...</td>\n",
" <td>244.00</td>\n",
" <td>256.00</td>\n",
" <td>26.0</td>\n",
" <td>1.0</td>\n",
" <td>8.00</td>\n",
" <td>1.0</td>\n",
" <td>1335.00</td>\n",
" <td>273.00</td>\n",
" <td>328.00</td>\n",
" <td>45.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Bologna</th>\n",
" <td>Bologna</td>\n",
" <td>25.00</td>\n",
" <td>52.400</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>27.00</td>\n",
" <td>20.00</td>\n",
" <td>4.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>280.00</td>\n",
" <td>268.00</td>\n",
" <td>38.0</td>\n",
" <td>3.0</td>\n",
" <td>4.00</td>\n",
" <td>1.0</td>\n",
" <td>1204.00</td>\n",
" <td>250.00</td>\n",
" <td>210.00</td>\n",
" <td>54.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cremonese</th>\n",
" <td>Cremonese</td>\n",
" <td>31.00</td>\n",
" <td>43.800</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>15.00</td>\n",
" <td>7.00</td>\n",
" <td>2.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>239.00</td>\n",
" <td>271.00</td>\n",
" <td>36.0</td>\n",
" <td>3.0</td>\n",
" <td>4.00</td>\n",
" <td>0.0</td>\n",
" <td>1229.00</td>\n",
" <td>409.00</td>\n",
" <td>314.00</td>\n",
" <td>56.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Empoli</th>\n",
" <td>Empoli</td>\n",
" <td>28.00</td>\n",
" <td>47.500</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>21.00</td>\n",
" <td>11.00</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>283.00</td>\n",
" <td>253.00</td>\n",
" <td>36.0</td>\n",
" <td>2.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>1148.00</td>\n",
" <td>263.00</td>\n",
" <td>217.00</td>\n",
" <td>54.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Fiorentina</th>\n",
" <td>Fiorentina</td>\n",
" <td>28.00</td>\n",
" <td>57.200</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>23.00</td>\n",
" <td>18.00</td>\n",
" <td>2.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>307.00</td>\n",
" <td>269.00</td>\n",
" <td>59.0</td>\n",
" <td>1.0</td>\n",
" <td>4.00</td>\n",
" <td>0.0</td>\n",
" <td>1130.00</td>\n",
" <td>289.00</td>\n",
" <td>328.00</td>\n",
" <td>46.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Verona</th>\n",
" <td>Hellas Verona</td>\n",
" <td>34.00</td>\n",
" <td>42.900</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>18.00</td>\n",
" <td>15.00</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>234.00</td>\n",
" <td>315.00</td>\n",
" <td>25.0</td>\n",
" <td>1.0</td>\n",
" <td>0.00</td>\n",
" <td>2.0</td>\n",
" <td>1231.00</td>\n",
" <td>423.00</td>\n",
" <td>445.00</td>\n",
" <td>48.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Inter</th>\n",
" <td>Inter</td>\n",
" <td>23.00</td>\n",
" <td>54.500</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>40.00</td>\n",
" <td>27.00</td>\n",
" <td>2.00</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>276.00</td>\n",
" <td>248.00</td>\n",
" <td>19.0</td>\n",
" <td>2.0</td>\n",
" <td>2.00</td>\n",
" <td>1.0</td>\n",
" <td>1007.00</td>\n",
" <td>231.00</td>\n",
" <td>288.00</td>\n",
" <td>44.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Juventus</th>\n",
" <td>Juventus</td>\n",
" <td>26.00</td>\n",
" <td>49.000</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>34.00</td>\n",
" <td>26.00</td>\n",
" <td>3.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>246.00</td>\n",
" <td>242.00</td>\n",
" <td>29.0</td>\n",
" <td>0.0</td>\n",
" <td>4.00</td>\n",
" <td>0.0</td>\n",
" <td>1134.00</td>\n",
" <td>258.00</td>\n",
" <td>272.00</td>\n",
" <td>48.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lazio</th>\n",
" <td>Lazio</td>\n",
" <td>21.00</td>\n",
" <td>51.800</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>36.00</td>\n",
" <td>26.00</td>\n",
" <td>3.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>308.00</td>\n",
" <td>218.00</td>\n",
" <td>44.0</td>\n",
" <td>1.0</td>\n",
" <td>4.00</td>\n",
" <td>1.0</td>\n",
" <td>1233.00</td>\n",
" <td>218.00</td>\n",
" <td>229.00</td>\n",
" <td>48.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lecce</th>\n",
" <td>Lecce</td>\n",
" <td>26.00</td>\n",
" <td>42.400</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>20.00</td>\n",
" <td>14.00</td>\n",
" <td>1.00</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>283.00</td>\n",
" <td>300.00</td>\n",
" <td>45.0</td>\n",
" <td>3.0</td>\n",
" <td>2.00</td>\n",
" <td>2.0</td>\n",
" <td>1200.00</td>\n",
" <td>417.00</td>\n",
" <td>332.00</td>\n",
" <td>55.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Milan</th>\n",
" <td>Milan</td>\n",
" <td>27.00</td>\n",
" <td>53.500</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>36.00</td>\n",
" <td>31.00</td>\n",
" <td>2.00</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>275.00</td>\n",
" <td>261.00</td>\n",
" <td>25.0</td>\n",
" <td>4.0</td>\n",
" <td>2.00</td>\n",
" <td>2.0</td>\n",
" <td>1125.00</td>\n",
" <td>263.00</td>\n",
" <td>325.00</td>\n",
" <td>44.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Monza</th>\n",
" <td>Monza</td>\n",
" <td>29.00</td>\n",
" <td>55.000</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>27.00</td>\n",
" <td>17.00</td>\n",
" <td>4.00</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>318.00</td>\n",
" <td>281.00</td>\n",
" <td>37.0</td>\n",
" <td>0.0</td>\n",
" <td>4.00</td>\n",
" <td>1.0</td>\n",
" <td>1145.00</td>\n",
" <td>242.00</td>\n",
" <td>253.00</td>\n",
" <td>48.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Napoli</th>\n",
" <td>Napoli</td>\n",
" <td>24.00</td>\n",
" <td>61.600</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>54.00</td>\n",
" <td>42.00</td>\n",
" <td>5.00</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>298.00</td>\n",
" <td>199.00</td>\n",
" <td>28.0</td>\n",
" <td>1.0</td>\n",
" <td>5.00</td>\n",
" <td>0.0</td>\n",
" <td>1100.00</td>\n",
" <td>232.00</td>\n",
" <td>280.00</td>\n",
" <td>45.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Roma</th>\n",
" <td>Roma</td>\n",
" <td>26.00</td>\n",
" <td>49.300</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>29.00</td>\n",
" <td>19.00</td>\n",
" <td>4.00</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>316.00</td>\n",
" <td>246.00</td>\n",
" <td>12.0</td>\n",
" <td>0.0</td>\n",
" <td>6.00</td>\n",
" <td>0.0</td>\n",
" <td>1156.00</td>\n",
" <td>221.00</td>\n",
" <td>266.00</td>\n",
" <td>45.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Salernitana</th>\n",
" <td>Salernitana</td>\n",
" <td>28.00</td>\n",
" <td>46.000</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>24.00</td>\n",
" <td>16.00</td>\n",
" <td>1.00</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>252.00</td>\n",
" <td>259.00</td>\n",
" <td>57.0</td>\n",
" <td>8.0</td>\n",
" <td>1.00</td>\n",
" <td>1.0</td>\n",
" <td>1213.00</td>\n",
" <td>291.00</td>\n",
" <td>285.00</td>\n",
" <td>50.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sampdoria</th>\n",
" <td>Sampdoria</td>\n",
" <td>31.00</td>\n",
" <td>47.300</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>10.00</td>\n",
" <td>8.00</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>339.00</td>\n",
" <td>300.00</td>\n",
" <td>59.0</td>\n",
" <td>4.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>1189.00</td>\n",
" <td>362.00</td>\n",
" <td>349.00</td>\n",
" <td>50.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sassuolo</th>\n",
" <td>Sassuolo</td>\n",
" <td>29.00</td>\n",
" <td>48.700</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>25.00</td>\n",
" <td>18.00</td>\n",
" <td>4.00</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>287.00</td>\n",
" <td>206.00</td>\n",
" <td>72.0</td>\n",
" <td>2.0</td>\n",
" <td>5.00</td>\n",
" <td>1.0</td>\n",
" <td>1131.00</td>\n",
" <td>256.00</td>\n",
" <td>206.00</td>\n",
" <td>55.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Spezia</th>\n",
" <td>Spezia</td>\n",
" <td>33.00</td>\n",
" <td>45.500</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>17.00</td>\n",
" <td>10.00</td>\n",
" <td>3.00</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>235.00</td>\n",
" <td>291.00</td>\n",
" <td>53.0</td>\n",
" <td>1.0</td>\n",
" <td>3.00</td>\n",
" <td>2.0</td>\n",
" <td>1275.00</td>\n",
" <td>343.00</td>\n",
" <td>306.00</td>\n",
" <td>52.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Torino</th>\n",
" <td>Torino</td>\n",
" <td>27.00</td>\n",
" <td>53.000</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>22.00</td>\n",
" <td>17.00</td>\n",
" <td>1.00</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>239.00</td>\n",
" <td>306.00</td>\n",
" <td>24.0</td>\n",
" <td>3.0</td>\n",
" <td>1.00</td>\n",
" <td>0.0</td>\n",
" <td>1155.00</td>\n",
" <td>367.00</td>\n",
" <td>333.00</td>\n",
" <td>52.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Udinese</th>\n",
" <td>Udinese</td>\n",
" <td>25.00</td>\n",
" <td>49.900</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>29.00</td>\n",
" <td>25.00</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>282.00</td>\n",
" <td>252.00</td>\n",
" <td>34.0</td>\n",
" <td>2.0</td>\n",
" <td>0.00</td>\n",
" <td>1.0</td>\n",
" <td>1101.00</td>\n",
" <td>233.00</td>\n",
" <td>277.00</td>\n",
" <td>45.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Avg</th>\n",
" <td>Avg</td>\n",
" <td>27.25</td>\n",
" <td>49.995</td>\n",
" <td>22.0</td>\n",
" <td>242.0</td>\n",
" <td>1980.0</td>\n",
" <td>27.35</td>\n",
" <td>19.75</td>\n",
" <td>2.35</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>277.05</td>\n",
" <td>262.05</td>\n",
" <td>37.9</td>\n",
" <td>2.1</td>\n",
" <td>2.95</td>\n",
" <td>0.8</td>\n",
" <td>1172.05</td>\n",
" <td>292.05</td>\n",
" <td>292.15</td>\n",
" <td>49.82</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>21 rows × 303 columns</p>\n",
"</div>"
],
"text/plain": [
" team team_players_used team_possession team_games \\\n",
"Atalanta Atalanta 24.00 48.600 22.0 \n",
"Bologna Bologna 25.00 52.400 22.0 \n",
"Cremonese Cremonese 31.00 43.800 22.0 \n",
"Empoli Empoli 28.00 47.500 22.0 \n",
"Fiorentina Fiorentina 28.00 57.200 22.0 \n",
"Verona Hellas Verona 34.00 42.900 22.0 \n",
"Inter Inter 23.00 54.500 22.0 \n",
"Juventus Juventus 26.00 49.000 22.0 \n",
"Lazio Lazio 21.00 51.800 22.0 \n",
"Lecce Lecce 26.00 42.400 22.0 \n",
"Milan Milan 27.00 53.500 22.0 \n",
"Monza Monza 29.00 55.000 22.0 \n",
"Napoli Napoli 24.00 61.600 22.0 \n",
"Roma Roma 26.00 49.300 22.0 \n",
"Salernitana Salernitana 28.00 46.000 22.0 \n",
"Sampdoria Sampdoria 31.00 47.300 22.0 \n",
"Sassuolo Sassuolo 29.00 48.700 22.0 \n",
"Spezia Spezia 33.00 45.500 22.0 \n",
"Torino Torino 27.00 53.000 22.0 \n",
"Udinese Udinese 25.00 49.900 22.0 \n",
"Avg Avg 27.25 49.995 22.0 \n",
"\n",
" team_games_starts team_minutes team_goals team_assists \\\n",
"Atalanta 242.0 1980.0 40.00 28.00 \n",
"Bologna 242.0 1980.0 27.00 20.00 \n",
"Cremonese 242.0 1980.0 15.00 7.00 \n",
"Empoli 242.0 1980.0 21.00 11.00 \n",
"Fiorentina 242.0 1980.0 23.00 18.00 \n",
"Verona 242.0 1980.0 18.00 15.00 \n",
"Inter 242.0 1980.0 40.00 27.00 \n",
"Juventus 242.0 1980.0 34.00 26.00 \n",
"Lazio 242.0 1980.0 36.00 26.00 \n",
"Lecce 242.0 1980.0 20.00 14.00 \n",
"Milan 242.0 1980.0 36.00 31.00 \n",
"Monza 242.0 1980.0 27.00 17.00 \n",
"Napoli 242.0 1980.0 54.00 42.00 \n",
"Roma 242.0 1980.0 29.00 19.00 \n",
"Salernitana 242.0 1980.0 24.00 16.00 \n",
"Sampdoria 242.0 1980.0 10.00 8.00 \n",
"Sassuolo 242.0 1980.0 25.00 18.00 \n",
"Spezia 242.0 1980.0 17.00 10.00 \n",
"Torino 242.0 1980.0 22.00 17.00 \n",
"Udinese 242.0 1980.0 29.00 25.00 \n",
"Avg 242.0 1980.0 27.35 19.75 \n",
"\n",
" team_pens_made team_pens_att ... vs_team_fouls \\\n",
"Atalanta 6.00 8.0 ... 244.00 \n",
"Bologna 4.00 4.0 ... 280.00 \n",
"Cremonese 2.00 4.0 ... 239.00 \n",
"Empoli 0.00 0.0 ... 283.00 \n",
"Fiorentina 2.00 4.0 ... 307.00 \n",
"Verona 0.00 0.0 ... 234.00 \n",
"Inter 2.00 2.0 ... 276.00 \n",
"Juventus 3.00 4.0 ... 246.00 \n",
"Lazio 3.00 4.0 ... 308.00 \n",
"Lecce 1.00 2.0 ... 283.00 \n",
"Milan 2.00 2.0 ... 275.00 \n",
"Monza 4.00 4.0 ... 318.00 \n",
"Napoli 5.00 6.0 ... 298.00 \n",
"Roma 4.00 6.0 ... 316.00 \n",
"Salernitana 1.00 1.0 ... 252.00 \n",
"Sampdoria 0.00 0.0 ... 339.00 \n",
"Sassuolo 4.00 5.0 ... 287.00 \n",
"Spezia 3.00 3.0 ... 235.00 \n",
"Torino 1.00 1.0 ... 239.00 \n",
"Udinese 0.00 0.0 ... 282.00 \n",
"Avg 2.35 3.0 ... 277.05 \n",
"\n",
" vs_team_fouled vs_team_offsides vs_team_pens_won \\\n",
"Atalanta 256.00 26.0 1.0 \n",
"Bologna 268.00 38.0 3.0 \n",
"Cremonese 271.00 36.0 3.0 \n",
"Empoli 253.00 36.0 2.0 \n",
"Fiorentina 269.00 59.0 1.0 \n",
"Verona 315.00 25.0 1.0 \n",
"Inter 248.00 19.0 2.0 \n",
"Juventus 242.00 29.0 0.0 \n",
"Lazio 218.00 44.0 1.0 \n",
"Lecce 300.00 45.0 3.0 \n",
"Milan 261.00 25.0 4.0 \n",
"Monza 281.00 37.0 0.0 \n",
"Napoli 199.00 28.0 1.0 \n",
"Roma 246.00 12.0 0.0 \n",
"Salernitana 259.00 57.0 8.0 \n",
"Sampdoria 300.00 59.0 4.0 \n",
"Sassuolo 206.00 72.0 2.0 \n",
"Spezia 291.00 53.0 1.0 \n",
"Torino 306.00 24.0 3.0 \n",
"Udinese 252.00 34.0 2.0 \n",
"Avg 262.05 37.9 2.1 \n",
"\n",
" vs_team_pens_conceded vs_team_own_goals \\\n",
"Atalanta 8.00 1.0 \n",
"Bologna 4.00 1.0 \n",
"Cremonese 4.00 0.0 \n",
"Empoli 0.00 0.0 \n",
"Fiorentina 4.00 0.0 \n",
"Verona 0.00 2.0 \n",
"Inter 2.00 1.0 \n",
"Juventus 4.00 0.0 \n",
"Lazio 4.00 1.0 \n",
"Lecce 2.00 2.0 \n",
"Milan 2.00 2.0 \n",
"Monza 4.00 1.0 \n",
"Napoli 5.00 0.0 \n",
"Roma 6.00 0.0 \n",
"Salernitana 1.00 1.0 \n",
"Sampdoria 0.00 0.0 \n",
"Sassuolo 5.00 1.0 \n",
"Spezia 3.00 2.0 \n",
"Torino 1.00 0.0 \n",
"Udinese 0.00 1.0 \n",
"Avg 2.95 0.8 \n",
"\n",
" vs_team_ball_recoveries vs_team_aerials_won \\\n",
"Atalanta 1335.00 273.00 \n",
"Bologna 1204.00 250.00 \n",
"Cremonese 1229.00 409.00 \n",
"Empoli 1148.00 263.00 \n",
"Fiorentina 1130.00 289.00 \n",
"Verona 1231.00 423.00 \n",
"Inter 1007.00 231.00 \n",
"Juventus 1134.00 258.00 \n",
"Lazio 1233.00 218.00 \n",
"Lecce 1200.00 417.00 \n",
"Milan 1125.00 263.00 \n",
"Monza 1145.00 242.00 \n",
"Napoli 1100.00 232.00 \n",
"Roma 1156.00 221.00 \n",
"Salernitana 1213.00 291.00 \n",
"Sampdoria 1189.00 362.00 \n",
"Sassuolo 1131.00 256.00 \n",
"Spezia 1275.00 343.00 \n",
"Torino 1155.00 367.00 \n",
"Udinese 1101.00 233.00 \n",
"Avg 1172.05 292.05 \n",
"\n",
" vs_team_aerials_lost vs_team_aerials_won_pct \n",
"Atalanta 328.00 45.40 \n",
"Bologna 210.00 54.30 \n",
"Cremonese 314.00 56.60 \n",
"Empoli 217.00 54.80 \n",
"Fiorentina 328.00 46.80 \n",
"Verona 445.00 48.70 \n",
"Inter 288.00 44.50 \n",
"Juventus 272.00 48.70 \n",
"Lazio 229.00 48.80 \n",
"Lecce 332.00 55.70 \n",
"Milan 325.00 44.70 \n",
"Monza 253.00 48.90 \n",
"Napoli 280.00 45.30 \n",
"Roma 266.00 45.40 \n",
"Salernitana 285.00 50.50 \n",
"Sampdoria 349.00 50.90 \n",
"Sassuolo 206.00 55.40 \n",
"Spezia 306.00 52.90 \n",
"Torino 333.00 52.40 \n",
"Udinese 277.00 45.70 \n",
"Avg 292.15 49.82 \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": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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": 19,
"id": "8aad9652",
"metadata": {},
"outputs": [],
"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": 20,
"id": "4e2bf9dc",
"metadata": {},
"outputs": [],
"source": [
"def sample_predict(X, iterations = 100):\n",
" y = np.zeros((2, X.shape[0]))\n",
" \n",
" dist = modelb(X)\n",
" \n",
" for i in range(iterations):\n",
" y[0, :] += dist[0].sample()\n",
" y[1, :] += dist[1].sample()\n",
" \n",
" return y.transpose() / iterations\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "c2674211",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.14539483185579238\n",
"0.16229047232752447\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.13160209075894191\n",
"0.16563346611529572\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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": 48,
"id": "41e7e1ee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/2500\n",
"9/9 [==============================] - 4s 92ms/step - loss: 105.9979 - distribution_lambda_21_loss: 99.1596 - distribution_lambda_22_loss: 5.7268 - distribution_lambda_23_loss: 1.1114 - val_loss: 85.6839 - val_distribution_lambda_21_loss: 79.7444 - val_distribution_lambda_22_loss: 4.8681 - val_distribution_lambda_23_loss: 1.0713\n",
"Epoch 2/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 78.7734 - distribution_lambda_21_loss: 72.8187 - distribution_lambda_22_loss: 4.8669 - distribution_lambda_23_loss: 1.0879 - val_loss: 63.5727 - val_distribution_lambda_21_loss: 58.3870 - val_distribution_lambda_22_loss: 4.1357 - val_distribution_lambda_23_loss: 1.0500\n",
"Epoch 3/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 59.3165 - distribution_lambda_21_loss: 54.1085 - distribution_lambda_22_loss: 4.1424 - distribution_lambda_23_loss: 1.0655 - val_loss: 48.0409 - val_distribution_lambda_21_loss: 43.4830 - val_distribution_lambda_22_loss: 3.5318 - val_distribution_lambda_23_loss: 1.0260\n",
"Epoch 4/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 45.1089 - distribution_lambda_21_loss: 40.5643 - distribution_lambda_22_loss: 3.4981 - distribution_lambda_23_loss: 1.0466 - val_loss: 37.6652 - val_distribution_lambda_21_loss: 33.5340 - val_distribution_lambda_22_loss: 3.1345 - val_distribution_lambda_23_loss: 0.9967\n",
"Epoch 5/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 36.3207 - distribution_lambda_21_loss: 32.1626 - distribution_lambda_22_loss: 3.1592 - distribution_lambda_23_loss: 0.9990 - val_loss: 30.6755 - val_distribution_lambda_21_loss: 26.8368 - val_distribution_lambda_22_loss: 2.8735 - val_distribution_lambda_23_loss: 0.9652\n",
"Epoch 6/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 30.0433 - distribution_lambda_21_loss: 26.1435 - distribution_lambda_22_loss: 2.9074 - distribution_lambda_23_loss: 0.9924 - val_loss: 25.8243 - val_distribution_lambda_21_loss: 22.1859 - val_distribution_lambda_22_loss: 2.7075 - val_distribution_lambda_23_loss: 0.9309\n",
"Epoch 7/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 25.5853 - distribution_lambda_21_loss: 21.8961 - distribution_lambda_22_loss: 2.7424 - distribution_lambda_23_loss: 0.9468 - val_loss: 22.3435 - val_distribution_lambda_21_loss: 18.8484 - val_distribution_lambda_22_loss: 2.5991 - val_distribution_lambda_23_loss: 0.8960\n",
"Epoch 8/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 22.2391 - distribution_lambda_21_loss: 18.7085 - distribution_lambda_22_loss: 2.6146 - distribution_lambda_23_loss: 0.9160 - val_loss: 19.7279 - val_distribution_lambda_21_loss: 16.3430 - val_distribution_lambda_22_loss: 2.5234 - val_distribution_lambda_23_loss: 0.8615\n",
"Epoch 9/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 19.7891 - distribution_lambda_21_loss: 16.3677 - distribution_lambda_22_loss: 2.5346 - distribution_lambda_23_loss: 0.8867 - val_loss: 17.6639 - val_distribution_lambda_21_loss: 14.3678 - val_distribution_lambda_22_loss: 2.4684 - val_distribution_lambda_23_loss: 0.8277\n",
"Epoch 10/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 17.8097 - distribution_lambda_21_loss: 14.4868 - distribution_lambda_22_loss: 2.4627 - distribution_lambda_23_loss: 0.8602 - val_loss: 16.0307 - val_distribution_lambda_21_loss: 12.8070 - val_distribution_lambda_22_loss: 2.4279 - val_distribution_lambda_23_loss: 0.7958\n",
"Epoch 11/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 16.3632 - distribution_lambda_21_loss: 13.1148 - distribution_lambda_22_loss: 2.4236 - distribution_lambda_23_loss: 0.8248 - val_loss: 14.6871 - val_distribution_lambda_21_loss: 11.5260 - val_distribution_lambda_22_loss: 2.3953 - val_distribution_lambda_23_loss: 0.7657\n",
"Epoch 12/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 15.1242 - distribution_lambda_21_loss: 11.9372 - distribution_lambda_22_loss: 2.3933 - distribution_lambda_23_loss: 0.7937 - val_loss: 13.5635 - val_distribution_lambda_21_loss: 10.4565 - val_distribution_lambda_22_loss: 2.3686 - val_distribution_lambda_23_loss: 0.7383\n",
"Epoch 13/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 14.0484 - distribution_lambda_21_loss: 10.9176 - distribution_lambda_22_loss: 2.3586 - distribution_lambda_23_loss: 0.7722 - val_loss: 12.6253 - val_distribution_lambda_21_loss: 9.5670 - val_distribution_lambda_22_loss: 2.3459 - val_distribution_lambda_23_loss: 0.7124\n",
"Epoch 14/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 12.9538 - distribution_lambda_21_loss: 9.8800 - distribution_lambda_22_loss: 2.3146 - distribution_lambda_23_loss: 0.7592 - val_loss: 11.8338 - val_distribution_lambda_21_loss: 8.8172 - val_distribution_lambda_22_loss: 2.3259 - val_distribution_lambda_23_loss: 0.6906\n",
"Epoch 15/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 12.2002 - distribution_lambda_21_loss: 9.1799 - distribution_lambda_22_loss: 2.2893 - distribution_lambda_23_loss: 0.7309 - val_loss: 11.1579 - val_distribution_lambda_21_loss: 8.1779 - val_distribution_lambda_22_loss: 2.3086 - val_distribution_lambda_23_loss: 0.6713\n",
"Epoch 16/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 11.4904 - distribution_lambda_21_loss: 8.5120 - distribution_lambda_22_loss: 2.2737 - distribution_lambda_23_loss: 0.7046 - val_loss: 10.5751 - val_distribution_lambda_21_loss: 7.6283 - val_distribution_lambda_22_loss: 2.2929 - val_distribution_lambda_23_loss: 0.6539\n",
"Epoch 17/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 10.8519 - distribution_lambda_21_loss: 7.8997 - distribution_lambda_22_loss: 2.2509 - distribution_lambda_23_loss: 0.7013 - val_loss: 10.0686 - val_distribution_lambda_21_loss: 7.1506 - val_distribution_lambda_22_loss: 2.2795 - val_distribution_lambda_23_loss: 0.6384\n",
"Epoch 18/2500\n",
"9/9 [==============================] - 0s 9ms/step - loss: 10.4668 - distribution_lambda_21_loss: 7.5402 - distribution_lambda_22_loss: 2.2457 - distribution_lambda_23_loss: 0.6809 - val_loss: 9.6223 - val_distribution_lambda_21_loss: 6.7302 - val_distribution_lambda_22_loss: 2.2674 - val_distribution_lambda_23_loss: 0.6247\n",
"Epoch 19/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 9.9741 - distribution_lambda_21_loss: 7.0720 - distribution_lambda_22_loss: 2.2290 - distribution_lambda_23_loss: 0.6732 - val_loss: 9.2232 - val_distribution_lambda_21_loss: 6.3542 - val_distribution_lambda_22_loss: 2.2564 - val_distribution_lambda_23_loss: 0.6126\n",
"Epoch 20/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 9.6570 - distribution_lambda_21_loss: 6.7690 - distribution_lambda_22_loss: 2.2201 - distribution_lambda_23_loss: 0.6680 - val_loss: 8.8727 - val_distribution_lambda_21_loss: 6.0233 - val_distribution_lambda_22_loss: 2.2463 - val_distribution_lambda_23_loss: 0.6031\n",
"Epoch 21/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 9.1742 - distribution_lambda_21_loss: 6.3275 - distribution_lambda_22_loss: 2.1976 - distribution_lambda_23_loss: 0.6491 - val_loss: 8.5593 - val_distribution_lambda_21_loss: 5.7278 - val_distribution_lambda_22_loss: 2.2370 - val_distribution_lambda_23_loss: 0.5945\n",
"Epoch 22/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 8.9076 - distribution_lambda_21_loss: 6.0645 - distribution_lambda_22_loss: 2.1787 - distribution_lambda_23_loss: 0.6644 - val_loss: 8.2789 - val_distribution_lambda_21_loss: 5.4624 - val_distribution_lambda_22_loss: 2.2286 - val_distribution_lambda_23_loss: 0.5879\n",
"Epoch 23/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 8.5358 - distribution_lambda_21_loss: 5.7052 - distribution_lambda_22_loss: 2.1787 - distribution_lambda_23_loss: 0.6519 - val_loss: 8.0257 - val_distribution_lambda_21_loss: 5.2236 - val_distribution_lambda_22_loss: 2.2205 - val_distribution_lambda_23_loss: 0.5816\n",
"Epoch 24/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 8.4028 - distribution_lambda_21_loss: 5.5807 - distribution_lambda_22_loss: 2.1705 - distribution_lambda_23_loss: 0.6516 - val_loss: 7.7929 - val_distribution_lambda_21_loss: 5.0043 - val_distribution_lambda_22_loss: 2.2129 - val_distribution_lambda_23_loss: 0.5758\n",
"Epoch 25/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 8ms/step - loss: 7.9928 - distribution_lambda_21_loss: 5.2062 - distribution_lambda_22_loss: 2.1347 - distribution_lambda_23_loss: 0.6519 - val_loss: 7.5821 - val_distribution_lambda_21_loss: 4.8055 - val_distribution_lambda_22_loss: 2.2062 - val_distribution_lambda_23_loss: 0.5704\n",
"Epoch 26/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 7.8182 - distribution_lambda_21_loss: 5.0559 - distribution_lambda_22_loss: 2.1282 - distribution_lambda_23_loss: 0.6342 - val_loss: 7.3876 - val_distribution_lambda_21_loss: 4.6212 - val_distribution_lambda_22_loss: 2.2002 - val_distribution_lambda_23_loss: 0.5661\n",
"Epoch 27/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 7.7128 - distribution_lambda_21_loss: 4.9529 - distribution_lambda_22_loss: 2.1422 - distribution_lambda_23_loss: 0.6178 - val_loss: 7.2065 - val_distribution_lambda_21_loss: 4.4503 - val_distribution_lambda_22_loss: 2.1940 - val_distribution_lambda_23_loss: 0.5623\n",
"Epoch 28/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 7.4002 - distribution_lambda_21_loss: 4.6500 - distribution_lambda_22_loss: 2.1165 - distribution_lambda_23_loss: 0.6336 - val_loss: 7.0442 - val_distribution_lambda_21_loss: 4.2971 - val_distribution_lambda_22_loss: 2.1883 - val_distribution_lambda_23_loss: 0.5589\n",
"Epoch 29/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 7.2548 - distribution_lambda_21_loss: 4.5241 - distribution_lambda_22_loss: 2.1095 - distribution_lambda_23_loss: 0.6212 - val_loss: 6.8956 - val_distribution_lambda_21_loss: 4.1569 - val_distribution_lambda_22_loss: 2.1828 - val_distribution_lambda_23_loss: 0.5559\n",
"Epoch 30/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 7.1770 - distribution_lambda_21_loss: 4.4404 - distribution_lambda_22_loss: 2.1102 - distribution_lambda_23_loss: 0.6263 - val_loss: 6.7581 - val_distribution_lambda_21_loss: 4.0280 - val_distribution_lambda_22_loss: 2.1772 - val_distribution_lambda_23_loss: 0.5529\n",
"Epoch 31/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 6.9895 - distribution_lambda_21_loss: 4.2876 - distribution_lambda_22_loss: 2.0909 - distribution_lambda_23_loss: 0.6111 - val_loss: 6.6330 - val_distribution_lambda_21_loss: 3.9108 - val_distribution_lambda_22_loss: 2.1718 - val_distribution_lambda_23_loss: 0.5505\n",
"Epoch 32/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 6.8257 - distribution_lambda_21_loss: 4.1273 - distribution_lambda_22_loss: 2.0803 - distribution_lambda_23_loss: 0.6181 - val_loss: 6.5196 - val_distribution_lambda_21_loss: 3.8050 - val_distribution_lambda_22_loss: 2.1666 - val_distribution_lambda_23_loss: 0.5480\n",
"Epoch 33/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 6.7505 - distribution_lambda_21_loss: 4.0401 - distribution_lambda_22_loss: 2.0864 - distribution_lambda_23_loss: 0.6239 - val_loss: 6.4166 - val_distribution_lambda_21_loss: 3.7090 - val_distribution_lambda_22_loss: 2.1614 - val_distribution_lambda_23_loss: 0.5462\n",
"Epoch 34/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.6118 - distribution_lambda_21_loss: 3.9332 - distribution_lambda_22_loss: 2.0693 - distribution_lambda_23_loss: 0.6093 - val_loss: 6.3249 - val_distribution_lambda_21_loss: 3.6238 - val_distribution_lambda_22_loss: 2.1566 - val_distribution_lambda_23_loss: 0.5446\n",
"Epoch 35/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.4325 - distribution_lambda_21_loss: 3.7742 - distribution_lambda_22_loss: 2.0541 - distribution_lambda_23_loss: 0.6041 - val_loss: 6.2434 - val_distribution_lambda_21_loss: 3.5486 - val_distribution_lambda_22_loss: 2.1521 - val_distribution_lambda_23_loss: 0.5428\n",
"Epoch 36/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.3696 - distribution_lambda_21_loss: 3.7154 - distribution_lambda_22_loss: 2.0558 - distribution_lambda_23_loss: 0.5984 - val_loss: 6.1683 - val_distribution_lambda_21_loss: 3.4798 - val_distribution_lambda_22_loss: 2.1472 - val_distribution_lambda_23_loss: 0.5413\n",
"Epoch 37/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 6.3098 - distribution_lambda_21_loss: 3.6503 - distribution_lambda_22_loss: 2.0563 - distribution_lambda_23_loss: 0.6032 - val_loss: 6.0985 - val_distribution_lambda_21_loss: 3.4167 - val_distribution_lambda_22_loss: 2.1418 - val_distribution_lambda_23_loss: 0.5399\n",
"Epoch 38/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.2258 - distribution_lambda_21_loss: 3.5802 - distribution_lambda_22_loss: 2.0415 - distribution_lambda_23_loss: 0.6041 - val_loss: 6.0338 - val_distribution_lambda_21_loss: 3.3590 - val_distribution_lambda_22_loss: 2.1360 - val_distribution_lambda_23_loss: 0.5389\n",
"Epoch 39/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.1506 - distribution_lambda_21_loss: 3.5101 - distribution_lambda_22_loss: 2.0366 - distribution_lambda_23_loss: 0.6038 - val_loss: 5.9750 - val_distribution_lambda_21_loss: 3.3062 - val_distribution_lambda_22_loss: 2.1308 - val_distribution_lambda_23_loss: 0.5379\n",
"Epoch 40/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.1343 - distribution_lambda_21_loss: 3.4843 - distribution_lambda_22_loss: 2.0372 - distribution_lambda_23_loss: 0.6128 - val_loss: 5.9197 - val_distribution_lambda_21_loss: 3.2571 - val_distribution_lambda_22_loss: 2.1254 - val_distribution_lambda_23_loss: 0.5372\n",
"Epoch 41/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 6.0310 - distribution_lambda_21_loss: 3.4096 - distribution_lambda_22_loss: 2.0239 - distribution_lambda_23_loss: 0.5975 - val_loss: 5.8688 - val_distribution_lambda_21_loss: 3.2121 - val_distribution_lambda_22_loss: 2.1202 - val_distribution_lambda_23_loss: 0.5365\n",
"Epoch 42/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.9923 - distribution_lambda_21_loss: 3.3726 - distribution_lambda_22_loss: 2.0239 - distribution_lambda_23_loss: 0.5958 - val_loss: 5.8208 - val_distribution_lambda_21_loss: 3.1700 - val_distribution_lambda_22_loss: 2.1150 - val_distribution_lambda_23_loss: 0.5358\n",
"Epoch 43/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.9203 - distribution_lambda_21_loss: 3.3229 - distribution_lambda_22_loss: 2.0137 - distribution_lambda_23_loss: 0.5837 - val_loss: 5.7753 - val_distribution_lambda_21_loss: 3.1307 - val_distribution_lambda_22_loss: 2.1094 - val_distribution_lambda_23_loss: 0.5352\n",
"Epoch 44/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.8580 - distribution_lambda_21_loss: 3.2589 - distribution_lambda_22_loss: 1.9993 - distribution_lambda_23_loss: 0.5999 - val_loss: 5.7338 - val_distribution_lambda_21_loss: 3.0947 - val_distribution_lambda_22_loss: 2.1043 - val_distribution_lambda_23_loss: 0.5348\n",
"Epoch 45/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.7954 - distribution_lambda_21_loss: 3.1941 - distribution_lambda_22_loss: 1.9937 - distribution_lambda_23_loss: 0.6075 - val_loss: 5.6946 - val_distribution_lambda_21_loss: 3.0612 - val_distribution_lambda_22_loss: 2.0991 - val_distribution_lambda_23_loss: 0.5342\n",
"Epoch 46/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 5.7733 - distribution_lambda_21_loss: 3.1895 - distribution_lambda_22_loss: 1.9894 - distribution_lambda_23_loss: 0.5943 - val_loss: 5.6568 - val_distribution_lambda_21_loss: 3.0296 - val_distribution_lambda_22_loss: 2.0935 - val_distribution_lambda_23_loss: 0.5337\n",
"Epoch 47/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.6955 - distribution_lambda_21_loss: 3.1222 - distribution_lambda_22_loss: 1.9767 - distribution_lambda_23_loss: 0.5965 - val_loss: 5.6208 - val_distribution_lambda_21_loss: 2.9999 - val_distribution_lambda_22_loss: 2.0879 - val_distribution_lambda_23_loss: 0.5330\n",
"Epoch 48/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.6881 - distribution_lambda_21_loss: 3.1119 - distribution_lambda_22_loss: 1.9775 - distribution_lambda_23_loss: 0.5987 - val_loss: 5.5863 - val_distribution_lambda_21_loss: 2.9714 - val_distribution_lambda_22_loss: 2.0824 - val_distribution_lambda_23_loss: 0.5325\n",
"Epoch 49/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 5.6101 - distribution_lambda_21_loss: 3.0519 - distribution_lambda_22_loss: 1.9617 - distribution_lambda_23_loss: 0.5965 - val_loss: 5.5540 - val_distribution_lambda_21_loss: 2.9446 - val_distribution_lambda_22_loss: 2.0774 - val_distribution_lambda_23_loss: 0.5320\n",
"Epoch 50/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.6327 - distribution_lambda_21_loss: 3.0776 - distribution_lambda_22_loss: 1.9589 - distribution_lambda_23_loss: 0.5963 - val_loss: 5.5222 - val_distribution_lambda_21_loss: 2.9184 - val_distribution_lambda_22_loss: 2.0725 - val_distribution_lambda_23_loss: 0.5313\n",
"Epoch 51/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.5639 - distribution_lambda_21_loss: 3.0150 - distribution_lambda_22_loss: 1.9560 - distribution_lambda_23_loss: 0.5928 - val_loss: 5.4911 - val_distribution_lambda_21_loss: 2.8936 - val_distribution_lambda_22_loss: 2.0670 - val_distribution_lambda_23_loss: 0.5305\n",
"Epoch 52/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.5253 - distribution_lambda_21_loss: 2.9883 - distribution_lambda_22_loss: 1.9436 - distribution_lambda_23_loss: 0.5933 - val_loss: 5.4618 - val_distribution_lambda_21_loss: 2.8699 - val_distribution_lambda_22_loss: 2.0619 - val_distribution_lambda_23_loss: 0.5300\n",
"Epoch 53/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.4855 - distribution_lambda_21_loss: 2.9541 - distribution_lambda_22_loss: 1.9366 - distribution_lambda_23_loss: 0.5948 - val_loss: 5.4334 - val_distribution_lambda_21_loss: 2.8472 - val_distribution_lambda_22_loss: 2.0565 - val_distribution_lambda_23_loss: 0.5297\n",
"Epoch 54/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.4553 - distribution_lambda_21_loss: 2.9255 - distribution_lambda_22_loss: 1.9343 - distribution_lambda_23_loss: 0.5955 - val_loss: 5.4053 - val_distribution_lambda_21_loss: 2.8253 - val_distribution_lambda_22_loss: 2.0504 - val_distribution_lambda_23_loss: 0.5296\n",
"Epoch 55/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.4078 - distribution_lambda_21_loss: 2.9006 - distribution_lambda_22_loss: 1.9204 - distribution_lambda_23_loss: 0.5867 - val_loss: 5.3775 - val_distribution_lambda_21_loss: 2.8037 - val_distribution_lambda_22_loss: 2.0444 - val_distribution_lambda_23_loss: 0.5294\n",
"Epoch 56/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.4246 - distribution_lambda_21_loss: 2.9127 - distribution_lambda_22_loss: 1.9143 - distribution_lambda_23_loss: 0.5975 - val_loss: 5.3503 - val_distribution_lambda_21_loss: 2.7818 - val_distribution_lambda_22_loss: 2.0390 - val_distribution_lambda_23_loss: 0.5296\n",
"Epoch 57/2500\n",
"9/9 [==============================] - 0s 9ms/step - loss: 5.3840 - distribution_lambda_21_loss: 2.8874 - distribution_lambda_22_loss: 1.9077 - distribution_lambda_23_loss: 0.5890 - val_loss: 5.3198 - val_distribution_lambda_21_loss: 2.7601 - val_distribution_lambda_22_loss: 2.0303 - val_distribution_lambda_23_loss: 0.5294\n",
"Epoch 58/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 5.3309 - distribution_lambda_21_loss: 2.8348 - distribution_lambda_22_loss: 1.9033 - distribution_lambda_23_loss: 0.5928 - val_loss: 5.2913 - val_distribution_lambda_21_loss: 2.7388 - val_distribution_lambda_22_loss: 2.0236 - val_distribution_lambda_23_loss: 0.5289\n",
"Epoch 59/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.2624 - distribution_lambda_21_loss: 2.7902 - distribution_lambda_22_loss: 1.8949 - distribution_lambda_23_loss: 0.5773 - val_loss: 5.2639 - val_distribution_lambda_21_loss: 2.7180 - val_distribution_lambda_22_loss: 2.0177 - val_distribution_lambda_23_loss: 0.5283\n",
"Epoch 60/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.2548 - distribution_lambda_21_loss: 2.7808 - distribution_lambda_22_loss: 1.8888 - distribution_lambda_23_loss: 0.5851 - val_loss: 5.2368 - val_distribution_lambda_21_loss: 2.6968 - val_distribution_lambda_22_loss: 2.0122 - val_distribution_lambda_23_loss: 0.5279\n",
"Epoch 61/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.2165 - distribution_lambda_21_loss: 2.7734 - distribution_lambda_22_loss: 1.8733 - distribution_lambda_23_loss: 0.5697 - val_loss: 5.2109 - val_distribution_lambda_21_loss: 2.6752 - val_distribution_lambda_22_loss: 2.0083 - val_distribution_lambda_23_loss: 0.5274\n",
"Epoch 62/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.2068 - distribution_lambda_21_loss: 2.7475 - distribution_lambda_22_loss: 1.8764 - distribution_lambda_23_loss: 0.5829 - val_loss: 5.1847 - val_distribution_lambda_21_loss: 2.6537 - val_distribution_lambda_22_loss: 2.0039 - val_distribution_lambda_23_loss: 0.5271\n",
"Epoch 63/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.1724 - distribution_lambda_21_loss: 2.7130 - distribution_lambda_22_loss: 1.8680 - distribution_lambda_23_loss: 0.5913 - val_loss: 5.1578 - val_distribution_lambda_21_loss: 2.6314 - val_distribution_lambda_22_loss: 1.9995 - val_distribution_lambda_23_loss: 0.5269\n",
"Epoch 64/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.1202 - distribution_lambda_21_loss: 2.6835 - distribution_lambda_22_loss: 1.8437 - distribution_lambda_23_loss: 0.5930 - val_loss: 5.1296 - val_distribution_lambda_21_loss: 2.6095 - val_distribution_lambda_22_loss: 1.9932 - val_distribution_lambda_23_loss: 0.5269\n",
"Epoch 65/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 5.1123 - distribution_lambda_21_loss: 2.6680 - distribution_lambda_22_loss: 1.8541 - distribution_lambda_23_loss: 0.5902 - val_loss: 5.1007 - val_distribution_lambda_21_loss: 2.5870 - val_distribution_lambda_22_loss: 1.9869 - val_distribution_lambda_23_loss: 0.5268\n",
"Epoch 66/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.0831 - distribution_lambda_21_loss: 2.6541 - distribution_lambda_22_loss: 1.8444 - distribution_lambda_23_loss: 0.5846 - val_loss: 5.0679 - val_distribution_lambda_21_loss: 2.5642 - val_distribution_lambda_22_loss: 1.9773 - val_distribution_lambda_23_loss: 0.5264\n",
"Epoch 67/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.0532 - distribution_lambda_21_loss: 2.6333 - distribution_lambda_22_loss: 1.8254 - distribution_lambda_23_loss: 0.5945 - val_loss: 5.0383 - val_distribution_lambda_21_loss: 2.5415 - val_distribution_lambda_22_loss: 1.9708 - val_distribution_lambda_23_loss: 0.5260\n",
"Epoch 68/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 5.0339 - distribution_lambda_21_loss: 2.6105 - distribution_lambda_22_loss: 1.8396 - distribution_lambda_23_loss: 0.5838 - val_loss: 5.0107 - val_distribution_lambda_21_loss: 2.5194 - val_distribution_lambda_22_loss: 1.9655 - val_distribution_lambda_23_loss: 0.5258\n",
"Epoch 69/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.9953 - distribution_lambda_21_loss: 2.5868 - distribution_lambda_22_loss: 1.8247 - distribution_lambda_23_loss: 0.5837 - val_loss: 4.9836 - val_distribution_lambda_21_loss: 2.4974 - val_distribution_lambda_22_loss: 1.9607 - val_distribution_lambda_23_loss: 0.5255\n",
"Epoch 70/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.9511 - distribution_lambda_21_loss: 2.5448 - distribution_lambda_22_loss: 1.8202 - distribution_lambda_23_loss: 0.5861 - val_loss: 4.9589 - val_distribution_lambda_21_loss: 2.4773 - val_distribution_lambda_22_loss: 1.9563 - val_distribution_lambda_23_loss: 0.5253\n",
"Epoch 71/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.9208 - distribution_lambda_21_loss: 2.5329 - distribution_lambda_22_loss: 1.8046 - distribution_lambda_23_loss: 0.5833 - val_loss: 4.9375 - val_distribution_lambda_21_loss: 2.4599 - val_distribution_lambda_22_loss: 1.9524 - val_distribution_lambda_23_loss: 0.5251\n",
"Epoch 72/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.8908 - distribution_lambda_21_loss: 2.5111 - distribution_lambda_22_loss: 1.7971 - distribution_lambda_23_loss: 0.5827 - val_loss: 4.9146 - val_distribution_lambda_21_loss: 2.4448 - val_distribution_lambda_22_loss: 1.9446 - val_distribution_lambda_23_loss: 0.5252\n",
"Epoch 73/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 4.9349 - distribution_lambda_21_loss: 2.5340 - distribution_lambda_22_loss: 1.8105 - distribution_lambda_23_loss: 0.5903 - val_loss: 4.8940 - val_distribution_lambda_21_loss: 2.4307 - val_distribution_lambda_22_loss: 1.9382 - val_distribution_lambda_23_loss: 0.5251\n",
"Epoch 74/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.8707 - distribution_lambda_21_loss: 2.4844 - distribution_lambda_22_loss: 1.8005 - distribution_lambda_23_loss: 0.5858 - val_loss: 4.8764 - val_distribution_lambda_21_loss: 2.4185 - val_distribution_lambda_22_loss: 1.9326 - val_distribution_lambda_23_loss: 0.5253\n",
"Epoch 75/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.8535 - distribution_lambda_21_loss: 2.4736 - distribution_lambda_22_loss: 1.7936 - distribution_lambda_23_loss: 0.5863 - val_loss: 4.8603 - val_distribution_lambda_21_loss: 2.4076 - val_distribution_lambda_22_loss: 1.9277 - val_distribution_lambda_23_loss: 0.5250\n",
