{ "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_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) \n", "db4 = pd.read_excel('mid_outputs/season2223/database_entries.xlsx', index_col = 0) " ] }, { "cell_type": "code", "execution_count": 4, "id": "f71fa9a4", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...miscontrolsdispossessedfoulsfouledaerials_wonaerials_lostcarriesprogressive_carriescarries_into_final_thirdcarries_into_penalty_area
01ZappacostaAtalantaSassuolo06.5000.06.5...0.0183490.0091740.0091740.0152910.0091740.0152910.3761470.0336390.0152910.012232
11DjimsitiAtalantaSassuolo06.0000.06.0...0.0046080.0000000.0115210.0023040.0345620.0207370.2995390.0000000.0000000.000000
21KolasinacAtalantaSassuolo06.5000.06.5...0.0092760.0018550.0092760.0148420.0166980.0222630.3784790.0148420.0166980.001855
31ZorteaAtalantaSassuolo07.0100.010.0...0.0000000.0208330.0312500.0000000.0000000.0104170.4479170.0625000.0416670.010417
41RuggeriAtalantaSassuolo06.5010.07.5...0.0102040.0020410.0142860.0040820.0102040.0204080.3571430.0163270.0142860.004082
..................................................................
3059538Miguel VelosoVeronaMilan05.5000.05.5...0.0060190.0060190.0171970.0068790.0120380.0120380.2656920.0146170.0111780.000860
3059638TamezeVeronaMilan05.5000.05.5...0.0128670.0112170.0105580.0102280.0089080.0102280.2352360.0105580.0112170.001320
3059738Sulemana I.VeronaMilan06.0000.55.5...0.0153610.0138250.0168970.0046080.0153610.0184330.2012290.0061440.0107530.000000
3059838DjuricVeronaMilan05.5000.05.5...0.0190340.0109810.0175700.0212300.1442170.0417280.1918010.0014640.0036600.002196
3059938NgongeVeronaMilan05.5000.05.5...0.0308720.0161070.0174500.0147650.0228190.0469800.2429530.0241610.0147650.012081
\n", "

30600 rows × 122 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote goals \\\n", "0 1 Zappacosta Atalanta Sassuolo 0 6.5 0 \n", "1 1 Djimsiti Atalanta Sassuolo 0 6.0 0 \n", "2 1 Kolasinac Atalanta Sassuolo 0 6.5 0 \n", "3 1 Zortea Atalanta Sassuolo 0 7.0 1 \n", "4 1 Ruggeri Atalanta Sassuolo 0 6.5 0 \n", "... ... ... ... ... ... ... ... \n", "30595 38 Miguel Veloso Verona Milan 0 5.5 0 \n", "30596 38 Tameze Verona Milan 0 5.5 0 \n", "30597 38 Sulemana I. Verona Milan 0 6.0 0 \n", "30598 38 Djuric Verona Milan 0 5.5 0 \n", "30599 38 Ngonge Verona Milan 0 5.5 0 \n", "\n", " assists cards_malus fantavote ... miscontrols dispossessed \\\n", "0 0 0.0 6.5 ... 0.018349 0.009174 \n", "1 0 0.0 6.0 ... 0.004608 0.000000 \n", "2 0 0.0 6.5 ... 0.009276 0.001855 \n", "3 0 0.0 10.0 ... 0.000000 0.020833 \n", "4 1 0.0 7.5 ... 0.010204 0.002041 \n", "... ... ... ... ... ... ... \n", "30595 0 0.0 5.5 ... 0.006019 0.006019 \n", "30596 0 0.0 5.5 ... 0.012867 0.011217 \n", "30597 0 0.5 5.5 ... 0.015361 0.013825 \n", "30598 0 0.0 5.5 ... 0.019034 0.010981 \n", "30599 0 0.0 5.5 ... 0.030872 0.016107 \n", "\n", " fouls fouled aerials_won aerials_lost carries \\\n", "0 0.009174 0.015291 0.009174 0.015291 0.376147 \n", "1 0.011521 0.002304 0.034562 0.020737 0.299539 \n", "2 0.009276 0.014842 0.016698 0.022263 0.378479 \n", "3 0.031250 0.000000 0.000000 0.010417 0.447917 \n", "4 0.014286 0.004082 0.010204 0.020408 0.357143 \n", "... ... ... ... ... ... \n", "30595 0.017197 0.006879 0.012038 0.012038 0.265692 \n", "30596 0.010558 0.010228 0.008908 0.010228 0.235236 \n", "30597 0.016897 0.004608 0.015361 0.018433 0.201229 \n", "30598 0.017570 0.021230 0.144217 0.041728 0.191801 \n", "30599 0.017450 0.014765 0.022819 0.046980 0.242953 \n", "\n", " progressive_carries carries_into_final_third \\\n", "0 0.033639 0.015291 \n", "1 0.000000 0.000000 \n", "2 0.014842 0.016698 \n", "3 0.062500 0.041667 \n", "4 0.016327 0.014286 \n", "... ... ... \n", "30595 0.014617 0.011178 \n", "30596 0.010558 0.011217 \n", "30597 0.006144 0.010753 \n", "30598 0.001464 0.003660 \n", "30599 0.024161 0.014765 \n", "\n", " carries_into_penalty_area \n", "0 0.012232 \n", "1 0.000000 \n", "2 0.001855 \n", "3 0.010417 \n", "4 0.004082 \n", "... ... \n", "30595 0.000860 \n", "30596 0.001320 \n", "30597 0.000000 \n", "30598 0.002196 \n", "30599 0.012081 \n", "\n", "[30600 rows x 122 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db = pd.concat([db1, db2, db3, db4], ignore_index = True) \n", "\n", "db" ] }, { "cell_type": "code", "execution_count": 5, "id": "1d024554", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...gk_psxggk_psnpxg_per_shot_on_target_againstgk_psxg_netgk_passes_completed_launchedgk_passes_launchedgk_passesgk_passes_throwsgk_goal_kicksgk_crossesgk_crosses_stopped
01MussoAtalantaSassuolo06.5000.06.5...2.1000000.2100000.10000014.00000048.000000119.00000025.00000028.00000043.0000004.000000
11SkorupskiBolognaMilan16.0-200.04.0...4.2000000.2500000.20000028.00000060.000000159.00000025.00000034.00000089.0000003.000000
21RadunovicCagliariTorino06.5000.06.5...8.7000000.360000-0.30000033.00000080.000000124.00000023.00000057.00000087.0000005.000000
31CaprileEmpoliVerona15.0-100.04.0...4.9333330.203333-1.4000008.66666738.66666783.00000017.66666717.33333336.6666672.000000
41TerraccianoFiorentinaGenoa06.0-100.05.0...4.1000000.2400000.10000028.00000057.000000151.00000014.00000022.00000044.0000003.000000
..................................................................
240438Russo A.SassuoloFiorentina15.0-300.02.0...32.5500000.325000-12.116667146.666667365.333333957.000000156.166667238.833333391.50000023.333333
240538ZoetSpeziaRoma05.5-200.53.0...10.0166670.158333-1.81666746.000000145.333333254.16666737.33333351.833333130.3333335.500000
240638Milinkovic-Savic V.TorinoInter15.0-100.04.0...35.8000000.230000-5.200000285.000000939.0000001506.000000185.000000286.000000469.00000036.000000
240738SilvestriUdineseJuventus16.5-100.05.5...48.7000000.3100002.700000144.000000380.000000872.000000142.000000302.000000547.00000013.000000
240838Montipo'VeronaMilan06.0-300.03.0...49.6000000.270000-6.400000360.000000775.000000905.000000124.000000284.000000496.00000026.000000
\n", "

2409 rows × 102 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote \\\n", "0 1 Musso Atalanta Sassuolo 0 6.5 \n", "1 1 Skorupski Bologna Milan 1 6.0 \n", "2 1 Radunovic Cagliari Torino 0 6.5 \n", "3 1 Caprile Empoli Verona 1 5.0 \n", "4 1 Terracciano Fiorentina Genoa 0 6.0 \n", "... ... ... ... ... ... ... \n", "2404 38 Russo A. Sassuolo Fiorentina 1 5.0 \n", "2405 38 Zoet Spezia Roma 0 5.5 \n", "2406 38 Milinkovic-Savic V. Torino Inter 1 5.0 \n", "2407 38 Silvestri Udinese Juventus 1 6.5 \n", "2408 38 Montipo' Verona Milan 0 6.0 \n", "\n", " goals assists cards_malus fantavote ... gk_psxg \\\n", "0 0 0 0.0 6.5 ... 2.100000 \n", "1 -2 0 0.0 4.0 ... 4.200000 \n", "2 0 0 0.0 6.5 ... 8.700000 \n", "3 -1 0 0.0 4.0 ... 4.933333 \n", "4 -1 0 0.0 5.0 ... 4.100000 \n", "... ... ... ... ... ... ... \n", "2404 -3 0 0.0 2.0 ... 32.550000 \n", "2405 -2 0 0.5 3.0 ... 10.016667 \n", "2406 -1 0 0.0 4.0 ... 35.800000 \n", "2407 -1 0 0.0 5.5 ... 48.700000 \n", "2408 -3 0 0.0 3.0 ... 49.600000 \n", "\n", " gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n", "0 0.210000 0.100000 \n", "1 0.250000 0.200000 \n", "2 0.360000 -0.300000 \n", "3 0.203333 -1.400000 \n", "4 0.240000 0.100000 \n", "... ... ... \n", "2404 0.325000 -12.116667 \n", "2405 0.158333 -1.816667 \n", "2406 0.230000 -5.200000 \n", "2407 0.310000 2.700000 \n", "2408 0.270000 -6.400000 \n", "\n", " gk_passes_completed_launched gk_passes_launched gk_passes \\\n", "0 14.000000 48.000000 119.000000 \n", "1 28.000000 60.000000 159.000000 \n", "2 33.000000 80.000000 124.000000 \n", "3 8.666667 38.666667 83.000000 \n", "4 28.000000 57.000000 151.000000 \n", "... ... ... ... \n", "2404 146.666667 365.333333 957.000000 \n", "2405 46.000000 145.333333 254.166667 \n", "2406 285.000000 939.000000 1506.000000 \n", "2407 144.000000 380.000000 872.000000 \n", "2408 360.000000 775.000000 905.000000 \n", "\n", " gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n", "0 25.000000 28.000000 43.000000 4.000000 \n", "1 25.000000 34.000000 89.000000 3.000000 \n", "2 23.000000 57.000000 87.000000 5.000000 \n", "3 17.666667 17.333333 36.666667 2.000000 \n", "4 14.000000 22.000000 44.000000 3.000000 \n", "... ... ... ... ... \n", "2404 156.166667 238.833333 391.500000 23.333333 \n", "2405 37.333333 51.833333 130.333333 5.500000 \n", "2406 185.000000 286.000000 469.000000 36.000000 \n", "2407 142.000000 302.000000 547.000000 13.000000 \n", "2408 124.000000 284.000000 496.000000 26.000000 \n", "\n", "[2409 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", "db_gk4 = pd.read_excel('mid_outputs/season2223/database_entries_gk.xlsx', index_col = 0) \n", "\n", "db_gk = pd.concat([db_gk1, db_gk2, db_gk3, db_gk4], 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/season2223/players_stats.xlsx', index_col = 3)\n", "players_old_2 = pd.read_excel('mid_outputs/season2122/players_stats.xlsx', index_col = 3)\n", "players_old_3 = 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_6176\\661405348.py:3: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction.\n", " avg_row = pd.DataFrame(index = ['Avg'], data = [team_data.mean()], columns = team_data.columns)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
teamteam_players_usedteam_possessionteam_gamesteam_games_startsteam_minutesteam_goalsteam_assiststeam_pens_madeteam_pens_att...vs_team_foulsvs_team_fouledvs_team_offsidesvs_team_pens_wonvs_team_pens_concededvs_team_own_goalsvs_team_ball_recoveriesvs_team_aerials_wonvs_team_aerials_lostvs_team_aerials_won_pct
AtalantaAtalanta24.050.506.066.0540.011.011.000.000.00...57.0074.04.000.00.000.00347.0097.00109.0047.100
BolognaBologna23.054.706.066.0540.03.02.000.001.00...71.0070.016.000.01.000.00292.0047.0073.0039.200
CagliariCagliari22.038.206.066.0540.02.02.000.000.00...50.0065.011.000.00.000.00332.0092.0071.0056.400
EmpoliEmpoli28.045.306.066.0540.01.01.000.000.00...84.0074.010.001.00.000.00313.0082.0060.0057.700
FiorentinaFiorentina24.057.206.066.0540.012.09.000.000.00...75.0063.08.001.00.000.00311.0096.0075.0056.100