"Epoch 76/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.8568 - distribution_lambda_21_loss: 2.4885 - distribution_lambda_22_loss: 1.7881 - distribution_lambda_23_loss: 0.5802 - val_loss: 4.8464 - val_distribution_lambda_21_loss: 2.3978 - val_distribution_lambda_22_loss: 1.9241 - val_distribution_lambda_23_loss: 0.5245\n",
"Epoch 77/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.8119 - distribution_lambda_21_loss: 2.4553 - distribution_lambda_22_loss: 1.7746 - distribution_lambda_23_loss: 0.5821 - val_loss: 4.8342 - val_distribution_lambda_21_loss: 2.3891 - val_distribution_lambda_22_loss: 1.9211 - val_distribution_lambda_23_loss: 0.5240\n",
"Epoch 78/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.8140 - distribution_lambda_21_loss: 2.4573 - distribution_lambda_22_loss: 1.7739 - distribution_lambda_23_loss: 0.5828 - val_loss: 4.8199 - val_distribution_lambda_21_loss: 2.3811 - val_distribution_lambda_22_loss: 1.9150 - val_distribution_lambda_23_loss: 0.5238\n",
"Epoch 79/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.8036 - distribution_lambda_21_loss: 2.4506 - distribution_lambda_22_loss: 1.7722 - distribution_lambda_23_loss: 0.5808 - val_loss: 4.8069 - val_distribution_lambda_21_loss: 2.3739 - val_distribution_lambda_22_loss: 1.9096 - val_distribution_lambda_23_loss: 0.5235\n",
"Epoch 80/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7941 - distribution_lambda_21_loss: 2.4430 - distribution_lambda_22_loss: 1.7710 - distribution_lambda_23_loss: 0.5802 - val_loss: 4.7949 - val_distribution_lambda_21_loss: 2.3673 - val_distribution_lambda_22_loss: 1.9045 - val_distribution_lambda_23_loss: 0.5232\n",
"Epoch 81/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7763 - distribution_lambda_21_loss: 2.4231 - distribution_lambda_22_loss: 1.7636 - distribution_lambda_23_loss: 0.5896 - val_loss: 4.7830 - val_distribution_lambda_21_loss: 2.3612 - val_distribution_lambda_22_loss: 1.8990 - val_distribution_lambda_23_loss: 0.5228\n",
"Epoch 82/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7386 - distribution_lambda_21_loss: 2.4028 - distribution_lambda_22_loss: 1.7584 - distribution_lambda_23_loss: 0.5774 - val_loss: 4.7718 - val_distribution_lambda_21_loss: 2.3556 - val_distribution_lambda_22_loss: 1.8938 - val_distribution_lambda_23_loss: 0.5224\n",
"Epoch 83/2500\n",
"9/9 [==============================] - 0s 9ms/step - loss: 4.7326 - distribution_lambda_21_loss: 2.4027 - distribution_lambda_22_loss: 1.7492 - distribution_lambda_23_loss: 0.5807 - val_loss: 4.7611 - val_distribution_lambda_21_loss: 2.3503 - val_distribution_lambda_22_loss: 1.8888 - val_distribution_lambda_23_loss: 0.5220\n",
"Epoch 84/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 4.7188 - distribution_lambda_21_loss: 2.4056 - distribution_lambda_22_loss: 1.7458 - distribution_lambda_23_loss: 0.5675 - val_loss: 4.7491 - val_distribution_lambda_21_loss: 2.3453 - val_distribution_lambda_22_loss: 1.8824 - val_distribution_lambda_23_loss: 0.5214\n",
"Epoch 85/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7238 - distribution_lambda_21_loss: 2.4008 - distribution_lambda_22_loss: 1.7458 - distribution_lambda_23_loss: 0.5772 - val_loss: 4.7343 - val_distribution_lambda_21_loss: 2.3404 - val_distribution_lambda_22_loss: 1.8731 - val_distribution_lambda_23_loss: 0.5208\n",
"Epoch 86/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7255 - distribution_lambda_21_loss: 2.4062 - distribution_lambda_22_loss: 1.7348 - distribution_lambda_23_loss: 0.5845 - val_loss: 4.7242 - val_distribution_lambda_21_loss: 2.3356 - val_distribution_lambda_22_loss: 1.8679 - val_distribution_lambda_23_loss: 0.5207\n",
"Epoch 87/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.7136 - distribution_lambda_21_loss: 2.3928 - distribution_lambda_22_loss: 1.7470 - distribution_lambda_23_loss: 0.5738 - val_loss: 4.7131 - val_distribution_lambda_21_loss: 2.3311 - val_distribution_lambda_22_loss: 1.8612 - val_distribution_lambda_23_loss: 0.5208\n",
"Epoch 88/2500\n",
"9/9 [==============================] - 0s 11ms/step - loss: 4.7067 - distribution_lambda_21_loss: 2.3838 - distribution_lambda_22_loss: 1.7326 - distribution_lambda_23_loss: 0.5903 - val_loss: 4.7038 - val_distribution_lambda_21_loss: 2.3268 - val_distribution_lambda_22_loss: 1.8553 - val_distribution_lambda_23_loss: 0.5217\n",
"Epoch 89/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.7275 - distribution_lambda_21_loss: 2.4055 - distribution_lambda_22_loss: 1.7403 - distribution_lambda_23_loss: 0.5818 - val_loss: 4.6948 - val_distribution_lambda_21_loss: 2.3226 - val_distribution_lambda_22_loss: 1.8502 - val_distribution_lambda_23_loss: 0.5220\n",
"Epoch 90/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.6876 - distribution_lambda_21_loss: 2.3873 - distribution_lambda_22_loss: 1.7224 - distribution_lambda_23_loss: 0.5779 - val_loss: 4.6873 - val_distribution_lambda_21_loss: 2.3185 - val_distribution_lambda_22_loss: 1.8462 - val_distribution_lambda_23_loss: 0.5226\n",
"Epoch 91/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.6549 - distribution_lambda_21_loss: 2.3703 - distribution_lambda_22_loss: 1.7166 - distribution_lambda_23_loss: 0.5680 - val_loss: 4.6781 - val_distribution_lambda_21_loss: 2.3147 - val_distribution_lambda_22_loss: 1.8413 - val_distribution_lambda_23_loss: 0.5221\n",
"Epoch 92/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.6607 - distribution_lambda_21_loss: 2.3683 - distribution_lambda_22_loss: 1.7182 - distribution_lambda_23_loss: 0.5742 - val_loss: 4.6687 - val_distribution_lambda_21_loss: 2.3109 - val_distribution_lambda_22_loss: 1.8361 - val_distribution_lambda_23_loss: 0.5217\n",
"Epoch 93/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.6547 - distribution_lambda_21_loss: 2.3620 - distribution_lambda_22_loss: 1.7154 - distribution_lambda_23_loss: 0.5773 - val_loss: 4.6550 - val_distribution_lambda_21_loss: 2.3073 - val_distribution_lambda_22_loss: 1.8265 - val_distribution_lambda_23_loss: 0.5212\n",
"Epoch 94/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 4.6291 - distribution_lambda_21_loss: 2.3495 - distribution_lambda_22_loss: 1.7106 - distribution_lambda_23_loss: 0.5690 - val_loss: 4.6439 - val_distribution_lambda_21_loss: 2.3037 - val_distribution_lambda_22_loss: 1.8191 - val_distribution_lambda_23_loss: 0.5211\n",
"Epoch 95/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.6264 - distribution_lambda_21_loss: 2.3478 - distribution_lambda_22_loss: 1.7099 - distribution_lambda_23_loss: 0.5687 - val_loss: 4.6345 - val_distribution_lambda_21_loss: 2.3003 - val_distribution_lambda_22_loss: 1.8134 - val_distribution_lambda_23_loss: 0.5209\n",
"Epoch 96/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 4.6236 - distribution_lambda_21_loss: 2.3460 - distribution_lambda_22_loss: 1.6918 - distribution_lambda_23_loss: 0.5858 - val_loss: 4.6256 - val_distribution_lambda_21_loss: 2.2969 - val_distribution_lambda_22_loss: 1.8081 - val_distribution_lambda_23_loss: 0.5207\n",
"Epoch 97/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 4.6377 - distribution_lambda_21_loss: 2.3501 - distribution_lambda_22_loss: 1.7044 - distribution_lambda_23_loss: 0.5831 - val_loss: 4.6184 - val_distribution_lambda_21_loss: 2.2935 - val_distribution_lambda_22_loss: 1.8043 - val_distribution_lambda_23_loss: 0.5205\n",
"Epoch 98/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.6048 - distribution_lambda_21_loss: 2.3356 - distribution_lambda_22_loss: 1.6908 - distribution_lambda_23_loss: 0.5784 - val_loss: 4.6105 - val_distribution_lambda_21_loss: 2.2902 - val_distribution_lambda_22_loss: 1.7997 - val_distribution_lambda_23_loss: 0.5207\n",
"Epoch 99/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.6229 - distribution_lambda_21_loss: 2.3394 - distribution_lambda_22_loss: 1.7019 - distribution_lambda_23_loss: 0.5817 - val_loss: 4.5986 - val_distribution_lambda_21_loss: 2.2869 - val_distribution_lambda_22_loss: 1.7909 - val_distribution_lambda_23_loss: 0.5207\n",
"Epoch 100/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.5778 - distribution_lambda_21_loss: 2.3266 - distribution_lambda_22_loss: 1.6843 - distribution_lambda_23_loss: 0.5669 - val_loss: 4.5898 - val_distribution_lambda_21_loss: 2.2838 - val_distribution_lambda_22_loss: 1.7856 - val_distribution_lambda_23_loss: 0.5204\n",
"Epoch 101/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5721 - distribution_lambda_21_loss: 2.3273 - distribution_lambda_22_loss: 1.6810 - distribution_lambda_23_loss: 0.5639 - val_loss: 4.5824 - val_distribution_lambda_21_loss: 2.2806 - val_distribution_lambda_22_loss: 1.7818 - val_distribution_lambda_23_loss: 0.5200\n",
"Epoch 102/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5774 - distribution_lambda_21_loss: 2.3234 - distribution_lambda_22_loss: 1.6877 - distribution_lambda_23_loss: 0.5664 - val_loss: 4.5757 - val_distribution_lambda_21_loss: 2.2775 - val_distribution_lambda_22_loss: 1.7784 - val_distribution_lambda_23_loss: 0.5198\n",
"Epoch 103/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5602 - distribution_lambda_21_loss: 2.3152 - distribution_lambda_22_loss: 1.6793 - distribution_lambda_23_loss: 0.5656 - val_loss: 4.5699 - val_distribution_lambda_21_loss: 2.2745 - val_distribution_lambda_22_loss: 1.7759 - val_distribution_lambda_23_loss: 0.5196\n",
"Epoch 104/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5679 - distribution_lambda_21_loss: 2.3177 - distribution_lambda_22_loss: 1.6779 - distribution_lambda_23_loss: 0.5724 - val_loss: 4.5628 - val_distribution_lambda_21_loss: 2.2714 - val_distribution_lambda_22_loss: 1.7721 - val_distribution_lambda_23_loss: 0.5192\n",
"Epoch 105/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5556 - distribution_lambda_21_loss: 2.3122 - distribution_lambda_22_loss: 1.6815 - distribution_lambda_23_loss: 0.5620 - val_loss: 4.5546 - val_distribution_lambda_21_loss: 2.2685 - val_distribution_lambda_22_loss: 1.7674 - val_distribution_lambda_23_loss: 0.5187\n",
"Epoch 106/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5503 - distribution_lambda_21_loss: 2.3061 - distribution_lambda_22_loss: 1.6770 - distribution_lambda_23_loss: 0.5673 - val_loss: 4.5472 - val_distribution_lambda_21_loss: 2.2655 - val_distribution_lambda_22_loss: 1.7631 - val_distribution_lambda_23_loss: 0.5186\n",
"Epoch 107/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5596 - distribution_lambda_21_loss: 2.3097 - distribution_lambda_22_loss: 1.6718 - distribution_lambda_23_loss: 0.5782 - val_loss: 4.5436 - val_distribution_lambda_21_loss: 2.2625 - val_distribution_lambda_22_loss: 1.7621 - val_distribution_lambda_23_loss: 0.5190\n",
"Epoch 108/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5472 - distribution_lambda_21_loss: 2.2981 - distribution_lambda_22_loss: 1.6684 - distribution_lambda_23_loss: 0.5808 - val_loss: 4.5384 - val_distribution_lambda_21_loss: 2.2596 - val_distribution_lambda_22_loss: 1.7597 - val_distribution_lambda_23_loss: 0.5191\n",
"Epoch 109/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.5229 - distribution_lambda_21_loss: 2.2858 - distribution_lambda_22_loss: 1.6662 - distribution_lambda_23_loss: 0.5709 - val_loss: 4.5315 - val_distribution_lambda_21_loss: 2.2568 - val_distribution_lambda_22_loss: 1.7559 - val_distribution_lambda_23_loss: 0.5189\n",
"Epoch 110/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.5430 - distribution_lambda_21_loss: 2.3024 - distribution_lambda_22_loss: 1.6690 - distribution_lambda_23_loss: 0.5716 - val_loss: 4.5263 - val_distribution_lambda_21_loss: 2.2539 - val_distribution_lambda_22_loss: 1.7534 - val_distribution_lambda_23_loss: 0.5190\n",
"Epoch 111/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5415 - distribution_lambda_21_loss: 2.2988 - distribution_lambda_22_loss: 1.6768 - distribution_lambda_23_loss: 0.5659 - val_loss: 4.5219 - val_distribution_lambda_21_loss: 2.2510 - val_distribution_lambda_22_loss: 1.7519 - val_distribution_lambda_23_loss: 0.5190\n",
"Epoch 112/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.5239 - distribution_lambda_21_loss: 2.2859 - distribution_lambda_22_loss: 1.6650 - distribution_lambda_23_loss: 0.5730 - val_loss: 4.5177 - val_distribution_lambda_21_loss: 2.2481 - val_distribution_lambda_22_loss: 1.7504 - val_distribution_lambda_23_loss: 0.5192\n",
"Epoch 113/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5104 - distribution_lambda_21_loss: 2.2810 - distribution_lambda_22_loss: 1.6635 - distribution_lambda_23_loss: 0.5659 - val_loss: 4.5127 - val_distribution_lambda_21_loss: 2.2453 - val_distribution_lambda_22_loss: 1.7483 - val_distribution_lambda_23_loss: 0.5190\n",
"Epoch 114/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5269 - distribution_lambda_21_loss: 2.2888 - distribution_lambda_22_loss: 1.6693 - distribution_lambda_23_loss: 0.5687 - val_loss: 4.5074 - val_distribution_lambda_21_loss: 2.2425 - val_distribution_lambda_22_loss: 1.7460 - val_distribution_lambda_23_loss: 0.5189\n",
"Epoch 115/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5061 - distribution_lambda_21_loss: 2.2789 - distribution_lambda_22_loss: 1.6557 - distribution_lambda_23_loss: 0.5715 - val_loss: 4.5022 - val_distribution_lambda_21_loss: 2.2397 - val_distribution_lambda_22_loss: 1.7436 - val_distribution_lambda_23_loss: 0.5188\n",
"Epoch 116/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5100 - distribution_lambda_21_loss: 2.2762 - distribution_lambda_22_loss: 1.6615 - distribution_lambda_23_loss: 0.5723 - val_loss: 4.4954 - val_distribution_lambda_21_loss: 2.2370 - val_distribution_lambda_22_loss: 1.7402 - val_distribution_lambda_23_loss: 0.5181\n",
"Epoch 117/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4834 - distribution_lambda_21_loss: 2.2639 - distribution_lambda_22_loss: 1.6464 - distribution_lambda_23_loss: 0.5730 - val_loss: 4.4909 - val_distribution_lambda_21_loss: 2.2343 - val_distribution_lambda_22_loss: 1.7387 - val_distribution_lambda_23_loss: 0.5180\n",
"Epoch 118/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.5086 - distribution_lambda_21_loss: 2.2703 - distribution_lambda_22_loss: 1.6619 - distribution_lambda_23_loss: 0.5763 - val_loss: 4.4878 - val_distribution_lambda_21_loss: 2.2315 - val_distribution_lambda_22_loss: 1.7381 - val_distribution_lambda_23_loss: 0.5182\n",
"Epoch 119/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4808 - distribution_lambda_21_loss: 2.2558 - distribution_lambda_22_loss: 1.6534 - distribution_lambda_23_loss: 0.5716 - val_loss: 4.4817 - val_distribution_lambda_21_loss: 2.2288 - val_distribution_lambda_22_loss: 1.7345 - val_distribution_lambda_23_loss: 0.5184\n",
"Epoch 120/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4920 - distribution_lambda_21_loss: 2.2700 - distribution_lambda_22_loss: 1.6505 - distribution_lambda_23_loss: 0.5715 - val_loss: 4.4779 - val_distribution_lambda_21_loss: 2.2260 - val_distribution_lambda_22_loss: 1.7332 - val_distribution_lambda_23_loss: 0.5187\n",
"Epoch 121/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 4.4869 - distribution_lambda_21_loss: 2.2591 - distribution_lambda_22_loss: 1.6562 - distribution_lambda_23_loss: 0.5716 - val_loss: 4.4740 - val_distribution_lambda_21_loss: 2.2233 - val_distribution_lambda_22_loss: 1.7320 - val_distribution_lambda_23_loss: 0.5187\n",
"Epoch 122/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4821 - distribution_lambda_21_loss: 2.2700 - distribution_lambda_22_loss: 1.6454 - distribution_lambda_23_loss: 0.5668 - val_loss: 4.4706 - val_distribution_lambda_21_loss: 2.2205 - val_distribution_lambda_22_loss: 1.7315 - val_distribution_lambda_23_loss: 0.5186\n",
"Epoch 123/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4716 - distribution_lambda_21_loss: 2.2496 - distribution_lambda_22_loss: 1.6469 - distribution_lambda_23_loss: 0.5751 - val_loss: 4.4669 - val_distribution_lambda_21_loss: 2.2177 - val_distribution_lambda_22_loss: 1.7307 - val_distribution_lambda_23_loss: 0.5184\n",
"Epoch 124/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4727 - distribution_lambda_21_loss: 2.2515 - distribution_lambda_22_loss: 1.6454 - distribution_lambda_23_loss: 0.5758 - val_loss: 4.4620 - val_distribution_lambda_21_loss: 2.2150 - val_distribution_lambda_22_loss: 1.7283 - val_distribution_lambda_23_loss: 0.5188\n",
"Epoch 125/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4775 - distribution_lambda_21_loss: 2.2518 - distribution_lambda_22_loss: 1.6495 - distribution_lambda_23_loss: 0.5761 - val_loss: 4.4589 - val_distribution_lambda_21_loss: 2.2122 - val_distribution_lambda_22_loss: 1.7274 - val_distribution_lambda_23_loss: 0.5193\n",
"Epoch 126/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4695 - distribution_lambda_21_loss: 2.2477 - distribution_lambda_22_loss: 1.6489 - distribution_lambda_23_loss: 0.5729 - val_loss: 4.4546 - val_distribution_lambda_21_loss: 2.2095 - val_distribution_lambda_22_loss: 1.7254 - val_distribution_lambda_23_loss: 0.5198\n",
"Epoch 127/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4493 - distribution_lambda_21_loss: 2.2428 - distribution_lambda_22_loss: 1.6488 - distribution_lambda_23_loss: 0.5577 - val_loss: 4.4492 - val_distribution_lambda_21_loss: 2.2068 - val_distribution_lambda_22_loss: 1.7230 - val_distribution_lambda_23_loss: 0.5194\n",
"Epoch 128/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4605 - distribution_lambda_21_loss: 2.2389 - distribution_lambda_22_loss: 1.6583 - distribution_lambda_23_loss: 0.5633 - val_loss: 4.4456 - val_distribution_lambda_21_loss: 2.2041 - val_distribution_lambda_22_loss: 1.7224 - val_distribution_lambda_23_loss: 0.5191\n",
"Epoch 129/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4413 - distribution_lambda_21_loss: 2.2311 - distribution_lambda_22_loss: 1.6471 - distribution_lambda_23_loss: 0.5631 - val_loss: 4.4420 - val_distribution_lambda_21_loss: 2.2013 - val_distribution_lambda_22_loss: 1.7221 - val_distribution_lambda_23_loss: 0.5185\n",
"Epoch 130/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4431 - distribution_lambda_21_loss: 2.2244 - distribution_lambda_22_loss: 1.6459 - distribution_lambda_23_loss: 0.5728 - val_loss: 4.4362 - val_distribution_lambda_21_loss: 2.1987 - val_distribution_lambda_22_loss: 1.7195 - val_distribution_lambda_23_loss: 0.5181\n",
"Epoch 131/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4692 - distribution_lambda_21_loss: 2.2332 - distribution_lambda_22_loss: 1.6513 - distribution_lambda_23_loss: 0.5847 - val_loss: 4.4326 - val_distribution_lambda_21_loss: 2.1960 - val_distribution_lambda_22_loss: 1.7185 - val_distribution_lambda_23_loss: 0.5182\n",
"Epoch 132/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4311 - distribution_lambda_21_loss: 2.2212 - distribution_lambda_22_loss: 1.6402 - distribution_lambda_23_loss: 0.5697 - val_loss: 4.4280 - val_distribution_lambda_21_loss: 2.1933 - val_distribution_lambda_22_loss: 1.7171 - val_distribution_lambda_23_loss: 0.5176\n",
"Epoch 133/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4472 - distribution_lambda_21_loss: 2.2314 - distribution_lambda_22_loss: 1.6414 - distribution_lambda_23_loss: 0.5744 - val_loss: 4.4256 - val_distribution_lambda_21_loss: 2.1906 - val_distribution_lambda_22_loss: 1.7173 - val_distribution_lambda_23_loss: 0.5177\n",
"Epoch 134/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4102 - distribution_lambda_21_loss: 2.2171 - distribution_lambda_22_loss: 1.6358 - distribution_lambda_23_loss: 0.5573 - val_loss: 4.4233 - val_distribution_lambda_21_loss: 2.1879 - val_distribution_lambda_22_loss: 1.7180 - val_distribution_lambda_23_loss: 0.5175\n",
"Epoch 135/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4103 - distribution_lambda_21_loss: 2.2155 - distribution_lambda_22_loss: 1.6385 - distribution_lambda_23_loss: 0.5563 - val_loss: 4.4204 - val_distribution_lambda_21_loss: 2.1852 - val_distribution_lambda_22_loss: 1.7179 - val_distribution_lambda_23_loss: 0.5174\n",
"Epoch 136/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.4151 - distribution_lambda_21_loss: 2.2110 - distribution_lambda_22_loss: 1.6387 - distribution_lambda_23_loss: 0.5654 - val_loss: 4.4183 - val_distribution_lambda_21_loss: 2.1824 - val_distribution_lambda_22_loss: 1.7180 - val_distribution_lambda_23_loss: 0.5179\n",
"Epoch 137/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4191 - distribution_lambda_21_loss: 2.2089 - distribution_lambda_22_loss: 1.6418 - distribution_lambda_23_loss: 0.5683 - val_loss: 4.4118 - val_distribution_lambda_21_loss: 2.1797 - val_distribution_lambda_22_loss: 1.7145 - val_distribution_lambda_23_loss: 0.5176\n",
"Epoch 138/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4029 - distribution_lambda_21_loss: 2.2032 - distribution_lambda_22_loss: 1.6410 - distribution_lambda_23_loss: 0.5587 - val_loss: 4.4075 - val_distribution_lambda_21_loss: 2.1770 - val_distribution_lambda_22_loss: 1.7133 - val_distribution_lambda_23_loss: 0.5172\n",
"Epoch 139/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4106 - distribution_lambda_21_loss: 2.2045 - distribution_lambda_22_loss: 1.6411 - distribution_lambda_23_loss: 0.5650 - val_loss: 4.4051 - val_distribution_lambda_21_loss: 2.1743 - val_distribution_lambda_22_loss: 1.7141 - val_distribution_lambda_23_loss: 0.5167\n",
"Epoch 140/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3970 - distribution_lambda_21_loss: 2.1962 - distribution_lambda_22_loss: 1.6409 - distribution_lambda_23_loss: 0.5598 - val_loss: 4.4004 - val_distribution_lambda_21_loss: 2.1716 - val_distribution_lambda_22_loss: 1.7124 - val_distribution_lambda_23_loss: 0.5164\n",
"Epoch 141/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4000 - distribution_lambda_21_loss: 2.2029 - distribution_lambda_22_loss: 1.6376 - distribution_lambda_23_loss: 0.5595 - val_loss: 4.3965 - val_distribution_lambda_21_loss: 2.1688 - val_distribution_lambda_22_loss: 1.7117 - val_distribution_lambda_23_loss: 0.5159\n",
"Epoch 142/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3883 - distribution_lambda_21_loss: 2.1906 - distribution_lambda_22_loss: 1.6376 - distribution_lambda_23_loss: 0.5602 - val_loss: 4.3918 - val_distribution_lambda_21_loss: 2.1661 - val_distribution_lambda_22_loss: 1.7103 - val_distribution_lambda_23_loss: 0.5154\n",
"Epoch 143/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.4197 - distribution_lambda_21_loss: 2.2024 - distribution_lambda_22_loss: 1.6465 - distribution_lambda_23_loss: 0.5708 - val_loss: 4.3891 - val_distribution_lambda_21_loss: 2.1633 - val_distribution_lambda_22_loss: 1.7104 - val_distribution_lambda_23_loss: 0.5154\n",
"Epoch 144/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3999 - distribution_lambda_21_loss: 2.1877 - distribution_lambda_22_loss: 1.6400 - distribution_lambda_23_loss: 0.5722 - val_loss: 4.3871 - val_distribution_lambda_21_loss: 2.1605 - val_distribution_lambda_22_loss: 1.7111 - val_distribution_lambda_23_loss: 0.5156\n",
"Epoch 145/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 4.3855 - distribution_lambda_21_loss: 2.1875 - distribution_lambda_22_loss: 1.6360 - distribution_lambda_23_loss: 0.5621 - val_loss: 4.3845 - val_distribution_lambda_21_loss: 2.1577 - val_distribution_lambda_22_loss: 1.7113 - val_distribution_lambda_23_loss: 0.5155\n",
"Epoch 146/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3806 - distribution_lambda_21_loss: 2.1831 - distribution_lambda_22_loss: 1.6349 - distribution_lambda_23_loss: 0.5626 - val_loss: 4.3817 - val_distribution_lambda_21_loss: 2.1549 - val_distribution_lambda_22_loss: 1.7112 - val_distribution_lambda_23_loss: 0.5156\n",
"Epoch 147/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3667 - distribution_lambda_21_loss: 2.1727 - distribution_lambda_22_loss: 1.6345 - distribution_lambda_23_loss: 0.5595 - val_loss: 4.3788 - val_distribution_lambda_21_loss: 2.1522 - val_distribution_lambda_22_loss: 1.7113 - val_distribution_lambda_23_loss: 0.5153\n",
"Epoch 148/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3703 - distribution_lambda_21_loss: 2.1758 - distribution_lambda_22_loss: 1.6354 - distribution_lambda_23_loss: 0.5591 - val_loss: 4.3755 - val_distribution_lambda_21_loss: 2.1494 - val_distribution_lambda_22_loss: 1.7111 - val_distribution_lambda_23_loss: 0.5150\n",
"Epoch 149/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3615 - distribution_lambda_21_loss: 2.1683 - distribution_lambda_22_loss: 1.6365 - distribution_lambda_23_loss: 0.5567 - val_loss: 4.3716 - val_distribution_lambda_21_loss: 2.1466 - val_distribution_lambda_22_loss: 1.7104 - val_distribution_lambda_23_loss: 0.5146\n",
"Epoch 150/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3590 - distribution_lambda_21_loss: 2.1644 - distribution_lambda_22_loss: 1.6368 - distribution_lambda_23_loss: 0.5577 - val_loss: 4.3681 - val_distribution_lambda_21_loss: 2.1438 - val_distribution_lambda_22_loss: 1.7099 - val_distribution_lambda_23_loss: 0.5144\n",
"Epoch 151/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3692 - distribution_lambda_21_loss: 2.1645 - distribution_lambda_22_loss: 1.6343 - distribution_lambda_23_loss: 0.5704 - val_loss: 4.3659 - val_distribution_lambda_21_loss: 2.1410 - val_distribution_lambda_22_loss: 1.7103 - val_distribution_lambda_23_loss: 0.5146\n",
"Epoch 152/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3701 - distribution_lambda_21_loss: 2.1704 - distribution_lambda_22_loss: 1.6409 - distribution_lambda_23_loss: 0.5587 - val_loss: 4.3621 - val_distribution_lambda_21_loss: 2.1382 - val_distribution_lambda_22_loss: 1.7099 - val_distribution_lambda_23_loss: 0.5141\n",
"Epoch 153/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3513 - distribution_lambda_21_loss: 2.1563 - distribution_lambda_22_loss: 1.6327 - distribution_lambda_23_loss: 0.5623 - val_loss: 4.3593 - val_distribution_lambda_21_loss: 2.1353 - val_distribution_lambda_22_loss: 1.7100 - val_distribution_lambda_23_loss: 0.5140\n",
"Epoch 154/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3587 - distribution_lambda_21_loss: 2.1542 - distribution_lambda_22_loss: 1.6369 - distribution_lambda_23_loss: 0.5676 - val_loss: 4.3551 - val_distribution_lambda_21_loss: 2.1325 - val_distribution_lambda_22_loss: 1.7084 - val_distribution_lambda_23_loss: 0.5142\n",
"Epoch 155/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.3507 - distribution_lambda_21_loss: 2.1585 - distribution_lambda_22_loss: 1.6287 - distribution_lambda_23_loss: 0.5635 - val_loss: 4.3504 - val_distribution_lambda_21_loss: 2.1296 - val_distribution_lambda_22_loss: 1.7066 - val_distribution_lambda_23_loss: 0.5142\n",
"Epoch 156/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3406 - distribution_lambda_21_loss: 2.1468 - distribution_lambda_22_loss: 1.6303 - distribution_lambda_23_loss: 0.5635 - val_loss: 4.3479 - val_distribution_lambda_21_loss: 2.1268 - val_distribution_lambda_22_loss: 1.7064 - val_distribution_lambda_23_loss: 0.5148\n",
"Epoch 157/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3313 - distribution_lambda_21_loss: 2.1461 - distribution_lambda_22_loss: 1.6314 - distribution_lambda_23_loss: 0.5538 - val_loss: 4.3447 - val_distribution_lambda_21_loss: 2.1239 - val_distribution_lambda_22_loss: 1.7059 - val_distribution_lambda_23_loss: 0.5149\n",
"Epoch 158/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3541 - distribution_lambda_21_loss: 2.1515 - distribution_lambda_22_loss: 1.6326 - distribution_lambda_23_loss: 0.5701 - val_loss: 4.3432 - val_distribution_lambda_21_loss: 2.1210 - val_distribution_lambda_22_loss: 1.7071 - val_distribution_lambda_23_loss: 0.5152\n",
"Epoch 159/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3389 - distribution_lambda_21_loss: 2.1354 - distribution_lambda_22_loss: 1.6313 - distribution_lambda_23_loss: 0.5722 - val_loss: 4.3410 - val_distribution_lambda_21_loss: 2.1181 - val_distribution_lambda_22_loss: 1.7070 - val_distribution_lambda_23_loss: 0.5159\n",
"Epoch 160/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3330 - distribution_lambda_21_loss: 2.1365 - distribution_lambda_22_loss: 1.6290 - distribution_lambda_23_loss: 0.5676 - val_loss: 4.3392 - val_distribution_lambda_21_loss: 2.1152 - val_distribution_lambda_22_loss: 1.7072 - val_distribution_lambda_23_loss: 0.5168\n",
"Epoch 161/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3274 - distribution_lambda_21_loss: 2.1308 - distribution_lambda_22_loss: 1.6362 - distribution_lambda_23_loss: 0.5604 - val_loss: 4.3375 - val_distribution_lambda_21_loss: 2.1123 - val_distribution_lambda_22_loss: 1.7082 - val_distribution_lambda_23_loss: 0.5170\n",
"Epoch 162/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3229 - distribution_lambda_21_loss: 2.1324 - distribution_lambda_22_loss: 1.6283 - distribution_lambda_23_loss: 0.5623 - val_loss: 4.3344 - val_distribution_lambda_21_loss: 2.1094 - val_distribution_lambda_22_loss: 1.7079 - val_distribution_lambda_23_loss: 0.5171\n",
"Epoch 163/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3333 - distribution_lambda_21_loss: 2.1336 - distribution_lambda_22_loss: 1.6358 - distribution_lambda_23_loss: 0.5639 - val_loss: 4.3293 - val_distribution_lambda_21_loss: 2.1064 - val_distribution_lambda_22_loss: 1.7066 - val_distribution_lambda_23_loss: 0.5163\n",
"Epoch 164/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3353 - distribution_lambda_21_loss: 2.1373 - distribution_lambda_22_loss: 1.6367 - distribution_lambda_23_loss: 0.5612 - val_loss: 4.3254 - val_distribution_lambda_21_loss: 2.1035 - val_distribution_lambda_22_loss: 1.7063 - val_distribution_lambda_23_loss: 0.5155\n",
"Epoch 165/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3177 - distribution_lambda_21_loss: 2.1226 - distribution_lambda_22_loss: 1.6257 - distribution_lambda_23_loss: 0.5694 - val_loss: 4.3211 - val_distribution_lambda_21_loss: 2.1005 - val_distribution_lambda_22_loss: 1.7056 - val_distribution_lambda_23_loss: 0.5150\n",
"Epoch 166/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3161 - distribution_lambda_21_loss: 2.1216 - distribution_lambda_22_loss: 1.6319 - distribution_lambda_23_loss: 0.5626 - val_loss: 4.3178 - val_distribution_lambda_21_loss: 2.0976 - val_distribution_lambda_22_loss: 1.7056 - val_distribution_lambda_23_loss: 0.5147\n",
"Epoch 167/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3189 - distribution_lambda_21_loss: 2.1198 - distribution_lambda_22_loss: 1.6298 - distribution_lambda_23_loss: 0.5693 - val_loss: 4.3151 - val_distribution_lambda_21_loss: 2.0946 - val_distribution_lambda_22_loss: 1.7058 - val_distribution_lambda_23_loss: 0.5148\n",
"Epoch 168/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3164 - distribution_lambda_21_loss: 2.1197 - distribution_lambda_22_loss: 1.6341 - distribution_lambda_23_loss: 0.5625 - val_loss: 4.3139 - val_distribution_lambda_21_loss: 2.0915 - val_distribution_lambda_22_loss: 1.7068 - val_distribution_lambda_23_loss: 0.5156\n",
"Epoch 169/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 4.3134 - distribution_lambda_21_loss: 2.1263 - distribution_lambda_22_loss: 1.6300 - distribution_lambda_23_loss: 0.5572 - val_loss: 4.3126 - val_distribution_lambda_21_loss: 2.0885 - val_distribution_lambda_22_loss: 1.7083 - val_distribution_lambda_23_loss: 0.5159\n",
"Epoch 170/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2944 - distribution_lambda_21_loss: 2.1104 - distribution_lambda_22_loss: 1.6218 - distribution_lambda_23_loss: 0.5622 - val_loss: 4.3090 - val_distribution_lambda_21_loss: 2.0854 - val_distribution_lambda_22_loss: 1.7077 - val_distribution_lambda_23_loss: 0.5158\n",
"Epoch 171/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2889 - distribution_lambda_21_loss: 2.1033 - distribution_lambda_22_loss: 1.6327 - distribution_lambda_23_loss: 0.5530 - val_loss: 4.3061 - val_distribution_lambda_21_loss: 2.0824 - val_distribution_lambda_22_loss: 1.7085 - val_distribution_lambda_23_loss: 0.5153\n",
"Epoch 172/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2947 - distribution_lambda_21_loss: 2.1048 - distribution_lambda_22_loss: 1.6312 - distribution_lambda_23_loss: 0.5588 - val_loss: 4.3047 - val_distribution_lambda_21_loss: 2.0793 - val_distribution_lambda_22_loss: 1.7104 - val_distribution_lambda_23_loss: 0.5150\n",
"Epoch 173/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.3064 - distribution_lambda_21_loss: 2.1098 - distribution_lambda_22_loss: 1.6402 - distribution_lambda_23_loss: 0.5563 - val_loss: 4.3016 - val_distribution_lambda_21_loss: 2.0762 - val_distribution_lambda_22_loss: 1.7106 - val_distribution_lambda_23_loss: 0.5148\n",
"Epoch 174/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2831 - distribution_lambda_21_loss: 2.0952 - distribution_lambda_22_loss: 1.6300 - distribution_lambda_23_loss: 0.5580 - val_loss: 4.2961 - val_distribution_lambda_21_loss: 2.0732 - val_distribution_lambda_22_loss: 1.7088 - val_distribution_lambda_23_loss: 0.5142\n",
"Epoch 175/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2999 - distribution_lambda_21_loss: 2.0975 - distribution_lambda_22_loss: 1.6345 - distribution_lambda_23_loss: 0.5680 - val_loss: 4.2894 - val_distribution_lambda_21_loss: 2.0701 - val_distribution_lambda_22_loss: 1.7060 - val_distribution_lambda_23_loss: 0.5134\n",
"Epoch 176/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2926 - distribution_lambda_21_loss: 2.0902 - distribution_lambda_22_loss: 1.6390 - distribution_lambda_23_loss: 0.5634 - val_loss: 4.2833 - val_distribution_lambda_21_loss: 2.0669 - val_distribution_lambda_22_loss: 1.7032 - val_distribution_lambda_23_loss: 0.5131\n",
"Epoch 177/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2704 - distribution_lambda_21_loss: 2.0848 - distribution_lambda_22_loss: 1.6285 - distribution_lambda_23_loss: 0.5571 - val_loss: 4.2793 - val_distribution_lambda_21_loss: 2.0638 - val_distribution_lambda_22_loss: 1.7027 - val_distribution_lambda_23_loss: 0.5128\n",
"Epoch 178/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2914 - distribution_lambda_21_loss: 2.0915 - distribution_lambda_22_loss: 1.6390 - distribution_lambda_23_loss: 0.5609 - val_loss: 4.2759 - val_distribution_lambda_21_loss: 2.0607 - val_distribution_lambda_22_loss: 1.7029 - val_distribution_lambda_23_loss: 0.5123\n",
"Epoch 179/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2813 - distribution_lambda_21_loss: 2.0831 - distribution_lambda_22_loss: 1.6397 - distribution_lambda_23_loss: 0.5585 - val_loss: 4.2724 - val_distribution_lambda_21_loss: 2.0575 - val_distribution_lambda_22_loss: 1.7026 - val_distribution_lambda_23_loss: 0.5123\n",
"Epoch 180/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2654 - distribution_lambda_21_loss: 2.0708 - distribution_lambda_22_loss: 1.6308 - distribution_lambda_23_loss: 0.5637 - val_loss: 4.2696 - val_distribution_lambda_21_loss: 2.0543 - val_distribution_lambda_22_loss: 1.7028 - val_distribution_lambda_23_loss: 0.5125\n",
"Epoch 181/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2543 - distribution_lambda_21_loss: 2.0742 - distribution_lambda_22_loss: 1.6299 - distribution_lambda_23_loss: 0.5501 - val_loss: 4.2667 - val_distribution_lambda_21_loss: 2.0511 - val_distribution_lambda_22_loss: 1.7036 - val_distribution_lambda_23_loss: 0.5120\n",
"Epoch 182/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2689 - distribution_lambda_21_loss: 2.0724 - distribution_lambda_22_loss: 1.6252 - distribution_lambda_23_loss: 0.5713 - val_loss: 4.2645 - val_distribution_lambda_21_loss: 2.0479 - val_distribution_lambda_22_loss: 1.7045 - val_distribution_lambda_23_loss: 0.5121\n",
"Epoch 183/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2608 - distribution_lambda_21_loss: 2.0644 - distribution_lambda_22_loss: 1.6280 - distribution_lambda_23_loss: 0.5684 - val_loss: 4.2615 - val_distribution_lambda_21_loss: 2.0447 - val_distribution_lambda_22_loss: 1.7048 - val_distribution_lambda_23_loss: 0.5121\n",
"Epoch 184/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2739 - distribution_lambda_21_loss: 2.0686 - distribution_lambda_22_loss: 1.6399 - distribution_lambda_23_loss: 0.5654 - val_loss: 4.2583 - val_distribution_lambda_21_loss: 2.0414 - val_distribution_lambda_22_loss: 1.7047 - val_distribution_lambda_23_loss: 0.5122\n",
"Epoch 185/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2404 - distribution_lambda_21_loss: 2.0580 - distribution_lambda_22_loss: 1.6335 - distribution_lambda_23_loss: 0.5488 - val_loss: 4.2568 - val_distribution_lambda_21_loss: 2.0381 - val_distribution_lambda_22_loss: 1.7065 - val_distribution_lambda_23_loss: 0.5122\n",
"Epoch 186/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2356 - distribution_lambda_21_loss: 2.0527 - distribution_lambda_22_loss: 1.6271 - distribution_lambda_23_loss: 0.5558 - val_loss: 4.2540 - val_distribution_lambda_21_loss: 2.0349 - val_distribution_lambda_22_loss: 1.7066 - val_distribution_lambda_23_loss: 0.5126\n",
"Epoch 187/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2258 - distribution_lambda_21_loss: 2.0471 - distribution_lambda_22_loss: 1.6292 - distribution_lambda_23_loss: 0.5495 - val_loss: 4.2496 - val_distribution_lambda_21_loss: 2.0316 - val_distribution_lambda_22_loss: 1.7058 - val_distribution_lambda_23_loss: 0.5122\n",
"Epoch 188/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2289 - distribution_lambda_21_loss: 2.0456 - distribution_lambda_22_loss: 1.6285 - distribution_lambda_23_loss: 0.5548 - val_loss: 4.2469 - val_distribution_lambda_21_loss: 2.0283 - val_distribution_lambda_22_loss: 1.7061 - val_distribution_lambda_23_loss: 0.5125\n",
"Epoch 189/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2438 - distribution_lambda_21_loss: 2.0510 - distribution_lambda_22_loss: 1.6426 - distribution_lambda_23_loss: 0.5502 - val_loss: 4.2433 - val_distribution_lambda_21_loss: 2.0249 - val_distribution_lambda_22_loss: 1.7062 - val_distribution_lambda_23_loss: 0.5122\n",
"Epoch 190/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2344 - distribution_lambda_21_loss: 2.0408 - distribution_lambda_22_loss: 1.6315 - distribution_lambda_23_loss: 0.5620 - val_loss: 4.2386 - val_distribution_lambda_21_loss: 2.0216 - val_distribution_lambda_22_loss: 1.7047 - val_distribution_lambda_23_loss: 0.5123\n",
"Epoch 191/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2287 - distribution_lambda_21_loss: 2.0350 - distribution_lambda_22_loss: 1.6302 - distribution_lambda_23_loss: 0.5634 - val_loss: 4.2353 - val_distribution_lambda_21_loss: 2.0182 - val_distribution_lambda_22_loss: 1.7042 - val_distribution_lambda_23_loss: 0.5129\n",
"Epoch 192/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2270 - distribution_lambda_21_loss: 2.0375 - distribution_lambda_22_loss: 1.6355 - distribution_lambda_23_loss: 0.5540 - val_loss: 4.2322 - val_distribution_lambda_21_loss: 2.0148 - val_distribution_lambda_22_loss: 1.7046 - val_distribution_lambda_23_loss: 0.5128\n",
"Epoch 193/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 4.2161 - distribution_lambda_21_loss: 2.0311 - distribution_lambda_22_loss: 1.6282 - distribution_lambda_23_loss: 0.5569 - val_loss: 4.2280 - val_distribution_lambda_21_loss: 2.0114 - val_distribution_lambda_22_loss: 1.7040 - val_distribution_lambda_23_loss: 0.5126\n",
"Epoch 194/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2044 - distribution_lambda_21_loss: 2.0212 - distribution_lambda_22_loss: 1.6256 - distribution_lambda_23_loss: 0.5576 - val_loss: 4.2237 - val_distribution_lambda_21_loss: 2.0080 - val_distribution_lambda_22_loss: 1.7033 - val_distribution_lambda_23_loss: 0.5124\n",
"Epoch 195/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2163 - distribution_lambda_21_loss: 2.0297 - distribution_lambda_22_loss: 1.6261 - distribution_lambda_23_loss: 0.5606 - val_loss: 4.2206 - val_distribution_lambda_21_loss: 2.0046 - val_distribution_lambda_22_loss: 1.7035 - val_distribution_lambda_23_loss: 0.5125\n",
"Epoch 196/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2116 - distribution_lambda_21_loss: 2.0191 - distribution_lambda_22_loss: 1.6370 - distribution_lambda_23_loss: 0.5554 - val_loss: 4.2182 - val_distribution_lambda_21_loss: 2.0011 - val_distribution_lambda_22_loss: 1.7043 - val_distribution_lambda_23_loss: 0.5128\n",
"Epoch 197/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1952 - distribution_lambda_21_loss: 2.0123 - distribution_lambda_22_loss: 1.6274 - distribution_lambda_23_loss: 0.5554 - val_loss: 4.2144 - val_distribution_lambda_21_loss: 1.9976 - val_distribution_lambda_22_loss: 1.7043 - val_distribution_lambda_23_loss: 0.5126\n",
"Epoch 198/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.2024 - distribution_lambda_21_loss: 2.0148 - distribution_lambda_22_loss: 1.6304 - distribution_lambda_23_loss: 0.5572 - val_loss: 4.2106 - val_distribution_lambda_21_loss: 1.9941 - val_distribution_lambda_22_loss: 1.7044 - val_distribution_lambda_23_loss: 0.5120\n",