FrosinoneFrosinone24.049.206.066.0540.09.05.002.002.00...73.0054.015.000.02.000.00325.0079.0080.0049.700
GenoaGenoa22.034.306.066.0540.08.07.000.000.00...67.0060.012.000.00.000.00295.0066.0083.0044.300
VeronaHellas Verona22.045.206.066.0540.04.02.000.000.00...84.0084.011.001.00.000.00326.00116.00117.0049.800
InterInter22.053.206.066.0540.015.012.002.002.00...70.0064.09.000.02.000.00248.0046.0077.0037.400
JuventusJuventus22.050.306.066.0540.011.09.001.002.00...80.0071.06.000.02.001.00267.0041.0067.0038.000
LazioLazio20.054.006.066.0540.07.06.001.001.00...69.0067.010.000.01.000.00282.0066.0053.0055.500
LecceLecce22.046.706.066.0540.08.06.002.002.00...88.0078.05.000.02.000.00295.0067.0073.0047.900
MilanMilan23.056.806.066.0540.013.08.003.003.00...80.0060.08.001.03.000.00281.0065.0061.0051.600
MonzaMonza23.054.206.066.0540.04.03.000.000.00...65.0068.011.002.00.000.00281.0074.0056.0056.900
NapoliNapoli20.060.706.066.0540.012.07.002.004.00...73.0060.09.001.04.000.00254.0052.0056.0048.100
RomaRoma23.059.706.066.0540.012.09.001.001.00...58.0067.04.001.01.001.00267.0083.00104.0044.400
SalernitanaSalernitana22.052.306.066.0540.04.03.000.000.00...94.0070.012.000.00.000.00311.00120.0082.0059.400
SassuoloSassuolo25.042.306.066.0540.010.07.001.001.00...63.0055.020.002.01.001.00299.0085.0055.0060.700
TorinoTorino23.049.206.066.0540.06.04.000.000.00...61.0064.07.001.00.000.00302.0093.0082.0053.100
UdineseUdinese24.046.206.066.0540.02.02.000.000.00...65.0074.011.001.00.000.00297.0068.00101.0040.200
AvgAvg22.950.016.066.0540.07.75.750.750.95...71.3567.19.950.60.950.15296.2576.7576.7549.675
\n", "

21 rows × 303 columns

\n", "
" ], "text/plain": [ " team team_players_used team_possession team_games \\\n", "Atalanta Atalanta 24.0 50.50 6.0 \n", "Bologna Bologna 23.0 54.70 6.0 \n", "Cagliari Cagliari 22.0 38.20 6.0 \n", "Empoli Empoli 28.0 45.30 6.0 \n", "Fiorentina Fiorentina 24.0 57.20 6.0 \n", "Frosinone Frosinone 24.0 49.20 6.0 \n", "Genoa Genoa 22.0 34.30 6.0 \n", "Verona Hellas Verona 22.0 45.20 6.0 \n", "Inter Inter 22.0 53.20 6.0 \n", "Juventus Juventus 22.0 50.30 6.0 \n", "Lazio Lazio 20.0 54.00 6.0 \n", "Lecce Lecce 22.0 46.70 6.0 \n", "Milan Milan 23.0 56.80 6.0 \n", "Monza Monza 23.0 54.20 6.0 \n", "Napoli Napoli 20.0 60.70 6.0 \n", "Roma Roma 23.0 59.70 6.0 \n", "Salernitana Salernitana 22.0 52.30 6.0 \n", "Sassuolo Sassuolo 25.0 42.30 6.0 \n", "Torino Torino 23.0 49.20 6.0 \n", "Udinese Udinese 24.0 46.20 6.0 \n", "Avg Avg 22.9 50.01 6.0 \n", "\n", " team_games_starts team_minutes team_goals team_assists \\\n", "Atalanta 66.0 540.0 11.0 11.00 \n", "Bologna 66.0 540.0 3.0 2.00 \n", "Cagliari 66.0 540.0 2.0 2.00 \n", "Empoli 66.0 540.0 1.0 1.00 \n", "Fiorentina 66.0 540.0 12.0 9.00 \n", "Frosinone 66.0 540.0 9.0 5.00 \n", "Genoa 66.0 540.0 8.0 7.00 \n", "Verona 66.0 540.0 4.0 2.00 \n", "Inter 66.0 540.0 15.0 12.00 \n", "Juventus 66.0 540.0 11.0 9.00 \n", "Lazio 66.0 540.0 7.0 6.00 \n", "Lecce 66.0 540.0 8.0 6.00 \n", "Milan 66.0 540.0 13.0 8.00 \n", "Monza 66.0 540.0 4.0 3.00 \n", "Napoli 66.0 540.0 12.0 7.00 \n", "Roma 66.0 540.0 12.0 9.00 \n", "Salernitana 66.0 540.0 4.0 3.00 \n", "Sassuolo 66.0 540.0 10.0 7.00 \n", "Torino 66.0 540.0 6.0 4.00 \n", "Udinese 66.0 540.0 2.0 2.00 \n", "Avg 66.0 540.0 7.7 5.75 \n", "\n", " team_pens_made team_pens_att ... vs_team_fouls \\\n", "Atalanta 0.00 0.00 ... 57.00 \n", "Bologna 0.00 1.00 ... 71.00 \n", "Cagliari 0.00 0.00 ... 50.00 \n", "Empoli 0.00 0.00 ... 84.00 \n", "Fiorentina 0.00 0.00 ... 75.00 \n", "Frosinone 2.00 2.00 ... 73.00 \n", "Genoa 0.00 0.00 ... 67.00 \n", "Verona 0.00 0.00 ... 84.00 \n", "Inter 2.00 2.00 ... 70.00 \n", "Juventus 1.00 2.00 ... 80.00 \n", "Lazio 1.00 1.00 ... 69.00 \n", "Lecce 2.00 2.00 ... 88.00 \n", "Milan 3.00 3.00 ... 80.00 \n", "Monza 0.00 0.00 ... 65.00 \n", "Napoli 2.00 4.00 ... 73.00 \n", "Roma 1.00 1.00 ... 58.00 \n", "Salernitana 0.00 0.00 ... 94.00 \n", "Sassuolo 1.00 1.00 ... 63.00 \n", "Torino 0.00 0.00 ... 61.00 \n", "Udinese 0.00 0.00 ... 65.00 \n", "Avg 0.75 0.95 ... 71.35 \n", "\n", " vs_team_fouled vs_team_offsides vs_team_pens_won \\\n", "Atalanta 74.0 4.00 0.0 \n", "Bologna 70.0 16.00 0.0 \n", "Cagliari 65.0 11.00 0.0 \n", "Empoli 74.0 10.00 1.0 \n", "Fiorentina 63.0 8.00 1.0 \n", "Frosinone 54.0 15.00 0.0 \n", "Genoa 60.0 12.00 0.0 \n", "Verona 84.0 11.00 1.0 \n", "Inter 64.0 9.00 0.0 \n", "Juventus 71.0 6.00 0.0 \n", "Lazio 67.0 10.00 0.0 \n", "Lecce 78.0 5.00 0.0 \n", "Milan 60.0 8.00 1.0 \n", "Monza 68.0 11.00 2.0 \n", "Napoli 60.0 9.00 1.0 \n", "Roma 67.0 4.00 1.0 \n", "Salernitana 70.0 12.00 0.0 \n", "Sassuolo 55.0 20.00 2.0 \n", "Torino 64.0 7.00 1.0 \n", "Udinese 74.0 11.00 1.0 \n", "Avg 67.1 9.95 0.6 \n", "\n", " vs_team_pens_conceded vs_team_own_goals \\\n", "Atalanta 0.00 0.00 \n", "Bologna 1.00 0.00 \n", "Cagliari 0.00 0.00 \n", "Empoli 0.00 0.00 \n", "Fiorentina 0.00 0.00 \n", "Frosinone 2.00 0.00 \n", "Genoa 0.00 0.00 \n", "Verona 0.00 0.00 \n", "Inter 2.00 0.00 \n", "Juventus 2.00 1.00 \n", "Lazio 1.00 0.00 \n", "Lecce 2.00 0.00 \n", "Milan 3.00 0.00 \n", "Monza 0.00 0.00 \n", "Napoli 4.00 0.00 \n", "Roma 1.00 1.00 \n", "Salernitana 0.00 0.00 \n", "Sassuolo 1.00 1.00 \n", "Torino 0.00 0.00 \n", "Udinese 0.00 0.00 \n", "Avg 0.95 0.15 \n", "\n", " vs_team_ball_recoveries vs_team_aerials_won \\\n", "Atalanta 347.00 97.00 \n", "Bologna 292.00 47.00 \n", "Cagliari 332.00 92.00 \n", "Empoli 313.00 82.00 \n", "Fiorentina 311.00 96.00 \n", "Frosinone 325.00 79.00 \n", "Genoa 295.00 66.00 \n", "Verona 326.00 116.00 \n", "Inter 248.00 46.00 \n", "Juventus 267.00 41.00 \n", "Lazio 282.00 66.00 \n", "Lecce 295.00 67.00 \n", "Milan 281.00 65.00 \n", "Monza 281.00 74.00 \n", "Napoli 254.00 52.00 \n", "Roma 267.00 83.00 \n", "Salernitana 311.00 120.00 \n", "Sassuolo 299.00 85.00 \n", "Torino 302.00 93.00 \n", "Udinese 297.00 68.00 \n", "Avg 296.25 76.75 \n", "\n", " vs_team_aerials_lost vs_team_aerials_won_pct \n", "Atalanta 109.00 47.100 \n", "Bologna 73.00 39.200 \n", "Cagliari 71.00 56.400 \n", "Empoli 60.00 57.700 \n", "Fiorentina 75.00 56.100 \n", "Frosinone 80.00 49.700 \n", "Genoa 83.00 44.300 \n", "Verona 117.00 49.800 \n", "Inter 77.00 37.400 \n", "Juventus 67.00 38.000 \n", "Lazio 53.00 55.500 \n", "Lecce 73.00 47.900 \n", "Milan 61.00 51.600 \n", "Monza 56.00 56.900 \n", "Napoli 56.00 48.100 \n", "Roma 104.00 44.400 \n", "Salernitana 82.00 59.400 \n", "Sassuolo 55.00 60.700 \n", "Torino 82.00 53.100 \n", "Udinese 101.00 40.200 \n", "Avg 76.75 49.675 \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": "4e6700ec", "metadata": {}, "source": [ "Load data from previous seasons in other leagues, for new players (rookies) in Serie A" ] }, { "cell_type": "code", "execution_count": 11, "id": "3223cfe3", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Unnamed: 0nationalitypositionteamteam.1agebirth_yeargamesgames_startsminutes...vs_team_pens_concededvs_team_own_goalsleagueseasonsurnameinitialnamevote_avgvote_stdr
player
Kolasinac0ba BIHDFMarseilleMarseille29199333262214...76Ligue-12022-2023KolasinacSSead Kolašinac60.3D
Freuler1ch SUIMFNott'ham ForestNott'ham Forest30199228242161...62Premier-League2022-2023FreulerRRemo Freuler60.3C
Karlsson2se SWEFWAZ AlkmaarAZ Alkmaar24199823211777...33Eredivisie2022-2023KarlssonJJesper Karlsson60.3A
Kristiansen3dk DENDFLeicester CityLeicester City1920021211892...62Premier-League2022-2023KristiansenVVictor Bernth Kristiansen60.3D
Mina4co COLDFEvertonEverton27199477594...22Premier-League2022-2023MinaYYerry Mina60.3D
Monterisi5it ITADFFrosinoneFrosinone202001116615...02Serie-B2022-2023MonterisiIIlario Monterisi60.3D
Pavard6fr FRADFBayern MunichBayern Munich26199630272431...52Bundesliga2022-2023PavardBBenjamin Pavard60.3D
Thuram7fr FRAFWM'GladbachM'Gladbach24199730282513...60Bundesliga2022-2023ThuramMMarcus Thuram60.3A
Klaassen8nl NEDMFAjaxAjax29199333212046...50Eredivisie2022-2023KlaassenDDavy Klaassen60.3C
Sanchez9cl CHIFW,MFMarseilleMarseille33198835322679...76Ligue-12022-2023SanchezAAlexis Sánchez60.3A
Weah10us USADF,FWLilleLille22200029181748...120Ligue-12022-2023WeahTTimothy Weah60.3C
Guendouzi11fr FRAMFMarseilleMarseille23199933252108...76Ligue-12022-2023GuendouziMMattéo Guendouzi60.3C
Kamada12jp JPNMFEint FrankfurtEint Frankfurt25199632252265...62Bundesliga2022-2023KamadaDDaichi Kamada60.3C
Chukwueze13ng NGAFW,MFVillarrealVillarreal23199937272339...72La-Liga2022-2023ChukwuezeSSamuel Chukwueze60.3C
Pulisic14us USAFW,DFChelseaChelsea231998248821...31Premier-League2022-2023PulisicCChristian Pulisic60.3C
Loftus-Cheek15eng ENGMF,DFChelseaChelsea26199625191536...31Premier-League2022-2023Loftus-CheekRRuben Loftus-Cheek60.3C
Lindstrom16dk DENMF,FWEint FrankfurtEint Frankfurt22200027221679...62Bundesliga2022-2023LindstrmJJesper Lindstrøm60.3C
Cajuste17se SWEMFReimsReims22199931141530...80Ligue-12022-2023CajusteJJens Cajuste60.3C
Cheddira18ma MARFWBariBari24199831302495...02Serie-B2022-2023CheddiraWWalid Cheddira60.3A
Lapadula19pe PERFWCagliariCagliari32199036332882...00Serie-B2022-2023LapadulaGGianluca Lapadula60.3A
Kristensen20dk DENDFLeeds UnitedLeeds United25199726211960...33Premier-League2022-2023NissenRRasmus Nissen60.3D
Azmoun21ir IRNFW,MFLeverkusenLeverkusen271995238927...70Bundesliga2022-2023AzmounSSardar Azmoun60.3A
Renato Sanches22pt PORMFParis S-GParis S-G241997236717...73Ligue-12022-2023SanchesRRenato Sanches60.3C
N'dicka23fr FRADFEint FrankfurtEint Frankfurt22199930302692...62Bundesliga2022-2023NDickaOObite N'Dicka60.3D
Aouar24dz ALGMFLyonLyon241998166526...82Ligue-12022-2023AouarHHoussem Aouar60.3C
Pedersen25no NORDFFeyenoordFeyenoord22200029252117...34Eredivisie2022-2023PedersenMMarcus Pedersen60.3D
Castillejo26es ESPFW,MFValenciaValencia27199525171362...82La-Liga2022-2023CastillejoSSamu Castillejo60.3C
Lucca27it ITAFW,MFAjaxAjax212000140150...50Eredivisie2022-2023LuccaLLorenzo Lucca60.3A
Folorunsho28ng NGAMF,FWBariBari24199827251995...02Serie-B2022-2023FolorunshoMMichael Folorunsho60.3C
Gudmundsson A.29is ISLMF,FWGenoaGenoa25199736322696...00Serie-B2022-2023GumundssonAAlbert Guðmundsson60.3C