"Epoch 199/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1896 - distribution_lambda_21_loss: 2.0111 - distribution_lambda_22_loss: 1.6319 - distribution_lambda_23_loss: 0.5466 - val_loss: 4.2052 - val_distribution_lambda_21_loss: 1.9906 - val_distribution_lambda_22_loss: 1.7032 - val_distribution_lambda_23_loss: 0.5113\n",
"Epoch 200/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1878 - distribution_lambda_21_loss: 2.0052 - distribution_lambda_22_loss: 1.6269 - distribution_lambda_23_loss: 0.5557 - val_loss: 4.2019 - val_distribution_lambda_21_loss: 1.9871 - val_distribution_lambda_22_loss: 1.7038 - val_distribution_lambda_23_loss: 0.5110\n",
"Epoch 201/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1777 - distribution_lambda_21_loss: 2.0027 - distribution_lambda_22_loss: 1.6228 - distribution_lambda_23_loss: 0.5522 - val_loss: 4.1997 - val_distribution_lambda_21_loss: 1.9835 - val_distribution_lambda_22_loss: 1.7051 - val_distribution_lambda_23_loss: 0.5111\n",
"Epoch 202/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1866 - distribution_lambda_21_loss: 2.0032 - distribution_lambda_22_loss: 1.6278 - distribution_lambda_23_loss: 0.5556 - val_loss: 4.1957 - val_distribution_lambda_21_loss: 1.9799 - val_distribution_lambda_22_loss: 1.7051 - val_distribution_lambda_23_loss: 0.5107\n",
"Epoch 203/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1844 - distribution_lambda_21_loss: 1.9942 - distribution_lambda_22_loss: 1.6255 - distribution_lambda_23_loss: 0.5648 - val_loss: 4.1866 - val_distribution_lambda_21_loss: 1.9763 - val_distribution_lambda_22_loss: 1.6999 - val_distribution_lambda_23_loss: 0.5104\n",
"Epoch 204/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1523 - distribution_lambda_21_loss: 1.9893 - distribution_lambda_22_loss: 1.6211 - distribution_lambda_23_loss: 0.5420 - val_loss: 4.1831 - val_distribution_lambda_21_loss: 1.9727 - val_distribution_lambda_22_loss: 1.7001 - val_distribution_lambda_23_loss: 0.5103\n",
"Epoch 205/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1636 - distribution_lambda_21_loss: 1.9850 - distribution_lambda_22_loss: 1.6242 - distribution_lambda_23_loss: 0.5544 - val_loss: 4.1805 - val_distribution_lambda_21_loss: 1.9691 - val_distribution_lambda_22_loss: 1.7013 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 206/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1665 - distribution_lambda_21_loss: 1.9921 - distribution_lambda_22_loss: 1.6286 - distribution_lambda_23_loss: 0.5458 - val_loss: 4.1771 - val_distribution_lambda_21_loss: 1.9654 - val_distribution_lambda_22_loss: 1.7019 - val_distribution_lambda_23_loss: 0.5098\n",
"Epoch 207/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1635 - distribution_lambda_21_loss: 1.9799 - distribution_lambda_22_loss: 1.6248 - distribution_lambda_23_loss: 0.5588 - val_loss: 4.1748 - val_distribution_lambda_21_loss: 1.9617 - val_distribution_lambda_22_loss: 1.7030 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 208/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1497 - distribution_lambda_21_loss: 1.9766 - distribution_lambda_22_loss: 1.6239 - distribution_lambda_23_loss: 0.5493 - val_loss: 4.1715 - val_distribution_lambda_21_loss: 1.9580 - val_distribution_lambda_22_loss: 1.7036 - val_distribution_lambda_23_loss: 0.5099\n",
"Epoch 209/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1445 - distribution_lambda_21_loss: 1.9699 - distribution_lambda_22_loss: 1.6226 - distribution_lambda_23_loss: 0.5520 - val_loss: 4.1705 - val_distribution_lambda_21_loss: 1.9542 - val_distribution_lambda_22_loss: 1.7061 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 210/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.1404 - distribution_lambda_21_loss: 1.9692 - distribution_lambda_22_loss: 1.6253 - distribution_lambda_23_loss: 0.5458 - val_loss: 4.1680 - val_distribution_lambda_21_loss: 1.9505 - val_distribution_lambda_22_loss: 1.7072 - val_distribution_lambda_23_loss: 0.5104\n",
"Epoch 211/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.1316 - distribution_lambda_21_loss: 1.9639 - distribution_lambda_22_loss: 1.6197 - distribution_lambda_23_loss: 0.5480 - val_loss: 4.1651 - val_distribution_lambda_21_loss: 1.9467 - val_distribution_lambda_22_loss: 1.7079 - val_distribution_lambda_23_loss: 0.5106\n",
"Epoch 212/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1301 - distribution_lambda_21_loss: 1.9587 - distribution_lambda_22_loss: 1.6267 - distribution_lambda_23_loss: 0.5447 - val_loss: 4.1611 - val_distribution_lambda_21_loss: 1.9429 - val_distribution_lambda_22_loss: 1.7076 - val_distribution_lambda_23_loss: 0.5106\n",
"Epoch 213/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1349 - distribution_lambda_21_loss: 1.9570 - distribution_lambda_22_loss: 1.6256 - distribution_lambda_23_loss: 0.5523 - val_loss: 4.1573 - val_distribution_lambda_21_loss: 1.9391 - val_distribution_lambda_22_loss: 1.7076 - val_distribution_lambda_23_loss: 0.5106\n",
"Epoch 214/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1264 - distribution_lambda_21_loss: 1.9529 - distribution_lambda_22_loss: 1.6287 - distribution_lambda_23_loss: 0.5449 - val_loss: 4.1515 - val_distribution_lambda_21_loss: 1.9353 - val_distribution_lambda_22_loss: 1.7057 - val_distribution_lambda_23_loss: 0.5105\n",
"Epoch 215/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1387 - distribution_lambda_21_loss: 1.9496 - distribution_lambda_22_loss: 1.6289 - distribution_lambda_23_loss: 0.5603 - val_loss: 4.1458 - val_distribution_lambda_21_loss: 1.9314 - val_distribution_lambda_22_loss: 1.7039 - val_distribution_lambda_23_loss: 0.5105\n",
"Epoch 216/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1239 - distribution_lambda_21_loss: 1.9464 - distribution_lambda_22_loss: 1.6246 - distribution_lambda_23_loss: 0.5529 - val_loss: 4.1390 - val_distribution_lambda_21_loss: 1.9275 - val_distribution_lambda_22_loss: 1.7016 - val_distribution_lambda_23_loss: 0.5099\n",
"Epoch 217/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 4.1261 - distribution_lambda_21_loss: 1.9425 - distribution_lambda_22_loss: 1.6226 - distribution_lambda_23_loss: 0.5610 - val_loss: 4.1356 - val_distribution_lambda_21_loss: 1.9236 - val_distribution_lambda_22_loss: 1.7024 - val_distribution_lambda_23_loss: 0.5096\n",
"Epoch 218/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.1253 - distribution_lambda_21_loss: 1.9349 - distribution_lambda_22_loss: 1.6232 - distribution_lambda_23_loss: 0.5671 - val_loss: 4.1355 - val_distribution_lambda_21_loss: 1.9197 - val_distribution_lambda_22_loss: 1.7057 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 219/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.1107 - distribution_lambda_21_loss: 1.9313 - distribution_lambda_22_loss: 1.6223 - distribution_lambda_23_loss: 0.5571 - val_loss: 4.1325 - val_distribution_lambda_21_loss: 1.9157 - val_distribution_lambda_22_loss: 1.7064 - val_distribution_lambda_23_loss: 0.5105\n",
"Epoch 220/2500\n",
"9/9 [==============================] - 0s 9ms/step - loss: 4.1133 - distribution_lambda_21_loss: 1.9282 - distribution_lambda_22_loss: 1.6279 - distribution_lambda_23_loss: 0.5572 - val_loss: 4.1240 - val_distribution_lambda_21_loss: 1.9117 - val_distribution_lambda_22_loss: 1.7020 - val_distribution_lambda_23_loss: 0.5103\n",
"Epoch 221/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.0968 - distribution_lambda_21_loss: 1.9226 - distribution_lambda_22_loss: 1.6228 - distribution_lambda_23_loss: 0.5514 - val_loss: 4.1174 - val_distribution_lambda_21_loss: 1.9077 - val_distribution_lambda_22_loss: 1.6999 - val_distribution_lambda_23_loss: 0.5098\n",
"Epoch 222/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.1206 - distribution_lambda_21_loss: 1.9286 - distribution_lambda_22_loss: 1.6324 - distribution_lambda_23_loss: 0.5596 - val_loss: 4.1139 - val_distribution_lambda_21_loss: 1.9036 - val_distribution_lambda_22_loss: 1.6999 - val_distribution_lambda_23_loss: 0.5104\n",
"Epoch 223/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.0832 - distribution_lambda_21_loss: 1.9138 - distribution_lambda_22_loss: 1.6253 - distribution_lambda_23_loss: 0.5442 - val_loss: 4.1131 - val_distribution_lambda_21_loss: 1.8995 - val_distribution_lambda_22_loss: 1.7031 - val_distribution_lambda_23_loss: 0.5105\n",
"Epoch 224/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.1130 - distribution_lambda_21_loss: 1.9220 - distribution_lambda_22_loss: 1.6397 - distribution_lambda_23_loss: 0.5513 - val_loss: 4.1108 - val_distribution_lambda_21_loss: 1.8954 - val_distribution_lambda_22_loss: 1.7053 - val_distribution_lambda_23_loss: 0.5100\n",
"Epoch 225/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 4.0804 - distribution_lambda_21_loss: 1.9131 - distribution_lambda_22_loss: 1.6140 - distribution_lambda_23_loss: 0.5532 - val_loss: 4.1093 - val_distribution_lambda_21_loss: 1.8913 - val_distribution_lambda_22_loss: 1.7079 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 226/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0851 - distribution_lambda_21_loss: 1.9077 - distribution_lambda_22_loss: 1.6237 - distribution_lambda_23_loss: 0.5537 - val_loss: 4.1053 - val_distribution_lambda_21_loss: 1.8871 - val_distribution_lambda_22_loss: 1.7081 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 227/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0792 - distribution_lambda_21_loss: 1.9040 - distribution_lambda_22_loss: 1.6261 - distribution_lambda_23_loss: 0.5491 - val_loss: 4.1008 - val_distribution_lambda_21_loss: 1.8830 - val_distribution_lambda_22_loss: 1.7077 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 228/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0729 - distribution_lambda_21_loss: 1.8941 - distribution_lambda_22_loss: 1.6248 - distribution_lambda_23_loss: 0.5540 - val_loss: 4.0931 - val_distribution_lambda_21_loss: 1.8788 - val_distribution_lambda_22_loss: 1.7041 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 229/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0686 - distribution_lambda_21_loss: 1.8931 - distribution_lambda_22_loss: 1.6314 - distribution_lambda_23_loss: 0.5441 - val_loss: 4.0880 - val_distribution_lambda_21_loss: 1.8746 - val_distribution_lambda_22_loss: 1.7032 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 230/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0564 - distribution_lambda_21_loss: 1.8916 - distribution_lambda_22_loss: 1.6211 - distribution_lambda_23_loss: 0.5438 - val_loss: 4.0848 - val_distribution_lambda_21_loss: 1.8703 - val_distribution_lambda_22_loss: 1.7043 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 231/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0596 - distribution_lambda_21_loss: 1.8853 - distribution_lambda_22_loss: 1.6281 - distribution_lambda_23_loss: 0.5462 - val_loss: 4.0785 - val_distribution_lambda_21_loss: 1.8659 - val_distribution_lambda_22_loss: 1.7028 - val_distribution_lambda_23_loss: 0.5098\n",
"Epoch 232/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0771 - distribution_lambda_21_loss: 1.8863 - distribution_lambda_22_loss: 1.6351 - distribution_lambda_23_loss: 0.5557 - val_loss: 4.0728 - val_distribution_lambda_21_loss: 1.8616 - val_distribution_lambda_22_loss: 1.7022 - val_distribution_lambda_23_loss: 0.5089\n",
"Epoch 233/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0414 - distribution_lambda_21_loss: 1.8750 - distribution_lambda_22_loss: 1.6233 - distribution_lambda_23_loss: 0.5431 - val_loss: 4.0688 - val_distribution_lambda_21_loss: 1.8573 - val_distribution_lambda_22_loss: 1.7034 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 234/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0597 - distribution_lambda_21_loss: 1.8721 - distribution_lambda_22_loss: 1.6275 - distribution_lambda_23_loss: 0.5601 - val_loss: 4.0602 - val_distribution_lambda_21_loss: 1.8529 - val_distribution_lambda_22_loss: 1.6992 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 235/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0351 - distribution_lambda_21_loss: 1.8624 - distribution_lambda_22_loss: 1.6250 - distribution_lambda_23_loss: 0.5477 - val_loss: 4.0539 - val_distribution_lambda_21_loss: 1.8485 - val_distribution_lambda_22_loss: 1.6971 - val_distribution_lambda_23_loss: 0.5083\n",
"Epoch 236/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0452 - distribution_lambda_21_loss: 1.8598 - distribution_lambda_22_loss: 1.6287 - distribution_lambda_23_loss: 0.5567 - val_loss: 4.0500 - val_distribution_lambda_21_loss: 1.8441 - val_distribution_lambda_22_loss: 1.6975 - val_distribution_lambda_23_loss: 0.5085\n",
"Epoch 237/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0273 - distribution_lambda_21_loss: 1.8564 - distribution_lambda_22_loss: 1.6236 - distribution_lambda_23_loss: 0.5473 - val_loss: 4.0453 - val_distribution_lambda_21_loss: 1.8396 - val_distribution_lambda_22_loss: 1.6972 - val_distribution_lambda_23_loss: 0.5086\n",
"Epoch 238/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0277 - distribution_lambda_21_loss: 1.8518 - distribution_lambda_22_loss: 1.6230 - distribution_lambda_23_loss: 0.5529 - val_loss: 4.0413 - val_distribution_lambda_21_loss: 1.8351 - val_distribution_lambda_22_loss: 1.6979 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 239/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0410 - distribution_lambda_21_loss: 1.8538 - distribution_lambda_22_loss: 1.6314 - distribution_lambda_23_loss: 0.5558 - val_loss: 4.0381 - val_distribution_lambda_21_loss: 1.8305 - val_distribution_lambda_22_loss: 1.6994 - val_distribution_lambda_23_loss: 0.5082\n",
"Epoch 240/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0274 - distribution_lambda_21_loss: 1.8408 - distribution_lambda_22_loss: 1.6262 - distribution_lambda_23_loss: 0.5604 - val_loss: 4.0348 - val_distribution_lambda_21_loss: 1.8259 - val_distribution_lambda_22_loss: 1.7005 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 241/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 4.0124 - distribution_lambda_21_loss: 1.8435 - distribution_lambda_22_loss: 1.6283 - distribution_lambda_23_loss: 0.5406 - val_loss: 4.0334 - val_distribution_lambda_21_loss: 1.8213 - val_distribution_lambda_22_loss: 1.7039 - val_distribution_lambda_23_loss: 0.5082\n",
"Epoch 242/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 4.0032 - distribution_lambda_21_loss: 1.8360 - distribution_lambda_22_loss: 1.6223 - distribution_lambda_23_loss: 0.5450 - val_loss: 4.0280 - val_distribution_lambda_21_loss: 1.8166 - val_distribution_lambda_22_loss: 1.7033 - val_distribution_lambda_23_loss: 0.5080\n",
"Epoch 243/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9962 - distribution_lambda_21_loss: 1.8280 - distribution_lambda_22_loss: 1.6216 - distribution_lambda_23_loss: 0.5467 - val_loss: 4.0215 - val_distribution_lambda_21_loss: 1.8119 - val_distribution_lambda_22_loss: 1.7015 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 244/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0010 - distribution_lambda_21_loss: 1.8276 - distribution_lambda_22_loss: 1.6256 - distribution_lambda_23_loss: 0.5478 - val_loss: 4.0165 - val_distribution_lambda_21_loss: 1.8072 - val_distribution_lambda_22_loss: 1.7014 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 245/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9966 - distribution_lambda_21_loss: 1.8245 - distribution_lambda_22_loss: 1.6237 - distribution_lambda_23_loss: 0.5484 - val_loss: 4.0115 - val_distribution_lambda_21_loss: 1.8024 - val_distribution_lambda_22_loss: 1.7011 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 246/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 4.0004 - distribution_lambda_21_loss: 1.8226 - distribution_lambda_22_loss: 1.6298 - distribution_lambda_23_loss: 0.5480 - val_loss: 4.0090 - val_distribution_lambda_21_loss: 1.7976 - val_distribution_lambda_22_loss: 1.7033 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 247/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9982 - distribution_lambda_21_loss: 1.8180 - distribution_lambda_22_loss: 1.6385 - distribution_lambda_23_loss: 0.5416 - val_loss: 4.0062 - val_distribution_lambda_21_loss: 1.7928 - val_distribution_lambda_22_loss: 1.7049 - val_distribution_lambda_23_loss: 0.5085\n",
"Epoch 248/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9753 - distribution_lambda_21_loss: 1.8075 - distribution_lambda_22_loss: 1.6287 - distribution_lambda_23_loss: 0.5391 - val_loss: 3.9992 - val_distribution_lambda_21_loss: 1.7879 - val_distribution_lambda_22_loss: 1.7029 - val_distribution_lambda_23_loss: 0.5083\n",
"Epoch 249/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9696 - distribution_lambda_21_loss: 1.8002 - distribution_lambda_22_loss: 1.6212 - distribution_lambda_23_loss: 0.5482 - val_loss: 3.9936 - val_distribution_lambda_21_loss: 1.7830 - val_distribution_lambda_22_loss: 1.7022 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 250/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9591 - distribution_lambda_21_loss: 1.7927 - distribution_lambda_22_loss: 1.6181 - distribution_lambda_23_loss: 0.5483 - val_loss: 3.9865 - val_distribution_lambda_21_loss: 1.7781 - val_distribution_lambda_22_loss: 1.7001 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 251/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9680 - distribution_lambda_21_loss: 1.7876 - distribution_lambda_22_loss: 1.6236 - distribution_lambda_23_loss: 0.5568 - val_loss: 3.9819 - val_distribution_lambda_21_loss: 1.7731 - val_distribution_lambda_22_loss: 1.6998 - val_distribution_lambda_23_loss: 0.5090\n",
"Epoch 252/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9470 - distribution_lambda_21_loss: 1.7855 - distribution_lambda_22_loss: 1.6222 - distribution_lambda_23_loss: 0.5393 - val_loss: 3.9806 - val_distribution_lambda_21_loss: 1.7680 - val_distribution_lambda_22_loss: 1.7030 - val_distribution_lambda_23_loss: 0.5096\n",
"Epoch 253/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9560 - distribution_lambda_21_loss: 1.7800 - distribution_lambda_22_loss: 1.6157 - distribution_lambda_23_loss: 0.5603 - val_loss: 3.9794 - val_distribution_lambda_21_loss: 1.7629 - val_distribution_lambda_22_loss: 1.7063 - val_distribution_lambda_23_loss: 0.5102\n",
"Epoch 254/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9467 - distribution_lambda_21_loss: 1.7758 - distribution_lambda_22_loss: 1.6240 - distribution_lambda_23_loss: 0.5469 - val_loss: 3.9765 - val_distribution_lambda_21_loss: 1.7577 - val_distribution_lambda_22_loss: 1.7089 - val_distribution_lambda_23_loss: 0.5099\n",
"Epoch 255/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9402 - distribution_lambda_21_loss: 1.7697 - distribution_lambda_22_loss: 1.6195 - distribution_lambda_23_loss: 0.5511 - val_loss: 3.9723 - val_distribution_lambda_21_loss: 1.7525 - val_distribution_lambda_22_loss: 1.7097 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 256/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9491 - distribution_lambda_21_loss: 1.7654 - distribution_lambda_22_loss: 1.6230 - distribution_lambda_23_loss: 0.5607 - val_loss: 3.9678 - val_distribution_lambda_21_loss: 1.7473 - val_distribution_lambda_22_loss: 1.7105 - val_distribution_lambda_23_loss: 0.5100\n",
"Epoch 257/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9308 - distribution_lambda_21_loss: 1.7603 - distribution_lambda_22_loss: 1.6226 - distribution_lambda_23_loss: 0.5479 - val_loss: 3.9619 - val_distribution_lambda_21_loss: 1.7420 - val_distribution_lambda_22_loss: 1.7100 - val_distribution_lambda_23_loss: 0.5100\n",
"Epoch 258/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9339 - distribution_lambda_21_loss: 1.7598 - distribution_lambda_22_loss: 1.6245 - distribution_lambda_23_loss: 0.5496 - val_loss: 3.9597 - val_distribution_lambda_21_loss: 1.7365 - val_distribution_lambda_22_loss: 1.7124 - val_distribution_lambda_23_loss: 0.5108\n",
"Epoch 259/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9100 - distribution_lambda_21_loss: 1.7506 - distribution_lambda_22_loss: 1.6206 - distribution_lambda_23_loss: 0.5388 - val_loss: 3.9553 - val_distribution_lambda_21_loss: 1.7311 - val_distribution_lambda_22_loss: 1.7132 - val_distribution_lambda_23_loss: 0.5110\n",
"Epoch 260/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.9103 - distribution_lambda_21_loss: 1.7466 - distribution_lambda_22_loss: 1.6191 - distribution_lambda_23_loss: 0.5446 - val_loss: 3.9464 - val_distribution_lambda_21_loss: 1.7255 - val_distribution_lambda_22_loss: 1.7101 - val_distribution_lambda_23_loss: 0.5108\n",
"Epoch 261/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9028 - distribution_lambda_21_loss: 1.7395 - distribution_lambda_22_loss: 1.6210 - distribution_lambda_23_loss: 0.5423 - val_loss: 3.9356 - val_distribution_lambda_21_loss: 1.7200 - val_distribution_lambda_22_loss: 1.7057 - val_distribution_lambda_23_loss: 0.5099\n",
"Epoch 262/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.9167 - distribution_lambda_21_loss: 1.7383 - distribution_lambda_22_loss: 1.6321 - distribution_lambda_23_loss: 0.5464 - val_loss: 3.9309 - val_distribution_lambda_21_loss: 1.7143 - val_distribution_lambda_22_loss: 1.7068 - val_distribution_lambda_23_loss: 0.5098\n",
"Epoch 263/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8983 - distribution_lambda_21_loss: 1.7271 - distribution_lambda_22_loss: 1.6211 - distribution_lambda_23_loss: 0.5502 - val_loss: 3.9283 - val_distribution_lambda_21_loss: 1.7086 - val_distribution_lambda_22_loss: 1.7096 - val_distribution_lambda_23_loss: 0.5101\n",
"Epoch 264/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8920 - distribution_lambda_21_loss: 1.7234 - distribution_lambda_22_loss: 1.6210 - distribution_lambda_23_loss: 0.5476 - val_loss: 3.9266 - val_distribution_lambda_21_loss: 1.7028 - val_distribution_lambda_22_loss: 1.7125 - val_distribution_lambda_23_loss: 0.5113\n",
"Epoch 265/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 3.8742 - distribution_lambda_21_loss: 1.7131 - distribution_lambda_22_loss: 1.6205 - distribution_lambda_23_loss: 0.5406 - val_loss: 3.9162 - val_distribution_lambda_21_loss: 1.6970 - val_distribution_lambda_22_loss: 1.7084 - val_distribution_lambda_23_loss: 0.5108\n",
"Epoch 266/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8824 - distribution_lambda_21_loss: 1.7128 - distribution_lambda_22_loss: 1.6232 - distribution_lambda_23_loss: 0.5464 - val_loss: 3.9062 - val_distribution_lambda_21_loss: 1.6911 - val_distribution_lambda_22_loss: 1.7050 - val_distribution_lambda_23_loss: 0.5100\n",
"Epoch 267/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8498 - distribution_lambda_21_loss: 1.7035 - distribution_lambda_22_loss: 1.6130 - distribution_lambda_23_loss: 0.5332 - val_loss: 3.8981 - val_distribution_lambda_21_loss: 1.6853 - val_distribution_lambda_22_loss: 1.7041 - val_distribution_lambda_23_loss: 0.5087\n",
"Epoch 268/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8469 - distribution_lambda_21_loss: 1.6972 - distribution_lambda_22_loss: 1.6199 - distribution_lambda_23_loss: 0.5297 - val_loss: 3.8942 - val_distribution_lambda_21_loss: 1.6793 - val_distribution_lambda_22_loss: 1.7069 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 269/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8400 - distribution_lambda_21_loss: 1.6908 - distribution_lambda_22_loss: 1.6131 - distribution_lambda_23_loss: 0.5361 - val_loss: 3.8887 - val_distribution_lambda_21_loss: 1.6732 - val_distribution_lambda_22_loss: 1.7081 - val_distribution_lambda_23_loss: 0.5074\n",
"Epoch 270/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8456 - distribution_lambda_21_loss: 1.6837 - distribution_lambda_22_loss: 1.6142 - distribution_lambda_23_loss: 0.5477 - val_loss: 3.8801 - val_distribution_lambda_21_loss: 1.6669 - val_distribution_lambda_22_loss: 1.7056 - val_distribution_lambda_23_loss: 0.5075\n",
"Epoch 271/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8498 - distribution_lambda_21_loss: 1.6810 - distribution_lambda_22_loss: 1.6217 - distribution_lambda_23_loss: 0.5471 - val_loss: 3.8705 - val_distribution_lambda_21_loss: 1.6605 - val_distribution_lambda_22_loss: 1.7021 - val_distribution_lambda_23_loss: 0.5078\n",
"Epoch 272/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8455 - distribution_lambda_21_loss: 1.6727 - distribution_lambda_22_loss: 1.6177 - distribution_lambda_23_loss: 0.5550 - val_loss: 3.8646 - val_distribution_lambda_21_loss: 1.6541 - val_distribution_lambda_22_loss: 1.7023 - val_distribution_lambda_23_loss: 0.5082\n",
"Epoch 273/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.8367 - distribution_lambda_21_loss: 1.6703 - distribution_lambda_22_loss: 1.6262 - distribution_lambda_23_loss: 0.5402 - val_loss: 3.8601 - val_distribution_lambda_21_loss: 1.6476 - val_distribution_lambda_22_loss: 1.7041 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 274/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8166 - distribution_lambda_21_loss: 1.6585 - distribution_lambda_22_loss: 1.6197 - distribution_lambda_23_loss: 0.5385 - val_loss: 3.8580 - val_distribution_lambda_21_loss: 1.6409 - val_distribution_lambda_22_loss: 1.7079 - val_distribution_lambda_23_loss: 0.5092\n",
"Epoch 275/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8216 - distribution_lambda_21_loss: 1.6554 - distribution_lambda_22_loss: 1.6190 - distribution_lambda_23_loss: 0.5472 - val_loss: 3.8521 - val_distribution_lambda_21_loss: 1.6343 - val_distribution_lambda_22_loss: 1.7084 - val_distribution_lambda_23_loss: 0.5094\n",
"Epoch 276/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8195 - distribution_lambda_21_loss: 1.6467 - distribution_lambda_22_loss: 1.6303 - distribution_lambda_23_loss: 0.5425 - val_loss: 3.8451 - val_distribution_lambda_21_loss: 1.6275 - val_distribution_lambda_22_loss: 1.7087 - val_distribution_lambda_23_loss: 0.5089\n",
"Epoch 277/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8111 - distribution_lambda_21_loss: 1.6428 - distribution_lambda_22_loss: 1.6199 - distribution_lambda_23_loss: 0.5484 - val_loss: 3.8373 - val_distribution_lambda_21_loss: 1.6209 - val_distribution_lambda_22_loss: 1.7071 - val_distribution_lambda_23_loss: 0.5092\n",
"Epoch 278/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.8006 - distribution_lambda_21_loss: 1.6368 - distribution_lambda_22_loss: 1.6273 - distribution_lambda_23_loss: 0.5364 - val_loss: 3.8313 - val_distribution_lambda_21_loss: 1.6143 - val_distribution_lambda_22_loss: 1.7079 - val_distribution_lambda_23_loss: 0.5091\n",
"Epoch 279/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7860 - distribution_lambda_21_loss: 1.6272 - distribution_lambda_22_loss: 1.6188 - distribution_lambda_23_loss: 0.5401 - val_loss: 3.8249 - val_distribution_lambda_21_loss: 1.6076 - val_distribution_lambda_22_loss: 1.7087 - val_distribution_lambda_23_loss: 0.5086\n",
"Epoch 280/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7838 - distribution_lambda_21_loss: 1.6186 - distribution_lambda_22_loss: 1.6170 - distribution_lambda_23_loss: 0.5482 - val_loss: 3.8167 - val_distribution_lambda_21_loss: 1.6008 - val_distribution_lambda_22_loss: 1.7071 - val_distribution_lambda_23_loss: 0.5088\n",
"Epoch 281/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7936 - distribution_lambda_21_loss: 1.6125 - distribution_lambda_22_loss: 1.6206 - distribution_lambda_23_loss: 0.5604 - val_loss: 3.8104 - val_distribution_lambda_21_loss: 1.5941 - val_distribution_lambda_22_loss: 1.7065 - val_distribution_lambda_23_loss: 0.5099\n",
"Epoch 282/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7808 - distribution_lambda_21_loss: 1.6112 - distribution_lambda_22_loss: 1.6213 - distribution_lambda_23_loss: 0.5483 - val_loss: 3.8066 - val_distribution_lambda_21_loss: 1.5873 - val_distribution_lambda_22_loss: 1.7093 - val_distribution_lambda_23_loss: 0.5100\n",
"Epoch 283/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7533 - distribution_lambda_21_loss: 1.5985 - distribution_lambda_22_loss: 1.6158 - distribution_lambda_23_loss: 0.5390 - val_loss: 3.7963 - val_distribution_lambda_21_loss: 1.5807 - val_distribution_lambda_22_loss: 1.7066 - val_distribution_lambda_23_loss: 0.5091\n",
"Epoch 284/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7530 - distribution_lambda_21_loss: 1.6027 - distribution_lambda_22_loss: 1.6174 - distribution_lambda_23_loss: 0.5329 - val_loss: 3.7885 - val_distribution_lambda_21_loss: 1.5740 - val_distribution_lambda_22_loss: 1.7064 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 285/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7418 - distribution_lambda_21_loss: 1.5857 - distribution_lambda_22_loss: 1.6128 - distribution_lambda_23_loss: 0.5433 - val_loss: 3.7815 - val_distribution_lambda_21_loss: 1.5674 - val_distribution_lambda_22_loss: 1.7065 - val_distribution_lambda_23_loss: 0.5076\n",
"Epoch 286/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.7443 - distribution_lambda_21_loss: 1.5840 - distribution_lambda_22_loss: 1.6247 - distribution_lambda_23_loss: 0.5357 - val_loss: 3.7757 - val_distribution_lambda_21_loss: 1.5607 - val_distribution_lambda_22_loss: 1.7076 - val_distribution_lambda_23_loss: 0.5074\n",
"Epoch 287/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.7514 - distribution_lambda_21_loss: 1.5779 - distribution_lambda_22_loss: 1.6189 - distribution_lambda_23_loss: 0.5545 - val_loss: 3.7664 - val_distribution_lambda_21_loss: 1.5540 - val_distribution_lambda_22_loss: 1.7041 - val_distribution_lambda_23_loss: 0.5083\n",
"Epoch 288/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.7141 - distribution_lambda_21_loss: 1.5692 - distribution_lambda_22_loss: 1.6125 - distribution_lambda_23_loss: 0.5324 - val_loss: 3.7579 - val_distribution_lambda_21_loss: 1.5473 - val_distribution_lambda_22_loss: 1.7020 - val_distribution_lambda_23_loss: 0.5085\n",
"Epoch 289/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 3.7232 - distribution_lambda_21_loss: 1.5626 - distribution_lambda_22_loss: 1.6189 - distribution_lambda_23_loss: 0.5417 - val_loss: 3.7510 - val_distribution_lambda_21_loss: 1.5407 - val_distribution_lambda_22_loss: 1.7018 - val_distribution_lambda_23_loss: 0.5085\n",
"Epoch 290/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.7144 - distribution_lambda_21_loss: 1.5553 - distribution_lambda_22_loss: 1.6203 - distribution_lambda_23_loss: 0.5388 - val_loss: 3.7467 - val_distribution_lambda_21_loss: 1.5341 - val_distribution_lambda_22_loss: 1.7047 - val_distribution_lambda_23_loss: 0.5080\n",
"Epoch 291/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.7191 - distribution_lambda_21_loss: 1.5494 - distribution_lambda_22_loss: 1.6187 - distribution_lambda_23_loss: 0.5510 - val_loss: 3.7434 - val_distribution_lambda_21_loss: 1.5274 - val_distribution_lambda_22_loss: 1.7080 - val_distribution_lambda_23_loss: 0.5080\n",
"Epoch 292/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6879 - distribution_lambda_21_loss: 1.5411 - distribution_lambda_22_loss: 1.6120 - distribution_lambda_23_loss: 0.5348 - val_loss: 3.7415 - val_distribution_lambda_21_loss: 1.5207 - val_distribution_lambda_22_loss: 1.7124 - val_distribution_lambda_23_loss: 0.5084\n",
"Epoch 293/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6821 - distribution_lambda_21_loss: 1.5336 - distribution_lambda_22_loss: 1.6096 - distribution_lambda_23_loss: 0.5390 - val_loss: 3.7360 - val_distribution_lambda_21_loss: 1.5141 - val_distribution_lambda_22_loss: 1.7133 - val_distribution_lambda_23_loss: 0.5086\n",
"Epoch 294/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6938 - distribution_lambda_21_loss: 1.5306 - distribution_lambda_22_loss: 1.6200 - distribution_lambda_23_loss: 0.5433 - val_loss: 3.7288 - val_distribution_lambda_21_loss: 1.5074 - val_distribution_lambda_22_loss: 1.7128 - val_distribution_lambda_23_loss: 0.5086\n",
"Epoch 295/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6730 - distribution_lambda_21_loss: 1.5257 - distribution_lambda_22_loss: 1.6086 - distribution_lambda_23_loss: 0.5387 - val_loss: 3.7216 - val_distribution_lambda_21_loss: 1.5007 - val_distribution_lambda_22_loss: 1.7127 - val_distribution_lambda_23_loss: 0.5083\n",
"Epoch 296/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6937 - distribution_lambda_21_loss: 1.5168 - distribution_lambda_22_loss: 1.6289 - distribution_lambda_23_loss: 0.5480 - val_loss: 3.7122 - val_distribution_lambda_21_loss: 1.4943 - val_distribution_lambda_22_loss: 1.7097 - val_distribution_lambda_23_loss: 0.5082\n",
"Epoch 297/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6623 - distribution_lambda_21_loss: 1.5129 - distribution_lambda_22_loss: 1.6162 - distribution_lambda_23_loss: 0.5333 - val_loss: 3.7052 - val_distribution_lambda_21_loss: 1.4878 - val_distribution_lambda_22_loss: 1.7099 - val_distribution_lambda_23_loss: 0.5075\n",
"Epoch 298/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6570 - distribution_lambda_21_loss: 1.5022 - distribution_lambda_22_loss: 1.6177 - distribution_lambda_23_loss: 0.5372 - val_loss: 3.6974 - val_distribution_lambda_21_loss: 1.4812 - val_distribution_lambda_22_loss: 1.7093 - val_distribution_lambda_23_loss: 0.5069\n",
"Epoch 299/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6508 - distribution_lambda_21_loss: 1.4981 - distribution_lambda_22_loss: 1.6201 - distribution_lambda_23_loss: 0.5326 - val_loss: 3.6914 - val_distribution_lambda_21_loss: 1.4745 - val_distribution_lambda_22_loss: 1.7104 - val_distribution_lambda_23_loss: 0.5065\n",
"Epoch 300/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6353 - distribution_lambda_21_loss: 1.4896 - distribution_lambda_22_loss: 1.6124 - distribution_lambda_23_loss: 0.5334 - val_loss: 3.6852 - val_distribution_lambda_21_loss: 1.4678 - val_distribution_lambda_22_loss: 1.7114 - val_distribution_lambda_23_loss: 0.5060\n",
"Epoch 301/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6457 - distribution_lambda_21_loss: 1.4827 - distribution_lambda_22_loss: 1.6237 - distribution_lambda_23_loss: 0.5394 - val_loss: 3.6829 - val_distribution_lambda_21_loss: 1.4614 - val_distribution_lambda_22_loss: 1.7152 - val_distribution_lambda_23_loss: 0.5063\n",
"Epoch 302/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6464 - distribution_lambda_21_loss: 1.4770 - distribution_lambda_22_loss: 1.6169 - distribution_lambda_23_loss: 0.5525 - val_loss: 3.6805 - val_distribution_lambda_21_loss: 1.4548 - val_distribution_lambda_22_loss: 1.7186 - val_distribution_lambda_23_loss: 0.5071\n",
"Epoch 303/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.6284 - distribution_lambda_21_loss: 1.4652 - distribution_lambda_22_loss: 1.6173 - distribution_lambda_23_loss: 0.5459 - val_loss: 3.6717 - val_distribution_lambda_21_loss: 1.4480 - val_distribution_lambda_22_loss: 1.7157 - val_distribution_lambda_23_loss: 0.5080\n",
"Epoch 304/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 3.6168 - distribution_lambda_21_loss: 1.4601 - distribution_lambda_22_loss: 1.6132 - distribution_lambda_23_loss: 0.5435 - val_loss: 3.6623 - val_distribution_lambda_21_loss: 1.4411 - val_distribution_lambda_22_loss: 1.7123 - val_distribution_lambda_23_loss: 0.5089\n",
"Epoch 305/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6299 - distribution_lambda_21_loss: 1.4624 - distribution_lambda_22_loss: 1.6234 - distribution_lambda_23_loss: 0.5441 - val_loss: 3.6542 - val_distribution_lambda_21_loss: 1.4341 - val_distribution_lambda_22_loss: 1.7105 - val_distribution_lambda_23_loss: 0.5095\n",
"Epoch 306/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.6101 - distribution_lambda_21_loss: 1.4522 - distribution_lambda_22_loss: 1.6174 - distribution_lambda_23_loss: 0.5404 - val_loss: 3.6462 - val_distribution_lambda_21_loss: 1.4274 - val_distribution_lambda_22_loss: 1.7098 - val_distribution_lambda_23_loss: 0.5090\n",
"Epoch 307/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.5919 - distribution_lambda_21_loss: 1.4400 - distribution_lambda_22_loss: 1.6149 - distribution_lambda_23_loss: 0.5370 - val_loss: 3.6397 - val_distribution_lambda_21_loss: 1.4205 - val_distribution_lambda_22_loss: 1.7112 - val_distribution_lambda_23_loss: 0.5080\n",
"Epoch 308/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.5959 - distribution_lambda_21_loss: 1.4339 - distribution_lambda_22_loss: 1.6122 - distribution_lambda_23_loss: 0.5498 - val_loss: 3.6319 - val_distribution_lambda_21_loss: 1.4132 - val_distribution_lambda_22_loss: 1.7110 - val_distribution_lambda_23_loss: 0.5077\n",
"Epoch 309/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.5917 - distribution_lambda_21_loss: 1.4307 - distribution_lambda_22_loss: 1.6179 - distribution_lambda_23_loss: 0.5431 - val_loss: 3.6253 - val_distribution_lambda_21_loss: 1.4058 - val_distribution_lambda_22_loss: 1.7118 - val_distribution_lambda_23_loss: 0.5078\n",
"Epoch 310/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.5699 - distribution_lambda_21_loss: 1.4211 - distribution_lambda_22_loss: 1.6173 - distribution_lambda_23_loss: 0.5315 - val_loss: 3.6192 - val_distribution_lambda_21_loss: 1.3981 - val_distribution_lambda_22_loss: 1.7132 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 311/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.5616 - distribution_lambda_21_loss: 1.4100 - distribution_lambda_22_loss: 1.6158 - distribution_lambda_23_loss: 0.5358 - val_loss: 3.6108 - val_distribution_lambda_21_loss: 1.3900 - val_distribution_lambda_22_loss: 1.7131 - val_distribution_lambda_23_loss: 0.5077\n",
"Epoch 312/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.5683 - distribution_lambda_21_loss: 1.4017 - distribution_lambda_22_loss: 1.6157 - distribution_lambda_23_loss: 0.5509 - val_loss: 3.6043 - val_distribution_lambda_21_loss: 1.3815 - val_distribution_lambda_22_loss: 1.7147 - val_distribution_lambda_23_loss: 0.5081\n",
"Epoch 313/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 3.5462 - distribution_lambda_21_loss: 1.3968 - distribution_lambda_22_loss: 1.6118 - distribution_lambda_23_loss: 0.5376 - val_loss: 3.5931 - val_distribution_lambda_21_loss: 1.3729 - val_distribution_lambda_22_loss: 1.7123 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 314/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.5296 - distribution_lambda_21_loss: 1.3863 - distribution_lambda_22_loss: 1.6076 - distribution_lambda_23_loss: 0.5356 - val_loss: 3.5828 - val_distribution_lambda_21_loss: 1.3641 - val_distribution_lambda_22_loss: 1.7116 - val_distribution_lambda_23_loss: 0.5070\n",
"Epoch 315/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.5317 - distribution_lambda_21_loss: 1.3762 - distribution_lambda_22_loss: 1.6100 - distribution_lambda_23_loss: 0.5455 - val_loss: 3.5756 - val_distribution_lambda_21_loss: 1.3550 - val_distribution_lambda_22_loss: 1.7131 - val_distribution_lambda_23_loss: 0.5075\n",
"Epoch 316/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.5228 - distribution_lambda_21_loss: 1.3708 - distribution_lambda_22_loss: 1.6140 - distribution_lambda_23_loss: 0.5379 - val_loss: 3.5686 - val_distribution_lambda_21_loss: 1.3460 - val_distribution_lambda_22_loss: 1.7160 - val_distribution_lambda_23_loss: 0.5067\n",
"Epoch 317/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 3.5378 - distribution_lambda_21_loss: 1.3647 - distribution_lambda_22_loss: 1.6233 - distribution_lambda_23_loss: 0.5498 - val_loss: 3.5586 - val_distribution_lambda_21_loss: 1.3368 - val_distribution_lambda_22_loss: 1.7153 - val_distribution_lambda_23_loss: 0.5066\n",
"Epoch 318/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.5204 - distribution_lambda_21_loss: 1.3524 - distribution_lambda_22_loss: 1.6213 - distribution_lambda_23_loss: 0.5468 - val_loss: 3.5482 - val_distribution_lambda_21_loss: 1.3277 - val_distribution_lambda_22_loss: 1.7135 - val_distribution_lambda_23_loss: 0.5070\n",
"Epoch 319/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.4997 - distribution_lambda_21_loss: 1.3433 - distribution_lambda_22_loss: 1.6167 - distribution_lambda_23_loss: 0.5398 - val_loss: 3.5394 - val_distribution_lambda_21_loss: 1.3188 - val_distribution_lambda_22_loss: 1.7139 - val_distribution_lambda_23_loss: 0.5066\n",
"Epoch 320/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.4806 - distribution_lambda_21_loss: 1.3344 - distribution_lambda_22_loss: 1.6120 - distribution_lambda_23_loss: 0.5342 - val_loss: 3.5272 - val_distribution_lambda_21_loss: 1.3100 - val_distribution_lambda_22_loss: 1.7119 - val_distribution_lambda_23_loss: 0.5053\n",
"Epoch 321/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4841 - distribution_lambda_21_loss: 1.3281 - distribution_lambda_22_loss: 1.6124 - distribution_lambda_23_loss: 0.5436 - val_loss: 3.5183 - val_distribution_lambda_21_loss: 1.3012 - val_distribution_lambda_22_loss: 1.7116 - val_distribution_lambda_23_loss: 0.5055\n",