Bakker30nl NEDDF,MFLeverkusenLeverkusen22200028191659...70Bundesliga2022-2023BakkerMMitchel Bakker60.3D
Martin31es ESPDFMainz 05Mainz 0525199728201847...60Bundesliga2022-2023MartinAAarón Martín60.3D
Dragusin32ro ROUDFGenoaGenoa20200238373375...00Serie-B2022-2023DragusinRRadu Drăgușin60.3D
Viti33it ITADFNiceNice20200297634...61Ligue-12022-2023VitiMMattia Viti60.3D
Beukema34nl NEDDFAZ AlkmaarAZ Alkmaar23199826242198...33Eredivisie2022-2023BeukemaSSam Beukema60.3D
Reijnders35nl NEDMFAZ AlkmaarAZ Alkmaar24199834343046...33Eredivisie2022-2023ReijndersTTijjani Reijnders60.3C
Luvumbo36ao ANGFW,MFCagliariCagliari20200236151560...00Serie-B2022-2023ZitoZZito60.3A
Retegui37it ITAFWTigreTigre23199921201790...01Primera-Division2022-2023ReteguiMMateo Retegui60.3A
Fabbian38it ITAMFUS RegginaUS Reggina19200336342827...03Serie-B2022-2023FabbianGGiovanni Fabbian60.3C
Beltran L.39ar ARGFWRiver PlateRiver Plate21200125161371...01Primera-Division2022-2023BeltranLLucas Beltrán60.3A
Azzi40br BRADF,MFCagliariCagliari28199416131144...00Serie-B2022-2023AzziPPaulo Azzi60.3D
Nandez41uy URUMF,FWCagliariCagliari26199533302539...00Serie-B2022-2023NandezNNahitan Nández60.3C
Pavoletti42it ITAFW,MFCagliariCagliari3319882310989...00Serie-B2022-2023PavolettiLLeonardo Pavoletti60.3A
Makoumbou43cg CGOMFCagliariCagliari24199836332981...00Serie-B2022-2023MakoumbouAAntoine Makoumbou60.3C
Dossena44it ITADFCagliariCagliari23199823191703...00Serie-B2022-2023DossenaAAlberto Dossena60.3C
Strootman45nl NEDMFGenoaGenoa32199030252229...00Serie-B2022-2023StrootmanKKevin Strootman60.3C
Bani46it ITADFGenoaGenoa28199333312551...00Serie-B2022-2023BaniMMattia Bani60.3D
Frendrup47dk DENMFGenoaGenoa21200137322921...00Serie-B2022-2023FrendrupMMorten Frendrup60.3C
Sabelli48it ITADF,MFGenoaGenoa29199330292514...00Serie-B2022-2023SabelliSStefano Sabelli60.3D
Caso49it ITAFW,MFFrosinoneFrosinone23199835231890...02Serie-B2022-2023CasoGGiuseppe Caso60.3A
Baez50uy URUFWFrosinoneFrosinone271995175667...02Serie-B2022-2023BaezJJaime Báez60.3C
Mulattieri51it ITAFWFrosinoneFrosinone21200029151502...02Serie-B2022-2023MulattieriSSamuele Mulattieri60.3A
\n", "

52 rows × 384 columns

\n", "
" ], "text/plain": [ " Unnamed: 0 nationality position team \\\n", "player \n", "Kolasinac 0 ba BIH DF Marseille \n", "Freuler 1 ch SUI MF Nott'ham Forest \n", "Karlsson 2 se SWE FW AZ Alkmaar \n", "Kristiansen 3 dk DEN DF Leicester City \n", "Mina 4 co COL DF Everton \n", "Monterisi 5 it ITA DF Frosinone \n", "Pavard 6 fr FRA DF Bayern Munich \n", "Thuram 7 fr FRA FW M'Gladbach \n", "Klaassen 8 nl NED MF Ajax \n", "Sanchez 9 cl CHI FW,MF Marseille \n", "Weah 10 us USA DF,FW Lille \n", "Guendouzi 11 fr FRA MF Marseille \n", "Kamada 12 jp JPN MF Eint Frankfurt \n", "Chukwueze 13 ng NGA FW,MF Villarreal \n", "Pulisic 14 us USA FW,DF Chelsea \n", "Loftus-Cheek 15 eng ENG MF,DF Chelsea \n", "Lindstrom 16 dk DEN MF,FW Eint Frankfurt \n", "Cajuste 17 se SWE MF Reims \n", "Cheddira 18 ma MAR FW Bari \n", "Lapadula 19 pe PER FW Cagliari \n", "Kristensen 20 dk DEN DF Leeds United \n", "Azmoun 21 ir IRN FW,MF Leverkusen \n", "Renato Sanches 22 pt POR MF Paris S-G \n", "N'dicka 23 fr FRA DF Eint Frankfurt \n", "Aouar 24 dz ALG MF Lyon \n", "Pedersen 25 no NOR DF Feyenoord \n", "Castillejo 26 es ESP FW,MF Valencia \n", "Lucca 27 it ITA FW,MF Ajax \n", "Folorunsho 28 ng NGA MF,FW Bari \n", "Gudmundsson A. 29 is ISL MF,FW Genoa \n", "Bakker 30 nl NED DF,MF Leverkusen \n", "Martin 31 es ESP DF Mainz 05 \n", "Dragusin 32 ro ROU DF Genoa \n", "Viti 33 it ITA DF Nice \n", "Beukema 34 nl NED DF AZ Alkmaar \n", "Reijnders 35 nl NED MF AZ Alkmaar \n", "Luvumbo 36 ao ANG FW,MF Cagliari \n", "Retegui 37 it ITA FW Tigre \n", "Fabbian 38 it ITA MF US Reggina \n", "Beltran L. 39 ar ARG FW River Plate \n", "Azzi 40 br BRA DF,MF Cagliari \n", "Nandez 41 uy URU MF,FW Cagliari \n", "Pavoletti 42 it ITA FW,MF Cagliari \n", "Makoumbou 43 cg CGO MF Cagliari \n", "Dossena 44 it ITA DF Cagliari \n", "Strootman 45 nl NED MF Genoa \n", "Bani 46 it ITA DF Genoa \n", "Frendrup 47 dk DEN MF Genoa \n", "Sabelli 48 it ITA DF,MF Genoa \n", "Caso 49 it ITA FW,MF Frosinone \n", "Baez 50 uy URU FW Frosinone \n", "Mulattieri 51 it ITA FW Frosinone \n", "\n", " team.1 age birth_year games games_starts \\\n", "player \n", "Kolasinac Marseille 29 1993 33 26 \n", "Freuler Nott'ham Forest 30 1992 28 24 \n", "Karlsson AZ Alkmaar 24 1998 23 21 \n", "Kristiansen Leicester City 19 2002 12 11 \n", "Mina Everton 27 1994 7 7 \n", "Monterisi Frosinone 20 2001 11 6 \n", "Pavard Bayern Munich 26 1996 30 27 \n", "Thuram M'Gladbach 24 1997 30 28 \n", "Klaassen Ajax 29 1993 33 21 \n", "Sanchez Marseille 33 1988 35 32 \n", "Weah Lille 22 2000 29 18 \n", "Guendouzi Marseille 23 1999 33 25 \n", "Kamada Eint Frankfurt 25 1996 32 25 \n", "Chukwueze Villarreal 23 1999 37 27 \n", "Pulisic Chelsea 23 1998 24 8 \n", "Loftus-Cheek Chelsea 26 1996 25 19 \n", "Lindstrom Eint Frankfurt 22 2000 27 22 \n", "Cajuste Reims 22 1999 31 14 \n", "Cheddira Bari 24 1998 31 30 \n", "Lapadula Cagliari 32 1990 36 33 \n", "Kristensen Leeds United 25 1997 26 21 \n", "Azmoun Leverkusen 27 1995 23 8 \n", "Renato Sanches Paris S-G 24 1997 23 6 \n", "N'dicka Eint Frankfurt 22 1999 30 30 \n", "Aouar Lyon 24 1998 16 6 \n", "Pedersen Feyenoord 22 2000 29 25 \n", "Castillejo Valencia 27 1995 25 17 \n", "Lucca Ajax 21 2000 14 0 \n", "Folorunsho Bari 24 1998 27 25 \n", "Gudmundsson A. Genoa 25 1997 36 32 \n", "Bakker Leverkusen 22 2000 28 19 \n", "Martin Mainz 05 25 1997 28 20 \n", "Dragusin Genoa 20 2002 38 37 \n", "Viti Nice 20 2002 9 7 \n", "Beukema AZ Alkmaar 23 1998 26 24 \n", "Reijnders AZ Alkmaar 24 1998 34 34 \n", "Luvumbo Cagliari 20 2002 36 15 \n", "Retegui Tigre 23 1999 21 20 \n", "Fabbian US Reggina 19 2003 36 34 \n", "Beltran L. River Plate 21 2001 25 16 \n", "Azzi Cagliari 28 1994 16 13 \n", "Nandez Cagliari 26 1995 33 30 \n", "Pavoletti Cagliari 33 1988 23 10 \n", "Makoumbou Cagliari 24 1998 36 33 \n", "Dossena Cagliari 23 1998 23 19 \n", "Strootman Genoa 32 1990 30 25 \n", "Bani Genoa 28 1993 33 31 \n", "Frendrup Genoa 21 2001 37 32 \n", "Sabelli Genoa 29 1993 30 29 \n", "Caso Frosinone 23 1998 35 23 \n", "Baez Frosinone 27 1995 17 5 \n", "Mulattieri Frosinone 21 2000 29 15 \n", "\n", " minutes ... vs_team_pens_conceded vs_team_own_goals \\\n", "player ... \n", "Kolasinac 2214 ... 7 6 \n", "Freuler 2161 ... 6 2 \n", "Karlsson 1777 ... 3 3 \n", "Kristiansen 892 ... 6 2 \n", "Mina 594 ... 2 2 \n", "Monterisi 615 ... 0 2 \n", "Pavard 2431 ... 5 2 \n", "Thuram 2513 ... 6 0 \n", "Klaassen 2046 ... 5 0 \n", "Sanchez 2679 ... 7 6 \n", "Weah 1748 ... 12 0 \n", "Guendouzi 2108 ... 7 6 \n", "Kamada 2265 ... 6 2 \n", "Chukwueze 2339 ... 7 2 \n", "Pulisic 821 ... 3 1 \n", "Loftus-Cheek 1536 ... 3 1 \n", "Lindstrom 1679 ... 6 2 \n", "Cajuste 1530 ... 8 0 \n", "Cheddira 2495 ... 0 2 \n", "Lapadula 2882 ... 0 0 \n", "Kristensen 1960 ... 3 3 \n", "Azmoun 927 ... 7 0 \n", "Renato Sanches 717 ... 7 3 \n", "N'dicka 2692 ... 6 2 \n", "Aouar 526 ... 8 2 \n", "Pedersen 2117 ... 3 4 \n", "Castillejo 1362 ... 8 2 \n", "Lucca 150 ... 5 0 \n", "Folorunsho 1995 ... 0 2 \n", "Gudmundsson A. 2696 ... 0 0 \n", "Bakker 1659 ... 7 0 \n", "Martin 1847 ... 6 0 \n", "Dragusin 3375 ... 0 0 \n", "Viti 634 ... 6 1 \n", "Beukema 2198 ... 3 3 \n", "Reijnders 3046 ... 3 3 \n", "Luvumbo 1560 ... 0 0 \n", "Retegui 1790 ... 0 1 \n", "Fabbian 2827 ... 0 3 \n", "Beltran L. 1371 ... 0 1 \n", "Azzi 1144 ... 0 0 \n", "Nandez 2539 ... 0 0 \n", "Pavoletti 989 ... 0 0 \n", "Makoumbou 2981 ... 0 0 \n", "Dossena 1703 ... 0 0 \n", "Strootman 2229 ... 0 0 \n", "Bani 2551 ... 0 0 \n", "Frendrup 2921 ... 0 0 \n", "Sabelli 2514 ... 0 0 \n", "Caso 1890 ... 0 2 \n", "Baez 667 ... 0 2 \n", "Mulattieri 1502 ... 0 2 \n", "\n", " league season surname initial \\\n", "player \n", "Kolasinac Ligue-1 2022-2023 Kolasinac S \n", "Freuler Premier-League 2022-2023 Freuler R \n", "Karlsson Eredivisie 2022-2023 Karlsson J \n", "Kristiansen Premier-League 2022-2023 Kristiansen V \n", "Mina Premier-League 2022-2023 Mina Y \n", "Monterisi Serie-B 2022-2023 Monterisi I \n", "Pavard Bundesliga 2022-2023 Pavard B \n", "Thuram Bundesliga 2022-2023 Thuram M \n", "Klaassen Eredivisie 2022-2023 Klaassen D \n", "Sanchez Ligue-1 2022-2023 Sanchez A \n", "Weah Ligue-1 2022-2023 Weah T \n", "Guendouzi Ligue-1 2022-2023 Guendouzi M \n", "Kamada Bundesliga 2022-2023 Kamada D \n", "Chukwueze La-Liga 2022-2023 Chukwueze S \n", "Pulisic Premier-League 2022-2023 Pulisic C \n", "Loftus-Cheek Premier-League 2022-2023 Loftus-Cheek R \n", "Lindstrom Bundesliga 2022-2023 Lindstrm J \n", "Cajuste Ligue-1 2022-2023 Cajuste J \n", "Cheddira Serie-B 2022-2023 Cheddira W \n", "Lapadula Serie-B 2022-2023 Lapadula G \n", "Kristensen Premier-League 2022-2023 Nissen R \n", "Azmoun Bundesliga 2022-2023 Azmoun S \n", "Renato Sanches Ligue-1 2022-2023 Sanches R \n", "N'dicka Bundesliga 2022-2023 NDicka O \n", "Aouar Ligue-1 2022-2023 Aouar H \n", "Pedersen Eredivisie 2022-2023 Pedersen M \n", "Castillejo La-Liga 2022-2023 Castillejo S \n", "Lucca Eredivisie 2022-2023 Lucca L \n", "Folorunsho Serie-B 2022-2023 Folorunsho M \n", "Gudmundsson A. Serie-B 2022-2023 Gumundsson A \n", "Bakker Bundesliga 2022-2023 Bakker M \n", "Martin Bundesliga 2022-2023 Martin A \n", "Dragusin Serie-B 2022-2023 Dragusin R \n", "Viti Ligue-1 2022-2023 Viti M \n", "Beukema Eredivisie 2022-2023 Beukema S \n", "Reijnders Eredivisie 2022-2023 Reijnders T \n", "Luvumbo Serie-B 2022-2023 Zito Z \n", "Retegui Primera-Division 2022-2023 Retegui M \n", "Fabbian Serie-B 2022-2023 Fabbian G \n", "Beltran L. Primera-Division 2022-2023 Beltran L \n", "Azzi Serie-B 2022-2023 Azzi P \n", "Nandez Serie-B 2022-2023 Nandez N \n", "Pavoletti Serie-B 2022-2023 Pavoletti L \n", "Makoumbou Serie-B 2022-2023 Makoumbou A \n", "Dossena Serie-B 2022-2023 Dossena A \n", "Strootman Serie-B 2022-2023 Strootman K \n", "Bani Serie-B 2022-2023 Bani M \n", "Frendrup Serie-B 2022-2023 Frendrup M \n", "Sabelli Serie-B 2022-2023 Sabelli S \n", "Caso Serie-B 2022-2023 Caso G \n", "Baez Serie-B 2022-2023 Baez J \n", "Mulattieri Serie-B 2022-2023 Mulattieri S \n", "\n", " name vote_avg vote_std r \n", "player \n", "Kolasinac Sead Kolašinac 6 0.3 D \n", "Freuler Remo Freuler 6 0.3 C \n", "Karlsson Jesper Karlsson 6 0.3 A \n", "Kristiansen Victor Bernth Kristiansen 6 0.3 D \n", "Mina Yerry Mina 6 0.3 D \n", "Monterisi Ilario Monterisi 6 0.3 D \n", "Pavard Benjamin Pavard 6 0.3 D \n", "Thuram Marcus Thuram 6 0.3 A \n", "Klaassen Davy Klaassen 6 0.3 C \n", "Sanchez Alexis Sánchez 6 0.3 A \n", "Weah Timothy Weah 6 0.3 C \n", "Guendouzi Mattéo Guendouzi 6 0.3 C \n", "Kamada Daichi Kamada 6 0.3 C \n", "Chukwueze Samuel Chukwueze 6 0.3 C \n", "Pulisic Christian Pulisic 6 0.3 C \n", "Loftus-Cheek Ruben Loftus-Cheek 6 0.3 C \n", "Lindstrom Jesper Lindstrøm 6 0.3 C \n", "Cajuste Jens Cajuste 6 0.3 C \n", "Cheddira Walid Cheddira 6 0.3 A \n", "Lapadula Gianluca Lapadula 6 0.3 A \n", "Kristensen Rasmus Nissen 6 0.3 D \n", "Azmoun Sardar Azmoun 6 0.3 A \n", "Renato Sanches Renato Sanches 6 0.3 C \n", "N'dicka Obite N'Dicka 6 0.3 D \n", "Aouar Houssem Aouar 6 0.3 C \n", "Pedersen Marcus Pedersen 6 0.3 D \n", "Castillejo Samu Castillejo 6 0.3 C \n", "Lucca Lorenzo Lucca 6 0.3 A \n", "Folorunsho Michael Folorunsho 6 0.3 C \n", "Gudmundsson A. Albert Guðmundsson 6 0.3 C \n", "Bakker Mitchel Bakker 6 0.3 D \n", "Martin Aarón Martín 6 0.3 D \n", "Dragusin Radu Drăgușin 6 0.3 D \n", "Viti Mattia Viti 6 0.3 D \n", "Beukema Sam Beukema 6 0.3 D \n", "Reijnders Tijjani Reijnders 6 0.3 C \n", "Luvumbo Zito 6 0.3 A \n", "Retegui Mateo Retegui 6 0.3 A \n", "Fabbian Giovanni Fabbian 6 0.3 C \n", "Beltran L. Lucas Beltrán 6 0.3 A \n", "Azzi Paulo Azzi 6 0.3 D \n", "Nandez Nahitan Nández 6 0.3 C \n", "Pavoletti Leonardo Pavoletti 6 0.3 A \n", "Makoumbou Antoine Makoumbou 6 0.3 C \n", "Dossena Alberto Dossena 6 0.3 C \n", "Strootman Kevin Strootman 6 0.3 C \n", "Bani Mattia Bani 6 0.3 D \n", "Frendrup Morten Frendrup 6 0.3 C \n", "Sabelli Stefano Sabelli 6 0.3 D \n", "Caso Giuseppe Caso 6 0.3 A \n", "Baez Jaime Báez 6 0.3 C \n", "Mulattieri Samuele Mulattieri 6 0.3 A \n", "\n", "[52 rows x 384 columns]" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rookies_data = pd.read_excel('rookies_stats/out_data/rookies_stats.xlsx', index_col = 1)\n", "\n", "rookies_data" ] }, { "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": 12, "id": "6f8707b8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " \n", "Averaging players stats with past seasons:\n", "Szczesny 0.8351648351648353\n", "Meret 1\n", "Provedel 0.9230769230769229\n", "Maignan 1\n", "Rui Patricio 1\n", "Skorupski 0.9480249480249479\n", "Milinkovic-Savic V. 0.9230769230769229\n", "Di Gregorio 0.79002079002079\n", "Falcone 0.9230769230769229\n", "Silvestri 0.9230769230769229\n", "Terracciano 0.8063660477453581\n", "Carnesecchi 0.6062678062678064\n", "Montipo' 0.9480249480249479\n", "Ochoa 1\n", "Consigli 0.6681318681318682\n", "Musso 0.9743589743589745\n", "Cragno 1\n", "Perin 1\n", "Berisha 1\n", "Sportiello 1\n", "Mirante 1\n", "Sepe 1\n", "Lamanna 1\n", "Pegolo 1\n", "Perilli 1\n", "Padelli 1\n", "Gollini 1\n", "Perisan 1\n", "Audero 1\n", "Pinsoglio 1\n", "Fiorillo 1\n", "Cerofolini 1\n", "Rossi F. 1\n", "Ravaglia F. 1\n", "Brancolini 1\n", "Berardi A. 1\n", "Gemello 1\n", "Boer 1\n", "Bagnolini 1\n", "Svilar 1\n", "Sorrentino A. 1\n", "Dimarco 0.5314685314685313\n", "Di Lorenzo 0.47401247401247393\n", "Hernandez T. 0.4567307692307692\n", "Carlos Augusto 0.5261538461538462\n", "Danilo 0.47401247401247393\n", "Zappacosta 0.6959706959706958\n", "Schuurs 0.5846153846153845\n", "Posch 0.4871794871794871\n", "Bastoni 0.6047745358090184\n", "Smalling 0.2740384615384615\n", "Dumfries 0.42986425339366513\n", "Romagnoli 0.5158371040723981\n", "Pavard 0.10230769230769231 (rookie)\n", "Rrahmani 0.3023872679045092\n", "Spinazzola 0.6745562130177514\n", "Buongiorno 0.5158371040723981\n", "Bremer 0.5846153846153845\n", "Tomori 0.4428904428904428\n", "Biraghi 0.4428904428904428\n", "Mancini 0.501098901098901\n", "Darmian 0.5657568238213398\n", "Bakker 0.21923076923076926 (rookie)\n", "Mazzocchi 0.6495726495726495\n", "Doig 0.5314685314685315\n", "Calabria 0.4676923076923077\n", "Acerbi 0.2828784119106699\n", "Cuadrado 0.29702233250620347\n", "Ebuehi 0.44970414201183434\n", "Casale 0.40318302387267907\n", "Holm 0.4603846153846154\n", "Baschirotto 0.395010395010395\n", "Bijol 0.548076923076923\n", "Thiaw 0.8769230769230768\n", "Mario Rui 0.6643356643356643\n", "Milenkovic 0.6495726495726495\n", "Rodriguez R. 0.501098901098901\n", "Kolasinac 0.558041958041958 (rookie)\n", "N'dicka 0.3069230769230769 (rookie)\n", "Scalvini 0.548076923076923\n", "Perez N. 0.5158371040723981\n", "Kristensen 0.0 (rookie)\n", "Izzo 0.4871794871794871\n", "De Vrij 0.6495726495726495\n", "Faraoni 0.6354515050167223\n", "Toloi 0.2740384615384615\n", "Kyriakopoulos 1\n", "Kyriakopoulos 0.423342175066313 (two seasons ago)\n", "Bellanova 1\n", "Mari' 0.5846153846153845\n", "Dodo' 0.4428904428904428\n", "Lucumi' 0.4428904428904428\n", "Hien 0.3653846153846154\n", "Hysaj 0.3438914027149321\n", "D'ambrosio 0.6138461538461538\n", "Luperto 0.4871794871794871\n", "Djimsiti 0.6089743589743589\n", "Marusic 0.5314685314685313\n", "Martin 0.5480769230769231 (rookie)\n", "Mina 0.0 (rookie)\n", "Toljan 0.5657568238213398\n", "Llorente D. 1\n", "Martinez Quarta 0.4330484330484331\n", "Bastoni S. 0.16153846153846155\n", "Dragusin 0.4846153846153846 (rookie)\n", "Parisi 0.279020979020979\n", "Bradaric 0.5657568238213398\n", "Olivera 0.4871794871794871\n", "Gendrey 0.47401247401247393\n", "Kristiansen 1 (rookie)\n", "Beukema 0.7082840236686391 (rookie)\n", "Dossena 0.8006688963210702 (rookie)\n", "Pedersen 0.5291777188328912 (rookie)\n", "Juan Jesus 0.7794871794871795\n", "Gyomber 0.6495726495726495\n", "Alex Sandro 0.23384615384615384\n", "Hateboer 0.17194570135746606\n", "Palomino 0.38974358974358975\n", "Marchizza 1\n", "Gallo 0.4567307692307692\n", "Caldirola 0.4714640198511166\n", "Kalulu 0.17194570135746606\n", "Erlic 0.6263736263736263\n", "Vojvoda 0.3023872679045092\n", "Vasquez 0.7366153846153846\n", "Cambiaso 0.4795673076923077\n", "Pongracic 1\n", "Viti 1 (rookie)\n", "Viti 0.4603846153846154 (two seasons ago)\n", "Gatti 0.6495726495726496\n", "Birindelli 0.5657568238213398\n", "Azzi 0.9591346153846154 (rookie)\n", "Masina 0.0\n", "Romagnoli S. 1\n", "Pezzella Giu. 1\n", "Sabelli 0.5115384615384615 (rookie)\n", "Lazzari 0.31318681318681313\n", "Bani 0.558041958041958 (rookie)\n", "Djidji 0.0\n", "Lazaro 0.6354515050167223\n", "Augello 0.41476091476091476\n", "Zortea 0.9207692307692308\n", "Zortea 0.3762046521118139 (two seasons ago)\n", "Dawidowicz 0.7625418060200667\n", "Pirola 0.5621301775147929\n", "Lovato 1\n", "Ruggeri 1\n", "Obert 1 (two seasons ago)\n", "Terracciano F. 0.8769230769230768\n", "Ebosele 1\n", "Patric 0.3247863247863248\n", "Lykogiannis 0.4175824175824175\n", "Pellegrini Lu. 1\n", "Pellegrini Lu. 0.8525641025641026 (two seasons ago)\n", "Magnani 0.7307692307692307\n", "Ranieri L. 0.9743589743589742\n", "Ranieri L. 0.35851413543721244 (two seasons ago)\n", "Calafiori 1 (two seasons ago)\n", "Monterisi 1 (rookie)\n", "Ismajli 0.4676923076923077\n", "De Winter 0.6576923076923077\n", "Ehizibue 0.0\n", "Ferrari G. 0.17715617715617715\n", "Venuti 0.18054298642533936\n", "Karsdorp 0.44970414201183434\n", "Kjaer 0.6877828054298643\n", "Gunter 0.0\n", "Soumaoro 0.0\n", "Zanoli 0.0\n", "Zima 0.3247863247863248\n", "Hefti 0.7307692307692308 (two seasons ago)\n", "Ostigard 1\n", "Ostigard 1 (two seasons ago)\n", "Sambia 0.13286713286713286\n", "Rugani 0.3247863247863248\n", "De Sciglio 0.0\n", "Goldaniga 0.26573426573426573 (two seasons ago)\n", "Florenzi 1\n", "Florenzi 0.4871794871794872 (two seasons ago)\n", "De Silvestri 0.7794871794871795\n", "Fazio 0.41758241758241765\n", "Bereszynski 1\n", "Bereszynski 0.2630769230769231 (two seasons ago)\n", "Bonifazi 0.0\n", "Walukiewicz 1\n", "Walukiewicz 1 (two seasons ago)\n", "Okoli 0.5416289592760181\n", "Kumbulla 0.0\n", "Celik 0.1217948717948718\n", "Amione 0.11804733727810651\n", "Daniliuc 0.21652421652421655\n", "Soppy 0.40923076923076923\n", "Haps 0.0 (two seasons ago)\n", "Coppola D. 0.3076923076923077\n", "Cacace 0.7307692307692307\n", "Cacace 1 (two seasons ago)\n", "Ebosse 0.14615384615384616\n", "Guessand A. 1\n", "Cabal 0.7972027972027971\n", "Dermaku 0.0\n", "Tonelli 0.0\n", "Tonelli 0.20879120879120883 (two seasons ago)\n", "Amey 0.0\n", "Gila 0.0\n", "Bronn 0.0\n", "Guarino 0.0\n", "Carboni F. 1\n", "Zaccagni 0.501098901098901\n", "Koopmeiners 0.5314685314685313\n", "Luis Alberto 0.501098901098901\n", "Felipe Anderson 0.46153846153846145\n", "Rabiot 0.548076923076923\n", "Zielinski 0.47401247401247393\n", "Barella 0.501098901098901\n", "Pulisic 0.7673076923076924 (rookie)\n", "Orsolini 0.548076923076923\n", "Calhanoglu 0.5314685314685313\n", "Strefezza 0.501098901098901\n", "Chukwueze 0.41476091476091476 (rookie)\n", "Ferguson 0.548076923076923\n", "Candreva 0.501098901098901\n", "Frattesi 0.5115384615384616\n", "Samardzic 0.47401247401247393\n", "Vlasic 0.42986425339366513\n", "Bonaventura 0.5846153846153845\n", "Politano 0.6495726495726495\n", "El Shaarawy 0.6047745358090184\n", "Mkhitaryan 0.5657568238213398\n", "Aouar 0.7673076923076924 (rookie)\n", "Malinovskyi 0.40923076923076923 (two seasons ago)\n", "Gudmundsson A. 0.5115384615384616 (rookie)\n", "Kamada 0.3836538461538462 (rookie)\n", "Pellegrini Lo. 0.2740384615384615\n", "Kostic 0.316008316008316\n", "Radonjic 0.6263736263736263\n", "Baldanzi 0.6745562130177514\n", "Lovric 0.47401247401247393\n", "Lindstrom 0.0 (rookie)\n", "Lazovic 0.29230769230769227\n", "Pereyra 0.25791855203619907\n", "Renato Sanches 0.26688963210702343 (rookie)\n", "Pessina 0.501098901098901\n", "Guendouzi 0.37202797202797205 (rookie)\n", "Loftus-Cheek 0.7366153846153846 (rookie)\n", "Zambo Anguissa 0.4871794871794871\n", "Elmas 0.405982905982906\n", "Bajrami 0.9743589743589742\n", "Ricci