"Epoch 322/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4530 - distribution_lambda_21_loss: 1.3213 - distribution_lambda_22_loss: 1.6085 - distribution_lambda_23_loss: 0.5232 - val_loss: 3.5103 - val_distribution_lambda_21_loss: 1.2926 - val_distribution_lambda_22_loss: 1.7120 - val_distribution_lambda_23_loss: 0.5057\n",
"Epoch 323/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4680 - distribution_lambda_21_loss: 1.3085 - distribution_lambda_22_loss: 1.6154 - distribution_lambda_23_loss: 0.5441 - val_loss: 3.5027 - val_distribution_lambda_21_loss: 1.2841 - val_distribution_lambda_22_loss: 1.7136 - val_distribution_lambda_23_loss: 0.5050\n",
"Epoch 324/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4675 - distribution_lambda_21_loss: 1.2999 - distribution_lambda_22_loss: 1.6164 - distribution_lambda_23_loss: 0.5512 - val_loss: 3.4943 - val_distribution_lambda_21_loss: 1.2763 - val_distribution_lambda_22_loss: 1.7126 - val_distribution_lambda_23_loss: 0.5054\n",
"Epoch 325/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4358 - distribution_lambda_21_loss: 1.2927 - distribution_lambda_22_loss: 1.6117 - distribution_lambda_23_loss: 0.5314 - val_loss: 3.4856 - val_distribution_lambda_21_loss: 1.2687 - val_distribution_lambda_22_loss: 1.7120 - val_distribution_lambda_23_loss: 0.5049\n",
"Epoch 326/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4408 - distribution_lambda_21_loss: 1.2899 - distribution_lambda_22_loss: 1.6153 - distribution_lambda_23_loss: 0.5356 - val_loss: 3.4805 - val_distribution_lambda_21_loss: 1.2605 - val_distribution_lambda_22_loss: 1.7144 - val_distribution_lambda_23_loss: 0.5056\n",
"Epoch 327/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4475 - distribution_lambda_21_loss: 1.2807 - distribution_lambda_22_loss: 1.6226 - distribution_lambda_23_loss: 0.5442 - val_loss: 3.4720 - val_distribution_lambda_21_loss: 1.2523 - val_distribution_lambda_22_loss: 1.7133 - val_distribution_lambda_23_loss: 0.5064\n",
"Epoch 328/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.4104 - distribution_lambda_21_loss: 1.2732 - distribution_lambda_22_loss: 1.6126 - distribution_lambda_23_loss: 0.5246 - val_loss: 3.4639 - val_distribution_lambda_21_loss: 1.2443 - val_distribution_lambda_22_loss: 1.7135 - val_distribution_lambda_23_loss: 0.5061\n",
"Epoch 329/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.4350 - distribution_lambda_21_loss: 1.2749 - distribution_lambda_22_loss: 1.6285 - distribution_lambda_23_loss: 0.5315 - val_loss: 3.4574 - val_distribution_lambda_21_loss: 1.2360 - val_distribution_lambda_22_loss: 1.7155 - val_distribution_lambda_23_loss: 0.5058\n",
"Epoch 330/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.4089 - distribution_lambda_21_loss: 1.2574 - distribution_lambda_22_loss: 1.6211 - distribution_lambda_23_loss: 0.5304 - val_loss: 3.4467 - val_distribution_lambda_21_loss: 1.2276 - val_distribution_lambda_22_loss: 1.7139 - val_distribution_lambda_23_loss: 0.5052\n",
"Epoch 331/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3913 - distribution_lambda_21_loss: 1.2510 - distribution_lambda_22_loss: 1.6117 - distribution_lambda_23_loss: 0.5286 - val_loss: 3.4374 - val_distribution_lambda_21_loss: 1.2191 - val_distribution_lambda_22_loss: 1.7133 - val_distribution_lambda_23_loss: 0.5050\n",
"Epoch 332/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3762 - distribution_lambda_21_loss: 1.2374 - distribution_lambda_22_loss: 1.6043 - distribution_lambda_23_loss: 0.5345 - val_loss: 3.4309 - val_distribution_lambda_21_loss: 1.2101 - val_distribution_lambda_22_loss: 1.7158 - val_distribution_lambda_23_loss: 0.5050\n",
"Epoch 333/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3777 - distribution_lambda_21_loss: 1.2369 - distribution_lambda_22_loss: 1.6107 - distribution_lambda_23_loss: 0.5300 - val_loss: 3.4213 - val_distribution_lambda_21_loss: 1.2010 - val_distribution_lambda_22_loss: 1.7155 - val_distribution_lambda_23_loss: 0.5048\n",
"Epoch 334/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3778 - distribution_lambda_21_loss: 1.2261 - distribution_lambda_22_loss: 1.6152 - distribution_lambda_23_loss: 0.5365 - val_loss: 3.4136 - val_distribution_lambda_21_loss: 1.1911 - val_distribution_lambda_22_loss: 1.7168 - val_distribution_lambda_23_loss: 0.5057\n",
"Epoch 335/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.3637 - distribution_lambda_21_loss: 1.2198 - distribution_lambda_22_loss: 1.6107 - distribution_lambda_23_loss: 0.5332 - val_loss: 3.4047 - val_distribution_lambda_21_loss: 1.1804 - val_distribution_lambda_22_loss: 1.7181 - val_distribution_lambda_23_loss: 0.5061\n",
"Epoch 336/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3395 - distribution_lambda_21_loss: 1.2024 - distribution_lambda_22_loss: 1.6056 - distribution_lambda_23_loss: 0.5315 - val_loss: 3.3938 - val_distribution_lambda_21_loss: 1.1688 - val_distribution_lambda_22_loss: 1.7180 - val_distribution_lambda_23_loss: 0.5070\n",
"Epoch 337/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 3.3530 - distribution_lambda_21_loss: 1.2011 - distribution_lambda_22_loss: 1.6101 - distribution_lambda_23_loss: 0.5418 - val_loss: 3.3764 - val_distribution_lambda_21_loss: 1.1574 - val_distribution_lambda_22_loss: 1.7130 - val_distribution_lambda_23_loss: 0.5061\n",
"Epoch 338/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3234 - distribution_lambda_21_loss: 1.1887 - distribution_lambda_22_loss: 1.6047 - distribution_lambda_23_loss: 0.5300 - val_loss: 3.3614 - val_distribution_lambda_21_loss: 1.1456 - val_distribution_lambda_22_loss: 1.7105 - val_distribution_lambda_23_loss: 0.5052\n",
"Epoch 339/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.3428 - distribution_lambda_21_loss: 1.1907 - distribution_lambda_22_loss: 1.6180 - distribution_lambda_23_loss: 0.5342 - val_loss: 3.3503 - val_distribution_lambda_21_loss: 1.1333 - val_distribution_lambda_22_loss: 1.7123 - val_distribution_lambda_23_loss: 0.5046\n",
"Epoch 340/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.3274 - distribution_lambda_21_loss: 1.1748 - distribution_lambda_22_loss: 1.6145 - distribution_lambda_23_loss: 0.5380 - val_loss: 3.3421 - val_distribution_lambda_21_loss: 1.1218 - val_distribution_lambda_22_loss: 1.7153 - val_distribution_lambda_23_loss: 0.5050\n",
"Epoch 341/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.3242 - distribution_lambda_21_loss: 1.1673 - distribution_lambda_22_loss: 1.6143 - distribution_lambda_23_loss: 0.5426 - val_loss: 3.3323 - val_distribution_lambda_21_loss: 1.1114 - val_distribution_lambda_22_loss: 1.7162 - val_distribution_lambda_23_loss: 0.5048\n",
"Epoch 342/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.3093 - distribution_lambda_21_loss: 1.1648 - distribution_lambda_22_loss: 1.6129 - distribution_lambda_23_loss: 0.5317 - val_loss: 3.3219 - val_distribution_lambda_21_loss: 1.1027 - val_distribution_lambda_22_loss: 1.7143 - val_distribution_lambda_23_loss: 0.5049\n",
"Epoch 343/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2894 - distribution_lambda_21_loss: 1.1489 - distribution_lambda_22_loss: 1.6073 - distribution_lambda_23_loss: 0.5332 - val_loss: 3.3138 - val_distribution_lambda_21_loss: 1.0948 - val_distribution_lambda_22_loss: 1.7138 - val_distribution_lambda_23_loss: 0.5052\n",
"Epoch 344/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.2863 - distribution_lambda_21_loss: 1.1424 - distribution_lambda_22_loss: 1.6114 - distribution_lambda_23_loss: 0.5324 - val_loss: 3.3036 - val_distribution_lambda_21_loss: 1.0872 - val_distribution_lambda_22_loss: 1.7115 - val_distribution_lambda_23_loss: 0.5049\n",
"Epoch 345/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.2753 - distribution_lambda_21_loss: 1.1389 - distribution_lambda_22_loss: 1.6080 - distribution_lambda_23_loss: 0.5284 - val_loss: 3.2942 - val_distribution_lambda_21_loss: 1.0797 - val_distribution_lambda_22_loss: 1.7100 - val_distribution_lambda_23_loss: 0.5045\n",
"Epoch 346/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2650 - distribution_lambda_21_loss: 1.1279 - distribution_lambda_22_loss: 1.6085 - distribution_lambda_23_loss: 0.5286 - val_loss: 3.2860 - val_distribution_lambda_21_loss: 1.0728 - val_distribution_lambda_22_loss: 1.7092 - val_distribution_lambda_23_loss: 0.5041\n",
"Epoch 347/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2657 - distribution_lambda_21_loss: 1.1291 - distribution_lambda_22_loss: 1.5981 - distribution_lambda_23_loss: 0.5385 - val_loss: 3.2797 - val_distribution_lambda_21_loss: 1.0664 - val_distribution_lambda_22_loss: 1.7094 - val_distribution_lambda_23_loss: 0.5039\n",
"Epoch 348/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.2875 - distribution_lambda_21_loss: 1.1310 - distribution_lambda_22_loss: 1.6057 - distribution_lambda_23_loss: 0.5508 - val_loss: 3.2725 - val_distribution_lambda_21_loss: 1.0607 - val_distribution_lambda_22_loss: 1.7067 - val_distribution_lambda_23_loss: 0.5051\n",
"Epoch 349/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2564 - distribution_lambda_21_loss: 1.1100 - distribution_lambda_22_loss: 1.6033 - distribution_lambda_23_loss: 0.5431 - val_loss: 3.2615 - val_distribution_lambda_21_loss: 1.0547 - val_distribution_lambda_22_loss: 1.7015 - val_distribution_lambda_23_loss: 0.5053\n",
"Epoch 350/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2544 - distribution_lambda_21_loss: 1.1075 - distribution_lambda_22_loss: 1.6061 - distribution_lambda_23_loss: 0.5408 - val_loss: 3.2536 - val_distribution_lambda_21_loss: 1.0488 - val_distribution_lambda_22_loss: 1.6998 - val_distribution_lambda_23_loss: 0.5049\n",
"Epoch 351/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2268 - distribution_lambda_21_loss: 1.1107 - distribution_lambda_22_loss: 1.5924 - distribution_lambda_23_loss: 0.5238 - val_loss: 3.2419 - val_distribution_lambda_21_loss: 1.0432 - val_distribution_lambda_22_loss: 1.6951 - val_distribution_lambda_23_loss: 0.5036\n",
"Epoch 352/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2241 - distribution_lambda_21_loss: 1.0996 - distribution_lambda_22_loss: 1.5883 - distribution_lambda_23_loss: 0.5362 - val_loss: 3.2288 - val_distribution_lambda_21_loss: 1.0376 - val_distribution_lambda_22_loss: 1.6879 - val_distribution_lambda_23_loss: 0.5033\n",
"Epoch 353/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.2364 - distribution_lambda_21_loss: 1.1030 - distribution_lambda_22_loss: 1.5941 - distribution_lambda_23_loss: 0.5393 - val_loss: 3.1929 - val_distribution_lambda_21_loss: 1.0325 - val_distribution_lambda_22_loss: 1.6576 - val_distribution_lambda_23_loss: 0.5028\n",
"Epoch 354/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.2116 - distribution_lambda_21_loss: 1.0974 - distribution_lambda_22_loss: 1.5758 - distribution_lambda_23_loss: 0.5384 - val_loss: 3.1839 - val_distribution_lambda_21_loss: 1.0273 - val_distribution_lambda_22_loss: 1.6529 - val_distribution_lambda_23_loss: 0.5038\n",
"Epoch 355/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1835 - distribution_lambda_21_loss: 1.0810 - distribution_lambda_22_loss: 1.5713 - distribution_lambda_23_loss: 0.5311 - val_loss: 3.1853 - val_distribution_lambda_21_loss: 1.0221 - val_distribution_lambda_22_loss: 1.6585 - val_distribution_lambda_23_loss: 0.5046\n",
"Epoch 356/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1893 - distribution_lambda_21_loss: 1.0866 - distribution_lambda_22_loss: 1.5655 - distribution_lambda_23_loss: 0.5372 - val_loss: 3.1726 - val_distribution_lambda_21_loss: 1.0172 - val_distribution_lambda_22_loss: 1.6505 - val_distribution_lambda_23_loss: 0.5050\n",
"Epoch 357/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1693 - distribution_lambda_21_loss: 1.0828 - distribution_lambda_22_loss: 1.5602 - distribution_lambda_23_loss: 0.5263 - val_loss: 3.1635 - val_distribution_lambda_21_loss: 1.0124 - val_distribution_lambda_22_loss: 1.6464 - val_distribution_lambda_23_loss: 0.5046\n",
"Epoch 358/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.1908 - distribution_lambda_21_loss: 1.0803 - distribution_lambda_22_loss: 1.5666 - distribution_lambda_23_loss: 0.5440 - val_loss: 3.1558 - val_distribution_lambda_21_loss: 1.0078 - val_distribution_lambda_22_loss: 1.6436 - val_distribution_lambda_23_loss: 0.5044\n",
"Epoch 359/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.1597 - distribution_lambda_21_loss: 1.0784 - distribution_lambda_22_loss: 1.5437 - distribution_lambda_23_loss: 0.5376 - val_loss: 3.1605 - val_distribution_lambda_21_loss: 1.0032 - val_distribution_lambda_22_loss: 1.6524 - val_distribution_lambda_23_loss: 0.5049\n",
"Epoch 360/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.1666 - distribution_lambda_21_loss: 1.0667 - distribution_lambda_22_loss: 1.5672 - distribution_lambda_23_loss: 0.5327 - val_loss: 3.1504 - val_distribution_lambda_21_loss: 0.9985 - val_distribution_lambda_22_loss: 1.6468 - val_distribution_lambda_23_loss: 0.5051\n",
"Epoch 361/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 3.1413 - distribution_lambda_21_loss: 1.0571 - distribution_lambda_22_loss: 1.5516 - distribution_lambda_23_loss: 0.5326 - val_loss: 3.1430 - val_distribution_lambda_21_loss: 0.9937 - val_distribution_lambda_22_loss: 1.6440 - val_distribution_lambda_23_loss: 0.5052\n",
"Epoch 362/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 3.1568 - distribution_lambda_21_loss: 1.0582 - distribution_lambda_22_loss: 1.5641 - distribution_lambda_23_loss: 0.5345 - val_loss: 3.1372 - val_distribution_lambda_21_loss: 0.9892 - val_distribution_lambda_22_loss: 1.6422 - val_distribution_lambda_23_loss: 0.5058\n",
"Epoch 363/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1457 - distribution_lambda_21_loss: 1.0600 - distribution_lambda_22_loss: 1.5517 - distribution_lambda_23_loss: 0.5340 - val_loss: 3.1497 - val_distribution_lambda_21_loss: 0.9849 - val_distribution_lambda_22_loss: 1.6577 - val_distribution_lambda_23_loss: 0.5072\n",
"Epoch 364/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1342 - distribution_lambda_21_loss: 1.0470 - distribution_lambda_22_loss: 1.5531 - distribution_lambda_23_loss: 0.5341 - val_loss: 3.1338 - val_distribution_lambda_21_loss: 0.9802 - val_distribution_lambda_22_loss: 1.6457 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 365/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1429 - distribution_lambda_21_loss: 1.0485 - distribution_lambda_22_loss: 1.5594 - distribution_lambda_23_loss: 0.5349 - val_loss: 3.1196 - val_distribution_lambda_21_loss: 0.9757 - val_distribution_lambda_22_loss: 1.6358 - val_distribution_lambda_23_loss: 0.5082\n",
"Epoch 366/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1386 - distribution_lambda_21_loss: 1.0568 - distribution_lambda_22_loss: 1.5525 - distribution_lambda_23_loss: 0.5294 - val_loss: 3.1067 - val_distribution_lambda_21_loss: 0.9718 - val_distribution_lambda_22_loss: 1.6270 - val_distribution_lambda_23_loss: 0.5079\n",
"Epoch 367/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1552 - distribution_lambda_21_loss: 1.0557 - distribution_lambda_22_loss: 1.5558 - distribution_lambda_23_loss: 0.5437 - val_loss: 3.1047 - val_distribution_lambda_21_loss: 0.9681 - val_distribution_lambda_22_loss: 1.6297 - val_distribution_lambda_23_loss: 0.5069\n",
"Epoch 368/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1226 - distribution_lambda_21_loss: 1.0354 - distribution_lambda_22_loss: 1.5512 - distribution_lambda_23_loss: 0.5359 - val_loss: 3.1032 - val_distribution_lambda_21_loss: 0.9639 - val_distribution_lambda_22_loss: 1.6322 - val_distribution_lambda_23_loss: 0.5070\n",
"Epoch 369/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0971 - distribution_lambda_21_loss: 1.0265 - distribution_lambda_22_loss: 1.5521 - distribution_lambda_23_loss: 0.5184 - val_loss: 3.1047 - val_distribution_lambda_21_loss: 0.9596 - val_distribution_lambda_22_loss: 1.6379 - val_distribution_lambda_23_loss: 0.5072\n",
"Epoch 370/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.1047 - distribution_lambda_21_loss: 1.0301 - distribution_lambda_22_loss: 1.5461 - distribution_lambda_23_loss: 0.5284 - val_loss: 3.1025 - val_distribution_lambda_21_loss: 0.9556 - val_distribution_lambda_22_loss: 1.6391 - val_distribution_lambda_23_loss: 0.5078\n",
"Epoch 371/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0953 - distribution_lambda_21_loss: 1.0193 - distribution_lambda_22_loss: 1.5602 - distribution_lambda_23_loss: 0.5158 - val_loss: 3.0869 - val_distribution_lambda_21_loss: 0.9514 - val_distribution_lambda_22_loss: 1.6285 - val_distribution_lambda_23_loss: 0.5071\n",
"Epoch 372/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0860 - distribution_lambda_21_loss: 1.0177 - distribution_lambda_22_loss: 1.5412 - distribution_lambda_23_loss: 0.5272 - val_loss: 3.0817 - val_distribution_lambda_21_loss: 0.9473 - val_distribution_lambda_22_loss: 1.6283 - val_distribution_lambda_23_loss: 0.5061\n",
"Epoch 373/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0926 - distribution_lambda_21_loss: 1.0248 - distribution_lambda_22_loss: 1.5475 - distribution_lambda_23_loss: 0.5203 - val_loss: 3.0824 - val_distribution_lambda_21_loss: 0.9434 - val_distribution_lambda_22_loss: 1.6343 - val_distribution_lambda_23_loss: 0.5047\n",
"Epoch 374/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0743 - distribution_lambda_21_loss: 1.0112 - distribution_lambda_22_loss: 1.5396 - distribution_lambda_23_loss: 0.5235 - val_loss: 3.0680 - val_distribution_lambda_21_loss: 0.9392 - val_distribution_lambda_22_loss: 1.6248 - val_distribution_lambda_23_loss: 0.5040\n",
"Epoch 375/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0630 - distribution_lambda_21_loss: 1.0040 - distribution_lambda_22_loss: 1.5301 - distribution_lambda_23_loss: 0.5290 - val_loss: 3.0660 - val_distribution_lambda_21_loss: 0.9350 - val_distribution_lambda_22_loss: 1.6266 - val_distribution_lambda_23_loss: 0.5045\n",
"Epoch 376/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0715 - distribution_lambda_21_loss: 1.0100 - distribution_lambda_22_loss: 1.5333 - distribution_lambda_23_loss: 0.5282 - val_loss: 3.0536 - val_distribution_lambda_21_loss: 0.9308 - val_distribution_lambda_22_loss: 1.6187 - val_distribution_lambda_23_loss: 0.5041\n",
"Epoch 377/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0738 - distribution_lambda_21_loss: 0.9955 - distribution_lambda_22_loss: 1.5367 - distribution_lambda_23_loss: 0.5416 - val_loss: 3.0516 - val_distribution_lambda_21_loss: 0.9268 - val_distribution_lambda_22_loss: 1.6208 - val_distribution_lambda_23_loss: 0.5040\n",
"Epoch 378/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0669 - distribution_lambda_21_loss: 0.9964 - distribution_lambda_22_loss: 1.5327 - distribution_lambda_23_loss: 0.5377 - val_loss: 3.0454 - val_distribution_lambda_21_loss: 0.9229 - val_distribution_lambda_22_loss: 1.6184 - val_distribution_lambda_23_loss: 0.5042\n",
"Epoch 379/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0762 - distribution_lambda_21_loss: 0.9971 - distribution_lambda_22_loss: 1.5418 - distribution_lambda_23_loss: 0.5373 - val_loss: 3.0399 - val_distribution_lambda_21_loss: 0.9190 - val_distribution_lambda_22_loss: 1.6167 - val_distribution_lambda_23_loss: 0.5042\n",
"Epoch 380/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0809 - distribution_lambda_21_loss: 1.0115 - distribution_lambda_22_loss: 1.5388 - distribution_lambda_23_loss: 0.5306 - val_loss: 3.0396 - val_distribution_lambda_21_loss: 0.9158 - val_distribution_lambda_22_loss: 1.6196 - val_distribution_lambda_23_loss: 0.5043\n",
"Epoch 381/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0552 - distribution_lambda_21_loss: 0.9877 - distribution_lambda_22_loss: 1.5416 - distribution_lambda_23_loss: 0.5259 - val_loss: 3.0350 - val_distribution_lambda_21_loss: 0.9121 - val_distribution_lambda_22_loss: 1.6189 - val_distribution_lambda_23_loss: 0.5040\n",
"Epoch 382/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0635 - distribution_lambda_21_loss: 1.0003 - distribution_lambda_22_loss: 1.5458 - distribution_lambda_23_loss: 0.5174 - val_loss: 3.0471 - val_distribution_lambda_21_loss: 0.9092 - val_distribution_lambda_22_loss: 1.6346 - val_distribution_lambda_23_loss: 0.5033\n",
"Epoch 383/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0312 - distribution_lambda_21_loss: 0.9740 - distribution_lambda_22_loss: 1.5265 - distribution_lambda_23_loss: 0.5307 - val_loss: 3.0409 - val_distribution_lambda_21_loss: 0.9060 - val_distribution_lambda_22_loss: 1.6319 - val_distribution_lambda_23_loss: 0.5030\n",
"Epoch 384/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0320 - distribution_lambda_21_loss: 0.9764 - distribution_lambda_22_loss: 1.5285 - distribution_lambda_23_loss: 0.5271 - val_loss: 3.0253 - val_distribution_lambda_21_loss: 0.9027 - val_distribution_lambda_22_loss: 1.6202 - val_distribution_lambda_23_loss: 0.5024\n",
"Epoch 385/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 3.0280 - distribution_lambda_21_loss: 0.9770 - distribution_lambda_22_loss: 1.5228 - distribution_lambda_23_loss: 0.5282 - val_loss: 3.0235 - val_distribution_lambda_21_loss: 0.8995 - val_distribution_lambda_22_loss: 1.6217 - val_distribution_lambda_23_loss: 0.5023\n",
"Epoch 386/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0202 - distribution_lambda_21_loss: 0.9726 - distribution_lambda_22_loss: 1.5193 - distribution_lambda_23_loss: 0.5284 - val_loss: 3.0283 - val_distribution_lambda_21_loss: 0.8961 - val_distribution_lambda_22_loss: 1.6299 - val_distribution_lambda_23_loss: 0.5023\n",
"Epoch 387/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0325 - distribution_lambda_21_loss: 0.9739 - distribution_lambda_22_loss: 1.5200 - distribution_lambda_23_loss: 0.5387 - val_loss: 3.0161 - val_distribution_lambda_21_loss: 0.8922 - val_distribution_lambda_22_loss: 1.6219 - val_distribution_lambda_23_loss: 0.5020\n",
"Epoch 388/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0158 - distribution_lambda_21_loss: 0.9661 - distribution_lambda_22_loss: 1.5166 - distribution_lambda_23_loss: 0.5330 - val_loss: 3.0131 - val_distribution_lambda_21_loss: 0.8886 - val_distribution_lambda_22_loss: 1.6226 - val_distribution_lambda_23_loss: 0.5020\n",
"Epoch 389/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0279 - distribution_lambda_21_loss: 0.9663 - distribution_lambda_22_loss: 1.5265 - distribution_lambda_23_loss: 0.5351 - val_loss: 3.0046 - val_distribution_lambda_21_loss: 0.8852 - val_distribution_lambda_22_loss: 1.6180 - val_distribution_lambda_23_loss: 0.5014\n",
"Epoch 390/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0224 - distribution_lambda_21_loss: 0.9615 - distribution_lambda_22_loss: 1.5216 - distribution_lambda_23_loss: 0.5392 - val_loss: 2.9983 - val_distribution_lambda_21_loss: 0.8820 - val_distribution_lambda_22_loss: 1.6154 - val_distribution_lambda_23_loss: 0.5008\n",
"Epoch 391/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 3.0002 - distribution_lambda_21_loss: 0.9594 - distribution_lambda_22_loss: 1.5195 - distribution_lambda_23_loss: 0.5213 - val_loss: 2.9976 - val_distribution_lambda_21_loss: 0.8791 - val_distribution_lambda_22_loss: 1.6182 - val_distribution_lambda_23_loss: 0.5003\n",
"Epoch 392/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9771 - distribution_lambda_21_loss: 0.9464 - distribution_lambda_22_loss: 1.5185 - distribution_lambda_23_loss: 0.5122 - val_loss: 2.9844 - val_distribution_lambda_21_loss: 0.8759 - val_distribution_lambda_22_loss: 1.6094 - val_distribution_lambda_23_loss: 0.4992\n",
"Epoch 393/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9969 - distribution_lambda_21_loss: 0.9534 - distribution_lambda_22_loss: 1.5159 - distribution_lambda_23_loss: 0.5276 - val_loss: 2.9839 - val_distribution_lambda_21_loss: 0.8729 - val_distribution_lambda_22_loss: 1.6126 - val_distribution_lambda_23_loss: 0.4984\n",
"Epoch 394/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9757 - distribution_lambda_21_loss: 0.9429 - distribution_lambda_22_loss: 1.5183 - distribution_lambda_23_loss: 0.5145 - val_loss: 2.9863 - val_distribution_lambda_21_loss: 0.8700 - val_distribution_lambda_22_loss: 1.6183 - val_distribution_lambda_23_loss: 0.4980\n",
"Epoch 395/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9827 - distribution_lambda_21_loss: 0.9493 - distribution_lambda_22_loss: 1.5122 - distribution_lambda_23_loss: 0.5212 - val_loss: 2.9932 - val_distribution_lambda_21_loss: 0.8675 - val_distribution_lambda_22_loss: 1.6274 - val_distribution_lambda_23_loss: 0.4982\n",
"Epoch 396/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9827 - distribution_lambda_21_loss: 0.9402 - distribution_lambda_22_loss: 1.5221 - distribution_lambda_23_loss: 0.5204 - val_loss: 2.9919 - val_distribution_lambda_21_loss: 0.8651 - val_distribution_lambda_22_loss: 1.6281 - val_distribution_lambda_23_loss: 0.4987\n",
"Epoch 397/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9822 - distribution_lambda_21_loss: 0.9373 - distribution_lambda_22_loss: 1.5167 - distribution_lambda_23_loss: 0.5282 - val_loss: 2.9879 - val_distribution_lambda_21_loss: 0.8629 - val_distribution_lambda_22_loss: 1.6267 - val_distribution_lambda_23_loss: 0.4983\n",
"Epoch 398/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9806 - distribution_lambda_21_loss: 0.9402 - distribution_lambda_22_loss: 1.5179 - distribution_lambda_23_loss: 0.5225 - val_loss: 2.9785 - val_distribution_lambda_21_loss: 0.8605 - val_distribution_lambda_22_loss: 1.6198 - val_distribution_lambda_23_loss: 0.4982\n",
"Epoch 399/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9600 - distribution_lambda_21_loss: 0.9339 - distribution_lambda_22_loss: 1.5144 - distribution_lambda_23_loss: 0.5117 - val_loss: 2.9657 - val_distribution_lambda_21_loss: 0.8569 - val_distribution_lambda_22_loss: 1.6110 - val_distribution_lambda_23_loss: 0.4977\n",
"Epoch 400/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9599 - distribution_lambda_21_loss: 0.9308 - distribution_lambda_22_loss: 1.5128 - distribution_lambda_23_loss: 0.5163 - val_loss: 2.9706 - val_distribution_lambda_21_loss: 0.8541 - val_distribution_lambda_22_loss: 1.6180 - val_distribution_lambda_23_loss: 0.4985\n",
"Epoch 401/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9601 - distribution_lambda_21_loss: 0.9217 - distribution_lambda_22_loss: 1.5071 - distribution_lambda_23_loss: 0.5312 - val_loss: 2.9765 - val_distribution_lambda_21_loss: 0.8515 - val_distribution_lambda_22_loss: 1.6257 - val_distribution_lambda_23_loss: 0.4994\n",
"Epoch 402/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9706 - distribution_lambda_21_loss: 0.9309 - distribution_lambda_22_loss: 1.5172 - distribution_lambda_23_loss: 0.5225 - val_loss: 2.9757 - val_distribution_lambda_21_loss: 0.8500 - val_distribution_lambda_22_loss: 1.6264 - val_distribution_lambda_23_loss: 0.4993\n",
"Epoch 403/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9546 - distribution_lambda_21_loss: 0.9130 - distribution_lambda_22_loss: 1.5134 - distribution_lambda_23_loss: 0.5282 - val_loss: 2.9659 - val_distribution_lambda_21_loss: 0.8485 - val_distribution_lambda_22_loss: 1.6191 - val_distribution_lambda_23_loss: 0.4983\n",
"Epoch 404/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.9375 - distribution_lambda_21_loss: 0.9114 - distribution_lambda_22_loss: 1.5082 - distribution_lambda_23_loss: 0.5179 - val_loss: 2.9548 - val_distribution_lambda_21_loss: 0.8467 - val_distribution_lambda_22_loss: 1.6112 - val_distribution_lambda_23_loss: 0.4969\n",
"Epoch 405/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9310 - distribution_lambda_21_loss: 0.9158 - distribution_lambda_22_loss: 1.5117 - distribution_lambda_23_loss: 0.5034 - val_loss: 2.9511 - val_distribution_lambda_21_loss: 0.8438 - val_distribution_lambda_22_loss: 1.6114 - val_distribution_lambda_23_loss: 0.4959\n",
"Epoch 406/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9325 - distribution_lambda_21_loss: 0.9056 - distribution_lambda_22_loss: 1.5117 - distribution_lambda_23_loss: 0.5152 - val_loss: 2.9620 - val_distribution_lambda_21_loss: 0.8411 - val_distribution_lambda_22_loss: 1.6254 - val_distribution_lambda_23_loss: 0.4955\n",
"Epoch 407/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9525 - distribution_lambda_21_loss: 0.9126 - distribution_lambda_22_loss: 1.5117 - distribution_lambda_23_loss: 0.5282 - val_loss: 2.9631 - val_distribution_lambda_21_loss: 0.8393 - val_distribution_lambda_22_loss: 1.6286 - val_distribution_lambda_23_loss: 0.4953\n",
"Epoch 408/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9356 - distribution_lambda_21_loss: 0.8980 - distribution_lambda_22_loss: 1.5099 - distribution_lambda_23_loss: 0.5277 - val_loss: 2.9684 - val_distribution_lambda_21_loss: 0.8379 - val_distribution_lambda_22_loss: 1.6341 - val_distribution_lambda_23_loss: 0.4963\n",
"Epoch 409/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 7ms/step - loss: 2.9059 - distribution_lambda_21_loss: 0.8980 - distribution_lambda_22_loss: 1.4941 - distribution_lambda_23_loss: 0.5139 - val_loss: 2.9664 - val_distribution_lambda_21_loss: 0.8366 - val_distribution_lambda_22_loss: 1.6326 - val_distribution_lambda_23_loss: 0.4972\n",
"Epoch 410/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 2.9233 - distribution_lambda_21_loss: 0.8965 - distribution_lambda_22_loss: 1.4952 - distribution_lambda_23_loss: 0.5316 - val_loss: 2.9571 - val_distribution_lambda_21_loss: 0.8352 - val_distribution_lambda_22_loss: 1.6245 - val_distribution_lambda_23_loss: 0.4974\n",
"Epoch 411/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9562 - distribution_lambda_21_loss: 0.9117 - distribution_lambda_22_loss: 1.5162 - distribution_lambda_23_loss: 0.5284 - val_loss: 2.9559 - val_distribution_lambda_21_loss: 0.8333 - val_distribution_lambda_22_loss: 1.6247 - val_distribution_lambda_23_loss: 0.4979\n",
"Epoch 412/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9377 - distribution_lambda_21_loss: 0.9079 - distribution_lambda_22_loss: 1.5042 - distribution_lambda_23_loss: 0.5256 - val_loss: 2.9473 - val_distribution_lambda_21_loss: 0.8319 - val_distribution_lambda_22_loss: 1.6178 - val_distribution_lambda_23_loss: 0.4976\n",
"Epoch 413/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9115 - distribution_lambda_21_loss: 0.8923 - distribution_lambda_22_loss: 1.4984 - distribution_lambda_23_loss: 0.5208 - val_loss: 2.9413 - val_distribution_lambda_21_loss: 0.8301 - val_distribution_lambda_22_loss: 1.6156 - val_distribution_lambda_23_loss: 0.4956\n",
"Epoch 414/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9112 - distribution_lambda_21_loss: 0.8994 - distribution_lambda_22_loss: 1.5082 - distribution_lambda_23_loss: 0.5035 - val_loss: 2.9555 - val_distribution_lambda_21_loss: 0.8291 - val_distribution_lambda_22_loss: 1.6313 - val_distribution_lambda_23_loss: 0.4951\n",
"Epoch 415/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9204 - distribution_lambda_21_loss: 0.8880 - distribution_lambda_22_loss: 1.5062 - distribution_lambda_23_loss: 0.5262 - val_loss: 2.9515 - val_distribution_lambda_21_loss: 0.8277 - val_distribution_lambda_22_loss: 1.6290 - val_distribution_lambda_23_loss: 0.4948\n",
"Epoch 416/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9379 - distribution_lambda_21_loss: 0.8962 - distribution_lambda_22_loss: 1.5167 - distribution_lambda_23_loss: 0.5250 - val_loss: 2.9453 - val_distribution_lambda_21_loss: 0.8272 - val_distribution_lambda_22_loss: 1.6236 - val_distribution_lambda_23_loss: 0.4944\n",
"Epoch 417/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9102 - distribution_lambda_21_loss: 0.8806 - distribution_lambda_22_loss: 1.5000 - distribution_lambda_23_loss: 0.5296 - val_loss: 2.9427 - val_distribution_lambda_21_loss: 0.8264 - val_distribution_lambda_22_loss: 1.6225 - val_distribution_lambda_23_loss: 0.4938\n",
"Epoch 418/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8931 - distribution_lambda_21_loss: 0.8688 - distribution_lambda_22_loss: 1.5072 - distribution_lambda_23_loss: 0.5172 - val_loss: 2.9430 - val_distribution_lambda_21_loss: 0.8259 - val_distribution_lambda_22_loss: 1.6242 - val_distribution_lambda_23_loss: 0.4929\n",
"Epoch 419/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8887 - distribution_lambda_21_loss: 0.8634 - distribution_lambda_22_loss: 1.4984 - distribution_lambda_23_loss: 0.5270 - val_loss: 2.9476 - val_distribution_lambda_21_loss: 0.8265 - val_distribution_lambda_22_loss: 1.6283 - val_distribution_lambda_23_loss: 0.4928\n",
"Epoch 420/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8959 - distribution_lambda_21_loss: 0.8757 - distribution_lambda_22_loss: 1.5012 - distribution_lambda_23_loss: 0.5190 - val_loss: 2.9300 - val_distribution_lambda_21_loss: 0.8208 - val_distribution_lambda_22_loss: 1.6166 - val_distribution_lambda_23_loss: 0.4925\n",
"Epoch 421/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9075 - distribution_lambda_21_loss: 0.8823 - distribution_lambda_22_loss: 1.5053 - distribution_lambda_23_loss: 0.5199 - val_loss: 2.9178 - val_distribution_lambda_21_loss: 0.8187 - val_distribution_lambda_22_loss: 1.6086 - val_distribution_lambda_23_loss: 0.4905\n",
"Epoch 422/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8881 - distribution_lambda_21_loss: 0.8627 - distribution_lambda_22_loss: 1.5031 - distribution_lambda_23_loss: 0.5223 - val_loss: 2.9234 - val_distribution_lambda_21_loss: 0.8187 - val_distribution_lambda_22_loss: 1.6135 - val_distribution_lambda_23_loss: 0.4912\n",
"Epoch 423/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8841 - distribution_lambda_21_loss: 0.8597 - distribution_lambda_22_loss: 1.5117 - distribution_lambda_23_loss: 0.5127 - val_loss: 2.9231 - val_distribution_lambda_21_loss: 0.8186 - val_distribution_lambda_22_loss: 1.6127 - val_distribution_lambda_23_loss: 0.4918\n",
"Epoch 424/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8724 - distribution_lambda_21_loss: 0.8624 - distribution_lambda_22_loss: 1.4944 - distribution_lambda_23_loss: 0.5156 - val_loss: 2.9213 - val_distribution_lambda_21_loss: 0.8189 - val_distribution_lambda_22_loss: 1.6110 - val_distribution_lambda_23_loss: 0.4914\n",
"Epoch 425/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8678 - distribution_lambda_21_loss: 0.8549 - distribution_lambda_22_loss: 1.4938 - distribution_lambda_23_loss: 0.5191 - val_loss: 2.9222 - val_distribution_lambda_21_loss: 0.8185 - val_distribution_lambda_22_loss: 1.6129 - val_distribution_lambda_23_loss: 0.4908\n",
"Epoch 426/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.9004 - distribution_lambda_21_loss: 0.8766 - distribution_lambda_22_loss: 1.5082 - distribution_lambda_23_loss: 0.5156 - val_loss: 2.9250 - val_distribution_lambda_21_loss: 0.8191 - val_distribution_lambda_22_loss: 1.6156 - val_distribution_lambda_23_loss: 0.4903\n",
"Epoch 427/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8865 - distribution_lambda_21_loss: 0.8619 - distribution_lambda_22_loss: 1.5048 - distribution_lambda_23_loss: 0.5197 - val_loss: 2.9230 - val_distribution_lambda_21_loss: 0.8183 - val_distribution_lambda_22_loss: 1.6149 - val_distribution_lambda_23_loss: 0.4898\n",
"Epoch 428/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8514 - distribution_lambda_21_loss: 0.8466 - distribution_lambda_22_loss: 1.4872 - distribution_lambda_23_loss: 0.5176 - val_loss: 2.9159 - val_distribution_lambda_21_loss: 0.8176 - val_distribution_lambda_22_loss: 1.6083 - val_distribution_lambda_23_loss: 0.4900\n",
"Epoch 429/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8675 - distribution_lambda_21_loss: 0.8414 - distribution_lambda_22_loss: 1.5054 - distribution_lambda_23_loss: 0.5207 - val_loss: 2.9156 - val_distribution_lambda_21_loss: 0.8176 - val_distribution_lambda_22_loss: 1.6086 - val_distribution_lambda_23_loss: 0.4893\n",
"Epoch 430/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8672 - distribution_lambda_21_loss: 0.8507 - distribution_lambda_22_loss: 1.4998 - distribution_lambda_23_loss: 0.5167 - val_loss: 2.9355 - val_distribution_lambda_21_loss: 0.8179 - val_distribution_lambda_22_loss: 1.6275 - val_distribution_lambda_23_loss: 0.4901\n",
"Epoch 431/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8609 - distribution_lambda_21_loss: 0.8452 - distribution_lambda_22_loss: 1.4910 - distribution_lambda_23_loss: 0.5246 - val_loss: 2.9303 - val_distribution_lambda_21_loss: 0.8184 - val_distribution_lambda_22_loss: 1.6217 - val_distribution_lambda_23_loss: 0.4902\n",
"Epoch 432/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8428 - distribution_lambda_21_loss: 0.8410 - distribution_lambda_22_loss: 1.4876 - distribution_lambda_23_loss: 0.5142 - val_loss: 2.9122 - val_distribution_lambda_21_loss: 0.8177 - val_distribution_lambda_22_loss: 1.6054 - val_distribution_lambda_23_loss: 0.4890\n",
"Epoch 433/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.8422 - distribution_lambda_21_loss: 0.8339 - distribution_lambda_22_loss: 1.4962 - distribution_lambda_23_loss: 0.5121 - val_loss: 2.9152 - val_distribution_lambda_21_loss: 0.8176 - val_distribution_lambda_22_loss: 1.6092 - val_distribution_lambda_23_loss: 0.4884\n",
"Epoch 434/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8382 - distribution_lambda_21_loss: 0.8246 - distribution_lambda_22_loss: 1.5005 - distribution_lambda_23_loss: 0.5131 - val_loss: 2.9160 - val_distribution_lambda_21_loss: 0.8177 - val_distribution_lambda_22_loss: 1.6108 - val_distribution_lambda_23_loss: 0.4875\n",
"Epoch 435/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8415 - distribution_lambda_21_loss: 0.8396 - distribution_lambda_22_loss: 1.4870 - distribution_lambda_23_loss: 0.5149 - val_loss: 2.9247 - val_distribution_lambda_21_loss: 0.8199 - val_distribution_lambda_22_loss: 1.6176 - val_distribution_lambda_23_loss: 0.4872\n",
"Epoch 436/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8433 - distribution_lambda_21_loss: 0.8343 - distribution_lambda_22_loss: 1.4903 - distribution_lambda_23_loss: 0.5187 - val_loss: 2.9152 - val_distribution_lambda_21_loss: 0.8205 - val_distribution_lambda_22_loss: 1.6073 - val_distribution_lambda_23_loss: 0.4874\n",
"Epoch 437/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8399 - distribution_lambda_21_loss: 0.8382 - distribution_lambda_22_loss: 1.4852 - distribution_lambda_23_loss: 0.5164 - val_loss: 2.9134 - val_distribution_lambda_21_loss: 0.8208 - val_distribution_lambda_22_loss: 1.6056 - val_distribution_lambda_23_loss: 0.4870\n",
"Epoch 438/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.8178 - distribution_lambda_21_loss: 0.8186 - distribution_lambda_22_loss: 1.4927 - distribution_lambda_23_loss: 0.5065 - val_loss: 2.9033 - val_distribution_lambda_21_loss: 0.8177 - val_distribution_lambda_22_loss: 1.5985 - val_distribution_lambda_23_loss: 0.4871\n",
"Epoch 439/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8403 - distribution_lambda_21_loss: 0.8255 - distribution_lambda_22_loss: 1.4958 - distribution_lambda_23_loss: 0.5189 - val_loss: 2.9008 - val_distribution_lambda_21_loss: 0.8152 - val_distribution_lambda_22_loss: 1.5985 - val_distribution_lambda_23_loss: 0.4871\n",
"Epoch 440/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8407 - distribution_lambda_21_loss: 0.8213 - distribution_lambda_22_loss: 1.5028 - distribution_lambda_23_loss: 0.5166 - val_loss: 2.9034 - val_distribution_lambda_21_loss: 0.8133 - val_distribution_lambda_22_loss: 1.6038 - val_distribution_lambda_23_loss: 0.4863\n",
"Epoch 441/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8019 - distribution_lambda_21_loss: 0.8132 - distribution_lambda_22_loss: 1.4783 - distribution_lambda_23_loss: 0.5104 - val_loss: 2.9034 - val_distribution_lambda_21_loss: 0.8117 - val_distribution_lambda_22_loss: 1.6055 - val_distribution_lambda_23_loss: 0.4863\n",
"Epoch 442/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8068 - distribution_lambda_21_loss: 0.8064 - distribution_lambda_22_loss: 1.4821 - distribution_lambda_23_loss: 0.5182 - val_loss: 2.8918 - val_distribution_lambda_21_loss: 0.8144 - val_distribution_lambda_22_loss: 1.5923 - val_distribution_lambda_23_loss: 0.4851\n",
"Epoch 443/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8062 - distribution_lambda_21_loss: 0.8064 - distribution_lambda_22_loss: 1.4827 - distribution_lambda_23_loss: 0.5170 - val_loss: 2.8966 - val_distribution_lambda_21_loss: 0.8160 - val_distribution_lambda_22_loss: 1.5961 - val_distribution_lambda_23_loss: 0.4845\n",
"Epoch 444/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8006 - distribution_lambda_21_loss: 0.7934 - distribution_lambda_22_loss: 1.4845 - distribution_lambda_23_loss: 0.5226 - val_loss: 2.9094 - val_distribution_lambda_21_loss: 0.8170 - val_distribution_lambda_22_loss: 1.6073 - val_distribution_lambda_23_loss: 0.4850\n",
"Epoch 445/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8191 - distribution_lambda_21_loss: 0.8303 - distribution_lambda_22_loss: 1.4833 - distribution_lambda_23_loss: 0.5054 - val_loss: 2.9055 - val_distribution_lambda_21_loss: 0.8180 - val_distribution_lambda_22_loss: 1.6029 - val_distribution_lambda_23_loss: 0.4847\n",
"Epoch 446/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8108 - distribution_lambda_21_loss: 0.8052 - distribution_lambda_22_loss: 1.4935 - distribution_lambda_23_loss: 0.5121 - val_loss: 2.8924 - val_distribution_lambda_21_loss: 0.8179 - val_distribution_lambda_22_loss: 1.5905 - val_distribution_lambda_23_loss: 0.4840\n",
"Epoch 447/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7987 - distribution_lambda_21_loss: 0.7974 - distribution_lambda_22_loss: 1.4862 - distribution_lambda_23_loss: 0.5151 - val_loss: 2.8852 - val_distribution_lambda_21_loss: 0.8149 - val_distribution_lambda_22_loss: 1.5869 - val_distribution_lambda_23_loss: 0.4834\n",
"Epoch 448/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7775 - distribution_lambda_21_loss: 0.7946 - distribution_lambda_22_loss: 1.4792 - distribution_lambda_23_loss: 0.5037 - val_loss: 2.8775 - val_distribution_lambda_21_loss: 0.8104 - val_distribution_lambda_22_loss: 1.5830 - val_distribution_lambda_23_loss: 0.4841\n",
"Epoch 449/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8136 - distribution_lambda_21_loss: 0.8146 - distribution_lambda_22_loss: 1.4792 - distribution_lambda_23_loss: 0.5197 - val_loss: 2.8739 - val_distribution_lambda_21_loss: 0.8088 - val_distribution_lambda_22_loss: 1.5814 - val_distribution_lambda_23_loss: 0.4837\n",
"Epoch 450/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7709 - distribution_lambda_21_loss: 0.7829 - distribution_lambda_22_loss: 1.4857 - distribution_lambda_23_loss: 0.5023 - val_loss: 2.8830 - val_distribution_lambda_21_loss: 0.8084 - val_distribution_lambda_22_loss: 1.5915 - val_distribution_lambda_23_loss: 0.4830\n",
"Epoch 451/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7901 - distribution_lambda_21_loss: 0.7946 - distribution_lambda_22_loss: 1.4845 - distribution_lambda_23_loss: 0.5110 - val_loss: 2.8894 - val_distribution_lambda_21_loss: 0.8118 - val_distribution_lambda_22_loss: 1.5941 - val_distribution_lambda_23_loss: 0.4835\n",
"Epoch 452/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7652 - distribution_lambda_21_loss: 0.7819 - distribution_lambda_22_loss: 1.4772 - distribution_lambda_23_loss: 0.5060 - val_loss: 2.8979 - val_distribution_lambda_21_loss: 0.8159 - val_distribution_lambda_22_loss: 1.5980 - val_distribution_lambda_23_loss: 0.4840\n",
"Epoch 453/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7736 - distribution_lambda_21_loss: 0.7862 - distribution_lambda_22_loss: 1.4796 - distribution_lambda_23_loss: 0.5078 - val_loss: 2.9017 - val_distribution_lambda_21_loss: 0.8169 - val_distribution_lambda_22_loss: 1.6015 - val_distribution_lambda_23_loss: 0.4833\n",
"Epoch 454/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.8052 - distribution_lambda_21_loss: 0.7867 - distribution_lambda_22_loss: 1.4885 - distribution_lambda_23_loss: 0.5300 - val_loss: 2.8793 - val_distribution_lambda_21_loss: 0.8127 - val_distribution_lambda_22_loss: 1.5849 - val_distribution_lambda_23_loss: 0.4817\n",
"Epoch 455/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7761 - distribution_lambda_21_loss: 0.7911 - distribution_lambda_22_loss: 1.4774 - distribution_lambda_23_loss: 0.5076 - val_loss: 2.8686 - val_distribution_lambda_21_loss: 0.8054 - val_distribution_lambda_22_loss: 1.5818 - val_distribution_lambda_23_loss: 0.4813\n",
"Epoch 456/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7581 - distribution_lambda_21_loss: 0.7713 - distribution_lambda_22_loss: 1.4690 - distribution_lambda_23_loss: 0.5179 - val_loss: 2.8719 - val_distribution_lambda_21_loss: 0.8006 - val_distribution_lambda_22_loss: 1.5901 - val_distribution_lambda_23_loss: 0.4812\n",
"Epoch 457/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.7680 - distribution_lambda_21_loss: 0.7761 - distribution_lambda_22_loss: 1.4821 - distribution_lambda_23_loss: 0.5097 - val_loss: 2.8649 - val_distribution_lambda_21_loss: 0.7983 - val_distribution_lambda_22_loss: 1.5862 - val_distribution_lambda_23_loss: 0.4804\n",
"Epoch 458/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7597 - distribution_lambda_21_loss: 0.7648 - distribution_lambda_22_loss: 1.4762 - distribution_lambda_23_loss: 0.5187 - val_loss: 2.8655 - val_distribution_lambda_21_loss: 0.8022 - val_distribution_lambda_22_loss: 1.5840 - val_distribution_lambda_23_loss: 0.4793\n",
"Epoch 459/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7405 - distribution_lambda_21_loss: 0.7669 - distribution_lambda_22_loss: 1.4684 - distribution_lambda_23_loss: 0.5052 - val_loss: 2.8789 - val_distribution_lambda_21_loss: 0.8072 - val_distribution_lambda_22_loss: 1.5931 - val_distribution_lambda_23_loss: 0.4786\n",
"Epoch 460/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7384 - distribution_lambda_21_loss: 0.7662 - distribution_lambda_22_loss: 1.4722 - distribution_lambda_23_loss: 0.5001 - val_loss: 2.8823 - val_distribution_lambda_21_loss: 0.8117 - val_distribution_lambda_22_loss: 1.5927 - val_distribution_lambda_23_loss: 0.4778\n",
"Epoch 461/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7657 - distribution_lambda_21_loss: 0.7808 - distribution_lambda_22_loss: 1.4684 - distribution_lambda_23_loss: 0.5165 - val_loss: 2.8658 - val_distribution_lambda_21_loss: 0.8095 - val_distribution_lambda_22_loss: 1.5793 - val_distribution_lambda_23_loss: 0.4771\n",
"Epoch 462/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7345 - distribution_lambda_21_loss: 0.7550 - distribution_lambda_22_loss: 1.4727 - distribution_lambda_23_loss: 0.5068 - val_loss: 2.8762 - val_distribution_lambda_21_loss: 0.8116 - val_distribution_lambda_22_loss: 1.5860 - val_distribution_lambda_23_loss: 0.4786\n",
"Epoch 463/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7407 - distribution_lambda_21_loss: 0.7530 - distribution_lambda_22_loss: 1.4787 - distribution_lambda_23_loss: 0.5090 - val_loss: 2.8767 - val_distribution_lambda_21_loss: 0.8099 - val_distribution_lambda_22_loss: 1.5872 - val_distribution_lambda_23_loss: 0.4796\n",
"Epoch 464/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7610 - distribution_lambda_21_loss: 0.7645 - distribution_lambda_22_loss: 1.4758 - distribution_lambda_23_loss: 0.5207 - val_loss: 2.8592 - val_distribution_lambda_21_loss: 0.8017 - val_distribution_lambda_22_loss: 1.5780 - val_distribution_lambda_23_loss: 0.4796\n",
"Epoch 465/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7131 - distribution_lambda_21_loss: 0.7414 - distribution_lambda_22_loss: 1.4721 - distribution_lambda_23_loss: 0.4996 - val_loss: 2.8497 - val_distribution_lambda_21_loss: 0.7934 - val_distribution_lambda_22_loss: 1.5773 - val_distribution_lambda_23_loss: 0.4790\n",
"Epoch 466/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7203 - distribution_lambda_21_loss: 0.7491 - distribution_lambda_22_loss: 1.4687 - distribution_lambda_23_loss: 0.5025 - val_loss: 2.8606 - val_distribution_lambda_21_loss: 0.7957 - val_distribution_lambda_22_loss: 1.5867 - val_distribution_lambda_23_loss: 0.4782\n",
"Epoch 467/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7303 - distribution_lambda_21_loss: 0.7421 - distribution_lambda_22_loss: 1.4735 - distribution_lambda_23_loss: 0.5147 - val_loss: 2.8731 - val_distribution_lambda_21_loss: 0.7999 - val_distribution_lambda_22_loss: 1.5958 - val_distribution_lambda_23_loss: 0.4774\n",
"Epoch 468/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7637 - distribution_lambda_21_loss: 0.7737 - distribution_lambda_22_loss: 1.4808 - distribution_lambda_23_loss: 0.5093 - val_loss: 2.8524 - val_distribution_lambda_21_loss: 0.7930 - val_distribution_lambda_22_loss: 1.5819 - val_distribution_lambda_23_loss: 0.4775\n",
"Epoch 469/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7254 - distribution_lambda_21_loss: 0.7512 - distribution_lambda_22_loss: 1.4687 - distribution_lambda_23_loss: 0.5056 - val_loss: 2.8409 - val_distribution_lambda_21_loss: 0.7916 - val_distribution_lambda_22_loss: 1.5717 - val_distribution_lambda_23_loss: 0.4776\n",
"Epoch 470/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7306 - distribution_lambda_21_loss: 0.7577 - distribution_lambda_22_loss: 1.4737 - distribution_lambda_23_loss: 0.4993 - val_loss: 2.8438 - val_distribution_lambda_21_loss: 0.7938 - val_distribution_lambda_22_loss: 1.5730 - val_distribution_lambda_23_loss: 0.4770\n",
"Epoch 471/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7057 - distribution_lambda_21_loss: 0.7331 - distribution_lambda_22_loss: 1.4725 - distribution_lambda_23_loss: 0.5001 - val_loss: 2.8460 - val_distribution_lambda_21_loss: 0.7969 - val_distribution_lambda_22_loss: 1.5734 - val_distribution_lambda_23_loss: 0.4756\n",
"Epoch 472/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7011 - distribution_lambda_21_loss: 0.7274 - distribution_lambda_22_loss: 1.4731 - distribution_lambda_23_loss: 0.5006 - val_loss: 2.8367 - val_distribution_lambda_21_loss: 0.7950 - val_distribution_lambda_22_loss: 1.5673 - val_distribution_lambda_23_loss: 0.4744\n",
"Epoch 473/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7240 - distribution_lambda_21_loss: 0.7274 - distribution_lambda_22_loss: 1.4786 - distribution_lambda_23_loss: 0.5179 - val_loss: 2.8360 - val_distribution_lambda_21_loss: 0.7955 - val_distribution_lambda_22_loss: 1.5656 - val_distribution_lambda_23_loss: 0.4748\n",
"Epoch 474/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6894 - distribution_lambda_21_loss: 0.7284 - distribution_lambda_22_loss: 1.4620 - distribution_lambda_23_loss: 0.4990 - val_loss: 2.8563 - val_distribution_lambda_21_loss: 0.7993 - val_distribution_lambda_22_loss: 1.5795 - val_distribution_lambda_23_loss: 0.4774\n",
"Epoch 475/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7121 - distribution_lambda_21_loss: 0.7342 - distribution_lambda_22_loss: 1.4631 - distribution_lambda_23_loss: 0.5148 - val_loss: 2.8589 - val_distribution_lambda_21_loss: 0.7979 - val_distribution_lambda_22_loss: 1.5821 - val_distribution_lambda_23_loss: 0.4789\n",
"Epoch 476/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6985 - distribution_lambda_21_loss: 0.7217 - distribution_lambda_22_loss: 1.4706 - distribution_lambda_23_loss: 0.5062 - val_loss: 2.8336 - val_distribution_lambda_21_loss: 0.7858 - val_distribution_lambda_22_loss: 1.5699 - val_distribution_lambda_23_loss: 0.4779\n",
"Epoch 477/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6948 - distribution_lambda_21_loss: 0.7124 - distribution_lambda_22_loss: 1.4661 - distribution_lambda_23_loss: 0.5163 - val_loss: 2.8385 - val_distribution_lambda_21_loss: 0.7844 - val_distribution_lambda_22_loss: 1.5769 - val_distribution_lambda_23_loss: 0.4772\n",
"Epoch 478/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6722 - distribution_lambda_21_loss: 0.7105 - distribution_lambda_22_loss: 1.4605 - distribution_lambda_23_loss: 0.5012 - val_loss: 2.8565 - val_distribution_lambda_21_loss: 0.7919 - val_distribution_lambda_22_loss: 1.5880 - val_distribution_lambda_23_loss: 0.4765\n",
"Epoch 479/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6848 - distribution_lambda_21_loss: 0.7266 - distribution_lambda_22_loss: 1.4611 - distribution_lambda_23_loss: 0.4971 - val_loss: 2.8564 - val_distribution_lambda_21_loss: 0.7924 - val_distribution_lambda_22_loss: 1.5886 - val_distribution_lambda_23_loss: 0.4753\n",
"Epoch 480/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.7149 - distribution_lambda_21_loss: 0.7227 - distribution_lambda_22_loss: 1.4725 - distribution_lambda_23_loss: 0.5198 - val_loss: 2.8378 - val_distribution_lambda_21_loss: 0.7892 - val_distribution_lambda_22_loss: 1.5747 - val_distribution_lambda_23_loss: 0.4739\n",
"Epoch 481/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.6871 - distribution_lambda_21_loss: 0.7132 - distribution_lambda_22_loss: 1.4711 - distribution_lambda_23_loss: 0.5028 - val_loss: 2.8307 - val_distribution_lambda_21_loss: 0.7873 - val_distribution_lambda_22_loss: 1.5695 - val_distribution_lambda_23_loss: 0.4738\n",
"Epoch 482/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6680 - distribution_lambda_21_loss: 0.7076 - distribution_lambda_22_loss: 1.4573 - distribution_lambda_23_loss: 0.5030 - val_loss: 2.8334 - val_distribution_lambda_21_loss: 0.7897 - val_distribution_lambda_22_loss: 1.5698 - val_distribution_lambda_23_loss: 0.4740\n",
"Epoch 483/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6656 - distribution_lambda_21_loss: 0.7082 - distribution_lambda_22_loss: 1.4583 - distribution_lambda_23_loss: 0.4991 - val_loss: 2.8300 - val_distribution_lambda_21_loss: 0.7871 - val_distribution_lambda_22_loss: 1.5695 - val_distribution_lambda_23_loss: 0.4735\n",
"Epoch 484/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6840 - distribution_lambda_21_loss: 0.7195 - distribution_lambda_22_loss: 1.4608 - distribution_lambda_23_loss: 0.5037 - val_loss: 2.8118 - val_distribution_lambda_21_loss: 0.7756 - val_distribution_lambda_22_loss: 1.5639 - val_distribution_lambda_23_loss: 0.4723\n",
"Epoch 485/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6695 - distribution_lambda_21_loss: 0.7050 - distribution_lambda_22_loss: 1.4537 - distribution_lambda_23_loss: 0.5107 - val_loss: 2.8069 - val_distribution_lambda_21_loss: 0.7738 - val_distribution_lambda_22_loss: 1.5613 - val_distribution_lambda_23_loss: 0.4717\n",
"Epoch 486/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6727 - distribution_lambda_21_loss: 0.7005 - distribution_lambda_22_loss: 1.4608 - distribution_lambda_23_loss: 0.5113 - val_loss: 2.8044 - val_distribution_lambda_21_loss: 0.7712 - val_distribution_lambda_22_loss: 1.5621 - val_distribution_lambda_23_loss: 0.4712\n",
"Epoch 487/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6776 - distribution_lambda_21_loss: 0.7188 - distribution_lambda_22_loss: 1.4601 - distribution_lambda_23_loss: 0.4987 - val_loss: 2.8022 - val_distribution_lambda_21_loss: 0.7682 - val_distribution_lambda_22_loss: 1.5633 - val_distribution_lambda_23_loss: 0.4708\n",
"Epoch 488/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6392 - distribution_lambda_21_loss: 0.6870 - distribution_lambda_22_loss: 1.4535 - distribution_lambda_23_loss: 0.4987 - val_loss: 2.8278 - val_distribution_lambda_21_loss: 0.7756 - val_distribution_lambda_22_loss: 1.5811 - val_distribution_lambda_23_loss: 0.4712\n",
"Epoch 489/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6488 - distribution_lambda_21_loss: 0.7029 - distribution_lambda_22_loss: 1.4514 - distribution_lambda_23_loss: 0.4946 - val_loss: 2.8314 - val_distribution_lambda_21_loss: 0.7803 - val_distribution_lambda_22_loss: 1.5802 - val_distribution_lambda_23_loss: 0.4708\n",
"Epoch 490/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6698 - distribution_lambda_21_loss: 0.7120 - distribution_lambda_22_loss: 1.4671 - distribution_lambda_23_loss: 0.4907 - val_loss: 2.8168 - val_distribution_lambda_21_loss: 0.7828 - val_distribution_lambda_22_loss: 1.5644 - val_distribution_lambda_23_loss: 0.4697\n",
"Epoch 491/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6789 - distribution_lambda_21_loss: 0.6972 - distribution_lambda_22_loss: 1.4648 - distribution_lambda_23_loss: 0.5169 - val_loss: 2.8199 - val_distribution_lambda_21_loss: 0.7831 - val_distribution_lambda_22_loss: 1.5670 - val_distribution_lambda_23_loss: 0.4698\n",
"Epoch 492/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6479 - distribution_lambda_21_loss: 0.6850 - distribution_lambda_22_loss: 1.4567 - distribution_lambda_23_loss: 0.5062 - val_loss: 2.8129 - val_distribution_lambda_21_loss: 0.7789 - val_distribution_lambda_22_loss: 1.5649 - val_distribution_lambda_23_loss: 0.4691\n",
"Epoch 493/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6456 - distribution_lambda_21_loss: 0.6807 - distribution_lambda_22_loss: 1.4525 - distribution_lambda_23_loss: 0.5124 - val_loss: 2.7968 - val_distribution_lambda_21_loss: 0.7656 - val_distribution_lambda_22_loss: 1.5622 - val_distribution_lambda_23_loss: 0.4689\n",
"Epoch 494/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6657 - distribution_lambda_21_loss: 0.6932 - distribution_lambda_22_loss: 1.4635 - distribution_lambda_23_loss: 0.5089 - val_loss: 2.7955 - val_distribution_lambda_21_loss: 0.7598 - val_distribution_lambda_22_loss: 1.5668 - val_distribution_lambda_23_loss: 0.4690\n",
"Epoch 495/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6351 - distribution_lambda_21_loss: 0.6841 - distribution_lambda_22_loss: 1.4518 - distribution_lambda_23_loss: 0.4991 - val_loss: 2.8037 - val_distribution_lambda_21_loss: 0.7621 - val_distribution_lambda_22_loss: 1.5716 - val_distribution_lambda_23_loss: 0.4700\n",
"Epoch 496/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6324 - distribution_lambda_21_loss: 0.6715 - distribution_lambda_22_loss: 1.4567 - distribution_lambda_23_loss: 0.5043 - val_loss: 2.8005 - val_distribution_lambda_21_loss: 0.7675 - val_distribution_lambda_22_loss: 1.5650 - val_distribution_lambda_23_loss: 0.4681\n",
"Epoch 497/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6419 - distribution_lambda_21_loss: 0.6766 - distribution_lambda_22_loss: 1.4672 - distribution_lambda_23_loss: 0.4982 - val_loss: 2.7933 - val_distribution_lambda_21_loss: 0.7686 - val_distribution_lambda_22_loss: 1.5595 - val_distribution_lambda_23_loss: 0.4652\n",
"Epoch 498/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6208 - distribution_lambda_21_loss: 0.6641 - distribution_lambda_22_loss: 1.4544 - distribution_lambda_23_loss: 0.5024 - val_loss: 2.7971 - val_distribution_lambda_21_loss: 0.7691 - val_distribution_lambda_22_loss: 1.5634 - val_distribution_lambda_23_loss: 0.4646\n",
"Epoch 499/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6140 - distribution_lambda_21_loss: 0.6682 - distribution_lambda_22_loss: 1.4547 - distribution_lambda_23_loss: 0.4911 - val_loss: 2.7906 - val_distribution_lambda_21_loss: 0.7661 - val_distribution_lambda_22_loss: 1.5609 - val_distribution_lambda_23_loss: 0.4636\n",
"Epoch 500/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 2.6318 - distribution_lambda_21_loss: 0.6635 - distribution_lambda_22_loss: 1.4628 - distribution_lambda_23_loss: 0.5055 - val_loss: 2.7817 - val_distribution_lambda_21_loss: 0.7628 - val_distribution_lambda_22_loss: 1.5560 - val_distribution_lambda_23_loss: 0.4629\n",
"Epoch 501/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6227 - distribution_lambda_21_loss: 0.6506 - distribution_lambda_22_loss: 1.4652 - distribution_lambda_23_loss: 0.5068 - val_loss: 2.7808 - val_distribution_lambda_21_loss: 0.7610 - val_distribution_lambda_22_loss: 1.5577 - val_distribution_lambda_23_loss: 0.4621\n",
"Epoch 502/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6169 - distribution_lambda_21_loss: 0.6629 - distribution_lambda_22_loss: 1.4544 - distribution_lambda_23_loss: 0.4996 - val_loss: 2.7892 - val_distribution_lambda_21_loss: 0.7561 - val_distribution_lambda_22_loss: 1.5699 - val_distribution_lambda_23_loss: 0.4632\n",
"Epoch 503/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 2.6181 - distribution_lambda_21_loss: 0.6571 - distribution_lambda_22_loss: 1.4548 - distribution_lambda_23_loss: 0.5063 - val_loss: 2.7694 - val_distribution_lambda_21_loss: 0.7503 - val_distribution_lambda_22_loss: 1.5557 - val_distribution_lambda_23_loss: 0.4635\n",
"Epoch 504/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6281 - distribution_lambda_21_loss: 0.6726 - distribution_lambda_22_loss: 1.4512 - distribution_lambda_23_loss: 0.5043 - val_loss: 2.7494 - val_distribution_lambda_21_loss: 0.7429 - val_distribution_lambda_22_loss: 1.5438 - val_distribution_lambda_23_loss: 0.4627\n",
"Epoch 505/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 2.6018 - distribution_lambda_21_loss: 0.6517 - distribution_lambda_22_loss: 1.4551 - distribution_lambda_23_loss: 0.4949 - val_loss: 2.7509 - val_distribution_lambda_21_loss: 0.7425 - val_distribution_lambda_22_loss: 1.5460 - val_distribution_lambda_23_loss: 0.4623\n",
"Epoch 506/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6404 - distribution_lambda_21_loss: 0.6840 - distribution_lambda_22_loss: 1.4537 - distribution_lambda_23_loss: 0.5027 - val_loss: 2.7452 - val_distribution_lambda_21_loss: 0.7349 - val_distribution_lambda_22_loss: 1.5480 - val_distribution_lambda_23_loss: 0.4624\n",
"Epoch 507/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6251 - distribution_lambda_21_loss: 0.6678 - distribution_lambda_22_loss: 1.4511 - distribution_lambda_23_loss: 0.5062 - val_loss: 2.7536 - val_distribution_lambda_21_loss: 0.7365 - val_distribution_lambda_22_loss: 1.5534 - val_distribution_lambda_23_loss: 0.4636\n",
"Epoch 508/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5908 - distribution_lambda_21_loss: 0.6496 - distribution_lambda_22_loss: 1.4423 - distribution_lambda_23_loss: 0.4990 - val_loss: 2.7460 - val_distribution_lambda_21_loss: 0.7366 - val_distribution_lambda_22_loss: 1.5462 - val_distribution_lambda_23_loss: 0.4631\n",
"Epoch 509/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6259 - distribution_lambda_21_loss: 0.6650 - distribution_lambda_22_loss: 1.4582 - distribution_lambda_23_loss: 0.5027 - val_loss: 2.7433 - val_distribution_lambda_21_loss: 0.7371 - val_distribution_lambda_22_loss: 1.5433 - val_distribution_lambda_23_loss: 0.4629\n",
"Epoch 510/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6217 - distribution_lambda_21_loss: 0.6800 - distribution_lambda_22_loss: 1.4424 - distribution_lambda_23_loss: 0.4994 - val_loss: 2.7426 - val_distribution_lambda_21_loss: 0.7391 - val_distribution_lambda_22_loss: 1.5410 - val_distribution_lambda_23_loss: 0.4625\n",
"Epoch 511/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6398 - distribution_lambda_21_loss: 0.6842 - distribution_lambda_22_loss: 1.4483 - distribution_lambda_23_loss: 0.5073 - val_loss: 2.7641 - val_distribution_lambda_21_loss: 0.7450 - val_distribution_lambda_22_loss: 1.5547 - val_distribution_lambda_23_loss: 0.4644\n",
"Epoch 512/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6140 - distribution_lambda_21_loss: 0.6533 - distribution_lambda_22_loss: 1.4665 - distribution_lambda_23_loss: 0.4942 - val_loss: 2.7803 - val_distribution_lambda_21_loss: 0.7544 - val_distribution_lambda_22_loss: 1.5617 - val_distribution_lambda_23_loss: 0.4642\n",
"Epoch 513/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.6210 - distribution_lambda_21_loss: 0.6546 - distribution_lambda_22_loss: 1.4614 - distribution_lambda_23_loss: 0.5050 - val_loss: 2.7757 - val_distribution_lambda_21_loss: 0.7551 - val_distribution_lambda_22_loss: 1.5577 - val_distribution_lambda_23_loss: 0.4629\n",
"Epoch 514/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5813 - distribution_lambda_21_loss: 0.6475 - distribution_lambda_22_loss: 1.4492 - distribution_lambda_23_loss: 0.4846 - val_loss: 2.7788 - val_distribution_lambda_21_loss: 0.7484 - val_distribution_lambda_22_loss: 1.5674 - val_distribution_lambda_23_loss: 0.4631\n",
"Epoch 515/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5994 - distribution_lambda_21_loss: 0.6576 - distribution_lambda_22_loss: 1.4480 - distribution_lambda_23_loss: 0.4938 - val_loss: 2.7652 - val_distribution_lambda_21_loss: 0.7417 - val_distribution_lambda_22_loss: 1.5608 - val_distribution_lambda_23_loss: 0.4627\n",
"Epoch 516/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5829 - distribution_lambda_21_loss: 0.6426 - distribution_lambda_22_loss: 1.4447 - distribution_lambda_23_loss: 0.4955 - val_loss: 2.7514 - val_distribution_lambda_21_loss: 0.7395 - val_distribution_lambda_22_loss: 1.5513 - val_distribution_lambda_23_loss: 0.4607\n",
"Epoch 517/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5823 - distribution_lambda_21_loss: 0.6351 - distribution_lambda_22_loss: 1.4484 - distribution_lambda_23_loss: 0.4987 - val_loss: 2.7474 - val_distribution_lambda_21_loss: 0.7399 - val_distribution_lambda_22_loss: 1.5477 - val_distribution_lambda_23_loss: 0.4598\n",
"Epoch 518/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5638 - distribution_lambda_21_loss: 0.6338 - distribution_lambda_22_loss: 1.4434 - distribution_lambda_23_loss: 0.4866 - val_loss: 2.7534 - val_distribution_lambda_21_loss: 0.7384 - val_distribution_lambda_22_loss: 1.5545 - val_distribution_lambda_23_loss: 0.4606\n",
"Epoch 519/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5948 - distribution_lambda_21_loss: 0.6442 - distribution_lambda_22_loss: 1.4505 - distribution_lambda_23_loss: 0.5000 - val_loss: 2.7501 - val_distribution_lambda_21_loss: 0.7333 - val_distribution_lambda_22_loss: 1.5573 - val_distribution_lambda_23_loss: 0.4596\n",
"Epoch 520/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6145 - distribution_lambda_21_loss: 0.6549 - distribution_lambda_22_loss: 1.4601 - distribution_lambda_23_loss: 0.4995 - val_loss: 2.7462 - val_distribution_lambda_21_loss: 0.7327 - val_distribution_lambda_22_loss: 1.5554 - val_distribution_lambda_23_loss: 0.4581\n",
"Epoch 521/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5857 - distribution_lambda_21_loss: 0.6446 - distribution_lambda_22_loss: 1.4466 - distribution_lambda_23_loss: 0.4944 - val_loss: 2.7429 - val_distribution_lambda_21_loss: 0.7334 - val_distribution_lambda_22_loss: 1.5524 - val_distribution_lambda_23_loss: 0.4571\n",
"Epoch 522/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5813 - distribution_lambda_21_loss: 0.6378 - distribution_lambda_22_loss: 1.4456 - distribution_lambda_23_loss: 0.4978 - val_loss: 2.7382 - val_distribution_lambda_21_loss: 0.7283 - val_distribution_lambda_22_loss: 1.5521 - val_distribution_lambda_23_loss: 0.4578\n",
"Epoch 523/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5897 - distribution_lambda_21_loss: 0.6486 - distribution_lambda_22_loss: 1.4480 - distribution_lambda_23_loss: 0.4931 - val_loss: 2.7413 - val_distribution_lambda_21_loss: 0.7221 - val_distribution_lambda_22_loss: 1.5597 - val_distribution_lambda_23_loss: 0.4595\n",
"Epoch 524/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5703 - distribution_lambda_21_loss: 0.6299 - distribution_lambda_22_loss: 1.4404 - distribution_lambda_23_loss: 0.4999 - val_loss: 2.7490 - val_distribution_lambda_21_loss: 0.7266 - val_distribution_lambda_22_loss: 1.5619 - val_distribution_lambda_23_loss: 0.4605\n",
"Epoch 525/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5543 - distribution_lambda_21_loss: 0.6261 - distribution_lambda_22_loss: 1.4399 - distribution_lambda_23_loss: 0.4883 - val_loss: 2.7564 - val_distribution_lambda_21_loss: 0.7341 - val_distribution_lambda_22_loss: 1.5633 - val_distribution_lambda_23_loss: 0.4591\n",
"Epoch 526/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5975 - distribution_lambda_21_loss: 0.6437 - distribution_lambda_22_loss: 1.4447 - distribution_lambda_23_loss: 0.5090 - val_loss: 2.7503 - val_distribution_lambda_21_loss: 0.7279 - val_distribution_lambda_22_loss: 1.5650 - val_distribution_lambda_23_loss: 0.4574\n",
"Epoch 527/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5652 - distribution_lambda_21_loss: 0.6476 - distribution_lambda_22_loss: 1.4374 - distribution_lambda_23_loss: 0.4803 - val_loss: 2.7423 - val_distribution_lambda_21_loss: 0.7227 - val_distribution_lambda_22_loss: 1.5644 - val_distribution_lambda_23_loss: 0.4553\n",
"Epoch 528/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5525 - distribution_lambda_21_loss: 0.6281 - distribution_lambda_22_loss: 1.4299 - distribution_lambda_23_loss: 0.4945 - val_loss: 2.7490 - val_distribution_lambda_21_loss: 0.7232 - val_distribution_lambda_22_loss: 1.5694 - val_distribution_lambda_23_loss: 0.4564\n",
"Epoch 529/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 2.5628 - distribution_lambda_21_loss: 0.6303 - distribution_lambda_22_loss: 1.4379 - distribution_lambda_23_loss: 0.4947 - val_loss: 2.7425 - val_distribution_lambda_21_loss: 0.7215 - val_distribution_lambda_22_loss: 1.5642 - val_distribution_lambda_23_loss: 0.4568\n",
"Epoch 530/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5660 - distribution_lambda_21_loss: 0.6307 - distribution_lambda_22_loss: 1.4463 - distribution_lambda_23_loss: 0.4891 - val_loss: 2.7311 - val_distribution_lambda_21_loss: 0.7195 - val_distribution_lambda_22_loss: 1.5549 - val_distribution_lambda_23_loss: 0.4567\n",
"Epoch 531/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5557 - distribution_lambda_21_loss: 0.6242 - distribution_lambda_22_loss: 1.4352 - distribution_lambda_23_loss: 0.4963 - val_loss: 2.7392 - val_distribution_lambda_21_loss: 0.7199 - val_distribution_lambda_22_loss: 1.5619 - val_distribution_lambda_23_loss: 0.4574\n",
"Epoch 532/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5713 - distribution_lambda_21_loss: 0.6426 - distribution_lambda_22_loss: 1.4395 - distribution_lambda_23_loss: 0.4892 - val_loss: 2.7452 - val_distribution_lambda_21_loss: 0.7216 - val_distribution_lambda_22_loss: 1.5678 - val_distribution_lambda_23_loss: 0.4559\n",
"Epoch 533/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5520 - distribution_lambda_21_loss: 0.6076 - distribution_lambda_22_loss: 1.4444 - distribution_lambda_23_loss: 0.5000 - val_loss: 2.7308 - val_distribution_lambda_21_loss: 0.7210 - val_distribution_lambda_22_loss: 1.5547 - val_distribution_lambda_23_loss: 0.4551\n",
"Epoch 534/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5645 - distribution_lambda_21_loss: 0.6334 - distribution_lambda_22_loss: 1.4424 - distribution_lambda_23_loss: 0.4888 - val_loss: 2.7155 - val_distribution_lambda_21_loss: 0.7174 - val_distribution_lambda_22_loss: 1.5448 - val_distribution_lambda_23_loss: 0.4534\n",
"Epoch 535/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5303 - distribution_lambda_21_loss: 0.6054 - distribution_lambda_22_loss: 1.4392 - distribution_lambda_23_loss: 0.4858 - val_loss: 2.7229 - val_distribution_lambda_21_loss: 0.7210 - val_distribution_lambda_22_loss: 1.5493 - val_distribution_lambda_23_loss: 0.4526\n",
"Epoch 536/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5378 - distribution_lambda_21_loss: 0.6197 - distribution_lambda_22_loss: 1.4304 - distribution_lambda_23_loss: 0.4877 - val_loss: 2.7196 - val_distribution_lambda_21_loss: 0.7174 - val_distribution_lambda_22_loss: 1.5505 - val_distribution_lambda_23_loss: 0.4517\n",
"Epoch 537/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5265 - distribution_lambda_21_loss: 0.6155 - distribution_lambda_22_loss: 1.4310 - distribution_lambda_23_loss: 0.4800 - val_loss: 2.7272 - val_distribution_lambda_21_loss: 0.7212 - val_distribution_lambda_22_loss: 1.5548 - val_distribution_lambda_23_loss: 0.4512\n",
"Epoch 538/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.6017 - distribution_lambda_21_loss: 0.6555 - distribution_lambda_22_loss: 1.4571 - distribution_lambda_23_loss: 0.4891 - val_loss: 2.7231 - val_distribution_lambda_21_loss: 0.7250 - val_distribution_lambda_22_loss: 1.5479 - val_distribution_lambda_23_loss: 0.4501\n",
"Epoch 539/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5567 - distribution_lambda_21_loss: 0.6223 - distribution_lambda_22_loss: 1.4469 - distribution_lambda_23_loss: 0.4875 - val_loss: 2.7188 - val_distribution_lambda_21_loss: 0.7269 - val_distribution_lambda_22_loss: 1.5416 - val_distribution_lambda_23_loss: 0.4504\n",
"Epoch 540/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5387 - distribution_lambda_21_loss: 0.6145 - distribution_lambda_22_loss: 1.4383 - distribution_lambda_23_loss: 0.4860 - val_loss: 2.7312 - val_distribution_lambda_21_loss: 0.7273 - val_distribution_lambda_22_loss: 1.5531 - val_distribution_lambda_23_loss: 0.4508\n",
"Epoch 541/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5203 - distribution_lambda_21_loss: 0.6016 - distribution_lambda_22_loss: 1.4252 - distribution_lambda_23_loss: 0.4936 - val_loss: 2.7573 - val_distribution_lambda_21_loss: 0.7302 - val_distribution_lambda_22_loss: 1.5751 - val_distribution_lambda_23_loss: 0.4520\n",
"Epoch 542/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5752 - distribution_lambda_21_loss: 0.6501 - distribution_lambda_22_loss: 1.4346 - distribution_lambda_23_loss: 0.4906 - val_loss: 2.7640 - val_distribution_lambda_21_loss: 0.7271 - val_distribution_lambda_22_loss: 1.5823 - val_distribution_lambda_23_loss: 0.4546\n",
"Epoch 543/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5548 - distribution_lambda_21_loss: 0.6092 - distribution_lambda_22_loss: 1.4510 - distribution_lambda_23_loss: 0.4947 - val_loss: 2.7343 - val_distribution_lambda_21_loss: 0.7170 - val_distribution_lambda_22_loss: 1.5630 - val_distribution_lambda_23_loss: 0.4542\n",
"Epoch 544/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5274 - distribution_lambda_21_loss: 0.6121 - distribution_lambda_22_loss: 1.4338 - distribution_lambda_23_loss: 0.4815 - val_loss: 2.7121 - val_distribution_lambda_21_loss: 0.7111 - val_distribution_lambda_22_loss: 1.5496 - val_distribution_lambda_23_loss: 0.4514\n",
"Epoch 545/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5419 - distribution_lambda_21_loss: 0.6135 - distribution_lambda_22_loss: 1.4340 - distribution_lambda_23_loss: 0.4944 - val_loss: 2.6981 - val_distribution_lambda_21_loss: 0.7054 - val_distribution_lambda_22_loss: 1.5428 - val_distribution_lambda_23_loss: 0.4499\n",
"Epoch 546/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5692 - distribution_lambda_21_loss: 0.6184 - distribution_lambda_22_loss: 1.4547 - distribution_lambda_23_loss: 0.4961 - val_loss: 2.6994 - val_distribution_lambda_21_loss: 0.7047 - val_distribution_lambda_22_loss: 1.5447 - val_distribution_lambda_23_loss: 0.4499\n",
"Epoch 547/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5222 - distribution_lambda_21_loss: 0.5960 - distribution_lambda_22_loss: 1.4348 - distribution_lambda_23_loss: 0.4915 - val_loss: 2.7017 - val_distribution_lambda_21_loss: 0.7091 - val_distribution_lambda_22_loss: 1.5437 - val_distribution_lambda_23_loss: 0.4490\n",
"Epoch 548/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5168 - distribution_lambda_21_loss: 0.5944 - distribution_lambda_22_loss: 1.4292 - distribution_lambda_23_loss: 0.4932 - val_loss: 2.7049 - val_distribution_lambda_21_loss: 0.7103 - val_distribution_lambda_22_loss: 1.5463 - val_distribution_lambda_23_loss: 0.4483\n",
"Epoch 549/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5259 - distribution_lambda_21_loss: 0.6143 - distribution_lambda_22_loss: 1.4268 - distribution_lambda_23_loss: 0.4848 - val_loss: 2.7278 - val_distribution_lambda_21_loss: 0.7164 - val_distribution_lambda_22_loss: 1.5639 - val_distribution_lambda_23_loss: 0.4474\n",
"Epoch 550/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5191 - distribution_lambda_21_loss: 0.6095 - distribution_lambda_22_loss: 1.4277 - distribution_lambda_23_loss: 0.4819 - val_loss: 2.7349 - val_distribution_lambda_21_loss: 0.7190 - val_distribution_lambda_22_loss: 1.5702 - val_distribution_lambda_23_loss: 0.4456\n",
"Epoch 551/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5236 - distribution_lambda_21_loss: 0.6095 - distribution_lambda_22_loss: 1.4287 - distribution_lambda_23_loss: 0.4854 - val_loss: 2.7179 - val_distribution_lambda_21_loss: 0.7159 - val_distribution_lambda_22_loss: 1.5569 - val_distribution_lambda_23_loss: 0.4451\n",
"Epoch 552/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5257 - distribution_lambda_21_loss: 0.6131 - distribution_lambda_22_loss: 1.4249 - distribution_lambda_23_loss: 0.4877 - val_loss: 2.7031 - val_distribution_lambda_21_loss: 0.7095 - val_distribution_lambda_22_loss: 1.5485 - val_distribution_lambda_23_loss: 0.4452\n",
"Epoch 553/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 2.5131 - distribution_lambda_21_loss: 0.6019 - distribution_lambda_22_loss: 1.4290 - distribution_lambda_23_loss: 0.4822 - val_loss: 2.7022 - val_distribution_lambda_21_loss: 0.7081 - val_distribution_lambda_22_loss: 1.5498 - val_distribution_lambda_23_loss: 0.4443\n",
"Epoch 554/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5504 - distribution_lambda_21_loss: 0.6196 - distribution_lambda_22_loss: 1.4412 - distribution_lambda_23_loss: 0.4896 - val_loss: 2.7191 - val_distribution_lambda_21_loss: 0.7131 - val_distribution_lambda_22_loss: 1.5593 - val_distribution_lambda_23_loss: 0.4467\n",
"Epoch 555/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5381 - distribution_lambda_21_loss: 0.6197 - distribution_lambda_22_loss: 1.4259 - distribution_lambda_23_loss: 0.4926 - val_loss: 2.7231 - val_distribution_lambda_21_loss: 0.7119 - val_distribution_lambda_22_loss: 1.5617 - val_distribution_lambda_23_loss: 0.4495\n",
"Epoch 556/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5342 - distribution_lambda_21_loss: 0.6074 - distribution_lambda_22_loss: 1.4329 - distribution_lambda_23_loss: 0.4939 - val_loss: 2.7264 - val_distribution_lambda_21_loss: 0.7092 - val_distribution_lambda_22_loss: 1.5681 - val_distribution_lambda_23_loss: 0.4492\n",
"Epoch 557/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5272 - distribution_lambda_21_loss: 0.6194 - distribution_lambda_22_loss: 1.4247 - distribution_lambda_23_loss: 0.4831 - val_loss: 2.7147 - val_distribution_lambda_21_loss: 0.7037 - val_distribution_lambda_22_loss: 1.5643 - val_distribution_lambda_23_loss: 0.4467\n",
"Epoch 558/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5397 - distribution_lambda_21_loss: 0.6230 - distribution_lambda_22_loss: 1.4237 - distribution_lambda_23_loss: 0.4930 - val_loss: 2.7128 - val_distribution_lambda_21_loss: 0.7034 - val_distribution_lambda_22_loss: 1.5649 - val_distribution_lambda_23_loss: 0.4445\n",
"Epoch 559/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5282 - distribution_lambda_21_loss: 0.6051 - distribution_lambda_22_loss: 1.4284 - distribution_lambda_23_loss: 0.4947 - val_loss: 2.7110 - val_distribution_lambda_21_loss: 0.7063 - val_distribution_lambda_22_loss: 1.5609 - val_distribution_lambda_23_loss: 0.4438\n",
"Epoch 560/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5316 - distribution_lambda_21_loss: 0.6149 - distribution_lambda_22_loss: 1.4247 - distribution_lambda_23_loss: 0.4920 - val_loss: 2.7212 - val_distribution_lambda_21_loss: 0.7077 - val_distribution_lambda_22_loss: 1.5698 - val_distribution_lambda_23_loss: 0.4438\n",
"Epoch 561/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5069 - distribution_lambda_21_loss: 0.5903 - distribution_lambda_22_loss: 1.4354 - distribution_lambda_23_loss: 0.4812 - val_loss: 2.7247 - val_distribution_lambda_21_loss: 0.7136 - val_distribution_lambda_22_loss: 1.5678 - val_distribution_lambda_23_loss: 0.4433\n",
"Epoch 562/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5236 - distribution_lambda_21_loss: 0.5941 - distribution_lambda_22_loss: 1.4394 - distribution_lambda_23_loss: 0.4901 - val_loss: 2.7260 - val_distribution_lambda_21_loss: 0.7152 - val_distribution_lambda_22_loss: 1.5677 - val_distribution_lambda_23_loss: 0.4430\n",
"Epoch 563/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5049 - distribution_lambda_21_loss: 0.6029 - distribution_lambda_22_loss: 1.4190 - distribution_lambda_23_loss: 0.4831 - val_loss: 2.7250 - val_distribution_lambda_21_loss: 0.7118 - val_distribution_lambda_22_loss: 1.5711 - val_distribution_lambda_23_loss: 0.4421\n",
"Epoch 564/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4923 - distribution_lambda_21_loss: 0.5900 - distribution_lambda_22_loss: 1.4182 - distribution_lambda_23_loss: 0.4840 - val_loss: 2.7371 - val_distribution_lambda_21_loss: 0.7150 - val_distribution_lambda_22_loss: 1.5808 - val_distribution_lambda_23_loss: 0.4412\n",
"Epoch 565/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4856 - distribution_lambda_21_loss: 0.5850 - distribution_lambda_22_loss: 1.4268 - distribution_lambda_23_loss: 0.4738 - val_loss: 2.7235 - val_distribution_lambda_21_loss: 0.7128 - val_distribution_lambda_22_loss: 1.5707 - val_distribution_lambda_23_loss: 0.4401\n",
"Epoch 566/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4939 - distribution_lambda_21_loss: 0.6007 - distribution_lambda_22_loss: 1.4158 - distribution_lambda_23_loss: 0.4775 - val_loss: 2.7147 - val_distribution_lambda_21_loss: 0.7124 - val_distribution_lambda_22_loss: 1.5628 - val_distribution_lambda_23_loss: 0.4395\n",
"Epoch 567/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5146 - distribution_lambda_21_loss: 0.6116 - distribution_lambda_22_loss: 1.4277 - distribution_lambda_23_loss: 0.4753 - val_loss: 2.7043 - val_distribution_lambda_21_loss: 0.7025 - val_distribution_lambda_22_loss: 1.5598 - val_distribution_lambda_23_loss: 0.4420\n",
"Epoch 568/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4858 - distribution_lambda_21_loss: 0.5883 - distribution_lambda_22_loss: 1.4035 - distribution_lambda_23_loss: 0.4940 - val_loss: 2.7070 - val_distribution_lambda_21_loss: 0.6980 - val_distribution_lambda_22_loss: 1.5653 - val_distribution_lambda_23_loss: 0.4437\n",