S. 0.521978021978022\n", "Colpani 0.6495726495726495\n", "Ciurria 0.4871794871794871\n", "De Roon 0.501098901098901\n", "Pogba 0.9743589743589745\n", "Cristante 0.4871794871794871\n", "Locatelli 0.548076923076923\n", "Pasalic 0.3653846153846154\n", "Lobotka 0.46153846153846145\n", "Fagioli 0.5621301775147929\n", "Ikone' 0.08857808857808858\n", "Ilic 1\n", "Ilic 0.4795673076923077 (two seasons ago)\n", "Ederson D.s. 0.501098901098901\n", "Reijnders 0.5416289592760181 (rookie)\n", "Barak 0.19487179487179487\n", "Saponara 0.423342175066313\n", "Mandragora 0.6047745358090184\n", "Weah 0.6350132625994694 (rookie)\n", "Bennacer 0.0\n", "Duda 1\n", "Castrovilli 0.0\n", "Miranchuk 0.2116710875331565\n", "Matheus Henrique 0.5846153846153845\n", "De Ketelaere 0.5754807692307693\n", "Paredes 0.7366153846153846\n", "Sottil 0.6495726495726496\n", "Klaassen 0.09300699300699301 (rookie)\n", "Thorsby 0.43846153846153846 (two seasons ago)\n", "Nandez 0.558041958041958 (rookie)\n", "Tameze 0.3318087318087318\n", "Marin 0.4428904428904428\n", "Messias 0.12276923076923077\n", "Coulibaly L. 0.08351648351648353\n", "Krunic 0.6354515050167223\n", "Cataldi 0.5039787798408487\n", "Strootman 0.5115384615384615 (rookie)\n", "Duncan 0.5846153846153845\n", "Freuler 0.21923076923076926 (rookie)\n", "Gagliardini 0.9692307692307692\n", "Kastanos 0.6263736263736263\n", "Gyasi 0.3507692307692308\n", "Zalewski 0.3543123543123543\n", "Harroui 0.4003344481605351\n", "Frendrup 0.4977130977130977 (rookie)\n", "Blin 0.501098901098901\n", "Fabbian 0.2557692307692308 (rookie)\n", "Vecino 0.3653846153846154\n", "Sensi 0.10961538461538463\n", "Walace 0.47401247401247393\n", "Lopez M. 0.10230769230769231\n", "Bove 0.5314685314685315\n", "Aebischer 0.548076923076923\n", "Thorstvedt 0.3771712158808933\n", "Gonzalez J. 0.2505494505494505\n", "Moro N. 0.44970414201183434\n", "Oudin 0.18858560794044665\n", "Makoumbou 0.5115384615384616 (rookie)\n", "Machin 0.0\n", "Linetty 0.3653846153846154\n", "Castillejo 0.3683076923076923 (rookie)\n", "Rovella 0.3683076923076923\n", "Pobega 0.6153846153846154\n", "Miretti 0.5413105413105412\n", "Fazzini 0.6959706959706958\n", "Grassi 0.5846153846153845\n", "Baez 1 (rookie)\n", "Bourabia 0.1659043659043659\n", "Saelemaekers 0.20461538461538462\n", "Maldini 0.0\n", "Kovalenko 0.17051282051282055\n", "Maleh 0.7221719457013575\n", "Bohinen 0.6089743589743589\n", "Ranocchia F. 0.21923076923076926\n", "Folorunsho 0.6820512820512821 (rookie)\n", "Adopo 1\n", "Romero L. 0.5115384615384616\n", "Romero L. 1 (two seasons ago)\n", "Basic 0.0\n", "Asllani 0.2923076923076923\n", "Sulemana I. 0.9591346153846154\n", "Gaetano 0.0\n", "Obiang 0.0\n", "Maggiore 0.548076923076923\n", "Akpa Akpro 0.0\n", "Akpa Akpro 0.0 (two seasons ago)\n", "Urbanski 1\n", "Volpato 0.4384615384615385\n", "Volpato 1 (two seasons ago)\n", "Vignato S. 1\n", "Hrustic 0.0\n", "Viola 1 (two seasons ago)\n", "Rog 0.0 (two seasons ago)\n", "Nicolussi Caviglia 0.0\n", "Demme 0.0\n", "Pafundi 0.3653846153846154\n", "Adli 0.4871794871794872\n", "Zerbin 0.2923076923076923\n", "Carboni V. 1\n", "Faticanti 0.0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Osimhen 0.548076923076923\n", "Martinez L. 0.46153846153846145\n", "Rafael Leao 0.501098901098901\n", "Lukaku 0.4910769230769231\n", "Berardi 0.44970414201183434\n", "Immobile 0.5657568238213398\n", "Vlahovic 0.6495726495726495\n", "Dybala 0.4676923076923077\n", "Kvaratskhelia 0.42986425339366513\n", "Giroud 0.4428904428904428\n", "Scamacca 0.3410256410256411 (two seasons ago)\n", "Thuram 0.6138461538461538 (rookie)\n", "Lookman 0.5657568238213398\n", "Dia 0.2657342657342657\n", "Arnautovic 0.7307692307692307\n", "Retegui 0.8769230769230768 (rookie)\n", "Sanabria 0.3543123543123543\n", "Nzola 0.5940446650124069\n", "Lauriente' 0.6263736263736263\n", "Zapata D. 0.4910769230769231\n", "Chiesa 0.835164835164835\n", "Milik 0.6495726495726495\n", "Gonzalez N. 0.6089743589743589\n", "Pinamonti 0.548076923076923\n", "Beltran L. 0.7366153846153846 (rookie)\n", "Caprari 0.316008316008316\n", "Sanchez 0.1753846153846154 (rookie)\n", "Caputo 0.5567765567765568\n", "Belotti 0.5657568238213398\n", "Muriel 0.3023872679045092\n", "Lapadula 0.0 (rookie)\n", "Jovic 0.198014888337469\n", "Abraham 0.0\n", "Zirkzee 0.9230769230769229\n", "Ngonge 1\n", "Petagna 0.29702233250620347\n", "Simeone 0.5846153846153845\n", "Deulofeu 0.0\n", "Pedro 0.3247863247863248\n", "Shomurodov 1\n", "Azmoun 0.26688963210702343 (rookie)\n", "Cheddira 0.49503722084367247 (rookie)\n", "Karlsson 0.6672240802675585 (rookie)\n", "Brekalo 1\n", "Brekalo 0.4795673076923077 (two seasons ago)\n", "Cambiaghi 0.521978021978022\n", "Henry 0.1826923076923077\n", "Mulattieri 0.423342175066313 (rookie)\n", "Kean 0.31318681318681313\n", "Karamoh 0.5567765567765568\n", "Thauvin 1\n", "Kouame' 0.41758241758241765\n", "Raspadori 0.7015384615384613\n", "Colombo 0.37202797202797205\n", "Luvumbo 0.0 (rookie)\n", "Mota 0.6047745358090184\n", "Bonazzoli 0.7673076923076924\n", "Djuric 0.521978021978022\n", "Banda 0.3247863247863248\n", "Defrel 0.32478632478632474\n", "Sansone 0.3410256410256411\n", "Pellegri 0.9743589743589742\n", "Piccoli 0.9443786982248521\n", "Piccoli 1 (two seasons ago)\n", "Success 0.4871794871794871\n", "Botheim 0.6263736263736263\n", "Lucca 1 (rookie)\n", "Caso 0.43846153846153846 (rookie)\n", "Jovane 0.0 (two seasons ago)\n", "Soule' 0.9443786982248521\n", "Pavoletti 0.4003344481605351 (rookie)\n", "Cancellieri 0.9207692307692308\n", "Seck 0.46153846153846145\n", "Alvarez A. 0.0\n", "Ekuban 0.38974358974358975 (two seasons ago)\n", "Destro 0.5158371040723981\n", "Ceide 0.46153846153846145\n", "Ake' M. 0.0 (two seasons ago)\n", "Braaf 0.0\n", "Kallon 0.0\n", "Kaio Jorge 0.0\n", "Kaio Jorge 0.0 (two seasons ago)\n", "Vivaldo 0.0\n", "Players with low quantity of games:\n", "Natan 0.33333333333333337\n", "Kristiansen 0.6666666666666667\n", "Azzi 0.908253205128205\n", "Wieteska 0.5\n", "Lirola 0.16666666666666663\n", "Kabasele 0.6666666666666667\n", "Obert 0.6666666666666667\n", "Zemura 0.8333333333333334\n", "Hatzidiakos 0.5\n", "Carboni A. 0.33333333333333337\n", "Calafiori 0.5\n", "Monterisi 0.8333333333333334\n", "Tressoldi 0.0\n", "Vogliacco 0.0\n", "Di Pardo 0.8333333333333334\n", "Ostigard 0.8333333333333334\n", "Bisseck 0.16666666666666663\n", "Ferreira J. 0.8333333333333334\n", "Touba 0.33333333333333337\n", "Sazonov 0.16666666666666663\n", "Pereira P. 0.5\n", "Walukiewicz 0.6666666666666667\n", "Cittadini 0.0\n", "Cacace 0.9038461538461539\n", "Guessand A. 0.16666666666666663\n", "Cabal 0.7703962703962706\n", "Missori 0.16666666666666663\n", "Kayode 0.5\n", "Corazza 0.5\n", "Kristensen T. 0.33333333333333337\n", "Dermaku 0.16666666666666663\n", "Capradossi 0.0\n", "Bettella 0.0\n", "Amey 0.0\n", "Gila 0.6666666666666667\n", "Guarino 0.0\n", "Carboni F. 0.33333333333333337\n", "Smajlovic 0.0\n", "Matturro 0.16666666666666663\n", "N'guessan 0.0\n", "Mateus Lusuardi 0.0\n", "Kalaj 0.0\n", "Pierozzi 0.0\n", "Huijsen 0.0\n", "Bonfanti 0.0\n", "Pellegrino 0.0\n", "Comuzzo 0.0\n", "Pogba 0.3504273504273504\n", "Mboula 0.5\n", "Musah 0.6666666666666667\n", "Jankto 0.5\n", "Reinier 0.0\n", "Cajuste 0.0\n", "Mancosu 0.0\n", "Brescianini 0.8333333333333334\n", "Boloca 0.8333333333333334\n", "Machin 0.0\n", "Iling Junior 0.0\n", "Oristanio 0.8333333333333334\n", "Serdar 0.6666666666666667\n", "Payero 0.5\n", "Garritano 0.8333333333333334\n", "Racic 0.33333333333333337\n", "Infantino 0.5\n", "Martegani 0.8333333333333334\n", "Kutlu 0.33333333333333337\n", "Tchatchoua 0.0\n", "Quina 0.33333333333333337\n", "Adopo 0.5\n", "Romero L. 0.5737179487179487\n", "Tchaouna 0.5\n", "Sulemana I. 0.908253205128205\n", "Gelli 0.6666666666666667\n", "Suslov 0.5\n", "Jagiello 0.0\n", "Akpa Akpro 0.0\n", "Urbanski 0.33333333333333337\n", "Volpato 0.7282051282051283\n", "Vignato S. 0.6666666666666667\n", "Zarraga 0.33333333333333337\n", "Camara E. 0.0\n", "Amatucci 0.16666666666666663\n", "Pagano 0.5\n", "Prati 0.16666666666666663\n", "Viola 0.33333333333333337\n", "Lulic K. 0.0\n", "Pafundi 0.9070512820512819\n", "Adli 0.5940170940170939\n", "Bondo 0.16666666666666663\n", "Carboni V. 0.33333333333333337\n", "Faticanti 0.0\n", "Gineitis 0.16666666666666663\n", "Belardinelli 0.0\n", "El Azzouzi 0.8333333333333334\n", "Lipani 0.0\n", "Joselito 0.0\n", "Legowski 0.0\n", "Ibrahimovic A. 0.0\n", "Toure' E. 0.0\n", "Krstovic 0.8333333333333334\n", "Castellanos 0.8333333333333334\n", "Isaksen 0.8333333333333334\n", "Brenner 0.0\n", "Davis K. 0.0\n", "Piccoli 0.7500986193293885\n", "Jovane 0.0\n", "Soule' 0.7500986193293885\n", "Cuni 0.8333333333333334\n", "Maric 0.8333333333333334\n", "Cruz 0.0\n", "Van Hooijdonk 0.33333333333333337\n", "Kvernadze 0.33333333333333337\n", "Ikwuemesi 0.6666666666666667\n", "Puscas 0.16666666666666663\n", "Ake' M. 0.6666666666666667\n", "Vivaldo 0.0\n", "Bidaoui 0.0\n", "Shpendi S. 0.8333333333333334\n", "Burnete 0.16666666666666663\n", "Corfitzen 0.0\n", "Stewart 0.0\n", "Yildiz 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", "cols_toadapt_rookies = rookies_data.columns.intersection(cols_toadapt)\n", "\n", "players = players_orig.copy()\n", "\n", "min_games = 6\n", "\n", "current_season_games = max(10, 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", "\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", " elif(p in rookies_data.index):\n", " p_ = p\n", " weight = calc_weight(players.loc[p]['games'], rookies_data.loc[p_]['games'], False)\n", " players.at[p, cols_toadapt_rookies] = (players.loc[p][cols_toadapt_rookies] * weight + (1-weight) * rookies_data.loc[p_][cols_toadapt_rookies])\n", " \n", " print(p + ' ' + str(weight) + ' (rookie)') \n", "\n", " \n", " # to handle players like Scamacca, 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) + ' (two seasons ago)')\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", "\n", "# mean players stats based on old season\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_old.shape[0]):\n", " if(players_old['games'][i] >= min_games and (players_old['r'][i] == 'D')): # counting only defenders, to add a penalty\n", " mean_players_stats += players_old.loc[players_old.