"Epoch 569/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4870 - distribution_lambda_21_loss: 0.5811 - distribution_lambda_22_loss: 1.4150 - distribution_lambda_23_loss: 0.4909 - val_loss: 2.7029 - val_distribution_lambda_21_loss: 0.6992 - val_distribution_lambda_22_loss: 1.5609 - val_distribution_lambda_23_loss: 0.4428\n",
"Epoch 570/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5057 - distribution_lambda_21_loss: 0.5913 - distribution_lambda_22_loss: 1.4174 - distribution_lambda_23_loss: 0.4971 - val_loss: 2.7048 - val_distribution_lambda_21_loss: 0.7000 - val_distribution_lambda_22_loss: 1.5613 - val_distribution_lambda_23_loss: 0.4434\n",
"Epoch 571/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5050 - distribution_lambda_21_loss: 0.5910 - distribution_lambda_22_loss: 1.4249 - distribution_lambda_23_loss: 0.4891 - val_loss: 2.6942 - val_distribution_lambda_21_loss: 0.6995 - val_distribution_lambda_22_loss: 1.5526 - val_distribution_lambda_23_loss: 0.4421\n",
"Epoch 572/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4822 - distribution_lambda_21_loss: 0.5774 - distribution_lambda_22_loss: 1.4123 - distribution_lambda_23_loss: 0.4925 - val_loss: 2.6830 - val_distribution_lambda_21_loss: 0.6991 - val_distribution_lambda_22_loss: 1.5433 - val_distribution_lambda_23_loss: 0.4405\n",
"Epoch 573/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5140 - distribution_lambda_21_loss: 0.6004 - distribution_lambda_22_loss: 1.4308 - distribution_lambda_23_loss: 0.4828 - val_loss: 2.6897 - val_distribution_lambda_21_loss: 0.6996 - val_distribution_lambda_22_loss: 1.5497 - val_distribution_lambda_23_loss: 0.4405\n",
"Epoch 574/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4876 - distribution_lambda_21_loss: 0.5815 - distribution_lambda_22_loss: 1.4215 - distribution_lambda_23_loss: 0.4846 - val_loss: 2.6987 - val_distribution_lambda_21_loss: 0.6971 - val_distribution_lambda_22_loss: 1.5612 - val_distribution_lambda_23_loss: 0.4405\n",
"Epoch 575/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5177 - distribution_lambda_21_loss: 0.6007 - distribution_lambda_22_loss: 1.4341 - distribution_lambda_23_loss: 0.4829 - val_loss: 2.7024 - val_distribution_lambda_21_loss: 0.6927 - val_distribution_lambda_22_loss: 1.5685 - val_distribution_lambda_23_loss: 0.4412\n",
"Epoch 576/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5018 - distribution_lambda_21_loss: 0.6140 - distribution_lambda_22_loss: 1.4137 - distribution_lambda_23_loss: 0.4742 - val_loss: 2.6936 - val_distribution_lambda_21_loss: 0.6908 - val_distribution_lambda_22_loss: 1.5630 - val_distribution_lambda_23_loss: 0.4398\n",
"Epoch 577/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.4870 - distribution_lambda_21_loss: 0.5790 - distribution_lambda_22_loss: 1.4295 - distribution_lambda_23_loss: 0.4786 - val_loss: 2.6956 - val_distribution_lambda_21_loss: 0.6995 - val_distribution_lambda_22_loss: 1.5578 - val_distribution_lambda_23_loss: 0.4382\n",
"Epoch 578/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4721 - distribution_lambda_21_loss: 0.5777 - distribution_lambda_22_loss: 1.4156 - distribution_lambda_23_loss: 0.4788 - val_loss: 2.6946 - val_distribution_lambda_21_loss: 0.6968 - val_distribution_lambda_22_loss: 1.5599 - val_distribution_lambda_23_loss: 0.4379\n",
"Epoch 579/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4797 - distribution_lambda_21_loss: 0.5820 - distribution_lambda_22_loss: 1.4127 - distribution_lambda_23_loss: 0.4850 - val_loss: 2.6749 - val_distribution_lambda_21_loss: 0.6865 - val_distribution_lambda_22_loss: 1.5517 - val_distribution_lambda_23_loss: 0.4366\n",
"Epoch 580/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4721 - distribution_lambda_21_loss: 0.5822 - distribution_lambda_22_loss: 1.4152 - distribution_lambda_23_loss: 0.4748 - val_loss: 2.6753 - val_distribution_lambda_21_loss: 0.6874 - val_distribution_lambda_22_loss: 1.5522 - val_distribution_lambda_23_loss: 0.4356\n",
"Epoch 581/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4780 - distribution_lambda_21_loss: 0.5666 - distribution_lambda_22_loss: 1.4215 - distribution_lambda_23_loss: 0.4899 - val_loss: 2.6876 - val_distribution_lambda_21_loss: 0.6921 - val_distribution_lambda_22_loss: 1.5594 - val_distribution_lambda_23_loss: 0.4361\n",
"Epoch 582/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4829 - distribution_lambda_21_loss: 0.5874 - distribution_lambda_22_loss: 1.4140 - distribution_lambda_23_loss: 0.4815 - val_loss: 2.7057 - val_distribution_lambda_21_loss: 0.6896 - val_distribution_lambda_22_loss: 1.5768 - val_distribution_lambda_23_loss: 0.4393\n",
"Epoch 583/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4731 - distribution_lambda_21_loss: 0.5890 - distribution_lambda_22_loss: 1.4082 - distribution_lambda_23_loss: 0.4759 - val_loss: 2.7080 - val_distribution_lambda_21_loss: 0.6862 - val_distribution_lambda_22_loss: 1.5790 - val_distribution_lambda_23_loss: 0.4428\n",
"Epoch 584/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4731 - distribution_lambda_21_loss: 0.5702 - distribution_lambda_22_loss: 1.4157 - distribution_lambda_23_loss: 0.4872 - val_loss: 2.6900 - val_distribution_lambda_21_loss: 0.6819 - val_distribution_lambda_22_loss: 1.5657 - val_distribution_lambda_23_loss: 0.4424\n",
"Epoch 585/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5011 - distribution_lambda_21_loss: 0.5941 - distribution_lambda_22_loss: 1.4204 - distribution_lambda_23_loss: 0.4866 - val_loss: 2.6792 - val_distribution_lambda_21_loss: 0.6805 - val_distribution_lambda_22_loss: 1.5592 - val_distribution_lambda_23_loss: 0.4396\n",
"Epoch 586/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.5099 - distribution_lambda_21_loss: 0.5883 - distribution_lambda_22_loss: 1.4335 - distribution_lambda_23_loss: 0.4882 - val_loss: 2.6836 - val_distribution_lambda_21_loss: 0.6827 - val_distribution_lambda_22_loss: 1.5633 - val_distribution_lambda_23_loss: 0.4376\n",
"Epoch 587/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.5043 - distribution_lambda_21_loss: 0.5817 - distribution_lambda_22_loss: 1.4271 - distribution_lambda_23_loss: 0.4955 - val_loss: 2.6827 - val_distribution_lambda_21_loss: 0.6865 - val_distribution_lambda_22_loss: 1.5597 - val_distribution_lambda_23_loss: 0.4365\n",
"Epoch 588/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4708 - distribution_lambda_21_loss: 0.5734 - distribution_lambda_22_loss: 1.4126 - distribution_lambda_23_loss: 0.4848 - val_loss: 2.6904 - val_distribution_lambda_21_loss: 0.6894 - val_distribution_lambda_22_loss: 1.5644 - val_distribution_lambda_23_loss: 0.4366\n",
"Epoch 589/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4739 - distribution_lambda_21_loss: 0.5730 - distribution_lambda_22_loss: 1.4180 - distribution_lambda_23_loss: 0.4829 - val_loss: 2.6881 - val_distribution_lambda_21_loss: 0.6915 - val_distribution_lambda_22_loss: 1.5611 - val_distribution_lambda_23_loss: 0.4356\n",
"Epoch 590/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4653 - distribution_lambda_21_loss: 0.5907 - distribution_lambda_22_loss: 1.3981 - distribution_lambda_23_loss: 0.4765 - val_loss: 2.6874 - val_distribution_lambda_21_loss: 0.6942 - val_distribution_lambda_22_loss: 1.5572 - val_distribution_lambda_23_loss: 0.4360\n",
"Epoch 591/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4601 - distribution_lambda_21_loss: 0.5744 - distribution_lambda_22_loss: 1.4000 - distribution_lambda_23_loss: 0.4858 - val_loss: 2.6979 - val_distribution_lambda_21_loss: 0.6954 - val_distribution_lambda_22_loss: 1.5654 - val_distribution_lambda_23_loss: 0.4371\n",
"Epoch 592/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4739 - distribution_lambda_21_loss: 0.5792 - distribution_lambda_22_loss: 1.4085 - distribution_lambda_23_loss: 0.4862 - val_loss: 2.6840 - val_distribution_lambda_21_loss: 0.6898 - val_distribution_lambda_22_loss: 1.5582 - val_distribution_lambda_23_loss: 0.4360\n",
"Epoch 593/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4799 - distribution_lambda_21_loss: 0.5816 - distribution_lambda_22_loss: 1.4162 - distribution_lambda_23_loss: 0.4821 - val_loss: 2.6682 - val_distribution_lambda_21_loss: 0.6811 - val_distribution_lambda_22_loss: 1.5529 - val_distribution_lambda_23_loss: 0.4342\n",
"Epoch 594/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4737 - distribution_lambda_21_loss: 0.5719 - distribution_lambda_22_loss: 1.4025 - distribution_lambda_23_loss: 0.4994 - val_loss: 2.6661 - val_distribution_lambda_21_loss: 0.6771 - val_distribution_lambda_22_loss: 1.5552 - val_distribution_lambda_23_loss: 0.4338\n",
"Epoch 595/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4626 - distribution_lambda_21_loss: 0.5758 - distribution_lambda_22_loss: 1.4178 - distribution_lambda_23_loss: 0.4690 - val_loss: 2.6625 - val_distribution_lambda_21_loss: 0.6713 - val_distribution_lambda_22_loss: 1.5569 - val_distribution_lambda_23_loss: 0.4342\n",
"Epoch 596/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4529 - distribution_lambda_21_loss: 0.5824 - distribution_lambda_22_loss: 1.3955 - distribution_lambda_23_loss: 0.4751 - val_loss: 2.6702 - val_distribution_lambda_21_loss: 0.6753 - val_distribution_lambda_22_loss: 1.5602 - val_distribution_lambda_23_loss: 0.4347\n",
"Epoch 597/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4698 - distribution_lambda_21_loss: 0.5815 - distribution_lambda_22_loss: 1.4022 - distribution_lambda_23_loss: 0.4860 - val_loss: 2.6892 - val_distribution_lambda_21_loss: 0.6882 - val_distribution_lambda_22_loss: 1.5662 - val_distribution_lambda_23_loss: 0.4347\n",
"Epoch 598/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4614 - distribution_lambda_21_loss: 0.5719 - distribution_lambda_22_loss: 1.4044 - distribution_lambda_23_loss: 0.4850 - val_loss: 2.6915 - val_distribution_lambda_21_loss: 0.6905 - val_distribution_lambda_22_loss: 1.5667 - val_distribution_lambda_23_loss: 0.4344\n",
"Epoch 599/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4505 - distribution_lambda_21_loss: 0.5652 - distribution_lambda_22_loss: 1.4121 - distribution_lambda_23_loss: 0.4731 - val_loss: 2.6659 - val_distribution_lambda_21_loss: 0.6842 - val_distribution_lambda_22_loss: 1.5483 - val_distribution_lambda_23_loss: 0.4333\n",
"Epoch 600/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4620 - distribution_lambda_21_loss: 0.5765 - distribution_lambda_22_loss: 1.4112 - distribution_lambda_23_loss: 0.4743 - val_loss: 2.6591 - val_distribution_lambda_21_loss: 0.6780 - val_distribution_lambda_22_loss: 1.5482 - val_distribution_lambda_23_loss: 0.4330\n",
"Epoch 601/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.4323 - distribution_lambda_21_loss: 0.5658 - distribution_lambda_22_loss: 1.3890 - distribution_lambda_23_loss: 0.4776 - val_loss: 2.6809 - val_distribution_lambda_21_loss: 0.6806 - val_distribution_lambda_22_loss: 1.5677 - val_distribution_lambda_23_loss: 0.4325\n",
"Epoch 602/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4637 - distribution_lambda_21_loss: 0.5686 - distribution_lambda_22_loss: 1.4027 - distribution_lambda_23_loss: 0.4925 - val_loss: 2.6832 - val_distribution_lambda_21_loss: 0.6757 - val_distribution_lambda_22_loss: 1.5738 - val_distribution_lambda_23_loss: 0.4338\n",
"Epoch 603/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4411 - distribution_lambda_21_loss: 0.5683 - distribution_lambda_22_loss: 1.3972 - distribution_lambda_23_loss: 0.4757 - val_loss: 2.6740 - val_distribution_lambda_21_loss: 0.6736 - val_distribution_lambda_22_loss: 1.5681 - val_distribution_lambda_23_loss: 0.4322\n",
"Epoch 604/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4274 - distribution_lambda_21_loss: 0.5596 - distribution_lambda_22_loss: 1.3909 - distribution_lambda_23_loss: 0.4768 - val_loss: 2.6671 - val_distribution_lambda_21_loss: 0.6787 - val_distribution_lambda_22_loss: 1.5574 - val_distribution_lambda_23_loss: 0.4310\n",
"Epoch 605/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4394 - distribution_lambda_21_loss: 0.5640 - distribution_lambda_22_loss: 1.3969 - distribution_lambda_23_loss: 0.4785 - val_loss: 2.6765 - val_distribution_lambda_21_loss: 0.6844 - val_distribution_lambda_22_loss: 1.5604 - val_distribution_lambda_23_loss: 0.4317\n",
"Epoch 606/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4344 - distribution_lambda_21_loss: 0.5622 - distribution_lambda_22_loss: 1.3946 - distribution_lambda_23_loss: 0.4776 - val_loss: 2.6789 - val_distribution_lambda_21_loss: 0.6879 - val_distribution_lambda_22_loss: 1.5607 - val_distribution_lambda_23_loss: 0.4304\n",
"Epoch 607/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4131 - distribution_lambda_21_loss: 0.5556 - distribution_lambda_22_loss: 1.3924 - distribution_lambda_23_loss: 0.4652 - val_loss: 2.6623 - val_distribution_lambda_21_loss: 0.6848 - val_distribution_lambda_22_loss: 1.5495 - val_distribution_lambda_23_loss: 0.4280\n",
"Epoch 608/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4227 - distribution_lambda_21_loss: 0.5610 - distribution_lambda_22_loss: 1.3856 - distribution_lambda_23_loss: 0.4760 - val_loss: 2.6512 - val_distribution_lambda_21_loss: 0.6753 - val_distribution_lambda_22_loss: 1.5485 - val_distribution_lambda_23_loss: 0.4273\n",
"Epoch 609/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4167 - distribution_lambda_21_loss: 0.5494 - distribution_lambda_22_loss: 1.3926 - distribution_lambda_23_loss: 0.4747 - val_loss: 2.6581 - val_distribution_lambda_21_loss: 0.6778 - val_distribution_lambda_22_loss: 1.5530 - val_distribution_lambda_23_loss: 0.4274\n",
"Epoch 610/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.4423 - distribution_lambda_21_loss: 0.5677 - distribution_lambda_22_loss: 1.3971 - distribution_lambda_23_loss: 0.4775 - val_loss: 2.6536 - val_distribution_lambda_21_loss: 0.6720 - val_distribution_lambda_22_loss: 1.5549 - val_distribution_lambda_23_loss: 0.4267\n",
"Epoch 611/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4556 - distribution_lambda_21_loss: 0.5660 - distribution_lambda_22_loss: 1.3966 - distribution_lambda_23_loss: 0.4929 - val_loss: 2.6356 - val_distribution_lambda_21_loss: 0.6634 - val_distribution_lambda_22_loss: 1.5457 - val_distribution_lambda_23_loss: 0.4265\n",
"Epoch 612/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4031 - distribution_lambda_21_loss: 0.5514 - distribution_lambda_22_loss: 1.3846 - distribution_lambda_23_loss: 0.4671 - val_loss: 2.6336 - val_distribution_lambda_21_loss: 0.6655 - val_distribution_lambda_22_loss: 1.5429 - val_distribution_lambda_23_loss: 0.4253\n",
"Epoch 613/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4272 - distribution_lambda_21_loss: 0.5599 - distribution_lambda_22_loss: 1.3955 - distribution_lambda_23_loss: 0.4717 - val_loss: 2.6486 - val_distribution_lambda_21_loss: 0.6703 - val_distribution_lambda_22_loss: 1.5531 - val_distribution_lambda_23_loss: 0.4252\n",
"Epoch 614/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4338 - distribution_lambda_21_loss: 0.5453 - distribution_lambda_22_loss: 1.4054 - distribution_lambda_23_loss: 0.4832 - val_loss: 2.6432 - val_distribution_lambda_21_loss: 0.6728 - val_distribution_lambda_22_loss: 1.5449 - val_distribution_lambda_23_loss: 0.4255\n",
"Epoch 615/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4149 - distribution_lambda_21_loss: 0.5634 - distribution_lambda_22_loss: 1.3873 - distribution_lambda_23_loss: 0.4641 - val_loss: 2.6390 - val_distribution_lambda_21_loss: 0.6708 - val_distribution_lambda_22_loss: 1.5431 - val_distribution_lambda_23_loss: 0.4251\n",
"Epoch 616/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3929 - distribution_lambda_21_loss: 0.5411 - distribution_lambda_22_loss: 1.3843 - distribution_lambda_23_loss: 0.4674 - val_loss: 2.6434 - val_distribution_lambda_21_loss: 0.6690 - val_distribution_lambda_22_loss: 1.5492 - val_distribution_lambda_23_loss: 0.4252\n",
"Epoch 617/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4112 - distribution_lambda_21_loss: 0.5482 - distribution_lambda_22_loss: 1.3762 - distribution_lambda_23_loss: 0.4868 - val_loss: 2.6465 - val_distribution_lambda_21_loss: 0.6702 - val_distribution_lambda_22_loss: 1.5518 - val_distribution_lambda_23_loss: 0.4245\n",
"Epoch 618/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4331 - distribution_lambda_21_loss: 0.5574 - distribution_lambda_22_loss: 1.3887 - distribution_lambda_23_loss: 0.4870 - val_loss: 2.6437 - val_distribution_lambda_21_loss: 0.6691 - val_distribution_lambda_22_loss: 1.5503 - val_distribution_lambda_23_loss: 0.4243\n",
"Epoch 619/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4250 - distribution_lambda_21_loss: 0.5581 - distribution_lambda_22_loss: 1.3788 - distribution_lambda_23_loss: 0.4881 - val_loss: 2.6360 - val_distribution_lambda_21_loss: 0.6688 - val_distribution_lambda_22_loss: 1.5433 - val_distribution_lambda_23_loss: 0.4239\n",
"Epoch 620/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4166 - distribution_lambda_21_loss: 0.5637 - distribution_lambda_22_loss: 1.3870 - distribution_lambda_23_loss: 0.4659 - val_loss: 2.6219 - val_distribution_lambda_21_loss: 0.6610 - val_distribution_lambda_22_loss: 1.5366 - val_distribution_lambda_23_loss: 0.4243\n",
"Epoch 621/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4093 - distribution_lambda_21_loss: 0.5522 - distribution_lambda_22_loss: 1.3895 - distribution_lambda_23_loss: 0.4676 - val_loss: 2.6215 - val_distribution_lambda_21_loss: 0.6620 - val_distribution_lambda_22_loss: 1.5361 - val_distribution_lambda_23_loss: 0.4234\n",
"Epoch 622/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4217 - distribution_lambda_21_loss: 0.5554 - distribution_lambda_22_loss: 1.3888 - distribution_lambda_23_loss: 0.4776 - val_loss: 2.6471 - val_distribution_lambda_21_loss: 0.6678 - val_distribution_lambda_22_loss: 1.5547 - val_distribution_lambda_23_loss: 0.4246\n",
"Epoch 623/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3919 - distribution_lambda_21_loss: 0.5382 - distribution_lambda_22_loss: 1.3770 - distribution_lambda_23_loss: 0.4767 - val_loss: 2.6488 - val_distribution_lambda_21_loss: 0.6642 - val_distribution_lambda_22_loss: 1.5593 - val_distribution_lambda_23_loss: 0.4252\n",
"Epoch 624/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3891 - distribution_lambda_21_loss: 0.5388 - distribution_lambda_22_loss: 1.3706 - distribution_lambda_23_loss: 0.4796 - val_loss: 2.6332 - val_distribution_lambda_21_loss: 0.6619 - val_distribution_lambda_22_loss: 1.5473 - val_distribution_lambda_23_loss: 0.4241\n",
"Epoch 625/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.3941 - distribution_lambda_21_loss: 0.5367 - distribution_lambda_22_loss: 1.3931 - distribution_lambda_23_loss: 0.4644 - val_loss: 2.6514 - val_distribution_lambda_21_loss: 0.6663 - val_distribution_lambda_22_loss: 1.5580 - val_distribution_lambda_23_loss: 0.4271\n",
"Epoch 626/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3634 - distribution_lambda_21_loss: 0.5316 - distribution_lambda_22_loss: 1.3751 - distribution_lambda_23_loss: 0.4568 - val_loss: 2.6555 - val_distribution_lambda_21_loss: 0.6662 - val_distribution_lambda_22_loss: 1.5609 - val_distribution_lambda_23_loss: 0.4284\n",
"Epoch 627/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4179 - distribution_lambda_21_loss: 0.5416 - distribution_lambda_22_loss: 1.3921 - distribution_lambda_23_loss: 0.4842 - val_loss: 2.6322 - val_distribution_lambda_21_loss: 0.6593 - val_distribution_lambda_22_loss: 1.5461 - val_distribution_lambda_23_loss: 0.4268\n",
"Epoch 628/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3893 - distribution_lambda_21_loss: 0.5528 - distribution_lambda_22_loss: 1.3793 - distribution_lambda_23_loss: 0.4573 - val_loss: 2.6247 - val_distribution_lambda_21_loss: 0.6610 - val_distribution_lambda_22_loss: 1.5390 - val_distribution_lambda_23_loss: 0.4247\n",
"Epoch 629/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4134 - distribution_lambda_21_loss: 0.5422 - distribution_lambda_22_loss: 1.3959 - distribution_lambda_23_loss: 0.4754 - val_loss: 2.6301 - val_distribution_lambda_21_loss: 0.6673 - val_distribution_lambda_22_loss: 1.5411 - val_distribution_lambda_23_loss: 0.4217\n",
"Epoch 630/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4359 - distribution_lambda_21_loss: 0.5481 - distribution_lambda_22_loss: 1.3931 - distribution_lambda_23_loss: 0.4947 - val_loss: 2.6466 - val_distribution_lambda_21_loss: 0.6736 - val_distribution_lambda_22_loss: 1.5497 - val_distribution_lambda_23_loss: 0.4232\n",
"Epoch 631/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3699 - distribution_lambda_21_loss: 0.5328 - distribution_lambda_22_loss: 1.3640 - distribution_lambda_23_loss: 0.4731 - val_loss: 2.6532 - val_distribution_lambda_21_loss: 0.6731 - val_distribution_lambda_22_loss: 1.5565 - val_distribution_lambda_23_loss: 0.4236\n",
"Epoch 632/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4268 - distribution_lambda_21_loss: 0.5641 - distribution_lambda_22_loss: 1.3948 - distribution_lambda_23_loss: 0.4679 - val_loss: 2.6472 - val_distribution_lambda_21_loss: 0.6663 - val_distribution_lambda_22_loss: 1.5575 - val_distribution_lambda_23_loss: 0.4234\n",
"Epoch 633/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4016 - distribution_lambda_21_loss: 0.5464 - distribution_lambda_22_loss: 1.3766 - distribution_lambda_23_loss: 0.4785 - val_loss: 2.6309 - val_distribution_lambda_21_loss: 0.6554 - val_distribution_lambda_22_loss: 1.5530 - val_distribution_lambda_23_loss: 0.4225\n",
"Epoch 634/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3952 - distribution_lambda_21_loss: 0.5392 - distribution_lambda_22_loss: 1.3810 - distribution_lambda_23_loss: 0.4750 - val_loss: 2.6187 - val_distribution_lambda_21_loss: 0.6511 - val_distribution_lambda_22_loss: 1.5452 - val_distribution_lambda_23_loss: 0.4224\n",
"Epoch 635/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4047 - distribution_lambda_21_loss: 0.5467 - distribution_lambda_22_loss: 1.3884 - distribution_lambda_23_loss: 0.4695 - val_loss: 2.6426 - val_distribution_lambda_21_loss: 0.6666 - val_distribution_lambda_22_loss: 1.5538 - val_distribution_lambda_23_loss: 0.4222\n",
"Epoch 636/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3654 - distribution_lambda_21_loss: 0.5284 - distribution_lambda_22_loss: 1.3746 - distribution_lambda_23_loss: 0.4624 - val_loss: 2.6344 - val_distribution_lambda_21_loss: 0.6688 - val_distribution_lambda_22_loss: 1.5449 - val_distribution_lambda_23_loss: 0.4207\n",
"Epoch 637/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.4025 - distribution_lambda_21_loss: 0.5481 - distribution_lambda_22_loss: 1.3908 - distribution_lambda_23_loss: 0.4636 - val_loss: 2.6158 - val_distribution_lambda_21_loss: 0.6597 - val_distribution_lambda_22_loss: 1.5356 - val_distribution_lambda_23_loss: 0.4204\n",
"Epoch 638/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3781 - distribution_lambda_21_loss: 0.5400 - distribution_lambda_22_loss: 1.3677 - distribution_lambda_23_loss: 0.4704 - val_loss: 2.6280 - val_distribution_lambda_21_loss: 0.6620 - val_distribution_lambda_22_loss: 1.5453 - val_distribution_lambda_23_loss: 0.4207\n",
"Epoch 639/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3502 - distribution_lambda_21_loss: 0.5281 - distribution_lambda_22_loss: 1.3614 - distribution_lambda_23_loss: 0.4607 - val_loss: 2.6318 - val_distribution_lambda_21_loss: 0.6631 - val_distribution_lambda_22_loss: 1.5479 - val_distribution_lambda_23_loss: 0.4207\n",
"Epoch 640/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3792 - distribution_lambda_21_loss: 0.5310 - distribution_lambda_22_loss: 1.3730 - distribution_lambda_23_loss: 0.4752 - val_loss: 2.6476 - val_distribution_lambda_21_loss: 0.6673 - val_distribution_lambda_22_loss: 1.5574 - val_distribution_lambda_23_loss: 0.4229\n",
"Epoch 641/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3944 - distribution_lambda_21_loss: 0.5345 - distribution_lambda_22_loss: 1.3925 - distribution_lambda_23_loss: 0.4674 - val_loss: 2.6302 - val_distribution_lambda_21_loss: 0.6622 - val_distribution_lambda_22_loss: 1.5467 - val_distribution_lambda_23_loss: 0.4213\n",
"Epoch 642/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3982 - distribution_lambda_21_loss: 0.5468 - distribution_lambda_22_loss: 1.3831 - distribution_lambda_23_loss: 0.4683 - val_loss: 2.5989 - val_distribution_lambda_21_loss: 0.6503 - val_distribution_lambda_22_loss: 1.5285 - val_distribution_lambda_23_loss: 0.4201\n",
"Epoch 643/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3649 - distribution_lambda_21_loss: 0.5159 - distribution_lambda_22_loss: 1.3838 - distribution_lambda_23_loss: 0.4652 - val_loss: 2.6054 - val_distribution_lambda_21_loss: 0.6532 - val_distribution_lambda_22_loss: 1.5336 - val_distribution_lambda_23_loss: 0.4186\n",
"Epoch 644/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3468 - distribution_lambda_21_loss: 0.5219 - distribution_lambda_22_loss: 1.3680 - distribution_lambda_23_loss: 0.4570 - val_loss: 2.6326 - val_distribution_lambda_21_loss: 0.6624 - val_distribution_lambda_22_loss: 1.5520 - val_distribution_lambda_23_loss: 0.4182\n",
"Epoch 645/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3716 - distribution_lambda_21_loss: 0.5302 - distribution_lambda_22_loss: 1.3696 - distribution_lambda_23_loss: 0.4718 - val_loss: 2.6490 - val_distribution_lambda_21_loss: 0.6692 - val_distribution_lambda_22_loss: 1.5612 - val_distribution_lambda_23_loss: 0.4186\n",
"Epoch 646/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3284 - distribution_lambda_21_loss: 0.5186 - distribution_lambda_22_loss: 1.3609 - distribution_lambda_23_loss: 0.4489 - val_loss: 2.6577 - val_distribution_lambda_21_loss: 0.6724 - val_distribution_lambda_22_loss: 1.5671 - val_distribution_lambda_23_loss: 0.4182\n",
"Epoch 647/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3833 - distribution_lambda_21_loss: 0.5360 - distribution_lambda_22_loss: 1.3772 - distribution_lambda_23_loss: 0.4701 - val_loss: 2.6668 - val_distribution_lambda_21_loss: 0.6751 - val_distribution_lambda_22_loss: 1.5730 - val_distribution_lambda_23_loss: 0.4187\n",
"Epoch 648/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3916 - distribution_lambda_21_loss: 0.5405 - distribution_lambda_22_loss: 1.3745 - distribution_lambda_23_loss: 0.4766 - val_loss: 2.6548 - val_distribution_lambda_21_loss: 0.6660 - val_distribution_lambda_22_loss: 1.5700 - val_distribution_lambda_23_loss: 0.4188\n",
"Epoch 649/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.3750 - distribution_lambda_21_loss: 0.5293 - distribution_lambda_22_loss: 1.3762 - distribution_lambda_23_loss: 0.4695 - val_loss: 2.6282 - val_distribution_lambda_21_loss: 0.6537 - val_distribution_lambda_22_loss: 1.5562 - val_distribution_lambda_23_loss: 0.4183\n",
"Epoch 650/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3281 - distribution_lambda_21_loss: 0.5210 - distribution_lambda_22_loss: 1.3560 - distribution_lambda_23_loss: 0.4511 - val_loss: 2.6132 - val_distribution_lambda_21_loss: 0.6498 - val_distribution_lambda_22_loss: 1.5461 - val_distribution_lambda_23_loss: 0.4173\n",
"Epoch 651/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3531 - distribution_lambda_21_loss: 0.5185 - distribution_lambda_22_loss: 1.3710 - distribution_lambda_23_loss: 0.4636 - val_loss: 2.6157 - val_distribution_lambda_21_loss: 0.6540 - val_distribution_lambda_22_loss: 1.5448 - val_distribution_lambda_23_loss: 0.4169\n",
"Epoch 652/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3589 - distribution_lambda_21_loss: 0.5220 - distribution_lambda_22_loss: 1.3751 - distribution_lambda_23_loss: 0.4618 - val_loss: 2.6309 - val_distribution_lambda_21_loss: 0.6658 - val_distribution_lambda_22_loss: 1.5497 - val_distribution_lambda_23_loss: 0.4153\n",
"Epoch 653/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3614 - distribution_lambda_21_loss: 0.5206 - distribution_lambda_22_loss: 1.3706 - distribution_lambda_23_loss: 0.4702 - val_loss: 2.6501 - val_distribution_lambda_21_loss: 0.6724 - val_distribution_lambda_22_loss: 1.5615 - val_distribution_lambda_23_loss: 0.4162\n",
"Epoch 654/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3195 - distribution_lambda_21_loss: 0.5144 - distribution_lambda_22_loss: 1.3587 - distribution_lambda_23_loss: 0.4464 - val_loss: 2.6513 - val_distribution_lambda_21_loss: 0.6701 - val_distribution_lambda_22_loss: 1.5654 - val_distribution_lambda_23_loss: 0.4158\n",
"Epoch 655/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3429 - distribution_lambda_21_loss: 0.5167 - distribution_lambda_22_loss: 1.3602 - distribution_lambda_23_loss: 0.4660 - val_loss: 2.6523 - val_distribution_lambda_21_loss: 0.6654 - val_distribution_lambda_22_loss: 1.5696 - val_distribution_lambda_23_loss: 0.4173\n",
"Epoch 656/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3608 - distribution_lambda_21_loss: 0.5197 - distribution_lambda_22_loss: 1.3684 - distribution_lambda_23_loss: 0.4727 - val_loss: 2.6430 - val_distribution_lambda_21_loss: 0.6630 - val_distribution_lambda_22_loss: 1.5621 - val_distribution_lambda_23_loss: 0.4180\n",
"Epoch 657/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3315 - distribution_lambda_21_loss: 0.5140 - distribution_lambda_22_loss: 1.3607 - distribution_lambda_23_loss: 0.4568 - val_loss: 2.6414 - val_distribution_lambda_21_loss: 0.6641 - val_distribution_lambda_22_loss: 1.5589 - val_distribution_lambda_23_loss: 0.4183\n",
"Epoch 658/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3505 - distribution_lambda_21_loss: 0.5194 - distribution_lambda_22_loss: 1.3702 - distribution_lambda_23_loss: 0.4609 - val_loss: 2.6442 - val_distribution_lambda_21_loss: 0.6745 - val_distribution_lambda_22_loss: 1.5519 - val_distribution_lambda_23_loss: 0.4178\n",
"Epoch 659/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.3652 - distribution_lambda_21_loss: 0.5222 - distribution_lambda_22_loss: 1.3808 - distribution_lambda_23_loss: 0.4622 - val_loss: 2.6375 - val_distribution_lambda_21_loss: 0.6766 - val_distribution_lambda_22_loss: 1.5438 - val_distribution_lambda_23_loss: 0.4171\n",
"Epoch 660/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3432 - distribution_lambda_21_loss: 0.5274 - distribution_lambda_22_loss: 1.3576 - distribution_lambda_23_loss: 0.4581 - val_loss: 2.6423 - val_distribution_lambda_21_loss: 0.6728 - val_distribution_lambda_22_loss: 1.5545 - val_distribution_lambda_23_loss: 0.4150\n",
"Epoch 661/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3564 - distribution_lambda_21_loss: 0.4991 - distribution_lambda_22_loss: 1.3806 - distribution_lambda_23_loss: 0.4767 - val_loss: 2.6440 - val_distribution_lambda_21_loss: 0.6739 - val_distribution_lambda_22_loss: 1.5542 - val_distribution_lambda_23_loss: 0.4159\n",
"Epoch 662/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3469 - distribution_lambda_21_loss: 0.5155 - distribution_lambda_22_loss: 1.3552 - distribution_lambda_23_loss: 0.4762 - val_loss: 2.6243 - val_distribution_lambda_21_loss: 0.6662 - val_distribution_lambda_22_loss: 1.5412 - val_distribution_lambda_23_loss: 0.4169\n",
"Epoch 663/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3358 - distribution_lambda_21_loss: 0.5225 - distribution_lambda_22_loss: 1.3554 - distribution_lambda_23_loss: 0.4579 - val_loss: 2.6332 - val_distribution_lambda_21_loss: 0.6614 - val_distribution_lambda_22_loss: 1.5547 - val_distribution_lambda_23_loss: 0.4170\n",
"Epoch 664/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3307 - distribution_lambda_21_loss: 0.5102 - distribution_lambda_22_loss: 1.3498 - distribution_lambda_23_loss: 0.4707 - val_loss: 2.6698 - val_distribution_lambda_21_loss: 0.6639 - val_distribution_lambda_22_loss: 1.5877 - val_distribution_lambda_23_loss: 0.4182\n",
"Epoch 665/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3387 - distribution_lambda_21_loss: 0.4956 - distribution_lambda_22_loss: 1.3710 - distribution_lambda_23_loss: 0.4721 - val_loss: 2.6774 - val_distribution_lambda_21_loss: 0.6639 - val_distribution_lambda_22_loss: 1.5962 - val_distribution_lambda_23_loss: 0.4173\n",
"Epoch 666/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2956 - distribution_lambda_21_loss: 0.5057 - distribution_lambda_22_loss: 1.3384 - distribution_lambda_23_loss: 0.4515 - val_loss: 2.6540 - val_distribution_lambda_21_loss: 0.6607 - val_distribution_lambda_22_loss: 1.5790 - val_distribution_lambda_23_loss: 0.4143\n",
"Epoch 667/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3391 - distribution_lambda_21_loss: 0.5061 - distribution_lambda_22_loss: 1.3639 - distribution_lambda_23_loss: 0.4691 - val_loss: 2.6453 - val_distribution_lambda_21_loss: 0.6575 - val_distribution_lambda_22_loss: 1.5718 - val_distribution_lambda_23_loss: 0.4160\n",
"Epoch 668/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.3235 - distribution_lambda_21_loss: 0.5074 - distribution_lambda_22_loss: 1.3577 - distribution_lambda_23_loss: 0.4583 - val_loss: 2.6371 - val_distribution_lambda_21_loss: 0.6604 - val_distribution_lambda_22_loss: 1.5606 - val_distribution_lambda_23_loss: 0.4161\n",
"Epoch 669/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2836 - distribution_lambda_21_loss: 0.4923 - distribution_lambda_22_loss: 1.3323 - distribution_lambda_23_loss: 0.4590 - val_loss: 2.6602 - val_distribution_lambda_21_loss: 0.6659 - val_distribution_lambda_22_loss: 1.5780 - val_distribution_lambda_23_loss: 0.4163\n",
"Epoch 670/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3188 - distribution_lambda_21_loss: 0.5009 - distribution_lambda_22_loss: 1.3494 - distribution_lambda_23_loss: 0.4685 - val_loss: 2.6896 - val_distribution_lambda_21_loss: 0.6740 - val_distribution_lambda_22_loss: 1.5998 - val_distribution_lambda_23_loss: 0.4158\n",
"Epoch 671/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2994 - distribution_lambda_21_loss: 0.5013 - distribution_lambda_22_loss: 1.3473 - distribution_lambda_23_loss: 0.4509 - val_loss: 2.6872 - val_distribution_lambda_21_loss: 0.6781 - val_distribution_lambda_22_loss: 1.5950 - val_distribution_lambda_23_loss: 0.4142\n",
"Epoch 672/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3147 - distribution_lambda_21_loss: 0.5085 - distribution_lambda_22_loss: 1.3472 - distribution_lambda_23_loss: 0.4590 - val_loss: 2.6681 - val_distribution_lambda_21_loss: 0.6728 - val_distribution_lambda_22_loss: 1.5824 - val_distribution_lambda_23_loss: 0.4130\n",
"Epoch 673/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.3171 - distribution_lambda_21_loss: 0.5091 - distribution_lambda_22_loss: 1.3539 - distribution_lambda_23_loss: 0.4541 - val_loss: 2.6549 - val_distribution_lambda_21_loss: 0.6686 - val_distribution_lambda_22_loss: 1.5732 - val_distribution_lambda_23_loss: 0.4131\n",
"Epoch 674/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3119 - distribution_lambda_21_loss: 0.5001 - distribution_lambda_22_loss: 1.3522 - distribution_lambda_23_loss: 0.4595 - val_loss: 2.6306 - val_distribution_lambda_21_loss: 0.6568 - val_distribution_lambda_22_loss: 1.5606 - val_distribution_lambda_23_loss: 0.4132\n",
"Epoch 675/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3374 - distribution_lambda_21_loss: 0.5073 - distribution_lambda_22_loss: 1.3660 - distribution_lambda_23_loss: 0.4641 - val_loss: 2.6367 - val_distribution_lambda_21_loss: 0.6599 - val_distribution_lambda_22_loss: 1.5633 - val_distribution_lambda_23_loss: 0.4136\n",
"Epoch 676/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3063 - distribution_lambda_21_loss: 0.4930 - distribution_lambda_22_loss: 1.3527 - distribution_lambda_23_loss: 0.4607 - val_loss: 2.6594 - val_distribution_lambda_21_loss: 0.6709 - val_distribution_lambda_22_loss: 1.5746 - val_distribution_lambda_23_loss: 0.4139\n",
"Epoch 677/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3481 - distribution_lambda_21_loss: 0.5096 - distribution_lambda_22_loss: 1.3697 - distribution_lambda_23_loss: 0.4688 - val_loss: 2.6721 - val_distribution_lambda_21_loss: 0.6768 - val_distribution_lambda_22_loss: 1.5813 - val_distribution_lambda_23_loss: 0.4140\n",
"Epoch 678/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2828 - distribution_lambda_21_loss: 0.4920 - distribution_lambda_22_loss: 1.3476 - distribution_lambda_23_loss: 0.4431 - val_loss: 2.6787 - val_distribution_lambda_21_loss: 0.6819 - val_distribution_lambda_22_loss: 1.5834 - val_distribution_lambda_23_loss: 0.4135\n",
"Epoch 679/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3125 - distribution_lambda_21_loss: 0.4807 - distribution_lambda_22_loss: 1.3506 - distribution_lambda_23_loss: 0.4812 - val_loss: 2.6798 - val_distribution_lambda_21_loss: 0.6740 - val_distribution_lambda_22_loss: 1.5909 - val_distribution_lambda_23_loss: 0.4150\n",
"Epoch 680/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3016 - distribution_lambda_21_loss: 0.4969 - distribution_lambda_22_loss: 1.3497 - distribution_lambda_23_loss: 0.4550 - val_loss: 2.6444 - val_distribution_lambda_21_loss: 0.6682 - val_distribution_lambda_22_loss: 1.5626 - val_distribution_lambda_23_loss: 0.4135\n",
"Epoch 681/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3097 - distribution_lambda_21_loss: 0.4774 - distribution_lambda_22_loss: 1.3599 - distribution_lambda_23_loss: 0.4724 - val_loss: 2.6362 - val_distribution_lambda_21_loss: 0.6626 - val_distribution_lambda_22_loss: 1.5601 - val_distribution_lambda_23_loss: 0.4135\n",
"Epoch 682/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2768 - distribution_lambda_21_loss: 0.4854 - distribution_lambda_22_loss: 1.3405 - distribution_lambda_23_loss: 0.4509 - val_loss: 2.6458 - val_distribution_lambda_21_loss: 0.6657 - val_distribution_lambda_22_loss: 1.5684 - val_distribution_lambda_23_loss: 0.4117\n",
"Epoch 683/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2843 - distribution_lambda_21_loss: 0.4905 - distribution_lambda_22_loss: 1.3402 - distribution_lambda_23_loss: 0.4537 - val_loss: 2.6557 - val_distribution_lambda_21_loss: 0.6698 - val_distribution_lambda_22_loss: 1.5756 - val_distribution_lambda_23_loss: 0.4102\n",
"Epoch 684/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3055 - distribution_lambda_21_loss: 0.4969 - distribution_lambda_22_loss: 1.3571 - distribution_lambda_23_loss: 0.4516 - val_loss: 2.6359 - val_distribution_lambda_21_loss: 0.6637 - val_distribution_lambda_22_loss: 1.5637 - val_distribution_lambda_23_loss: 0.4084\n",
"Epoch 685/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2844 - distribution_lambda_21_loss: 0.4862 - distribution_lambda_22_loss: 1.3428 - distribution_lambda_23_loss: 0.4554 - val_loss: 2.6511 - val_distribution_lambda_21_loss: 0.6676 - val_distribution_lambda_22_loss: 1.5738 - val_distribution_lambda_23_loss: 0.4098\n",
"Epoch 686/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2667 - distribution_lambda_21_loss: 0.4872 - distribution_lambda_22_loss: 1.3199 - distribution_lambda_23_loss: 0.4596 - val_loss: 2.6607 - val_distribution_lambda_21_loss: 0.6658 - val_distribution_lambda_22_loss: 1.5845 - val_distribution_lambda_23_loss: 0.4103\n",
"Epoch 687/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2607 - distribution_lambda_21_loss: 0.4774 - distribution_lambda_22_loss: 1.3260 - distribution_lambda_23_loss: 0.4572 - val_loss: 2.6648 - val_distribution_lambda_21_loss: 0.6601 - val_distribution_lambda_22_loss: 1.5953 - val_distribution_lambda_23_loss: 0.4094\n",
"Epoch 688/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2717 - distribution_lambda_21_loss: 0.4868 - distribution_lambda_22_loss: 1.3355 - distribution_lambda_23_loss: 0.4494 - val_loss: 2.6486 - val_distribution_lambda_21_loss: 0.6591 - val_distribution_lambda_22_loss: 1.5821 - val_distribution_lambda_23_loss: 0.4074\n",
"Epoch 689/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2565 - distribution_lambda_21_loss: 0.4849 - distribution_lambda_22_loss: 1.3261 - distribution_lambda_23_loss: 0.4455 - val_loss: 2.6616 - val_distribution_lambda_21_loss: 0.6720 - val_distribution_lambda_22_loss: 1.5834 - val_distribution_lambda_23_loss: 0.4062\n",
"Epoch 690/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2852 - distribution_lambda_21_loss: 0.4856 - distribution_lambda_22_loss: 1.3457 - distribution_lambda_23_loss: 0.4540 - val_loss: 2.6060 - val_distribution_lambda_21_loss: 0.6561 - val_distribution_lambda_22_loss: 1.5443 - val_distribution_lambda_23_loss: 0.4056\n",
"Epoch 691/2500\n",
"9/9 [==============================] - 0s 8ms/step - loss: 2.2776 - distribution_lambda_21_loss: 0.4880 - distribution_lambda_22_loss: 1.3428 - distribution_lambda_23_loss: 0.4468 - val_loss: 2.5714 - val_distribution_lambda_21_loss: 0.6401 - val_distribution_lambda_22_loss: 1.5260 - val_distribution_lambda_23_loss: 0.4053\n",