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": 13, "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": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "players.columns[9:]" ] }, { "cell_type": "code", "execution_count": 14, "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": 15, "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": 16, "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": 17, "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": 18, "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": 19, "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": 19, "id": "04564bee", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\nicol\\anaconda3\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:549: ConvergenceWarning: lbfgs failed to converge (status=2):\n", "ABNORMAL_TERMINATION_IN_LNSRCH.\n", "\n", "Increase the number of iterations (max_iter) or scale the data as shown in:\n", " https://scikit-learn.org/stable/modules/preprocessing.html\n", " self.n_iter_ = _check_optimize_result(\"lbfgs\", opt_res, self.max_iter)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "0.15507286428738876\n", "0.18856961333473798\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.1354212153815001\n", "0.17392551015116653\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "regr = MLPRegressor(max_iter = 400000, solver = 'lbfgs', hidden_layer_sizes = (8, 8), alpha = 500, verbose = True)\n", "\n", "regr.fit(X_train, y_train)\n", "\n", "\n", "y_train_predict = regr.predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "\n", "plt.show()\n", "\n", "y_test_predict = regr.predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "f9513b25", "metadata": {}, "source": [ "Train neural network for outfield players.\n", "\n", "The outputs of the NN are probability distribution of SinhArcsinh type (a skewed distribution, which is a generalization of Gaussian)" ] }, { "cell_type": "code", "execution_count": 20, "id": "8aad9652", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/1000\n", "96/96 [==============================] - 4s 11ms/step - loss: 2.1171 - distribution_lambda_loss: 0.8241 - distribution_lambda_1_loss: 1.2930 - val_loss: 2.0956 - val_distribution_lambda_loss: 0.8197 - val_distribution_lambda_1_loss: 1.2759\n", "Epoch 2/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1179 - distribution_lambda_loss: 0.8238 - distribution_lambda_1_loss: 1.2940 - val_loss: 2.0975 - val_distribution_lambda_loss: 0.8208 - val_distribution_lambda_1_loss: 1.2767\n", "Epoch 3/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1124 - distribution_lambda_loss: 0.8215 - distribution_lambda_1_loss: 1.2909 - val_loss: 2.0966 - val_distribution_lambda_loss: 0.8195 - val_distribution_lambda_1_loss: 1.2771\n", "Epoch 4/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1125 - distribution_lambda_loss: 0.8226 - distribution_lambda_1_loss: 1.2899 - val_loss: 2.1005 - val_distribution_lambda_loss: 0.8228 - val_distribution_lambda_1_loss: 1.2777\n", "Epoch 5/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1162 - distribution_lambda_loss: 0.8239 - distribution_lambda_1_loss: 1.2924 - val_loss: 2.0953 - val_distribution_lambda_loss: 0.8193 - val_distribution_lambda_1_loss: 1.2760\n", "Epoch 6/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1138 - distribution_lambda_loss: 0.8226 - distribution_lambda_1_loss: 1.2912 - val_loss: 2.0971 - val_distribution_lambda_loss: 0.8194 - val_distribution_lambda_1_loss: 1.2777\n", "Epoch 7/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1162 - distribution_lambda_loss: 0.8238 - distribution_lambda_1_loss: 1.2924 - val_loss: 2.0987 - val_distribution_lambda_loss: 0.8205 - val_distribution_lambda_1_loss: 1.2782\n", "Epoch 8/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1099 - distribution_lambda_loss: 0.8210 - distribution_lambda_1_loss: 1.2890 - val_loss: 2.1007 - val_distribution_lambda_loss: 0.8221 - val_distribution_lambda_1_loss: 1.2787\n", "Epoch 9/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1124 - distribution_lambda_loss: 0.8222 - distribution_lambda_1_loss: 1.2902 - val_loss: 2.1003 - val_distribution_lambda_loss: 0.8213 - val_distribution_lambda_1_loss: 1.2790\n", "Epoch 10/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1128 - distribution_lambda_loss: 0.8224 - distribution_lambda_1_loss: 1.2905 - val_loss: 2.0984 - val_distribution_lambda_loss: 0.8200 - val_distribution_lambda_1_loss: 1.2784\n", "Epoch 11/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1155 - distribution_lambda_loss: 0.8234 - distribution_lambda_1_loss: 1.2921 - val_loss: 2.1033 - val_distribution_lambda_loss: 0.8219 - val_distribution_lambda_1_loss: 1.2814\n", "Epoch 12/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1129 - distribution_lambda_loss: 0.8218 - distribution_lambda_1_loss: 1.2911 - val_loss: 2.1035 - val_distribution_lambda_loss: 0.8227 - val_distribution_lambda_1_loss: 1.2808\n", "Epoch 13/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1085 - distribution_lambda_loss: 0.8194 - distribution_lambda_1_loss: 1.2891 - val_loss: 2.1037 - val_distribution_lambda_loss: 0.8229 - val_distribution_lambda_1_loss: 1.2808\n", "Epoch 14/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1067 - distribution_lambda_loss: 0.8190 - distribution_lambda_1_loss: 1.2876 - val_loss: 2.1064 - val_distribution_lambda_loss: 0.8235 - val_distribution_lambda_1_loss: 1.2828\n", "Epoch 15/1000\n", "96/96 [==============================] - 0s 3ms/step - loss: 2.1131 - distribution_lambda_loss: 0.8217 - distribution_lambda_1_loss: 1.2914 - val_loss: 2.1054 - val_distribution_lambda_loss: 0.8233 - val_distribution_lambda_1_loss: 1.2821\n" ] } ], "source": [ "load_model_of = True# load scaler and model weights for outfield player predictor\n", "refit_model_of = True\n", "\n", "if(load_model_of):\n", " scaler = pickle.load(open('saves/scaler.pkl', 'rb'))\n", " \n", " X_train = scaler.transform(X_train_)\n", " X_test = scaler.transform(X_test_)\n", "\n", "\n", "n_epochs = 1000\n", "\n", "n_samples = X_train.shape[0]\n", "\n", "batch_size = 256\n", "\n", "X_len = X_train.shape[1]\n", "y_len = y_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 1.2\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 10)\n", "neg_log_likelihood = lambda x, rv_x: -rv_x.log_prob(x)\n", "\n", "\n", "inputs = tfk.layers.Input(shape=(X_len,), name=\"input\")\n", "x = tfk.layers.Dropout(0.2)(inputs)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "x = tfk.layers.Dropout(0.2)(x)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "\n", "\n", "prob_dist_params = 4\n", "\n", "def prob_dist(t): \n", " return tfp.distributions.SinhArcsinh(loc=t[..., 0], scale=1e-3 + tf.math.softplus(t[..., 1]), skewness = t[..., 2], \n", " tailweight = tailweight_min + tailweight_range * tf.math.sigmoid(t[..., 3]),\n", " allow_nan_stats = False)\n", "\n", "x1 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x1)\n", "out_1 = tfp.layers.DistributionLambda(prob_dist)(x1)\n", "\n", "x2 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x2 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x2)\n", "\n", "\n", "modelb = tf.keras.Model(inputs, [out_1, out_2])\n", "\n", "modelb.compile(optimizer=tf.keras.optimizers.Nadam(learning_rate = 0.001), \n", " loss=neg_log_likelihood)\n", "\n", "if(load_model_of):\n", " modelb.load_weights('saves/modelb')\n", " \n", "if( (not load_model_of) or refit_model_of):\n", " modelb.fit(X_train.astype('float32'), [y_train[:, 0].astype('float32'), y_train[:, 1].astype('float32')], \n", " validation_data = (X_test.astype('float32'), [y_test[:, 0].astype('float32'), y_test[:, 1].astype('float32')]),\n", " batch_size = batch_size, shuffle = True, epochs=n_epochs, verbose=True, callbacks = [callback])" ] }, { "cell_type": "code", "execution_count": 21, "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": 22, "id": "c2674211", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.14248994674439097\n", "0.16946807672801856\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.13312004007562517\n", "0.14674466840894407\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_train_predict = sample_predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_test_predict = sample_predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "f574ffdb", "metadata": {}, "source": [ "Train neural network for goalkeepers.\n", "\n", "For clean sheet probability prediction, a Bernoulli distribution is used." ] }, { "cell_type": "code", "execution_count": 23, "id": "41e7e1ee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/2500\n", "16/16 [==============================] - 4s 48ms/step - loss: 2.8634 - distribution_lambda_2_loss: 0.8054 - distribution_lambda_3_loss: 1.5916 - distribution_lambda_4_loss: 0.4664 - val_loss: 2.8347 - val_distribution_lambda_2_loss: 0.7680 - val_distribution_lambda_3_loss: 1.5980 - val_distribution_lambda_4_loss: 0.4687\n", "Epoch 2/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8597 - distribution_lambda_2_loss: 0.7987 - distribution_lambda_3_loss: 1.5933 - distribution_lambda_4_loss: 0.4677 - val_loss: 2.8521 - val_distribution_lambda_2_loss: 0.7818 - val_distribution_lambda_3_loss: 1.6000 - val_distribution_lambda_4_loss: 0.4702\n", "Epoch 3/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8666 - distribution_lambda_2_loss: 0.8008 - distribution_lambda_3_loss: 1.5961 - distribution_lambda_4_loss: 0.4697 - val_loss: 2.8481 - val_distribution_lambda_2_loss: 0.7775 - val_distribution_lambda_3_loss: 1.5995 - val_distribution_lambda_4_loss: 0.4710\n", "Epoch 4/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8654 - distribution_lambda_2_loss: 0.7965 - distribution_lambda_3_loss: 1.5933 - distribution_lambda_4_loss: 0.4757 - val_loss: 2.8613 - val_distribution_lambda_2_loss: 0.7764 - val_distribution_lambda_3_loss: 1.6108 - val_distribution_lambda_4_loss: 0.4742\n", "Epoch 5/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8774 - distribution_lambda_2_loss: 0.8120 - distribution_lambda_3_loss: 1.5895 - distribution_lambda_4_loss: 0.4760 - val_loss: 2.8584 - val_distribution_lambda_2_loss: 0.7727 - val_distribution_lambda_3_loss: 1.6103 - val_distribution_lambda_4_loss: 0.4753\n", "Epoch 6/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8389 - distribution_lambda_2_loss: 0.7969 - distribution_lambda_3_loss: 1.5813 - distribution_lambda_4_loss: 0.4607 - val_loss: 2.8543 - val_distribution_lambda_2_loss: 0.7756 - val_distribution_lambda_3_loss: 1.6048 - val_distribution_lambda_4_loss: 0.4739\n", "Epoch 7/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8535 - distribution_lambda_2_loss: 0.8020 - distribution_lambda_3_loss: 1.5900 - distribution_lambda_4_loss: 0.4615 - val_loss: 2.8538 - val_distribution_lambda_2_loss: 0.7707 - val_distribution_lambda_3_loss: 1.6086 - val_distribution_lambda_4_loss: 0.4744\n", "Epoch 8/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8733 - distribution_lambda_2_loss: 0.8144 - distribution_lambda_3_loss: 1.5922 - distribution_lambda_4_loss: 0.4667 - val_loss: 2.8623 - val_distribution_lambda_2_loss: 0.7693 - val_distribution_lambda_3_loss: 1.6135 - val_distribution_lambda_4_loss: 0.4796\n", "Epoch 9/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8270 - distribution_lambda_2_loss: 0.7838 - distribution_lambda_3_loss: 1.5817 - distribution_lambda_4_loss: 0.4615 - val_loss: 2.8680 - val_distribution_lambda_2_loss: 0.7716 - val_distribution_lambda_3_loss: 1.6155 - val_distribution_lambda_4_loss: 0.4809\n", "Epoch 10/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8374 - distribution_lambda_2_loss: 0.7969 - distribution_lambda_3_loss: 1.5798 - distribution_lambda_4_loss: 0.4606 - val_loss: 2.8625 - val_distribution_lambda_2_loss: 0.7748 - val_distribution_lambda_3_loss: 1.6095 - val_distribution_lambda_4_loss: 0.4782\n", "Epoch 11/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8299 - distribution_lambda_2_loss: 0.7855 - distribution_lambda_3_loss: 1.5782 - distribution_lambda_4_loss: 0.4662 - val_loss: 2.8628 - val_distribution_lambda_2_loss: 0.7741 - val_distribution_lambda_3_loss: 1.6107 - val_distribution_lambda_4_loss: 0.4780\n", "Epoch 12/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8149 - distribution_lambda_2_loss: 0.7766 - distribution_lambda_3_loss: 1.5745 - distribution_lambda_4_loss: 0.4637 - val_loss: 2.8626 - val_distribution_lambda_2_loss: 0.7738 - val_distribution_lambda_3_loss: 1.6120 - val_distribution_lambda_4_loss: 0.4768\n", "Epoch 13/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8214 - distribution_lambda_2_loss: 0.7819 - distribution_lambda_3_loss: 1.5710 - distribution_lambda_4_loss: 0.4685 - val_loss: 2.8787 - val_distribution_lambda_2_loss: 0.7779 - val_distribution_lambda_3_loss: 1.6187 - val_distribution_lambda_4_loss: 0.4822\n", "Epoch 14/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8526 - distribution_lambda_2_loss: 0.8043 - distribution_lambda_3_loss: 1.5790 - distribution_lambda_4_loss: 0.4693 - val_loss: 2.8902 - val_distribution_lambda_2_loss: 0.7785 - val_distribution_lambda_3_loss: 1.6275 - val_distribution_lambda_4_loss: 0.4842\n", "Epoch 15/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8415 - distribution_lambda_2_loss: 0.7869 - distribution_lambda_3_loss: 1.5878 - distribution_lambda_4_loss: 0.4669 - val_loss: 2.8766 - val_distribution_lambda_2_loss: 0.7740 - val_distribution_lambda_3_loss: 1.6202 - val_distribution_lambda_4_loss: 0.4824\n", "Epoch 16/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8406 - distribution_lambda_2_loss: 0.7953 - distribution_lambda_3_loss: 1.5821 - distribution_lambda_4_loss: 0.4632 - val_loss: 2.8767 - val_distribution_lambda_2_loss: 0.7705 - val_distribution_lambda_3_loss: 1.6236 - val_distribution_lambda_4_loss: 0.4826\n", "Epoch 17/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8358 - distribution_lambda_2_loss: 0.7966 - distribution_lambda_3_loss: 1.5799 - distribution_lambda_4_loss: 0.4593 - val_loss: 2.8819 - val_distribution_lambda_2_loss: 0.7741 - val_distribution_lambda_3_loss: 1.6259 - val_distribution_lambda_4_loss: 0.4819\n", "Epoch 18/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8207 - distribution_lambda_2_loss: 0.7761 - distribution_lambda_3_loss: 1.5793 - distribution_lambda_4_loss: 0.4654 - val_loss: 2.8873 - val_distribution_lambda_2_loss: 0.7781 - val_distribution_lambda_3_loss: 1.6307 - val_distribution_lambda_4_loss: 0.4786\n", "Epoch 19/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8326 - distribution_lambda_2_loss: 0.7955 - distribution_lambda_3_loss: 1.5738 - distribution_lambda_4_loss: 0.4633 - val_loss: 2.8983 - val_distribution_lambda_2_loss: 0.7804 - val_distribution_lambda_3_loss: 1.6367 - val_distribution_lambda_4_loss: 0.4811\n", "Epoch 20/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8445 - distribution_lambda_2_loss: 0.7884 - distribution_lambda_3_loss: 1.5865 - distribution_lambda_4_loss: 0.4695 - val_loss: 2.8826 - val_distribution_lambda_2_loss: 0.7820 - val_distribution_lambda_3_loss: 1.6184 - val_distribution_lambda_4_loss: 0.4822\n", "Epoch 21/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8374 - distribution_lambda_2_loss: 0.7835 - distribution_lambda_3_loss: 1.5854 - distribution_lambda_4_loss: 0.4685 - val_loss: 2.8846 - val_distribution_lambda_2_loss: 0.7769 - val_distribution_lambda_3_loss: 1.6229 - val_distribution_lambda_4_loss: 0.4848\n", "Epoch 22/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8400 - distribution_lambda_2_loss: 0.7948 - distribution_lambda_3_loss: 1.5790 - distribution_lambda_4_loss: 0.4662 - val_loss: 2.8908 - val_distribution_lambda_2_loss: 0.7782 - val_distribution_lambda_3_loss: 1.6314 - val_distribution_lambda_4_loss: 0.4812\n", "Epoch 23/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8472 - distribution_lambda_2_loss: 0.7877 - distribution_lambda_3_loss: 1.5840 - distribution_lambda_4_loss: 0.4755 - val_loss: 2.8999 - val_distribution_lambda_2_loss: 0.7811 - val_distribution_lambda_3_loss: 1.6391 - val_distribution_lambda_4_loss: 0.4797\n", "Epoch 24/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8225 - distribution_lambda_2_loss: 0.7702 - distribution_lambda_3_loss: 1.5871 - distribution_lambda_4_loss: 0.4652 - val_loss: 2.8981 - val_distribution_lambda_2_loss: 0.7794 - val_distribution_lambda_3_loss: 1.6362 - val_distribution_lambda_4_loss: 0.4825\n", "Epoch 25/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "16/16 [==============================] - 0s 5ms/step - loss: 2.8163 - distribution_lambda_2_loss: 0.7790 - distribution_lambda_3_loss: 1.5738 - distribution_lambda_4_loss: 0.4635 - val_loss: 2.8908 - val_distribution_lambda_2_loss: 0.7764 - val_distribution_lambda_3_loss: 1.6334 - val_distribution_lambda_4_loss: 0.4810\n", "Epoch 26/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8344 - distribution_lambda_2_loss: 0.7955 - distribution_lambda_3_loss: 1.5742 - distribution_lambda_4_loss: 0.4646 - val_loss: 2.8899 - val_distribution_lambda_2_loss: 0.7748 - val_distribution_lambda_3_loss: 1.6302 - val_distribution_lambda_4_loss: 0.4848\n", "Epoch 27/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8272 - distribution_lambda_2_loss: 0.7940 - distribution_lambda_3_loss: 1.5721 - distribution_lambda_4_loss: 0.4612 - val_loss: 2.8895 - val_distribution_lambda_2_loss: 0.7721 - val_distribution_lambda_3_loss: 1.6310 - val_distribution_lambda_4_loss: 0.4864\n", "Epoch 28/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8510 - distribution_lambda_2_loss: 0.7977 - distribution_lambda_3_loss: 1.5849 - distribution_lambda_4_loss: 0.4685 - val_loss: 2.8974 - val_distribution_lambda_2_loss: 0.7757 - val_distribution_lambda_3_loss: 1.6330 - val_distribution_lambda_4_loss: 0.4887\n", "Epoch 29/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8032 - distribution_lambda_2_loss: 0.7804 - distribution_lambda_3_loss: 1.5614 - distribution_lambda_4_loss: 0.4614 - val_loss: 2.9068 - val_distribution_lambda_2_loss: 0.7785 - val_distribution_lambda_3_loss: 1.6408 - val_distribution_lambda_4_loss: 0.4874\n", "Epoch 30/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8399 - distribution_lambda_2_loss: 0.7932 - distribution_lambda_3_loss: 1.5785 - distribution_lambda_4_loss: 0.4683 - val_loss: 2.8928 - val_distribution_lambda_2_loss: 0.7740 - val_distribution_lambda_3_loss: 1.6321 - val_distribution_lambda_4_loss: 0.4866\n", "Epoch 31/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8046 - distribution_lambda_2_loss: 0.7735 - distribution_lambda_3_loss: 1.5688 - distribution_lambda_4_loss: 0.4623 - val_loss: 2.8941 - val_distribution_lambda_2_loss: 0.7781 - val_distribution_lambda_3_loss: 1.6307 - val_distribution_lambda_4_loss: 0.4853\n", "Epoch 32/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8254 - distribution_lambda_2_loss: 0.7854 - distribution_lambda_3_loss: 1.5765 - distribution_lambda_4_loss: 0.4635 - val_loss: 2.8962 - val_distribution_lambda_2_loss: 0.7771 - val_distribution_lambda_3_loss: 1.6321 - val_distribution_lambda_4_loss: 0.4870\n", "Epoch 33/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8149 - distribution_lambda_2_loss: 0.7800 - distribution_lambda_3_loss: 1.5666 - distribution_lambda_4_loss: 0.4683 - val_loss: 2.8964 - val_distribution_lambda_2_loss: 0.7785 - val_distribution_lambda_3_loss: 1.6312 - val_distribution_lambda_4_loss: 0.4867\n", "Epoch 34/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8012 - distribution_lambda_2_loss: 0.7745 - distribution_lambda_3_loss: 1.5747 - distribution_lambda_4_loss: 0.4520 - val_loss: 2.9002 - val_distribution_lambda_2_loss: 0.7763 - val_distribution_lambda_3_loss: 1.6351 - val_distribution_lambda_4_loss: 0.4889\n", "Epoch 35/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8321 - distribution_lambda_2_loss: 