"Epoch 692/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2898 - distribution_lambda_21_loss: 0.4766 - distribution_lambda_22_loss: 1.3405 - distribution_lambda_23_loss: 0.4727 - val_loss: 2.5821 - val_distribution_lambda_21_loss: 0.6396 - val_distribution_lambda_22_loss: 1.5365 - val_distribution_lambda_23_loss: 0.4059\n",
"Epoch 693/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2922 - distribution_lambda_21_loss: 0.4844 - distribution_lambda_22_loss: 1.3553 - distribution_lambda_23_loss: 0.4525 - val_loss: 2.6324 - val_distribution_lambda_21_loss: 0.6524 - val_distribution_lambda_22_loss: 1.5721 - val_distribution_lambda_23_loss: 0.4078\n",
"Epoch 694/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3056 - distribution_lambda_21_loss: 0.5086 - distribution_lambda_22_loss: 1.3430 - distribution_lambda_23_loss: 0.4540 - val_loss: 2.6564 - val_distribution_lambda_21_loss: 0.6639 - val_distribution_lambda_22_loss: 1.5841 - val_distribution_lambda_23_loss: 0.4084\n",
"Epoch 695/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2772 - distribution_lambda_21_loss: 0.4869 - distribution_lambda_22_loss: 1.3382 - distribution_lambda_23_loss: 0.4520 - val_loss: 2.6438 - val_distribution_lambda_21_loss: 0.6570 - val_distribution_lambda_22_loss: 1.5794 - val_distribution_lambda_23_loss: 0.4074\n",
"Epoch 696/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3019 - distribution_lambda_21_loss: 0.4865 - distribution_lambda_22_loss: 1.3616 - distribution_lambda_23_loss: 0.4538 - val_loss: 2.6273 - val_distribution_lambda_21_loss: 0.6517 - val_distribution_lambda_22_loss: 1.5690 - val_distribution_lambda_23_loss: 0.4065\n",
"Epoch 697/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 2.2538 - distribution_lambda_21_loss: 0.4669 - distribution_lambda_22_loss: 1.3284 - distribution_lambda_23_loss: 0.4584 - val_loss: 2.6089 - val_distribution_lambda_21_loss: 0.6498 - val_distribution_lambda_22_loss: 1.5534 - val_distribution_lambda_23_loss: 0.4057\n",
"Epoch 698/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2722 - distribution_lambda_21_loss: 0.4799 - distribution_lambda_22_loss: 1.3318 - distribution_lambda_23_loss: 0.4605 - val_loss: 2.5968 - val_distribution_lambda_21_loss: 0.6454 - val_distribution_lambda_22_loss: 1.5443 - val_distribution_lambda_23_loss: 0.4071\n",
"Epoch 699/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2819 - distribution_lambda_21_loss: 0.4813 - distribution_lambda_22_loss: 1.3534 - distribution_lambda_23_loss: 0.4472 - val_loss: 2.6049 - val_distribution_lambda_21_loss: 0.6493 - val_distribution_lambda_22_loss: 1.5466 - val_distribution_lambda_23_loss: 0.4090\n",
"Epoch 700/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2652 - distribution_lambda_21_loss: 0.4772 - distribution_lambda_22_loss: 1.3283 - distribution_lambda_23_loss: 0.4597 - val_loss: 2.6209 - val_distribution_lambda_21_loss: 0.6476 - val_distribution_lambda_22_loss: 1.5654 - val_distribution_lambda_23_loss: 0.4079\n",
"Epoch 701/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2714 - distribution_lambda_21_loss: 0.4756 - distribution_lambda_22_loss: 1.3405 - distribution_lambda_23_loss: 0.4553 - val_loss: 2.6321 - val_distribution_lambda_21_loss: 0.6464 - val_distribution_lambda_22_loss: 1.5787 - val_distribution_lambda_23_loss: 0.4070\n",
"Epoch 702/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2392 - distribution_lambda_21_loss: 0.4688 - distribution_lambda_22_loss: 1.3193 - distribution_lambda_23_loss: 0.4511 - val_loss: 2.6434 - val_distribution_lambda_21_loss: 0.6625 - val_distribution_lambda_22_loss: 1.5754 - val_distribution_lambda_23_loss: 0.4055\n",
"Epoch 703/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.3106 - distribution_lambda_21_loss: 0.4889 - distribution_lambda_22_loss: 1.3569 - distribution_lambda_23_loss: 0.4648 - val_loss: 2.6176 - val_distribution_lambda_21_loss: 0.6629 - val_distribution_lambda_22_loss: 1.5509 - val_distribution_lambda_23_loss: 0.4039\n",
"Epoch 704/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2903 - distribution_lambda_21_loss: 0.4775 - distribution_lambda_22_loss: 1.3537 - distribution_lambda_23_loss: 0.4591 - val_loss: 2.6004 - val_distribution_lambda_21_loss: 0.6467 - val_distribution_lambda_22_loss: 1.5489 - val_distribution_lambda_23_loss: 0.4048\n",
"Epoch 705/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2516 - distribution_lambda_21_loss: 0.4765 - distribution_lambda_22_loss: 1.3329 - distribution_lambda_23_loss: 0.4422 - val_loss: 2.6103 - val_distribution_lambda_21_loss: 0.6451 - val_distribution_lambda_22_loss: 1.5617 - val_distribution_lambda_23_loss: 0.4035\n",
"Epoch 706/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2415 - distribution_lambda_21_loss: 0.4674 - distribution_lambda_22_loss: 1.3315 - distribution_lambda_23_loss: 0.4426 - val_loss: 2.6142 - val_distribution_lambda_21_loss: 0.6548 - val_distribution_lambda_22_loss: 1.5563 - val_distribution_lambda_23_loss: 0.4030\n",
"Epoch 707/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2747 - distribution_lambda_21_loss: 0.4754 - distribution_lambda_22_loss: 1.3252 - distribution_lambda_23_loss: 0.4741 - val_loss: 2.6026 - val_distribution_lambda_21_loss: 0.6490 - val_distribution_lambda_22_loss: 1.5513 - val_distribution_lambda_23_loss: 0.4022\n",
"Epoch 708/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2765 - distribution_lambda_21_loss: 0.4668 - distribution_lambda_22_loss: 1.3442 - distribution_lambda_23_loss: 0.4655 - val_loss: 2.5754 - val_distribution_lambda_21_loss: 0.6401 - val_distribution_lambda_22_loss: 1.5337 - val_distribution_lambda_23_loss: 0.4016\n",
"Epoch 709/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2702 - distribution_lambda_21_loss: 0.4698 - distribution_lambda_22_loss: 1.3439 - distribution_lambda_23_loss: 0.4565 - val_loss: 2.5788 - val_distribution_lambda_21_loss: 0.6447 - val_distribution_lambda_22_loss: 1.5300 - val_distribution_lambda_23_loss: 0.4041\n",
"Epoch 710/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2494 - distribution_lambda_21_loss: 0.4728 - distribution_lambda_22_loss: 1.3306 - distribution_lambda_23_loss: 0.4459 - val_loss: 2.5872 - val_distribution_lambda_21_loss: 0.6391 - val_distribution_lambda_22_loss: 1.5434 - val_distribution_lambda_23_loss: 0.4047\n",
"Epoch 711/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2467 - distribution_lambda_21_loss: 0.4646 - distribution_lambda_22_loss: 1.3298 - distribution_lambda_23_loss: 0.4523 - val_loss: 2.5759 - val_distribution_lambda_21_loss: 0.6352 - val_distribution_lambda_22_loss: 1.5385 - val_distribution_lambda_23_loss: 0.4022\n",
"Epoch 712/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2494 - distribution_lambda_21_loss: 0.4693 - distribution_lambda_22_loss: 1.3316 - distribution_lambda_23_loss: 0.4485 - val_loss: 2.5882 - val_distribution_lambda_21_loss: 0.6408 - val_distribution_lambda_22_loss: 1.5460 - val_distribution_lambda_23_loss: 0.4014\n",
"Epoch 713/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2282 - distribution_lambda_21_loss: 0.4657 - distribution_lambda_22_loss: 1.3184 - distribution_lambda_23_loss: 0.4441 - val_loss: 2.6014 - val_distribution_lambda_21_loss: 0.6464 - val_distribution_lambda_22_loss: 1.5526 - val_distribution_lambda_23_loss: 0.4023\n",
"Epoch 714/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2511 - distribution_lambda_21_loss: 0.4676 - distribution_lambda_22_loss: 1.3295 - distribution_lambda_23_loss: 0.4540 - val_loss: 2.5913 - val_distribution_lambda_21_loss: 0.6470 - val_distribution_lambda_22_loss: 1.5415 - val_distribution_lambda_23_loss: 0.4028\n",
"Epoch 715/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2368 - distribution_lambda_21_loss: 0.4577 - distribution_lambda_22_loss: 1.3212 - distribution_lambda_23_loss: 0.4579 - val_loss: 2.6105 - val_distribution_lambda_21_loss: 0.6504 - val_distribution_lambda_22_loss: 1.5550 - val_distribution_lambda_23_loss: 0.4051\n",
"Epoch 716/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2525 - distribution_lambda_21_loss: 0.4726 - distribution_lambda_22_loss: 1.3302 - distribution_lambda_23_loss: 0.4497 - val_loss: 2.6050 - val_distribution_lambda_21_loss: 0.6494 - val_distribution_lambda_22_loss: 1.5503 - val_distribution_lambda_23_loss: 0.4053\n",
"Epoch 717/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2329 - distribution_lambda_21_loss: 0.4698 - distribution_lambda_22_loss: 1.3277 - distribution_lambda_23_loss: 0.4355 - val_loss: 2.5951 - val_distribution_lambda_21_loss: 0.6516 - val_distribution_lambda_22_loss: 1.5381 - val_distribution_lambda_23_loss: 0.4054\n",
"Epoch 718/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2472 - distribution_lambda_21_loss: 0.4537 - distribution_lambda_22_loss: 1.3386 - distribution_lambda_23_loss: 0.4548 - val_loss: 2.6117 - val_distribution_lambda_21_loss: 0.6601 - val_distribution_lambda_22_loss: 1.5467 - val_distribution_lambda_23_loss: 0.4049\n",
"Epoch 719/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2245 - distribution_lambda_21_loss: 0.4554 - distribution_lambda_22_loss: 1.3152 - distribution_lambda_23_loss: 0.4540 - val_loss: 2.6049 - val_distribution_lambda_21_loss: 0.6475 - val_distribution_lambda_22_loss: 1.5527 - val_distribution_lambda_23_loss: 0.4047\n",
"Epoch 720/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2412 - distribution_lambda_21_loss: 0.4624 - distribution_lambda_22_loss: 1.3340 - distribution_lambda_23_loss: 0.4448 - val_loss: 2.5774 - val_distribution_lambda_21_loss: 0.6331 - val_distribution_lambda_22_loss: 1.5431 - val_distribution_lambda_23_loss: 0.4012\n",
"Epoch 721/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.2209 - distribution_lambda_21_loss: 0.4457 - distribution_lambda_22_loss: 1.3218 - distribution_lambda_23_loss: 0.4534 - val_loss: 2.5849 - val_distribution_lambda_21_loss: 0.6372 - val_distribution_lambda_22_loss: 1.5462 - val_distribution_lambda_23_loss: 0.4015\n",
"Epoch 722/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2603 - distribution_lambda_21_loss: 0.4440 - distribution_lambda_22_loss: 1.3641 - distribution_lambda_23_loss: 0.4521 - val_loss: 2.5940 - val_distribution_lambda_21_loss: 0.6460 - val_distribution_lambda_22_loss: 1.5439 - val_distribution_lambda_23_loss: 0.4041\n",
"Epoch 723/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2511 - distribution_lambda_21_loss: 0.4556 - distribution_lambda_22_loss: 1.3300 - distribution_lambda_23_loss: 0.4655 - val_loss: 2.5809 - val_distribution_lambda_21_loss: 0.6482 - val_distribution_lambda_22_loss: 1.5304 - val_distribution_lambda_23_loss: 0.4023\n",
"Epoch 724/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2246 - distribution_lambda_21_loss: 0.4571 - distribution_lambda_22_loss: 1.3227 - distribution_lambda_23_loss: 0.4447 - val_loss: 2.5922 - val_distribution_lambda_21_loss: 0.6499 - val_distribution_lambda_22_loss: 1.5413 - val_distribution_lambda_23_loss: 0.4010\n",
"Epoch 725/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2543 - distribution_lambda_21_loss: 0.4680 - distribution_lambda_22_loss: 1.3334 - distribution_lambda_23_loss: 0.4530 - val_loss: 2.5916 - val_distribution_lambda_21_loss: 0.6428 - val_distribution_lambda_22_loss: 1.5499 - val_distribution_lambda_23_loss: 0.3990\n",
"Epoch 726/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2268 - distribution_lambda_21_loss: 0.4513 - distribution_lambda_22_loss: 1.3379 - distribution_lambda_23_loss: 0.4376 - val_loss: 2.6104 - val_distribution_lambda_21_loss: 0.6545 - val_distribution_lambda_22_loss: 1.5574 - val_distribution_lambda_23_loss: 0.3984\n",
"Epoch 727/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2336 - distribution_lambda_21_loss: 0.4660 - distribution_lambda_22_loss: 1.3196 - distribution_lambda_23_loss: 0.4481 - val_loss: 2.6119 - val_distribution_lambda_21_loss: 0.6591 - val_distribution_lambda_22_loss: 1.5530 - val_distribution_lambda_23_loss: 0.3998\n",
"Epoch 728/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2139 - distribution_lambda_21_loss: 0.4529 - distribution_lambda_22_loss: 1.3159 - distribution_lambda_23_loss: 0.4451 - val_loss: 2.5835 - val_distribution_lambda_21_loss: 0.6450 - val_distribution_lambda_22_loss: 1.5406 - val_distribution_lambda_23_loss: 0.3979\n",
"Epoch 729/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2207 - distribution_lambda_21_loss: 0.4483 - distribution_lambda_22_loss: 1.3219 - distribution_lambda_23_loss: 0.4506 - val_loss: 2.5625 - val_distribution_lambda_21_loss: 0.6386 - val_distribution_lambda_22_loss: 1.5288 - val_distribution_lambda_23_loss: 0.3952\n",
"Epoch 730/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1915 - distribution_lambda_21_loss: 0.4450 - distribution_lambda_22_loss: 1.3070 - distribution_lambda_23_loss: 0.4395 - val_loss: 2.5809 - val_distribution_lambda_21_loss: 0.6467 - val_distribution_lambda_22_loss: 1.5383 - val_distribution_lambda_23_loss: 0.3959\n",
"Epoch 731/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2078 - distribution_lambda_21_loss: 0.4582 - distribution_lambda_22_loss: 1.3093 - distribution_lambda_23_loss: 0.4402 - val_loss: 2.5764 - val_distribution_lambda_21_loss: 0.6435 - val_distribution_lambda_22_loss: 1.5364 - val_distribution_lambda_23_loss: 0.3965\n",
"Epoch 732/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2174 - distribution_lambda_21_loss: 0.4549 - distribution_lambda_22_loss: 1.3247 - distribution_lambda_23_loss: 0.4379 - val_loss: 2.5392 - val_distribution_lambda_21_loss: 0.6317 - val_distribution_lambda_22_loss: 1.5120 - val_distribution_lambda_23_loss: 0.3956\n",
"Epoch 733/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1774 - distribution_lambda_21_loss: 0.4441 - distribution_lambda_22_loss: 1.2893 - distribution_lambda_23_loss: 0.4440 - val_loss: 2.5619 - val_distribution_lambda_21_loss: 0.6454 - val_distribution_lambda_22_loss: 1.5210 - val_distribution_lambda_23_loss: 0.3955\n",
"Epoch 734/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2195 - distribution_lambda_21_loss: 0.4505 - distribution_lambda_22_loss: 1.3267 - distribution_lambda_23_loss: 0.4423 - val_loss: 2.5828 - val_distribution_lambda_21_loss: 0.6510 - val_distribution_lambda_22_loss: 1.5367 - val_distribution_lambda_23_loss: 0.3952\n",
"Epoch 735/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1968 - distribution_lambda_21_loss: 0.4446 - distribution_lambda_22_loss: 1.3087 - distribution_lambda_23_loss: 0.4434 - val_loss: 2.5751 - val_distribution_lambda_21_loss: 0.6445 - val_distribution_lambda_22_loss: 1.5359 - val_distribution_lambda_23_loss: 0.3946\n",
"Epoch 736/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1913 - distribution_lambda_21_loss: 0.4500 - distribution_lambda_22_loss: 1.3092 - distribution_lambda_23_loss: 0.4321 - val_loss: 2.5636 - val_distribution_lambda_21_loss: 0.6391 - val_distribution_lambda_22_loss: 1.5307 - val_distribution_lambda_23_loss: 0.3937\n",
"Epoch 737/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2160 - distribution_lambda_21_loss: 0.4637 - distribution_lambda_22_loss: 1.3111 - distribution_lambda_23_loss: 0.4412 - val_loss: 2.5845 - val_distribution_lambda_21_loss: 0.6435 - val_distribution_lambda_22_loss: 1.5458 - val_distribution_lambda_23_loss: 0.3951\n",
"Epoch 738/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1918 - distribution_lambda_21_loss: 0.4293 - distribution_lambda_22_loss: 1.3103 - distribution_lambda_23_loss: 0.4523 - val_loss: 2.5781 - val_distribution_lambda_21_loss: 0.6438 - val_distribution_lambda_22_loss: 1.5389 - val_distribution_lambda_23_loss: 0.3954\n",
"Epoch 739/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2044 - distribution_lambda_21_loss: 0.4453 - distribution_lambda_22_loss: 1.3180 - distribution_lambda_23_loss: 0.4411 - val_loss: 2.5776 - val_distribution_lambda_21_loss: 0.6495 - val_distribution_lambda_22_loss: 1.5340 - val_distribution_lambda_23_loss: 0.3940\n",
"Epoch 740/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.2110 - distribution_lambda_21_loss: 0.4469 - distribution_lambda_22_loss: 1.3000 - distribution_lambda_23_loss: 0.4641 - val_loss: 2.5698 - val_distribution_lambda_21_loss: 0.6520 - val_distribution_lambda_22_loss: 1.5233 - val_distribution_lambda_23_loss: 0.3945\n",
"Epoch 741/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1914 - distribution_lambda_21_loss: 0.4347 - distribution_lambda_22_loss: 1.3122 - distribution_lambda_23_loss: 0.4445 - val_loss: 2.5745 - val_distribution_lambda_21_loss: 0.6560 - val_distribution_lambda_22_loss: 1.5244 - val_distribution_lambda_23_loss: 0.3941\n",
"Epoch 742/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1996 - distribution_lambda_21_loss: 0.4458 - distribution_lambda_22_loss: 1.3150 - distribution_lambda_23_loss: 0.4388 - val_loss: 2.5635 - val_distribution_lambda_21_loss: 0.6500 - val_distribution_lambda_22_loss: 1.5208 - val_distribution_lambda_23_loss: 0.3926\n",
"Epoch 743/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1855 - distribution_lambda_21_loss: 0.4455 - distribution_lambda_22_loss: 1.2968 - distribution_lambda_23_loss: 0.4431 - val_loss: 2.5751 - val_distribution_lambda_21_loss: 0.6398 - val_distribution_lambda_22_loss: 1.5420 - val_distribution_lambda_23_loss: 0.3932\n",
"Epoch 744/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1731 - distribution_lambda_21_loss: 0.4369 - distribution_lambda_22_loss: 1.2988 - distribution_lambda_23_loss: 0.4373 - val_loss: 2.5893 - val_distribution_lambda_21_loss: 0.6528 - val_distribution_lambda_22_loss: 1.5412 - val_distribution_lambda_23_loss: 0.3953\n",
"Epoch 745/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.1905 - distribution_lambda_21_loss: 0.4346 - distribution_lambda_22_loss: 1.3130 - distribution_lambda_23_loss: 0.4429 - val_loss: 2.5925 - val_distribution_lambda_21_loss: 0.6487 - val_distribution_lambda_22_loss: 1.5447 - val_distribution_lambda_23_loss: 0.3991\n",
"Epoch 746/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1872 - distribution_lambda_21_loss: 0.4446 - distribution_lambda_22_loss: 1.3091 - distribution_lambda_23_loss: 0.4335 - val_loss: 2.5966 - val_distribution_lambda_21_loss: 0.6410 - val_distribution_lambda_22_loss: 1.5556 - val_distribution_lambda_23_loss: 0.4000\n",
"Epoch 747/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1703 - distribution_lambda_21_loss: 0.4190 - distribution_lambda_22_loss: 1.3071 - distribution_lambda_23_loss: 0.4441 - val_loss: 2.5831 - val_distribution_lambda_21_loss: 0.6432 - val_distribution_lambda_22_loss: 1.5421 - val_distribution_lambda_23_loss: 0.3978\n",
"Epoch 748/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1714 - distribution_lambda_21_loss: 0.4538 - distribution_lambda_22_loss: 1.2849 - distribution_lambda_23_loss: 0.4327 - val_loss: 2.5809 - val_distribution_lambda_21_loss: 0.6389 - val_distribution_lambda_22_loss: 1.5462 - val_distribution_lambda_23_loss: 0.3957\n",
"Epoch 749/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1847 - distribution_lambda_21_loss: 0.4329 - distribution_lambda_22_loss: 1.2974 - distribution_lambda_23_loss: 0.4544 - val_loss: 2.6216 - val_distribution_lambda_21_loss: 0.6568 - val_distribution_lambda_22_loss: 1.5681 - val_distribution_lambda_23_loss: 0.3967\n",
"Epoch 750/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1885 - distribution_lambda_21_loss: 0.4621 - distribution_lambda_22_loss: 1.2854 - distribution_lambda_23_loss: 0.4411 - val_loss: 2.6084 - val_distribution_lambda_21_loss: 0.6483 - val_distribution_lambda_22_loss: 1.5620 - val_distribution_lambda_23_loss: 0.3981\n",
"Epoch 751/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1933 - distribution_lambda_21_loss: 0.4406 - distribution_lambda_22_loss: 1.3033 - distribution_lambda_23_loss: 0.4494 - val_loss: 2.5865 - val_distribution_lambda_21_loss: 0.6456 - val_distribution_lambda_22_loss: 1.5431 - val_distribution_lambda_23_loss: 0.3978\n",
"Epoch 752/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2097 - distribution_lambda_21_loss: 0.4459 - distribution_lambda_22_loss: 1.3213 - distribution_lambda_23_loss: 0.4424 - val_loss: 2.5667 - val_distribution_lambda_21_loss: 0.6514 - val_distribution_lambda_22_loss: 1.5179 - val_distribution_lambda_23_loss: 0.3973\n",
"Epoch 753/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1804 - distribution_lambda_21_loss: 0.4226 - distribution_lambda_22_loss: 1.3096 - distribution_lambda_23_loss: 0.4482 - val_loss: 2.5650 - val_distribution_lambda_21_loss: 0.6544 - val_distribution_lambda_22_loss: 1.5149 - val_distribution_lambda_23_loss: 0.3958\n",
"Epoch 754/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1688 - distribution_lambda_21_loss: 0.4330 - distribution_lambda_22_loss: 1.3005 - distribution_lambda_23_loss: 0.4354 - val_loss: 2.5543 - val_distribution_lambda_21_loss: 0.6328 - val_distribution_lambda_22_loss: 1.5278 - val_distribution_lambda_23_loss: 0.3937\n",
"Epoch 755/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1866 - distribution_lambda_21_loss: 0.4304 - distribution_lambda_22_loss: 1.3085 - distribution_lambda_23_loss: 0.4477 - val_loss: 2.5524 - val_distribution_lambda_21_loss: 0.6323 - val_distribution_lambda_22_loss: 1.5261 - val_distribution_lambda_23_loss: 0.3940\n",
"Epoch 756/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1815 - distribution_lambda_21_loss: 0.4372 - distribution_lambda_22_loss: 1.3002 - distribution_lambda_23_loss: 0.4441 - val_loss: 2.5736 - val_distribution_lambda_21_loss: 0.6447 - val_distribution_lambda_22_loss: 1.5343 - val_distribution_lambda_23_loss: 0.3947\n",
"Epoch 757/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.2057 - distribution_lambda_21_loss: 0.4329 - distribution_lambda_22_loss: 1.3228 - distribution_lambda_23_loss: 0.4499 - val_loss: 2.5568 - val_distribution_lambda_21_loss: 0.6407 - val_distribution_lambda_22_loss: 1.5228 - val_distribution_lambda_23_loss: 0.3933\n",
"Epoch 758/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1545 - distribution_lambda_21_loss: 0.4209 - distribution_lambda_22_loss: 1.3001 - distribution_lambda_23_loss: 0.4335 - val_loss: 2.5535 - val_distribution_lambda_21_loss: 0.6401 - val_distribution_lambda_22_loss: 1.5220 - val_distribution_lambda_23_loss: 0.3914\n",
"Epoch 759/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1829 - distribution_lambda_21_loss: 0.4338 - distribution_lambda_22_loss: 1.2980 - distribution_lambda_23_loss: 0.4511 - val_loss: 2.5732 - val_distribution_lambda_21_loss: 0.6475 - val_distribution_lambda_22_loss: 1.5349 - val_distribution_lambda_23_loss: 0.3908\n",
"Epoch 760/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1907 - distribution_lambda_21_loss: 0.4352 - distribution_lambda_22_loss: 1.3059 - distribution_lambda_23_loss: 0.4497 - val_loss: 2.5825 - val_distribution_lambda_21_loss: 0.6472 - val_distribution_lambda_22_loss: 1.5442 - val_distribution_lambda_23_loss: 0.3910\n",
"Epoch 761/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1474 - distribution_lambda_21_loss: 0.4357 - distribution_lambda_22_loss: 1.2819 - distribution_lambda_23_loss: 0.4298 - val_loss: 2.5670 - val_distribution_lambda_21_loss: 0.6342 - val_distribution_lambda_22_loss: 1.5444 - val_distribution_lambda_23_loss: 0.3884\n",
"Epoch 762/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1547 - distribution_lambda_21_loss: 0.4268 - distribution_lambda_22_loss: 1.2954 - distribution_lambda_23_loss: 0.4324 - val_loss: 2.5744 - val_distribution_lambda_21_loss: 0.6398 - val_distribution_lambda_22_loss: 1.5461 - val_distribution_lambda_23_loss: 0.3885\n",
"Epoch 763/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1601 - distribution_lambda_21_loss: 0.4241 - distribution_lambda_22_loss: 1.2953 - distribution_lambda_23_loss: 0.4408 - val_loss: 2.5800 - val_distribution_lambda_21_loss: 0.6464 - val_distribution_lambda_22_loss: 1.5427 - val_distribution_lambda_23_loss: 0.3909\n",
"Epoch 764/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1529 - distribution_lambda_21_loss: 0.4244 - distribution_lambda_22_loss: 1.2887 - distribution_lambda_23_loss: 0.4397 - val_loss: 2.5629 - val_distribution_lambda_21_loss: 0.6336 - val_distribution_lambda_22_loss: 1.5405 - val_distribution_lambda_23_loss: 0.3889\n",
"Epoch 765/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1841 - distribution_lambda_21_loss: 0.4277 - distribution_lambda_22_loss: 1.3199 - distribution_lambda_23_loss: 0.4365 - val_loss: 2.5646 - val_distribution_lambda_21_loss: 0.6393 - val_distribution_lambda_22_loss: 1.5369 - val_distribution_lambda_23_loss: 0.3884\n",
"Epoch 766/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1522 - distribution_lambda_21_loss: 0.4307 - distribution_lambda_22_loss: 1.2945 - distribution_lambda_23_loss: 0.4270 - val_loss: 2.5892 - val_distribution_lambda_21_loss: 0.6592 - val_distribution_lambda_22_loss: 1.5415 - val_distribution_lambda_23_loss: 0.3885\n",
"Epoch 767/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1779 - distribution_lambda_21_loss: 0.4282 - distribution_lambda_22_loss: 1.3129 - distribution_lambda_23_loss: 0.4368 - val_loss: 2.5690 - val_distribution_lambda_21_loss: 0.6365 - val_distribution_lambda_22_loss: 1.5442 - val_distribution_lambda_23_loss: 0.3883\n",
"Epoch 768/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1308 - distribution_lambda_21_loss: 0.4252 - distribution_lambda_22_loss: 1.2713 - distribution_lambda_23_loss: 0.4343 - val_loss: 2.5720 - val_distribution_lambda_21_loss: 0.6275 - val_distribution_lambda_22_loss: 1.5570 - val_distribution_lambda_23_loss: 0.3875\n",
"Epoch 769/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 5ms/step - loss: 2.1110 - distribution_lambda_21_loss: 0.4010 - distribution_lambda_22_loss: 1.2772 - distribution_lambda_23_loss: 0.4327 - val_loss: 2.5974 - val_distribution_lambda_21_loss: 0.6388 - val_distribution_lambda_22_loss: 1.5706 - val_distribution_lambda_23_loss: 0.3879\n",
"Epoch 770/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1780 - distribution_lambda_21_loss: 0.4083 - distribution_lambda_22_loss: 1.3247 - distribution_lambda_23_loss: 0.4449 - val_loss: 2.5862 - val_distribution_lambda_21_loss: 0.6420 - val_distribution_lambda_22_loss: 1.5568 - val_distribution_lambda_23_loss: 0.3874\n",
"Epoch 771/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1658 - distribution_lambda_21_loss: 0.4251 - distribution_lambda_22_loss: 1.3011 - distribution_lambda_23_loss: 0.4396 - val_loss: 2.5648 - val_distribution_lambda_21_loss: 0.6402 - val_distribution_lambda_22_loss: 1.5382 - val_distribution_lambda_23_loss: 0.3863\n",
"Epoch 772/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1600 - distribution_lambda_21_loss: 0.4204 - distribution_lambda_22_loss: 1.3008 - distribution_lambda_23_loss: 0.4389 - val_loss: 2.5387 - val_distribution_lambda_21_loss: 0.6336 - val_distribution_lambda_22_loss: 1.5177 - val_distribution_lambda_23_loss: 0.3874\n",
"Epoch 773/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0969 - distribution_lambda_21_loss: 0.4011 - distribution_lambda_22_loss: 1.2749 - distribution_lambda_23_loss: 0.4208 - val_loss: 2.5479 - val_distribution_lambda_21_loss: 0.6322 - val_distribution_lambda_22_loss: 1.5302 - val_distribution_lambda_23_loss: 0.3855\n",
"Epoch 774/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1725 - distribution_lambda_21_loss: 0.4186 - distribution_lambda_22_loss: 1.3096 - distribution_lambda_23_loss: 0.4442 - val_loss: 2.5678 - val_distribution_lambda_21_loss: 0.6346 - val_distribution_lambda_22_loss: 1.5465 - val_distribution_lambda_23_loss: 0.3867\n",
"Epoch 775/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1349 - distribution_lambda_21_loss: 0.4047 - distribution_lambda_22_loss: 1.3015 - distribution_lambda_23_loss: 0.4287 - val_loss: 2.5801 - val_distribution_lambda_21_loss: 0.6417 - val_distribution_lambda_22_loss: 1.5506 - val_distribution_lambda_23_loss: 0.3879\n",
"Epoch 776/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1387 - distribution_lambda_21_loss: 0.4165 - distribution_lambda_22_loss: 1.2903 - distribution_lambda_23_loss: 0.4318 - val_loss: 2.5924 - val_distribution_lambda_21_loss: 0.6500 - val_distribution_lambda_22_loss: 1.5551 - val_distribution_lambda_23_loss: 0.3872\n",
"Epoch 777/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1622 - distribution_lambda_21_loss: 0.4188 - distribution_lambda_22_loss: 1.3039 - distribution_lambda_23_loss: 0.4396 - val_loss: 2.6014 - val_distribution_lambda_21_loss: 0.6437 - val_distribution_lambda_22_loss: 1.5699 - val_distribution_lambda_23_loss: 0.3878\n",
"Epoch 778/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1607 - distribution_lambda_21_loss: 0.4234 - distribution_lambda_22_loss: 1.2952 - distribution_lambda_23_loss: 0.4421 - val_loss: 2.6068 - val_distribution_lambda_21_loss: 0.6384 - val_distribution_lambda_22_loss: 1.5793 - val_distribution_lambda_23_loss: 0.3892\n",
"Epoch 779/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 2.1083 - distribution_lambda_21_loss: 0.4104 - distribution_lambda_22_loss: 1.2679 - distribution_lambda_23_loss: 0.4300 - val_loss: 2.5895 - val_distribution_lambda_21_loss: 0.6452 - val_distribution_lambda_22_loss: 1.5571 - val_distribution_lambda_23_loss: 0.3872\n",
"Epoch 780/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1354 - distribution_lambda_21_loss: 0.4238 - distribution_lambda_22_loss: 1.2802 - distribution_lambda_23_loss: 0.4314 - val_loss: 2.5535 - val_distribution_lambda_21_loss: 0.6276 - val_distribution_lambda_22_loss: 1.5396 - val_distribution_lambda_23_loss: 0.3863\n",
"Epoch 781/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1543 - distribution_lambda_21_loss: 0.4220 - distribution_lambda_22_loss: 1.2984 - distribution_lambda_23_loss: 0.4339 - val_loss: 2.5404 - val_distribution_lambda_21_loss: 0.6185 - val_distribution_lambda_22_loss: 1.5360 - val_distribution_lambda_23_loss: 0.3859\n",
"Epoch 782/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1368 - distribution_lambda_21_loss: 0.4141 - distribution_lambda_22_loss: 1.3009 - distribution_lambda_23_loss: 0.4217 - val_loss: 2.5809 - val_distribution_lambda_21_loss: 0.6294 - val_distribution_lambda_22_loss: 1.5645 - val_distribution_lambda_23_loss: 0.3870\n",
"Epoch 783/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1355 - distribution_lambda_21_loss: 0.4053 - distribution_lambda_22_loss: 1.3037 - distribution_lambda_23_loss: 0.4265 - val_loss: 2.6128 - val_distribution_lambda_21_loss: 0.6415 - val_distribution_lambda_22_loss: 1.5856 - val_distribution_lambda_23_loss: 0.3858\n",
"Epoch 784/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0847 - distribution_lambda_21_loss: 0.3991 - distribution_lambda_22_loss: 1.2642 - distribution_lambda_23_loss: 0.4214 - val_loss: 2.6219 - val_distribution_lambda_21_loss: 0.6515 - val_distribution_lambda_22_loss: 1.5854 - val_distribution_lambda_23_loss: 0.3851\n",
"Epoch 785/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1165 - distribution_lambda_21_loss: 0.4134 - distribution_lambda_22_loss: 1.2774 - distribution_lambda_23_loss: 0.4257 - val_loss: 2.5792 - val_distribution_lambda_21_loss: 0.6339 - val_distribution_lambda_22_loss: 1.5598 - val_distribution_lambda_23_loss: 0.3854\n",
"Epoch 786/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1402 - distribution_lambda_21_loss: 0.4179 - distribution_lambda_22_loss: 1.2815 - distribution_lambda_23_loss: 0.4408 - val_loss: 2.5578 - val_distribution_lambda_21_loss: 0.6267 - val_distribution_lambda_22_loss: 1.5455 - val_distribution_lambda_23_loss: 0.3856\n",
"Epoch 787/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0892 - distribution_lambda_21_loss: 0.4066 - distribution_lambda_22_loss: 1.2570 - distribution_lambda_23_loss: 0.4256 - val_loss: 2.5936 - val_distribution_lambda_21_loss: 0.6381 - val_distribution_lambda_22_loss: 1.5704 - val_distribution_lambda_23_loss: 0.3851\n",
"Epoch 788/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1109 - distribution_lambda_21_loss: 0.4036 - distribution_lambda_22_loss: 1.2743 - distribution_lambda_23_loss: 0.4329 - val_loss: 2.6195 - val_distribution_lambda_21_loss: 0.6413 - val_distribution_lambda_22_loss: 1.5915 - val_distribution_lambda_23_loss: 0.3867\n",
"Epoch 789/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1220 - distribution_lambda_21_loss: 0.4069 - distribution_lambda_22_loss: 1.2801 - distribution_lambda_23_loss: 0.4349 - val_loss: 2.6166 - val_distribution_lambda_21_loss: 0.6398 - val_distribution_lambda_22_loss: 1.5880 - val_distribution_lambda_23_loss: 0.3887\n",
"Epoch 790/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1158 - distribution_lambda_21_loss: 0.4074 - distribution_lambda_22_loss: 1.2850 - distribution_lambda_23_loss: 0.4235 - val_loss: 2.6016 - val_distribution_lambda_21_loss: 0.6319 - val_distribution_lambda_22_loss: 1.5801 - val_distribution_lambda_23_loss: 0.3896\n",
"Epoch 791/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1296 - distribution_lambda_21_loss: 0.4271 - distribution_lambda_22_loss: 1.2698 - distribution_lambda_23_loss: 0.4326 - val_loss: 2.6042 - val_distribution_lambda_21_loss: 0.6338 - val_distribution_lambda_22_loss: 1.5841 - val_distribution_lambda_23_loss: 0.3863\n",
"Epoch 792/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 2.1290 - distribution_lambda_21_loss: 0.4080 - distribution_lambda_22_loss: 1.2811 - distribution_lambda_23_loss: 0.4400 - val_loss: 2.5985 - val_distribution_lambda_21_loss: 0.6370 - val_distribution_lambda_22_loss: 1.5771 - val_distribution_lambda_23_loss: 0.3844\n",
"Epoch 793/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 7ms/step - loss: 2.0920 - distribution_lambda_21_loss: 0.4000 - distribution_lambda_22_loss: 1.2602 - distribution_lambda_23_loss: 0.4318 - val_loss: 2.5985 - val_distribution_lambda_21_loss: 0.6471 - val_distribution_lambda_22_loss: 1.5687 - val_distribution_lambda_23_loss: 0.3828\n",
"Epoch 794/2500\n",
"9/9 [==============================] - 0s 7ms/step - loss: 2.1297 - distribution_lambda_21_loss: 0.4058 - distribution_lambda_22_loss: 1.2942 - distribution_lambda_23_loss: 0.4296 - val_loss: 2.5964 - val_distribution_lambda_21_loss: 0.6469 - val_distribution_lambda_22_loss: 1.5696 - val_distribution_lambda_23_loss: 0.3798\n",
"Epoch 795/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1205 - distribution_lambda_21_loss: 0.4019 - distribution_lambda_22_loss: 1.2852 - distribution_lambda_23_loss: 0.4334 - val_loss: 2.5926 - val_distribution_lambda_21_loss: 0.6351 - val_distribution_lambda_22_loss: 1.5789 - val_distribution_lambda_23_loss: 0.3787\n",
"Epoch 796/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1172 - distribution_lambda_21_loss: 0.3956 - distribution_lambda_22_loss: 1.2797 - distribution_lambda_23_loss: 0.4419 - val_loss: 2.6057 - val_distribution_lambda_21_loss: 0.6332 - val_distribution_lambda_22_loss: 1.5917 - val_distribution_lambda_23_loss: 0.3809\n",
"Epoch 797/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1040 - distribution_lambda_21_loss: 0.3985 - distribution_lambda_22_loss: 1.2719 - distribution_lambda_23_loss: 0.4337 - val_loss: 2.6014 - val_distribution_lambda_21_loss: 0.6452 - val_distribution_lambda_22_loss: 1.5761 - val_distribution_lambda_23_loss: 0.3801\n",
"Epoch 798/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0939 - distribution_lambda_21_loss: 0.4036 - distribution_lambda_22_loss: 1.2665 - distribution_lambda_23_loss: 0.4237 - val_loss: 2.6163 - val_distribution_lambda_21_loss: 0.6465 - val_distribution_lambda_22_loss: 1.5900 - val_distribution_lambda_23_loss: 0.3797\n",
"Epoch 799/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1016 - distribution_lambda_21_loss: 0.4086 - distribution_lambda_22_loss: 1.2697 - distribution_lambda_23_loss: 0.4232 - val_loss: 2.6016 - val_distribution_lambda_21_loss: 0.6407 - val_distribution_lambda_22_loss: 1.5816 - val_distribution_lambda_23_loss: 0.3793\n",
"Epoch 800/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0821 - distribution_lambda_21_loss: 0.4079 - distribution_lambda_22_loss: 1.2491 - distribution_lambda_23_loss: 0.4251 - val_loss: 2.6166 - val_distribution_lambda_21_loss: 0.6443 - val_distribution_lambda_22_loss: 1.5929 - val_distribution_lambda_23_loss: 0.3794\n",
"Epoch 801/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0958 - distribution_lambda_21_loss: 0.3871 - distribution_lambda_22_loss: 1.2798 - distribution_lambda_23_loss: 0.4290 - val_loss: 2.6031 - val_distribution_lambda_21_loss: 0.6381 - val_distribution_lambda_22_loss: 1.5850 - val_distribution_lambda_23_loss: 0.3800\n",
"Epoch 802/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.0601 - distribution_lambda_21_loss: 0.3922 - distribution_lambda_22_loss: 1.2558 - distribution_lambda_23_loss: 0.4122 - val_loss: 2.5856 - val_distribution_lambda_21_loss: 0.6260 - val_distribution_lambda_22_loss: 1.5796 - val_distribution_lambda_23_loss: 0.3800\n",
"Epoch 803/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1125 - distribution_lambda_21_loss: 0.4097 - distribution_lambda_22_loss: 1.2716 - distribution_lambda_23_loss: 0.4311 - val_loss: 2.5869 - val_distribution_lambda_21_loss: 0.6293 - val_distribution_lambda_22_loss: 1.5783 - val_distribution_lambda_23_loss: 0.3792\n",
"Epoch 804/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1028 - distribution_lambda_21_loss: 0.4064 - distribution_lambda_22_loss: 1.2683 - distribution_lambda_23_loss: 0.4281 - val_loss: 2.5745 - val_distribution_lambda_21_loss: 0.6201 - val_distribution_lambda_22_loss: 1.5749 - val_distribution_lambda_23_loss: 0.3795\n",
"Epoch 805/2500\n",
"9/9 [==============================] - 0s 6ms/step - loss: 2.1012 - distribution_lambda_21_loss: 0.3907 - distribution_lambda_22_loss: 1.2847 - distribution_lambda_23_loss: 0.4257 - val_loss: 2.5832 - val_distribution_lambda_21_loss: 0.6258 - val_distribution_lambda_22_loss: 1.5785 - val_distribution_lambda_23_loss: 0.3789\n",
"Epoch 806/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1202 - distribution_lambda_21_loss: 0.3934 - distribution_lambda_22_loss: 1.2893 - distribution_lambda_23_loss: 0.4375 - val_loss: 2.5492 - val_distribution_lambda_21_loss: 0.6279 - val_distribution_lambda_22_loss: 1.5441 - val_distribution_lambda_23_loss: 0.3772\n",
"Epoch 807/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0868 - distribution_lambda_21_loss: 0.3804 - distribution_lambda_22_loss: 1.2706 - distribution_lambda_23_loss: 0.4359 - val_loss: 2.5646 - val_distribution_lambda_21_loss: 0.6407 - val_distribution_lambda_22_loss: 1.5464 - val_distribution_lambda_23_loss: 0.3775\n",
"Epoch 808/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1279 - distribution_lambda_21_loss: 0.3954 - distribution_lambda_22_loss: 1.2927 - distribution_lambda_23_loss: 0.4398 - val_loss: 2.5454 - val_distribution_lambda_21_loss: 0.6195 - val_distribution_lambda_22_loss: 1.5467 - val_distribution_lambda_23_loss: 0.3792\n",
"Epoch 809/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0938 - distribution_lambda_21_loss: 0.3961 - distribution_lambda_22_loss: 1.2694 - distribution_lambda_23_loss: 0.4283 - val_loss: 2.5654 - val_distribution_lambda_21_loss: 0.6194 - val_distribution_lambda_22_loss: 1.5646 - val_distribution_lambda_23_loss: 0.3815\n",
"Epoch 810/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1311 - distribution_lambda_21_loss: 0.4111 - distribution_lambda_22_loss: 1.2903 - distribution_lambda_23_loss: 0.4297 - val_loss: 2.6188 - val_distribution_lambda_21_loss: 0.6488 - val_distribution_lambda_22_loss: 1.5877 - val_distribution_lambda_23_loss: 0.3823\n",
"Epoch 811/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.1009 - distribution_lambda_21_loss: 0.4019 - distribution_lambda_22_loss: 1.2632 - distribution_lambda_23_loss: 0.4358 - val_loss: 2.6334 - val_distribution_lambda_21_loss: 0.6452 - val_distribution_lambda_22_loss: 1.6066 - val_distribution_lambda_23_loss: 0.3816\n",
"Epoch 812/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0880 - distribution_lambda_21_loss: 0.3785 - distribution_lambda_22_loss: 1.2761 - distribution_lambda_23_loss: 0.4334 - val_loss: 2.5874 - val_distribution_lambda_21_loss: 0.6287 - val_distribution_lambda_22_loss: 1.5783 - val_distribution_lambda_23_loss: 0.3804\n",
"Epoch 813/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0805 - distribution_lambda_21_loss: 0.3868 - distribution_lambda_22_loss: 1.2677 - distribution_lambda_23_loss: 0.4259 - val_loss: 2.5655 - val_distribution_lambda_21_loss: 0.6276 - val_distribution_lambda_22_loss: 1.5591 - val_distribution_lambda_23_loss: 0.3788\n",
"Epoch 814/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0828 - distribution_lambda_21_loss: 0.3872 - distribution_lambda_22_loss: 1.2669 - distribution_lambda_23_loss: 0.4287 - val_loss: 2.5787 - val_distribution_lambda_21_loss: 0.6367 - val_distribution_lambda_22_loss: 1.5628 - val_distribution_lambda_23_loss: 0.3793\n",
"Epoch 815/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0688 - distribution_lambda_21_loss: 0.3822 - distribution_lambda_22_loss: 1.2501 - distribution_lambda_23_loss: 0.4366 - val_loss: 2.6174 - val_distribution_lambda_21_loss: 0.6476 - val_distribution_lambda_22_loss: 1.5888 - val_distribution_lambda_23_loss: 0.3810\n",
"Epoch 816/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0728 - distribution_lambda_21_loss: 0.3944 - distribution_lambda_22_loss: 1.2538 - distribution_lambda_23_loss: 0.4246 - val_loss: 2.6198 - val_distribution_lambda_21_loss: 0.6442 - val_distribution_lambda_22_loss: 1.5957 - val_distribution_lambda_23_loss: 0.3798\n",
"Epoch 817/2500\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"9/9 [==============================] - 0s 6ms/step - loss: 2.0625 - distribution_lambda_21_loss: 0.3847 - distribution_lambda_22_loss: 1.2416 - distribution_lambda_23_loss: 0.4363 - val_loss: 2.6079 - val_distribution_lambda_21_loss: 0.6247 - val_distribution_lambda_22_loss: 1.6053 - val_distribution_lambda_23_loss: 0.3779\n",
"Epoch 818/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0822 - distribution_lambda_21_loss: 0.3917 - distribution_lambda_22_loss: 1.2572 - distribution_lambda_23_loss: 0.4333 - val_loss: 2.6130 - val_distribution_lambda_21_loss: 0.6191 - val_distribution_lambda_22_loss: 1.6167 - val_distribution_lambda_23_loss: 0.3771\n",
"Epoch 819/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0498 - distribution_lambda_21_loss: 0.3793 - distribution_lambda_22_loss: 1.2450 - distribution_lambda_23_loss: 0.4255 - val_loss: 2.6328 - val_distribution_lambda_21_loss: 0.6270 - val_distribution_lambda_22_loss: 1.6274 - val_distribution_lambda_23_loss: 0.3783\n",
"Epoch 820/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0865 - distribution_lambda_21_loss: 0.3950 - distribution_lambda_22_loss: 1.2662 - distribution_lambda_23_loss: 0.4253 - val_loss: 2.6273 - val_distribution_lambda_21_loss: 0.6253 - val_distribution_lambda_22_loss: 1.6256 - val_distribution_lambda_23_loss: 0.3764\n",
"Epoch 821/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0850 - distribution_lambda_21_loss: 0.3877 - distribution_lambda_22_loss: 1.2640 - distribution_lambda_23_loss: 0.4333 - val_loss: 2.6110 - val_distribution_lambda_21_loss: 0.6186 - val_distribution_lambda_22_loss: 1.6148 - val_distribution_lambda_23_loss: 0.3776\n",
"Epoch 822/2500\n",
"9/9 [==============================] - 0s 5ms/step - loss: 2.0699 - distribution_lambda_21_loss: 0.3884 - distribution_lambda_22_loss: 1.2563 - distribution_lambda_23_loss: 0.4253 - val_loss: 2.6213 - val_distribution_lambda_21_loss: 0.6317 - val_distribution_lambda_22_loss: 1.6136 - val_distribution_lambda_23_loss: 0.3760\n"
]
}
],
"source": [
"load_model_gk = True# load scaler and model weights for goalkeeper player predictor\n",
"refit_model_gk = False\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": 34,
"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": 49,
"id": "c41cf448",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.29228994199557035\n",
"0.5457850368866328\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.188949616879163\n",
"0.3638259422034872\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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": 51,
"id": "cecf5392",
"metadata": {},
"outputs": [],
"source": [
"save_model_of = True\n",
"save_model_gk = True\n",
"\n",
"if(save_model_of):\n",
" pickle.dump(scaler, open('saves/scaler.pkl', 'wb'))\n",
" modelb.save_weights('saves/modelb')\n",
" \n",
"if(save_model_gk):\n",
" pickle.dump(scaler_gk, open('saves/scaler_gk.pkl', 'wb'))\n",
" modelb_gk.save_weights('saves/modelb_gk')\n",
" "
]
},
{
"cell_type": "markdown",
"id": "32635a0e",
"metadata": {},
"source": [
"Generalized prediction function for a player (playing for team against opp_team, at home or not)\n",
"\n",
"Estimate prediction mean and sigma (using a custom definitions).\n",
"\n",
"Generate a plot.\n"
]
},
{
"cell_type": "code",
"execution_count": 23,
"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": 24,
"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": 25,
"id": "62b9f588",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>team1</th>\n",
" <th>team2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Fiorentina</td>\n",
" <td>Cremonese</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Verona</td>\n",
" <td>Napoli</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Juventus</td>\n",
" <td>Sassuolo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Lazio</td>\n",
" <td>Bologna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Lecce</td>\n",
" <td>Inter</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>375</th>\n",
" <td>38</td>\n",
" <td>Lecce</td>\n",
" <td>Bologna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>376</th>\n",
" <td>38</td>\n",
" <td>Sassuolo</td>\n",
" <td>Fiorentina</td>\n",
" </tr>\n",
" <tr>\n",
" <th>377</th>\n",
" <td>38</td>\n",
" <td>Milan</td>\n",
" <td>Verona</td>\n",
" </tr>\n",
" <tr>\n",
" <th>378</th>\n",
" <td>38</td>\n",
" <td>Torino</td>\n",
" <td>Inter</td>\n",
" </tr>\n",
" <tr>\n",
" <th>379</th>\n",
" <td>38</td>\n",
" <td>Udinese</td>\n",
" <td>Juventus</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>380 rows × 3 columns</p>\n",
"</div>"
],
"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": 25,
"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": 26,
"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": 27,
"id": "f79792b6",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>starter</th>\n",
" <th>percentage</th>\n",
" </tr>\n",
" <tr>\n",
" <th>player</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Falcone</th>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Gendrey</th>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Baschirotto</th>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Umtiti</th>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Gallo</th>\n",
" <td>0.65</td>\n",
" <td>65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Barrenechea</th>\n",
" <td>0.00</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Pogba</th>\n",
" <td>0.00</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Chiesa</th>\n",
" <td>0.40</td>\n",
" <td>55</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Soule'</th>\n",
" <td>0.00</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Milik</th>\n",
" <td>0.40</td>\n",
" <td>60</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>474 rows × 2 columns</p>\n",
"</div>"
],
"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": 27,
"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": 28,
"id": "5e63c2b7",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Meret: MV 6.24 ± 0.83; FV 5.13 + 1.01 (14.5% cs)\n",
"Provedel: MV 6.24 ± 0.83; FV 6.62 + 0.71 (96.3% cs)\n",
"Vicario: MV 6.24 ± 0.83; FV 5.09 + 0.90 (17.2% cs)\n",
"Szczesny: MV 6.24 ± 0.83; FV 6.39 + 0.69 (92.6% cs)\n",
"Falcone: MV 6.24 ± 0.83; FV 4.83 + 0.90 (1.1% cs)\n",
"Silvestri: MV 6.24 ± 0.83; FV 4.39 + 1.17 (0.9% cs)\n",
"Rui Patricio: MV 6.24 ± 0.83; FV 4.75 + 0.91 (3.2% cs)\n",
"Onana: MV 6.24 ± 0.83; FV 4.67 + 0.91 (3.5% cs)\n",
"Sepe: MV 6.24 ± 0.83; FV 5.77 + 0.83 (58.3% cs)\n",
"Milinkovic-Savic V.: MV 6.24 ± 0.83; FV 4.84 + 0.87 (6.9% cs)\n",
"Musso: MV 6.25 ± 0.82; FV 5.42 + 0.84 (25.0% cs)\n",
"Maignan: MV 6.24 ± 0.83; FV 5.36 + 0.82 (14.1% cs)\n",
"Carnesecchi: MV 6.24 ± 0.83; FV 4.39 + 1.15 (0.1% cs)\n",
"Di Gregorio: MV 6.24 ± 0.83; FV 4.55 + 1.07 (1.9% cs)\n",
"Audero: MV 6.24 ± 0.83; FV 5.17 + 0.83 (18.3% cs)\n",
"Montipo': MV 6.24 ± 0.83; FV 4.62 + 1.04 (0.1% cs)\n",
"Skorupski: MV 6.24 ± 0.83; FV 4.27 + 1.07 (1.9% cs)\n",
"Consigli: MV 6.24 ± 0.83; FV 4.27 + 1.30 (0.1% cs)\n",
"Dragowski: MV 6.24 ± 0.83; FV 4.49 + 1.03 (0.4% cs)\n",
"Terracciano: MV 6.24 ± 0.83; FV 5.35 + 0.85 (30.5% cs)\n",
"Tatarusanu: MV 6.24 ± 0.83; FV 5.44 + 0.97 (19.7% cs)\n",
"Handanovic: MV 6.24 ± 0.83; FV 4.94 + 0.89 (4.0% cs)\n",
"Sportiello: MV 6.18 ± 0.86; FV 5.72 + 1.09 (40.4% cs)\n",
"Perin: MV 6.24 ± 0.83; FV 5.31 + 0.79 (24.2% cs)\n",
"Zoet: MV 6.24 ± 0.83; FV 5.52 + 0.75 (18.9% cs)\n",
"Ochoa: MV 6.24 ± 0.83; FV 5.22 + 0.82 (15.7% cs)\n",
"Pegolo: MV 6.24 ± 0.83; FV 4.16 + 1.34 (0.1% cs)\n",
"Gollini: MV 6.25 ± 0.83; FV 4.93 + 1.34 (43.4% cs)\n",
"Mirante no data\n",
"Sarr M. no data\n",
"Lamanna no data\n",
"Ujkani no data\n",
"Berisha: MV 6.24 ± 0.83; FV 5.94 + 0.88 (65.1% cs)\n",
"Marchetti: MV 6.24 ± 0.83; FV 4.18 + 1.24 (0.1% cs)\n",
"Perilli: MV 6.24 ± 0.83; FV 4.29 + 1.29 (1.1% cs)\n",
"Padelli: MV 6.23 ± 0.83; FV 4.02 + 1.38 (0.3% cs)\n",
"Perisan: MV 6.26 ± 0.81; FV 5.53 + 0.94 (32.5% cs)\n",
"Bardi: MV 6.24 ± 0.83; FV 6.04 + 0.78 (78.7% cs)\n",
"Cordaz no data\n",
"Pinsoglio: MV 6.24 ± 0.83; FV 6.19 + 0.70 (86.7% cs)\n",
"Fiorillo: MV 6.24 ± 0.83; FV 4.96 + 0.82 (0.3% cs)\n",
"Cragno: MV 6.24 ± 0.83; FV 4.65 + 1.12 (0.1% cs)\n",
"Sirigu: MV 6.24 ± 0.83; FV 4.35 + 1.30 (0.0% cs)\n",
"Cerofolini no data\n",
"Rossi F.: MV 6.24 ± 0.83; FV 4.53 + 1.05 (0.8% cs)\n",
"Ravaglia F.: MV 6.24 ± 0.83; FV 4.70 + 0.92 (1.4% cs)\n",
"Brancolini no data\n",
"Bleve no data\n",
"Berardi A.: MV 6.23 ± 0.83; FV 3.86 + 1.53 (0.1% cs)\n",
"Russo A. no data\n",
"Gemello: MV 6.24 ± 0.83; FV 6.15 + 0.84 (78.0% cs)\n",
"Ravaglia: MV 6.24 ± 0.83; FV 5.89 + 0.71 (59.6% cs)\n",
"Boer no data\n",
"Adamonis no data\n",
"Marfella: MV 6.24 ± 0.83; FV 5.17 + 0.97 (11.7% cs)\n",
"Zovko: MV 6.24 ± 0.83; FV 4.26 + 1.19 (0.2% cs)\n",
"Piana no data\n",
"Bagnolini no data\n",
"Luis Maximiano: MV 6.24 ± 0.83; FV 6.75 + 0.74 (97.3% 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 6.24 ± 0.83; FV 5.24 + 0.78 (5.8% cs)\n",
"Dimarco: MV 6.24 ± 1.00; FV 6.79 + 1.87\n",
"Smalling: MV 6.25 ± 1.01; FV 6.66 + 1.74\n",
"Doig: MV 5.99 ± 1.03; FV 6.26 + 1.61\n",
"Carlos Augusto: MV 6.08 ± 1.06; FV 6.49 + 1.85\n",
"Kim: MV 6.23 ± 1.02; FV 6.49 + 1.50\n",
"Posch: MV 6.16 ± 1.11; FV 6.62 + 2.00\n",
"Di Lorenzo: MV 6.21 ± 0.98; FV 6.51 + 1.50\n",
"Danilo: MV 6.30 ± 0.99; FV 6.73 + 1.74\n",
"Hernandez T.: MV 6.32 ± 1.13; FV 6.96 + 2.22\n",
"Udogie: MV 5.90 ± 1.07; FV 6.07 + 1.53\n",
"Parisi: MV 6.17 ± 0.98; FV 6.54 + 1.59\n",
"Mario Rui: MV 6.14 ± 1.00; FV 6.33 + 1.32\n",
"Romagnoli: MV 6.20 ± 0.87; FV 6.37 + 1.23\n",
"Bastoni S.: MV 5.98 ± 0.94; FV 6.16 + 1.37\n",
"Mazzocchi: MV 6.13 ± 0.86; FV 6.52 + 1.49\n",
"Valeri: MV 6.08 ± 0.84; FV 6.36 + 1.28\n",
"Tomori: MV 6.17 ± 0.80; FV 6.37 + 1.17\n",
"Scalvini: MV 6.27 ± 1.07; FV 6.79 + 1.96\n",
"Toloi: MV 6.25 ± 1.02; FV 6.72 + 1.81\n",
"Demiral: MV 6.13 ± 0.80; FV 6.37 + 1.21\n",
"Maehle: MV 6.19 ± 0.99; FV 6.69 + 1.81\n",
"Dumfries: MV 6.00 ± 1.03; FV 6.30 + 1.64\n",
"Baschirotto: MV 6.06 ± 0.99; FV 6.32 + 1.46\n",
"Bijol: MV 5.76 ± 1.19; FV 5.85 + 1.55\n",
"Schuurs: MV 6.20 ± 0.82; FV 6.30 + 1.09\n",
"Juan Jesus: MV 6.15 ± 0.74; FV 6.33 + 1.06\n",
"Depaoli: MV 5.92 ± 0.87; FV 6.05 + 1.20\n",
"Mancini: MV 6.14 ± 0.86; FV 6.37 + 1.25\n",
"Ibanez: MV 5.79 ± 1.19; FV 5.92 + 1.57\n",
"Rodrigo Becao: MV 5.80 ± 1.09; FV 5.80 + 1.31\n",
"Ebuehi: MV 6.08 ± 0.82; FV 6.35 + 1.20\n",
"Gosens: MV 6.04 ± 0.75; FV 6.31 + 1.12\n",
"Darmian: MV 6.10 ± 0.76; FV 6.37 + 1.17\n",
"Reca: MV 5.88 ± 1.02; FV 6.01 + 1.44\n",
"Bremer: MV 6.20 ± 1.02; FV 6.60 + 1.66\n",
"Sernicola: MV 5.87 ± 1.07; FV 6.03 + 1.55\n",
"Rrahmani: MV 6.20 ± 1.02; FV 6.47 + 1.50\n",
"Vojvoda: MV 6.02 ± 0.79; FV 6.09 + 0.86\n",
"Holm: MV 5.89 ± 0.85; FV 6.01 + 1.17\n",
"Bastoni: MV 6.14 ± 0.84; FV 6.27 + 1.07\n",
"Milenkovic: MV 6.04 ± 0.93; FV 6.22 + 1.32\n",
"Kalulu: MV 6.06 ± 0.92; FV 6.24 + 1.17\n",
"Martinez Quarta: MV 6.06 ± 0.94; FV 6.24 + 1.29\n",
"Casale: MV 6.09 ± 0.82; FV 6.18 + 0.98\n",
"Perez N.: MV 5.79 ± 1.17; FV 5.90 + 1.55\n",
"Olivera: MV 6.10 ± 0.71; FV 6.30 + 1.00\n",
"Izzo: MV 6.04 ± 0.92; FV 6.18 + 1.19\n",
"Luperto: MV 5.90 ± 0.96; FV 5.88 + 0.92\n",
"Skriniar: MV 5.99 ± 0.79; FV 6.00 + 0.79\n",
"Rodriguez R.: MV 6.12 ± 0.69; FV 6.09 + 0.72\n",
"Marusic: MV 6.08 ± 0.79; FV 6.00 + 0.76\n",
"Lazzari: MV 6.06 ± 0.75; FV 6.02 + 0.73\n",
"Kyriakopoulos: MV 5.99 ± 0.91; FV 6.04 + 1.01\n",
"Ampadu: MV 5.77 ± 0.99; FV 5.73 + 1.14\n",
"Ismajli: MV 5.95 ± 0.85; FV 5.88 + 0.78\n",
"Llorente D.: MV 5.90 ± 1.07; FV 6.08 + 1.55\n",
"Cambiaso: MV 5.97 ± 0.77; FV 5.96 + 0.74\n",
"Hysaj: MV 6.04 ± 0.65; FV 5.95 + 0.55\n",
"Biraghi: MV 6.16 ± 0.87; FV 6.42 + 1.28\n",
"Medel: MV 5.97 ± 0.72; FV 5.91 + 0.64\n",
"Bonucci: MV 6.24 ± 1.04; FV 6.68 + 1.79\n",
"Calabria: MV 6.15 ± 0.96; FV 6.58 + 1.65\n",
"Acerbi: MV 6.06 ± 0.72; FV 6.05 + 0.71\n",
"Spinazzola: MV 6.16 ± 0.87; FV 6.53 + 1.50\n",
"Lykogiannis: MV 6.03 ± 0.81; FV 6.14 + 0.97\n",
"Pellegrini Lu.: MV 6.04 ± 0.72; FV 6.01 + 0.69\n",
"Djidji: MV 6.00 ± 0.79; FV 6.08 + 0.89\n",
"Lazaro: MV 6.16 ± 0.86; FV 6.34 + 1.16\n",
"Augello: MV 6.01 ± 0.91; FV 6.33 + 1.49\n",
"Gallo: MV 5.77 ± 0.79; FV 5.74 + 0.75\n",
"Singo: MV 6.12 ± 0.85; FV 6.39 + 1.25\n",
"Mari': MV 5.86 ± 1.07; FV 5.91 + 1.22\n",
"Caldirola: MV 5.89 ± 1.02; FV 5.99 + 1.30\n",
"Dodo': MV 5.93 ± 0.95; FV 5.98 + 1.13\n",
"De Vrij: MV 6.01 ± 0.82; FV 6.07 + 0.88\n",
"Patric: MV 6.07 ± 0.80; FV 5.96 + 0.75\n",
"Faraoni: MV 5.94 ± 0.88; FV 6.08 + 1.21\n",
"Ceccherini: MV 5.85 ± 1.07; FV 5.95 + 1.46\n",
"Hateboer: MV 6.06 ± 0.89; FV 6.34 + 1.41\n",
"Rogerio: MV 5.66 ± 0.84; FV 5.63 + 0.86\n",
"Umtiti: MV 5.80 ± 0.97; FV 5.75 + 1.00\n",
"Aina: MV 6.15 ± 0.87; FV 6.46 + 1.36\n",
"Birindelli: MV 5.80 ± 0.71; FV 5.78 + 0.74\n",
"Lucumi': MV 5.94 ± 0.81; FV 5.90 + 0.79\n",
"Ehizibue: MV 5.73 ± 1.01; FV 5.83 + 1.32\n",
"Bianchetti: MV 5.69 ± 1.03; FV 5.72 + 1.28\n",
"Ferrari G.: MV 5.65 ± 1.13; FV 5.66 + 1.29\n",
"Fazio: MV 5.65 ± 1.26; FV 5.69 + 1.40\n",
"Gravillon: MV 6.08 ± 0.79; FV 6.02 + 0.78\n",
"Buongiorno: MV 6.11 ± 0.75; FV 6.06 + 0.76\n",
"Gunter: MV 5.80 ± 0.95; FV 5.72 + 0.88\n",
"Troost-Ekong: MV 5.79 ± 0.93; FV 5.77 + 0.94\n",
"Soumaoro: MV 5.91 ± 0.92; FV 5.88 + 0.88\n",
"Ceccaroni: MV 5.81 ± 1.05; FV 5.83 + 1.21\n",
"Pongracic: MV 5.89 ± 0.79; FV 5.83 + 0.74\n",
"Soppy: MV 6.03 ± 0.73; FV 6.10 + 0.81\n",
"Gendrey: MV 5.84 ± 0.65; FV 5.83 + 0.55\n",
"Hien: MV 5.81 ± 0.94; FV 5.76 + 1.06\n",
"Ferrari A.: MV 5.69 ± 1.13; FV 5.70 + 1.35\n",
"Masina: MV 5.79 ± 0.92; FV 6.10 + 1.37\n",
"Zappacosta: MV 6.16 ± 0.81; FV 6.53 + 1.42\n",
"Gyomber: MV 5.90 ± 0.85; FV 5.88 + 0.81\n",
"Alex Sandro: MV 5.90 ± 0.87; FV 5.81 + 0.78\n",
"Pezzella Giu.: MV 5.85 ± 0.68; FV 5.84 + 0.57\n",
"Bereszynski: MV 5.82 ± 0.72; FV 5.79 + 0.74\n",
"Venuti: MV 5.90 ± 0.79; FV 5.92 + 0.85\n",
"Palomino: MV 6.17 ± 0.85; FV 6.40 + 1.26\n",
"Nuytinck: MV 5.90 ± 0.91; FV 5.88 + 0.89\n",
"Marlon: MV 5.74 ± 0.79; FV 5.67 + 0.77\n",
"Magnani: MV 5.77 ± 0.96; FV 5.71 + 1.04\n",
"Colley: MV 5.87 ± 1.02; FV 5.91 + 1.11\n",
"Nikolaou: MV 5.66 ± 0.88; FV 5.58 + 0.96\n",
"Terzic: MV 6.04 ± 0.61; FV 6.00 + 0.53\n",
"Igor: MV 5.87 ± 0.93; FV 5.84 + 1.00\n",
"Toljan: MV 5.60 ± 0.90; FV 5.55 + 0.90\n",
"Zortea: MV 5.74 ± 0.83; FV 5.77 + 0.96\n",
"Dawidowicz: MV 5.76 ± 1.00; FV 5.76 + 1.24\n",
"Celik: MV 5.77 ± 0.75; FV 5.72 + 0.74\n",
"Bellanova: MV 5.99 ± 0.87; FV 6.17 + 1.15\n",
"Erlic: MV 5.68 ± 1.06; FV 5.60 + 1.07\n",
"Ballo-Toure': MV 6.17 ± 0.74; FV 6.56 + 1.39\n",
"Dest: MV 5.93 ± 0.77; FV 5.95 + 0.74\n",
"Stojanovic: MV 5.75 ± 0.78; FV 5.70 + 0.76\n",
"Amian: MV 5.68 ± 0.82; FV 5.65 + 0.91\n",
"Bradaric: MV 5.74 ± 0.93; FV 5.73 + 1.05\n",
"Daniliuc: MV 5.75 ± 1.02; FV 5.74 + 1.15\n",
"Zima: MV 6.03 ± 0.75; FV 5.99 + 0.73\n",
"De Winter: MV 5.77 ± 0.82; FV 5.71 + 0.74\n",
"Quagliata: MV 5.88 ± 0.69; FV 5.90 + 0.70\n",
"Ebosse: MV 5.62 ± 0.82; FV 5.52 + 0.83\n",
"Aiwu: MV 5.83 ± 1.09; FV 5.93 + 1.48\n",
"Lochoshvili: MV 5.79 ± 0.99; FV 5.84 + 1.30\n",
"Bronn: MV 5.69 ± 0.80; FV 5.65 + 0.74\n",
"Thiaw: MV 6.03 ± 0.89; FV 6.05 + 0.91\n",
"Zeefuik: MV 5.86 ± 0.94; FV 5.91 + 1.23\n",
"Romagnoli S.: MV 5.84 ± 1.10; FV 5.98 + 1.54\n",
"Ghiglione: MV 5.81 ± 0.93; FV 5.92 + 1.28\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Rugani: MV 6.07 ± 0.59; FV 5.97 + 0.48\n",
"De Sciglio: MV 5.91 ± 0.62; FV 5.91 + 0.48\n",
"Djimsiti: MV 6.08 ± 0.72; FV 6.07 + 0.75\n",
"Caldara: MV 5.63 ± 1.02; FV 5.56 + 1.09\n",
"Karsdorp: MV 5.88 ± 0.80; FV 5.86 + 0.79\n",
"Marchizza: MV 5.79 ± 0.70; FV 5.79 + 0.62\n",
"Kjaer: MV 6.06 ± 0.70; FV 5.98 + 0.63\n",
"Okoli: MV 5.93 ± 0.79; FV 5.89 + 0.73\n",
"Amione: MV 5.85 ± 0.96; FV 5.91 + 1.25\n",
"Ruggeri: MV 6.07 ± 0.68; FV 6.07 + 0.70\n",
"Zanoli: MV 6.08 ± 0.85; FV 6.34 + 1.26\n",
"Wisniewski: MV 5.68 ± 0.77; FV 5.59 + 0.78\n",
"Radovanovic: MV 5.63 ± 0.80; FV 5.56 + 0.77\n",
"Dermaku: MV 5.95 ± 0.86; FV 5.97 + 0.94\n",
"D'ambrosio: MV 6.09 ± 0.75; FV 6.14 + 0.85\n",
"De Silvestri: MV 5.98 ± 1.01; FV 6.16 + 1.42\n",
"Chiriches: MV 5.68 ± 1.14; FV 5.64 + 1.22\n",
"Murru: MV 5.70 ± 0.76; FV 5.63 + 0.71\n",
"Bonifazi: MV 5.78 ± 0.83; FV 5.69 + 0.80\n",
"Donati: MV 5.78 ± 1.22; FV 5.99 + 1.71\n",
"Walukiewicz: MV 6.11 ± 0.70; FV 6.08 + 0.71\n",
"Ranieri L.: MV 5.92 ± 0.82; FV 5.97 + 1.04\n",
"Gabbia: MV 5.84 ± 0.77; FV 5.80 + 0.70\n",
"Kumbulla: MV 5.74 ± 1.09; FV 5.67 + 1.12\n",
"Adopo: MV 6.10 ± 0.66; FV 6.08 + 0.67\n",
"Pirola: MV 5.89 ± 1.10; FV 6.15 + 1.72\n",
"Lovato: MV 5.65 ± 1.02; FV 5.59 + 0.96\n",
"Tuia: MV 5.99 ± 0.60; FV 5.95 + 0.49\n",
"Ferrer: MV 5.80 ± 0.95; FV 5.80 + 1.16\n",
"Antov: MV 5.68 ± 1.06; FV 5.54 + 1.00\n",
"Vasquez: MV 5.74 ± 0.96; FV 5.69 + 1.09\n",
"Ruan: MV 5.69 ± 1.07; FV 5.55 + 1.02\n",
"Ostigard: MV 6.08 ± 0.75; FV 6.10 + 0.82\n",
"Coppola D.: MV 5.74 ± 0.78; FV 5.64 + 0.82\n",
"Cacace: MV 5.82 ± 0.64; FV 5.82 + 0.51\n",
"Gatti: MV 6.10 ± 0.80; FV 6.06 + 0.82\n",
"Gila: MV 6.02 ± 0.89; FV 5.96 + 0.87\n",
"Bayeye: MV 6.08 ± 0.82; FV 6.17 + 0.97\n",
"Sambia: MV 5.83 ± 0.81; FV 5.84 + 0.78\n",
"Moutinho J.: MV 5.79 ± 0.87; FV 5.76 + 1.03\n",
"Conti: MV 5.93 ± 0.83; FV 6.07 + 1.13\n",
"Marrone: MV 5.64 ± 0.88; FV 5.53 + 0.89\n",
"Tonelli: MV 5.77 ± 0.83; FV 5.71 + 0.75\n",
"Murillo: MV 5.68 ± 0.79; FV 5.60 + 0.72\n",
"Radu: MV 6.06 ± 0.78; FV 5.83 + 0.69\n",
"Paletta: MV 5.91 ± 0.96; FV 6.00 + 1.23\n",
"Florenzi: MV 6.16 ± 0.73; FV 6.42 + 1.19\n",
"Sala: MV 5.85 ± 0.80; FV 5.90 + 0.97\n",
"Fares: MV 5.80 ± 0.76; FV 5.76 + 0.72\n",
"Romagna: MV 5.73 ± 0.96; FV 5.72 + 1.08\n",
"Cassandro: MV 5.93 ± 0.82; FV 5.94 + 0.87\n",
"Muldur: MV 5.60 ± 0.86; FV 5.56 + 0.87\n",
"Amey: MV 6.03 ± 0.89; FV 6.09 + 1.00\n",
"Zanotti: MV 6.00 ± 0.84; FV 6.11 + 1.01\n",
"Ebosele: MV 5.86 ± 0.70; FV 5.87 + 0.72\n",
"Buta: MV 5.75 ± 1.05; FV 5.72 + 1.21\n",
"Abankwah: MV 5.74 ± 1.01; FV 5.70 + 1.16\n",
"Guessand A.: MV 5.75 ± 1.05; FV 5.72 + 1.21\n",
"Cabal: MV 5.84 ± 0.67; FV 5.76 + 0.62\n",
"Sosa: MV 5.67 ± 0.86; FV 5.59 + 0.89\n",
"Guarino: MV 5.97 ± 0.88; FV 6.01 + 0.94\n",
"Carboni F.: MV 5.92 ± 0.90; FV 5.97 + 1.05\n",
"Zaccagni: MV 6.47 ± 1.27; FV 7.42 + 3.02\n",
"Kvaratskhelia: MV 6.49 ± 1.41; FV 7.50 + 3.35\n",
"Milinkovic-Savic: MV 6.23 ± 1.22; FV 7.11 + 2.90\n",
"Barella: MV 6.29 ± 1.16; FV 7.02 + 2.42\n",
"Zielinski: MV 6.24 ± 1.04; FV 6.74 + 1.84\n",
"Luis Alberto: MV 6.31 ± 1.01; FV 7.00 + 2.17\n",
"Strefezza: MV 6.20 ± 1.01; FV 6.77 + 1.92\n",
"Felipe Anderson: MV 6.29 ± 1.15; FV 7.10 + 2.62\n",
"Koopmeiners: MV 6.38 ± 1.16; FV 7.19 + 2.55\n",
"Calhanoglu: MV 6.31 ± 0.98; FV 6.91 + 1.98\n",
"Frattesi: MV 6.04 ± 1.06; FV 6.48 + 1.89\n",
"Diaz B.: MV 6.31 ± 1.31; FV 7.21 + 2.92\n",
"Vlasic: MV 6.30 ± 1.07; FV 6.93 + 2.11\n",
"Zambo Anguissa: MV 6.21 ± 0.98; FV 6.61 + 1.63\n",
"Elmas: MV 6.16 ± 1.00; FV 6.73 + 1.91\n",
"Miranchuk: MV 6.39 ± 1.16; FV 7.14 + 2.40\n",
"Samardzic: MV 6.04 ± 1.08; FV 6.46 + 1.90\n",
"Pereyra: MV 5.95 ± 1.20; FV 6.35 + 2.07\n",
"Politano: MV 6.18 ± 0.82; FV 6.61 + 1.51\n",
"Rabiot: MV 6.32 ± 1.23; FV 7.16 + 2.71\n",
"Ciurria: MV 6.06 ± 1.08; FV 6.51 + 1.94\n",
"Lazovic: MV 6.14 ± 1.01; FV 6.63 + 1.83\n",
"Lobotka: MV 6.18 ± 0.81; FV 6.45 + 1.26\n",
"Radonjic: MV 6.26 ± 0.96; FV 6.80 + 1.81\n",
"Ferguson: MV 6.13 ± 0.94; FV 6.46 + 1.47\n",
"Bonaventura: MV 6.20 ± 1.00; FV 6.71 + 1.83\n",
"Pessina: MV 6.09 ± 1.05; FV 6.44 + 1.70\n",
"Tonali: MV 6.29 ± 1.14; FV 6.93 + 2.19\n",
"Kostic: MV 6.24 ± 1.06; FV 6.84 + 2.01\n",
"Baldanzi: MV 6.20 ± 1.03; FV 6.80 + 2.01\n",
"Lovric: MV 6.06 ± 0.94; FV 6.40 + 1.53\n",
"Pellegrini Lo.: MV 6.09 ± 1.17; FV 6.68 + 2.34\n",
"El Shaarawy: MV 6.20 ± 0.88; FV 6.78 + 1.84\n",
"Orsolini: MV 6.15 ± 1.32; FV 7.02 + 3.02\n",
"Ikone': MV 6.02 ± 1.07; FV 6.48 + 1.91\n",
"Candreva: MV 6.15 ± 1.07; FV 6.67 + 2.01\n",
"Bennacer: MV 6.16 ± 0.75; FV 6.48 + 1.28\n",
"Pasalic: MV 6.25 ± 1.22; FV 7.05 + 2.69\n",
"Mkhitaryan: MV 6.12 ± 1.00; FV 6.63 + 1.80\n",
"Colpani: MV 6.01 ± 0.81; FV 6.37 + 1.41\n",
"Pogba: MV 6.14 ± 0.82; FV 6.23 + 1.00\n",
"Chiesa: MV 6.10 ± 0.82; FV 6.34 + 1.15\n",
"Bandinelli: MV 5.99 ± 0.80; FV 6.15 + 1.05\n",
"Matic: MV 6.16 ± 0.82; FV 6.48 + 1.35\n",
"Fagioli: MV 6.21 ± 1.05; FV 6.71 + 1.83\n",
"Messias: MV 6.13 ± 1.14; FV 6.84 + 2.39\n",
"Arslan: MV 5.86 ± 0.77; FV 5.94 + 0.94\n",
"Ricci S.: MV 6.19 ± 0.82; FV 6.46 + 1.29\n",
"Ranocchia F.: MV 6.07 ± 0.83; FV 6.39 + 1.34\n",
"Verdi: MV 6.18 ± 1.21; FV 6.73 + 2.29\n",
"Sensi: MV 6.03 ± 1.08; FV 6.39 + 1.83\n",
"Barak: MV 5.94 ± 0.96; FV 6.26 + 1.59\n",
"Soriano: MV 6.06 ± 0.88; FV 6.36 + 1.40\n",
"Dominguez: MV 6.14 ± 0.98; FV 6.50 + 1.59\n",
"Vilhena: MV 5.93 ± 0.97; FV 6.22 + 1.58\n",
"Brozovic: MV 6.13 ± 0.86; FV 6.44 + 1.34\n",
"Cristante: MV 5.99 ± 0.87; FV 6.11 + 1.16\n",
"Thorstvedt: MV 5.85 ± 0.84; FV 6.01 + 1.13\n",
"De Ketelaere: MV 5.84 ± 0.73; FV 5.96 + 0.79\n",
"Saponara: MV 6.12 ± 1.13; FV 6.67 + 2.09\n",
"Vecino: MV 6.06 ± 0.87; FV 6.26 + 1.21\n",
"Locatelli: MV 6.11 ± 0.81; FV 6.21 + 0.97\n",
"Zaniolo: MV 5.94 ± 1.02; FV 6.20 + 1.64\n",
"Duda: MV 5.81 ± 0.69; FV 5.80 + 0.78\n",
"Maldini: MV 5.95 ± 0.91; FV 6.22 + 1.46\n",
"Marin: MV 6.01 ± 0.94; FV 6.21 + 1.30\n",
"Zalewski: MV 6.04 ± 0.77; FV 6.21 + 1.04\n",
"Bajrami: MV 5.95 ± 1.00; FV 6.30 + 1.63\n",
"Coulibaly L.: MV 5.97 ± 1.04; FV 6.29 + 1.73\n",
"Gonzalez J.: MV 5.93 ± 0.80; FV 6.04 + 1.00\n",
"De Roon: MV 6.19 ± 0.87; FV 6.59 + 1.55\n",
"Mandragora: MV 6.04 ± 0.98; FV 6.35 + 1.59\n",
"Wijnaldum: MV 6.19 ± 1.10; FV 6.85 + 2.29\n",
"Bourabia: MV 5.85 ± 0.79; FV 5.87 + 0.95\n",
"Sottil: MV 6.11 ± 1.10; FV 6.57 + 1.92\n",
"Aebischer: MV 5.95 ± 0.83; FV 6.13 + 1.19\n",
"Ederson D.s.: MV 6.02 ± 0.79; FV 6.23 + 1.10\n",
"Miretti: MV 6.02 ± 0.71; FV 6.15 + 0.80\n",
"Blin: MV 5.90 ± 0.74; FV 5.96 + 0.83\n",
"Hjulmand: MV 5.87 ± 0.90; FV 5.83 + 0.90\n",
"Cataldi: MV 6.03 ± 0.74; FV 5.97 + 0.68\n",
"Djuricic: MV 5.85 ± 0.94; FV 6.01 + 1.35\n",
"Linetty: MV 6.06 ± 0.82; FV 6.25 + 1.10\n",
"Haas: MV 5.96 ± 0.77; FV 6.11 + 0.99\n",
"Walace: MV 5.85 ± 0.92; FV 5.85 + 1.07\n",
"Agudelo: MV 5.84 ± 0.75; FV 5.92 + 0.96\n",
"Pobega: MV 6.11 ± 0.88; FV 6.54 + 1.51\n",
"Camara Ma.: MV 6.09 ± 0.87; FV 6.18 + 1.02\n",
"Paredes: MV 5.92 ± 0.69; FV 5.85 + 0.58\n",
"Ndombele': MV 5.98 ± 0.76; FV 6.14 + 0.97\n",
"Nicolussi Caviglia: MV 5.90 ± 1.05; FV 6.16 + 1.68\n",
"Rovella: MV 5.97 ± 1.08; FV 6.14 + 1.36\n",
"Amrabat: MV 5.98 ± 0.90; FV 6.06 + 1.11\n",
"Tameze: MV 5.86 ± 0.78; FV 5.83 + 0.87\n",
"Gyasi: MV 5.78 ± 0.91; FV 5.89 + 1.24\n",
"Ilic: MV 6.18 ± 0.86; FV 6.51 + 1.39\n",
"Matheus Henrique: MV 5.81 ± 0.91; FV 5.94 + 1.22\n",
"Harroui: MV 5.89 ± 0.87; FV 6.10 + 1.24\n",
"Volpato: MV 6.02 ± 1.14; FV 6.66 + 2.34\n",
"Pickel: MV 5.77 ± 0.82; FV 5.78 + 0.99\n",
"Moro N.: MV 6.11 ± 0.93; FV 6.43 + 1.43\n",
"Duncan: MV 5.94 ± 0.82; FV 6.12 + 1.23\n",
"Machin: MV 5.94 ± 0.95; FV 6.05 + 1.27\n",
"Cuadrado: MV 6.06 ± 0.92; FV 6.19 + 1.09\n",
"Ekdal: MV 5.82 ± 0.78; FV 5.82 + 0.91\n",
"Meite': MV 5.85 ± 0.94; FV 5.87 + 1.21\n",
"Schouten: MV 5.98 ± 0.85; FV 5.99 + 0.89\n",
"Obiang: MV 5.78 ± 0.64; FV 5.75 + 0.57\n",
"Kovalenko: MV 5.85 ± 0.79; FV 5.92 + 1.01\n",
"Crnigoj: MV 5.95 ± 0.79; FV 6.11 + 1.04\n",
"Basic: MV 6.04 ± 0.63; FV 6.03 + 0.61\n",
"Asllani: MV 6.04 ± 0.66; FV 6.08 + 0.68\n",
"Sabiri: MV 5.91 ± 0.92; FV 6.08 + 1.35\n",
"Terracciano F.: MV 5.97 ± 0.70; FV 6.04 + 0.79\n",
"Castagnetti: MV 5.88 ± 0.79; FV 5.89 + 0.90\n",
"Oudin: MV 5.87 ± 0.62; FV 5.90 + 0.52\n",
"Grassi: MV 5.93 ± 0.66; FV 5.91 + 0.55\n",
"Krunic: MV 6.00 ± 0.70; FV 6.06 + 0.75\n",
"Rincon: MV 5.79 ± 0.76; FV 5.73 + 0.77\n",
"Miguel Veloso: MV 5.87 ± 0.73; FV 5.85 + 0.78\n",
"Leris: MV 5.87 ± 0.88; FV 5.98 + 1.24\n",
"Esposito Sa.: MV 5.74 ± 0.87; FV 5.63 + 0.91\n",
"Henderson L.: MV 5.94 ± 0.76; FV 6.04 + 0.89\n",
"Lopez M.: MV 5.80 ± 0.84; FV 5.75 + 0.89\n",
"Cuisance: MV 5.82 ± 0.63; FV 5.82 + 0.57\n",
"Saelemaekers: MV 5.98 ± 0.76; FV 6.24 + 1.05\n",
"Maggiore: MV 5.95 ± 0.77; FV 6.08 + 0.96\n",
"Akpa Akpro: MV 5.97 ± 0.88; FV 6.03 + 0.98\n",
"Maleh: MV 5.87 ± 0.67; FV 5.94 + 0.74\n",
"Romero L.: MV 6.12 ± 0.98; FV 6.80 + 2.21\n",
"Ceide: MV 5.78 ± 0.66; FV 5.81 + 0.61\n",
"D'alessandro: MV 6.05 ± 0.65; FV 6.12 + 0.73\n",
"Benassi: MV 5.83 ± 0.80; FV 5.94 + 1.05\n",
"Gagliardini: MV 5.86 ± 0.64; FV 5.89 + 0.62\n",
"Vieira: MV 5.92 ± 0.66; FV 5.96 + 0.70\n",
"Bianco: MV 6.10 ± 0.80; FV 6.26 + 1.07\n",
"Vranckx: MV 5.85 ± 0.67; FV 5.90 + 0.63\n",
"Galdames: MV 5.87 ± 1.06; FV 5.98 + 1.47\n",
"Marcos Antonio: MV 6.11 ± 0.84; FV 6.73 + 1.90\n",
"Fazzini: MV 5.82 ± 0.64; FV 5.80 + 0.55\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Sulemana I.: MV 5.83 ± 0.65; FV 5.79 + 0.65\n",
"Tahirovic: MV 6.03 ± 0.65; FV 6.02 + 0.65\n",
"Abildgaard: MV 5.89 ± 0.61; FV 5.88 + 0.55\n",
"Barberis: MV 5.76 ± 0.84; FV 5.74 + 0.90\n",
"Kastanos: MV 5.97 ± 0.86; FV 6.16 + 1.18\n",
"Vignato: MV 6.01 ± 0.76; FV 6.13 + 0.86\n",
"Valoti: MV 5.84 ± 0.68; FV 5.83 + 0.70\n",
"Winks: MV 5.92 ± 0.78; FV 5.91 + 0.71\n",
"Askildsen: MV 5.73 ± 0.62; FV 5.71 + 0.53\n",
"Bove: MV 5.98 ± 0.86; FV 6.25 + 1.38\n",
"Bohinen: MV 5.82 ± 0.61; FV 5.84 + 0.48\n",
"D'andrea: MV 5.89 ± 0.72; FV 5.98 + 0.82\n",
"Iling-Junior: MV 6.01 ± 0.64; FV 6.04 + 0.63\n",
"Cipot: MV 5.91 ± 0.80; FV 5.98 + 1.00\n",
"Bakayoko: MV 5.86 ± 0.72; FV 5.83 + 0.63\n",
"Gaetano: MV 6.15 ± 0.74; FV 6.35 + 1.10\n",
"Zurkowski: MV 5.97 ± 0.96; FV 6.25 + 1.55\n",
"Castrovilli: MV 6.00 ± 0.80; FV 6.25 + 1.25\n",
"Demme: MV 5.90 ± 0.80; FV 5.99 + 1.00\n",
"Darboe: MV 5.91 ± 0.93; FV 5.93 + 1.02\n",
"Urbanski: MV 5.99 ± 0.90; FV 6.05 + 1.04\n",
"Bertini: MV 5.99 ± 0.86; FV 6.02 + 0.91\n",
"Yepes: MV 5.75 ± 0.89; FV 5.67 + 0.92\n",
"Pyyhtia: MV 5.87 ± 0.82; FV 5.83 + 0.84\n",
"Trimboli: MV 5.97 ± 0.88; FV 6.05 + 1.04\n",
"Pafundi: MV 5.96 ± 0.74; FV 5.88 + 0.65\n",
"Helgason: MV 5.85 ± 0.62; FV 5.85 + 0.51\n",
"Adli: MV 5.94 ± 0.69; FV 6.03 + 0.75\n",
"Vignato S.: MV 5.96 ± 0.91; FV 6.03 + 1.10\n",
"Hrustic: MV 5.67 ± 0.69; FV 5.64 + 0.71\n",
"Samek: MV 5.92 ± 0.85; FV 5.96 + 0.95\n",
"Zerbin: MV 5.82 ± 0.67; FV 5.84 + 0.74\n",
"Ilkhan: MV 5.93 ± 0.78; FV 5.95 + 0.78\n",
"Degli Innocenti: MV 5.97 ± 0.88; FV 6.03 + 0.98\n",
"Acella: MV 5.90 ± 1.05; FV 6.03 + 1.47\n",
"Carboni V.: MV 6.05 ± 0.77; FV 6.14 + 0.87\n",
"Paoletti: MV 5.92 ± 0.60; FV 5.91 + 0.45\n",
"Malagrida: MV 6.04 ± 0.96; FV 6.26 + 1.32\n",
"Faticanti: MV 5.94 ± 0.92; FV 6.02 + 1.15\n",
"Osimhen: MV 6.38 ± 1.48; FV 7.89 + 4.50\n",
"Martinez L.: MV 6.23 ± 1.44; FV 7.69 + 4.20\n",
"Dybala: MV 6.47 ± 1.37; FV 7.51 + 3.43\n",
"Rafael Leao: MV 6.44 ± 1.45; FV 7.65 + 3.92\n",
"Lookman: MV 6.46 ± 1.42; FV 7.65 + 3.83\n",
"Immobile: MV 6.30 ± 1.40; FV 7.57 + 3.90\n",
"Vlahovic: MV 6.16 ± 1.34; FV 7.32 + 3.51\n",
"Arnautovic: MV 6.16 ± 1.33; FV 7.23 + 3.36\n",
"Dia: MV 6.19 ± 1.33; FV 7.29 + 3.44\n",
"Dzeko: MV 6.16 ± 1.34; FV 7.25 + 3.36\n",
"Milik: MV 6.25 ± 1.20; FV 7.07 + 2.67\n",
"Nzola: MV 6.04 ± 1.35; FV 7.05 + 3.21\n",
"Beto: MV 5.86 ± 1.09; FV 6.38 + 2.02\n",
"Giroud: MV 6.27 ± 1.35; FV 7.38 + 3.54\n",
"Abraham: MV 6.14 ± 1.22; FV 7.03 + 2.90\n",
"Deulofeu: MV 6.15 ± 1.21; FV 6.84 + 2.47\n",
"Lauriente': MV 6.17 ± 1.34; FV 7.04 + 3.07\n",
"Simeone: MV 6.12 ± 1.32; FV 7.11 + 3.12\n",
"Lozano: MV 6.03 ± 1.04; FV 6.59 + 2.04\n",
"Correa: MV 6.05 ± 1.08; FV 6.68 + 2.23\n",
"Berardi: MV 6.17 ± 1.38; FV 7.30 + 3.51\n",
"Pedro: MV 6.20 ± 1.05; FV 6.86 + 2.24\n",
"Lukaku: MV 6.12 ± 1.34; FV 7.15 + 3.26\n",
"Sanabria: MV 6.24 ± 1.28; FV 7.22 + 3.15\n",
"Thauvin: MV 6.07 ± 1.10; FV 6.54 + 1.95\n",
"Cabral: MV 6.15 ± 1.26; FV 7.08 + 2.93\n",
"Hojlund: MV 6.25 ± 1.36; FV 7.39 + 3.56\n",
"Caprari: MV 5.97 ± 0.95; FV 6.29 + 1.53\n",
"Di Maria: MV 6.30 ± 1.26; FV 7.09 + 2.67\n",
"Piatek: MV 5.85 ± 0.99; FV 6.21 + 1.66\n",
"Rebic: MV 6.22 ± 1.36; FV 7.14 + 3.19\n",
"Bonazzoli: MV 6.01 ± 0.96; FV 6.41 + 1.71\n",
"Zapata D.: MV 6.09 ± 0.95; FV 6.49 + 1.60\n",
"Kouame': MV 6.09 ± 1.24; FV 6.84 + 2.60\n",
"Gonzalez N.: MV 6.21 ± 1.27; FV 7.05 + 2.81\n",
"Brekalo: MV 6.14 ± 1.18; FV 6.82 + 2.39\n",
"Mota: MV 5.99 ± 1.16; FV 6.55 + 2.23\n",
"Kean: MV 6.13 ± 1.30; FV 7.05 + 3.06\n",
"Okereke: MV 5.85 ± 1.05; FV 6.24 + 1.79\n",
"Ceesay: MV 5.89 ± 0.95; FV 6.21 + 1.52\n",
"Colombo: MV 5.87 ± 0.99; FV 6.24 + 1.68\n",
"Dessers: MV 5.95 ± 1.16; FV 6.53 + 2.25\n",
"Muriel: MV 6.13 ± 1.05; FV 6.51 + 1.72\n",
"Pinamonti: MV 5.77 ± 0.96; FV 6.11 + 1.58\n",
"Di Francesco F.: MV 5.92 ± 0.91; FV 6.13 + 1.31\n",
"Jovic: MV 5.97 ± 1.14; FV 6.47 + 2.12\n",
"Origi: MV 5.97 ± 1.06; FV 6.40 + 1.91\n",
"Caputo: MV 5.99 ± 1.13; FV 6.62 + 2.31\n",
"Boga: MV 6.42 ± 1.23; FV 7.25 + 2.65\n",
"Cambiaghi: MV 6.14 ± 1.04; FV 6.73 + 2.07\n",
"Alvarez A.: MV 5.88 ± 1.01; FV 6.22 + 1.64\n",
"Banda: MV 5.91 ± 0.74; FV 6.02 + 0.86\n",
"Ciofani D.: MV 6.01 ± 1.12; FV 6.48 + 2.05\n",
"Petagna: MV 5.96 ± 1.01; FV 6.32 + 1.68\n",
"Barrow: MV 5.98 ± 1.17; FV 6.42 + 2.08\n",
"Djuric: MV 5.93 ± 0.71; FV 6.06 + 0.87\n",
"Henry: MV 5.89 ± 1.06; FV 6.30 + 1.84\n",
"Success: MV 5.89 ± 0.92; FV 6.11 + 1.36\n",
"Gabbiadini: MV 5.94 ± 1.09; FV 6.43 + 2.01\n",
"Zirkzee: MV 6.01 ± 1.08; FV 6.37 + 1.77\n",
"Lammers: MV 5.82 ± 0.87; FV 6.01 + 1.26\n",
"Satriano: MV 5.89 ± 0.92; FV 6.09 + 1.33\n",
"Kallon: MV 5.87 ± 0.82; FV 6.05 + 1.18\n",
"Nestorovski: MV 6.06 ± 0.72; FV 6.52 + 1.43\n",
"Raspadori: MV 6.01 ± 1.05; FV 6.54 + 2.00\n",
"Botheim: MV 5.93 ± 0.95; FV 6.32 + 1.68\n",
"Gytkjaer: MV 5.84 ± 0.84; FV 6.05 + 1.27\n",
"Solbakken: MV 5.92 ± 1.00; FV 6.36 + 1.83\n",
"Lasagna: MV 5.78 ± 0.78; FV 5.84 + 0.98\n",
"Belotti: MV 5.78 ± 0.78; FV 5.90 + 1.01\n",
"Pellegri: MV 5.99 ± 0.89; FV 6.30 + 1.44\n",
"Buonaiuto: MV 5.91 ± 0.84; FV 6.10 + 1.17\n",
"Verde: MV 5.92 ± 1.09; FV 6.29 + 1.85\n",
"Destro: MV 6.00 ± 1.20; FV 6.61 + 2.37\n",
"Seck: MV 6.13 ± 0.66; FV 6.25 + 0.89\n",
"Sansone: MV 6.11 ± 1.16; FV 6.63 + 2.15\n",
"Quagliarella: MV 5.86 ± 0.78; FV 6.01 + 1.08\n",
"Defrel: MV 5.77 ± 0.87; FV 5.93 + 1.21\n",
"Pjaca: MV 5.92 ± 0.81; FV 6.04 + 0.93\n",
"Gaich: MV 5.87 ± 0.91; FV 6.08 + 1.39\n",
"Soule': MV 6.18 ± 0.80; FV 6.64 + 1.52\n",
"Tsadjout: MV 5.88 ± 0.98; FV 6.26 + 1.67\n",
"Piccoli: MV 5.81 ± 0.74; FV 5.86 + 0.75\n",
"Shomurodov: MV 5.88 ± 0.97; FV 6.23 + 1.63\n",
"Afena-Gyan: MV 5.69 ± 0.74; FV 5.72 + 0.87\n",
"Ngonge: MV 6.10 ± 1.16; FV 6.59 + 2.12\n",
"Karamoh: MV 6.22 ± 1.06; FV 6.92 + 2.30\n",
"Ibrahimovic: MV 6.37 ± 1.33; FV 7.38 + 3.18\n",
"Pussetto: MV 5.94 ± 1.06; FV 6.42 + 1.99\n",
"Cancellieri: MV 5.83 ± 0.62; FV 5.83 + 0.50\n",
"Valencia D.: MV 5.70 ± 0.60; FV 5.65 + 0.63\n",
"Oddei: MV 5.94 ± 0.86; FV 6.08 + 1.11\n",
"Braaf: MV 5.80 ± 0.88; FV 5.87 + 1.17\n",
"Raimondo: MV 6.00 ± 0.93; FV 6.08 + 1.07\n",
"Kaio Jorge: MV 5.95 ± 0.59; FV 5.98 + 0.50\n",
"De Luca: MV 5.97 ± 0.82; FV 6.06 + 0.93\n",
"Voelkerling Persson: MV 5.89 ± 0.65; FV 5.96 + 0.64\n",
"Montevago: MV 5.65 ± 0.64; FV 5.63 + 0.62\n",
"Krollis: MV 5.86 ± 0.95; FV 5.94 + 1.30\n",
"Vivaldo: MV 5.82 ± 1.04; FV 5.90 + 1.39\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>role</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>starter</th>\n",
" <th>vote%</th>\n",
" <th>MV</th>\n",
" <th>MV std</th>\n",
" <th>FV</th>\n",
" <th>FV std</th>\n",
" <th>MV loc</th>\n",
" <th>MV scale</th>\n",
" <th>MV skewness</th>\n",
" <th>MV tailweight</th>\n",
" <th>FV loc</th>\n",
" <th>FV scale</th>\n",
" <th>FV skewness</th>\n",
" <th>FV tailweight</th>\n",
" <th>Clean Sheet %</th>\n",
" </tr>\n",
" <tr>\n",
" <th>player</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Sportiello</th>\n",
" <td>P</td>\n",
" <td>Atalanta</td>\n",
" <td>Spezia</td>\n",
" <td>1</td>\n",
" <td>1.00</td>\n",
" <td>75</td>\n",
" <td>6.178402</td>\n",
" <td>0.428025</td>\n",
" <td>5.716108</td>\n",
" <td>0.546802</td>\n",
" <td>5.928400</td>\n",
" <td>0.263585</td>\n",
" <td>0.609268</td>\n",
" <td>1.588811</td>\n",
" <td>6.283780</td>\n",
" <td>0.623820</td>\n",
" <td>-0.625340</td>\n",
" <td>1.072692</td>\n",
" <td>40.422094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Musso</th>\n",
" <td>P</td>\n",
" <td>Atalanta</td>\n",
" <td>Spezia</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>5</td>\n",
" <td>6.246836</td>\n",
" <td>0.412463</td>\n",
" <td>5.418529</td>\n",
" <td>0.418830</td>\n",
" <td>6.005536</td>\n",
" <td>0.252778</td>\n",
" <td>0.612203</td>\n",
" <td>1.589951</td>\n",
" <td>5.813268</td>\n",
" <td>0.512082</td>\n",
" <td>-0.541122</td>\n",
" <td>1.031041</td>\n",
" <td>24.998909</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Rossi F.</th>\n",
" <td>P</td>\n",
" <td>Atalanta</td>\n",
" <td>Spezia</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>1</td>\n",
" <td>6.241959</td>\n",
" <td>0.413916</td>\n",
" <td>4.533127</td>\n",
" <td>0.526911</td>\n",
" <td>5.998054</td>\n",
" <td>0.249728</td>\n",
" <td>0.623062</td>\n",
" <td>1.589842</td>\n",
" <td>5.066249</td>\n",
" <td>0.630503</td>\n",
" <td>-0.590708</td>\n",
" <td>0.972040</td>\n",
" <td>0.773813</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scalvini</th>\n",
" <td>D</td>\n",
" <td>Atalanta</td>\n",
" <td>Spezia</td>\n",
" <td>1</td>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" <td>6.273323</td>\n",
" <td>0.537045</td>\n",
" <td>6.786601</td>\n",
" <td>0.980843</td>\n",
" <td>6.157186</td>\n",
" <td>0.598484</td>\n",
" <td>0.142554</td>\n",
" <td>0.937184</td>\n",
" <td>5.967968</td>\n",
" <td>1.206433</td>\n",
" <td>0.463573</td>\n",
" <td>1.599848</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Toloi</th>\n",
" <td>D</td>\n",
" <td>Atalanta</td>\n",
" <td>Spezia</td>\n",
" <td>1</td>\n",
" <td>1.00</td>\n",
" <td>90</td>\n",
" <td>6.254010</td>\n",
" <td>0.510611</td>\n",
" <td>6.719704</td>\n",
" <td>0.905750</td>\n",
" <td>6.162670</td>\n",
" <td>0.575446</td>\n",
" <td>0.116788</td>\n",
" <td>0.958888</td>\n",
" <td>5.978364</td>\n",
" <td>1.134393</td>\n",
" <td>0.448929</td>\n",
" <td>1.599858</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Gaich</th>\n",
" <td>A</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" <td>1</td>\n",
" <td>0.55</td>\n",
" <td>55</td>\n",
" <td>5.867453</td>\n",
" <td>0.457420</td>\n",
" <td>6.084643</td>\n",
" <td>0.692782</td>\n",
" <td>5.792738</td>\n",
" <td>0.519226</td>\n",
" <td>0.106163</td>\n",
" <td>1.045169</td>\n",
" <td>5.522809</td>\n",
" <td>0.874729</td>\n",
" <td>0.442301</td>\n",
" <td>1.599854</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Djuric</th>\n",
" <td>A</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" <td>1</td>\n",
" <td>0.45</td>\n",
" <td>60</td>\n",
" <td>5.927261</td>\n",
" <td>0.352975</td>\n",
" <td>6.058505</td>\n",
" <td>0.437122</td>\n",
" <td>5.883422</td>\n",
" <td>0.408226</td>\n",
" <td>0.079531</td>\n",
" <td>1.154408</td>\n",
" <td>5.803053</td>\n",
" <td>0.662872</td>\n",
" <td>0.278751</td>\n",
" <td>1.599918</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Kallon</th>\n",
" <td>A</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>40</td>\n",
" <td>5.874599</td>\n",
" <td>0.410965</td>\n",
" <td>6.049230</td>\n",
" <td>0.592300</td>\n",
" <td>5.806045</td>\n",
" <td>0.466689</td>\n",
" <td>0.108503</td>\n",
" <td>1.095199</td>\n",
" <td>5.593708</td>\n",
" <td>0.780142</td>\n",
" <td>0.407094</td>\n",
" <td>1.599884</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Braaf</th>\n",
" <td>A</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>35</td>\n",
" <td>5.796274</td>\n",
" <td>0.440012</td>\n",
" <td>5.869830</td>\n",
" <td>0.585489</td>\n",
" <td>5.757944</td>\n",
" <td>0.511931</td>\n",
" <td>0.055347</td>\n",
" <td>1.060328</td>\n",
" <td>5.505967</td>\n",
" <td>0.867116</td>\n",
" <td>0.301824</td>\n",
" <td>1.599889</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lasagna</th>\n",
" <td>A</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" <td>1</td>\n",
" <td>1.00</td>\n",
" <td>80</td>\n",
" <td>5.777834</td>\n",
" <td>0.389363</td>\n",
" <td>5.836037</td>\n",
" <td>0.489194</td>\n",
" <td>5.727798</td>\n",
" <td>0.448826</td>\n",
" <td>0.082488</td>\n",
" <td>1.123643</td>\n",
" <td>5.506660</td>\n",
" <td>0.698520</td>\n",
" <td>0.336068</td>\n",
" <td>1.599901</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>525 rows × 19 columns</p>\n",
"</div>"
],
"text/plain": [
" role team oppteam home starter vote% MV MV std \\\n",
"player \n",
"Sportiello P Atalanta Spezia 1 1.00 75 6.178402 0.428025 \n",
"Musso P Atalanta Spezia 1 0.00 5 6.246836 0.412463 \n",
"Rossi F. P Atalanta Spezia 1 0.00 1 6.241959 0.413916 \n",
"Scalvini D Atalanta Spezia 1 1.00 90 6.273323 0.537045 \n",
"Toloi D Atalanta Spezia 1 1.00 90 6.254010 0.510611 \n",
"... ... ... ... ... ... ... ... ... \n",
"Gaich A Verona Inter 1 0.55 55 5.867453 0.457420 \n",
"Djuric A Verona Inter 1 0.45 60 5.927261 0.352975 \n",
"Kallon A Verona Inter 1 0.00 40 5.874599 0.410965 \n",
"Braaf A Verona Inter 1 0.00 35 5.796274 0.440012 \n",
"Lasagna A Verona Inter 1 1.00 80 5.777834 0.389363 \n",
"\n",
" FV FV std MV loc MV scale MV skewness \\\n",
"player \n",
"Sportiello 5.716108 0.546802 5.928400 0.263585 0.609268 \n",
"Musso 5.418529 0.418830 6.005536 0.252778 0.612203 \n",
"Rossi F. 4.533127 0.526911 5.998054 0.249728 0.623062 \n",
"Scalvini 6.786601 0.980843 6.157186 0.598484 0.142554 \n",
"Toloi 6.719704 0.905750 6.162670 0.575446 0.116788 \n",
"... ... ... ... ... ... \n",
"Gaich 6.084643 0.692782 5.792738 0.519226 0.106163 \n",
"Djuric 6.058505 0.437122 5.883422 0.408226 0.079531 \n",
"Kallon 6.049230 0.592300 5.806045 0.466689 0.108503 \n",
"Braaf 5.869830 0.585489 5.757944 0.511931 0.055347 \n",
"Lasagna 5.836037 0.489194 5.727798 0.448826 0.082488 \n",
"\n",
" MV tailweight FV loc FV scale FV skewness FV tailweight \\\n",
"player \n",
"Sportiello 1.588811 6.283780 0.623820 -0.625340 1.072692 \n",
"Musso 1.589951 5.813268 0.512082 -0.541122 1.031041 \n",
"Rossi F. 1.589842 5.066249 0.630503 -0.590708 0.972040 \n",
"Scalvini 0.937184 5.967968 1.206433 0.463573 1.599848 \n",
"Toloi 0.958888 5.978364 1.134393 0.448929 1.599858 \n",
"... ... ... ... ... ... \n",
"Gaich 1.045169 5.522809 0.874729 0.442301 1.599854 \n",
"Djuric 1.154408 5.803053 0.662872 0.278751 1.599918 \n",
"Kallon 1.095199 5.593708 0.780142 0.407094 1.599884 \n",
"Braaf 1.060328 5.505967 0.867116 0.301824 1.599889 \n",
"Lasagna 1.123643 5.506660 0.698520 0.336068 1.599901 \n",
"\n",
" Clean Sheet % \n",
"player \n",
"Sportiello 40.422094 \n",
"Musso 24.998909 \n",
"Rossi F. 0.773813 \n",
"Scalvini 0.000000 \n",
"Toloi 0.000000 \n",
"... ... \n",
"Gaich 0.000000 \n",
"Djuric 0.000000 \n",
"Kallon 0.000000 \n",
"Braaf 0.000000 \n",
"Lasagna 0.000000 \n",
"\n",
"[525 rows x 19 columns]"
]
},
"execution_count": 28,
"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": 29,
"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": null,
"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": null,
"id": "60d73507",
"metadata": {},
"outputs": [],
"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": null,
"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",
" [<tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>,\n",
" <tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>,\n",
" <tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=int32>]]"
]
},
"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",
" [<tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>,\n",
" <tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>]]"
]
},
"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",
" [<tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>,\n",
" <tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>]]"
]
},
"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": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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",
" [<tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>,\n",
" <tfp.distributions._TensorCoercible 'tensor_coercible' batch_shape=[1] event_shape=[] dtype=float32>]]"
]
},
"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": [
"[<matplotlib.lines.Line2D at 0x203bcc464f0>]"
]
},
"execution_count": 110,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"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
}
Reference in New Issue View Git Blame Copy Permalink