0.7890 - distribution_lambda_3_loss: 1.5795 - distribution_lambda_4_loss: 0.4636 - val_loss: 2.8999 - val_distribution_lambda_2_loss: 0.7754 - val_distribution_lambda_3_loss: 1.6353 - val_distribution_lambda_4_loss: 0.4892\n", "Epoch 36/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8133 - distribution_lambda_2_loss: 0.7899 - distribution_lambda_3_loss: 1.5676 - distribution_lambda_4_loss: 0.4558 - val_loss: 2.8999 - val_distribution_lambda_2_loss: 0.7779 - val_distribution_lambda_3_loss: 1.6336 - val_distribution_lambda_4_loss: 0.4885\n", "Epoch 37/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8430 - distribution_lambda_2_loss: 0.7943 - distribution_lambda_3_loss: 1.5770 - distribution_lambda_4_loss: 0.4717 - val_loss: 2.9023 - val_distribution_lambda_2_loss: 0.7807 - val_distribution_lambda_3_loss: 1.6317 - val_distribution_lambda_4_loss: 0.4899\n", "Epoch 38/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8264 - distribution_lambda_2_loss: 0.7900 - distribution_lambda_3_loss: 1.5731 - distribution_lambda_4_loss: 0.4633 - val_loss: 2.9073 - val_distribution_lambda_2_loss: 0.7790 - val_distribution_lambda_3_loss: 1.6352 - val_distribution_lambda_4_loss: 0.4932\n", "Epoch 39/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8115 - distribution_lambda_2_loss: 0.7816 - distribution_lambda_3_loss: 1.5664 - distribution_lambda_4_loss: 0.4635 - val_loss: 2.9025 - val_distribution_lambda_2_loss: 0.7739 - val_distribution_lambda_3_loss: 1.6362 - val_distribution_lambda_4_loss: 0.4924\n", "Epoch 40/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8347 - distribution_lambda_2_loss: 0.7921 - distribution_lambda_3_loss: 1.5796 - distribution_lambda_4_loss: 0.4631 - val_loss: 2.9042 - val_distribution_lambda_2_loss: 0.7739 - val_distribution_lambda_3_loss: 1.6392 - val_distribution_lambda_4_loss: 0.4912\n", "Epoch 41/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.7897 - distribution_lambda_2_loss: 0.7750 - distribution_lambda_3_loss: 1.5617 - distribution_lambda_4_loss: 0.4530 - val_loss: 2.9112 - val_distribution_lambda_2_loss: 0.7757 - val_distribution_lambda_3_loss: 1.6417 - val_distribution_lambda_4_loss: 0.4938\n", "Epoch 42/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8251 - distribution_lambda_2_loss: 0.7946 - distribution_lambda_3_loss: 1.5715 - distribution_lambda_4_loss: 0.4591 - val_loss: 2.9113 - val_distribution_lambda_2_loss: 0.7758 - val_distribution_lambda_3_loss: 1.6388 - val_distribution_lambda_4_loss: 0.4967\n", "Epoch 43/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8015 - distribution_lambda_2_loss: 0.7707 - distribution_lambda_3_loss: 1.5683 - distribution_lambda_4_loss: 0.4625 - val_loss: 2.9087 - val_distribution_lambda_2_loss: 0.7814 - val_distribution_lambda_3_loss: 1.6368 - val_distribution_lambda_4_loss: 0.4905\n", "Epoch 44/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8238 - distribution_lambda_2_loss: 0.7827 - distribution_lambda_3_loss: 1.5784 - distribution_lambda_4_loss: 0.4626 - val_loss: 2.9051 - val_distribution_lambda_2_loss: 0.7797 - val_distribution_lambda_3_loss: 1.6353 - val_distribution_lambda_4_loss: 0.4901\n", "Epoch 45/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8192 - distribution_lambda_2_loss: 0.7826 - distribution_lambda_3_loss: 1.5739 - distribution_lambda_4_loss: 0.4627 - val_loss: 2.9100 - val_distribution_lambda_2_loss: 0.7799 - val_distribution_lambda_3_loss: 1.6398 - val_distribution_lambda_4_loss: 0.4904\n", "Epoch 46/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8152 - distribution_lambda_2_loss: 0.7811 - distribution_lambda_3_loss: 1.5690 - distribution_lambda_4_loss: 0.4651 - val_loss: 2.9097 - val_distribution_lambda_2_loss: 0.7803 - val_distribution_lambda_3_loss: 1.6381 - val_distribution_lambda_4_loss: 0.4914\n", "Epoch 47/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8123 - distribution_lambda_2_loss: 0.7940 - distribution_lambda_3_loss: 1.5635 - distribution_lambda_4_loss: 0.4548 - val_loss: 2.9142 - val_distribution_lambda_2_loss: 0.7813 - val_distribution_lambda_3_loss: 1.6402 - val_distribution_lambda_4_loss: 0.4927\n", "Epoch 48/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.8110 - distribution_lambda_2_loss: 0.7743 - distribution_lambda_3_loss: 1.5747 - distribution_lambda_4_loss: 0.4620 - val_loss: 2.9071 - val_distribution_lambda_2_loss: 0.7818 - val_distribution_lambda_3_loss: 1.6357 - val_distribution_lambda_4_loss: 0.4896\n", "Epoch 49/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "16/16 [==============================] - 0s 5ms/step - loss: 2.7890 - distribution_lambda_2_loss: 0.7829 - distribution_lambda_3_loss: 1.5567 - distribution_lambda_4_loss: 0.4494 - val_loss: 2.9067 - val_distribution_lambda_2_loss: 0.7840 - val_distribution_lambda_3_loss: 1.6363 - val_distribution_lambda_4_loss: 0.4863\n", "Epoch 50/2500\n", "16/16 [==============================] - 0s 5ms/step - loss: 2.8199 - distribution_lambda_2_loss: 0.7951 - distribution_lambda_3_loss: 1.5685 - distribution_lambda_4_loss: 0.4563 - val_loss: 2.9212 - val_distribution_lambda_2_loss: 0.7861 - val_distribution_lambda_3_loss: 1.6447 - val_distribution_lambda_4_loss: 0.4905\n", "Epoch 51/2500\n", "16/16 [==============================] - 0s 4ms/step - loss: 2.7944 - distribution_lambda_2_loss: 0.7789 - distribution_lambda_3_loss: 1.5600 - distribution_lambda_4_loss: 0.4556 - val_loss: 2.9107 - val_distribution_lambda_2_loss: 0.7799 - val_distribution_lambda_3_loss: 1.6433 - val_distribution_lambda_4_loss: 0.4875\n" ] } ], "source": [ "load_model_gk = True# load scaler and model weights for goalkeeper player predictor\n", "refit_model_gk = True\n", "\n", "if(load_model_gk):\n", " scaler_gk = pickle.load(open('saves/scaler_gk.pkl', 'rb'))\n", " \n", " X_gk_train = scaler_gk.transform(X_gk_train_)\n", " X_gk_test = scaler_gk.transform(X_gk_test_)\n", " \n", " \n", "n_epochs = 2500\n", "\n", "n_samples = X_gk_train.shape[0]\n", "\n", "batch_size = 128\n", "\n", "X_gk_len = X_gk_train.shape[1]\n", "y_gk_len = y_gk_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 0.8\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(0.3)(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(16, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dropout(0.2)(x1)\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(16, 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(0.2)(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": 24, "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": 25, "id": "c41cf448", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.0907258632073451\n", "0.3000061215338464\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.06439535566000021\n", "0.21148355905367822\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_gk_train_predict = sample_predict_gk(X_gk_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_train[:, 0], y_gk_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_train[:, 1], y_gk_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_train[:, 0], y_gk_train_predict[:, 0]))\n", "print(r2_score(y_gk_train[:, 1], y_gk_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_gk_test_predict = sample_predict_gk(X_gk_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_test[:, 0], y_gk_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_test[:, 1], y_gk_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_test[:, 0], y_gk_test_predict[:, 0]))\n", "print(r2_score(y_gk_test[:, 1], y_gk_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "91869883", "metadata": {}, "source": [ "Use the following codes to save the scalers and the model weights" ] }, { "cell_type": "code", "execution_count": 26, "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": 27, "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": 28, "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": 29, "id": "62b9f588", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " matchday team1 team2\n", "0 1 Bologna Milan\n", "1 1 Empoli Verona\n", "2 1 Frosinone Napoli\n", "3 1 Genoa Fiorentina\n", "4 1 Inter Monza\n", "5 1 Lecce Lazio\n", "6 1 Roma Salernitana\n", "7 1 Sassuolo Atalanta\n", "8 1 Torino Cagliari\n", "9 1 Udinese Juventus\n", "10 2 Cagliari Inter\n", "11 2 Fiorentina Lecce\n", "12 2 Frosinone Atalanta\n", "13 2 Verona Roma\n", "14 2 Juventus Bologna\n", "15 2 Lazio Genoa\n", "16 2 Milan Torino\n", "17 2 Monza Empoli\n", "18 2 Napoli Sassuolo\n", "19 2 Salernitana Udinese\n", "20 3 Atalanta Monza\n", "21 3 Bologna Cagliari\n", "22 3 Empoli Juventus\n", "23 3 Inter Fiorentina\n", "24 3 Lecce Salernitana\n", "25 3 Napoli Lazio\n", "26 3 Roma Milan\n", "27 3 Sassuolo Verona\n", "28 3 Torino Genoa\n", "29 3 Udinese Frosinone\n", "30 4 Cagliari Udinese\n", "31 4 Fiorentina Atalanta\n", "32 4 Frosinone Sassuolo\n", "33 4 Genoa Napoli\n", "34 4 Verona Bologna\n", "35 4 Inter Milan\n", "36 4 Juventus Lazio\n", "37 4 Monza Lecce\n", "38 4 Roma Empoli\n", "39 4 Salernitana Torino\n", "40 5 Atalanta Cagliari\n", "41 5 Bologna Napoli\n", "42 5 Empoli Inter\n", "43 5 Lazio Monza\n", "44 5 Lecce Genoa\n", "45 5 Milan Verona\n", "46 5 Salernitana Frosinone\n", "47 5 Sassuolo Juventus\n", "48 5 Torino Roma\n", "49 5 Udinese Fiorentina\n", "50 6 Cagliari Milan\n", "51 6 Empoli Salernitana\n", "52 6 Frosinone Fiorentina\n", "53 6 Genoa Roma\n", "54 6 Verona Atalanta\n", "55 6 Inter Sassuolo\n", "56 6 Juventus Lecce\n", "57 6 Lazio Torino\n", "58 6 Monza Bologna\n", "59 6 Napoli Udinese\n", "60 7 Atalanta Juventus\n", "61 7 Bologna Empoli\n", "62 7 Fiorentina Cagliari\n", "63 7 Lecce Napoli\n", "64 7 Milan Lazio\n", "65 7 Roma Frosinone\n", "66 7 Salernitana Inter\n", "67 7 Sassuolo Monza\n", "68 7 Torino Verona\n", "69 7 Udinese Genoa\n", "70 8 Cagliari Roma\n", "71 8 Empoli Udinese\n", "72 8 Frosinone Verona\n", "73 8 Genoa Milan\n", "74 8 Inter Bologna\n", "75 8 Juventus Torino\n", "76 8 Lazio Atalanta\n", "77 8 Lecce Sassuolo\n", "78 8 Monza Salernitana\n", "79 8 Napoli Fiorentina\n", "80 9 Atalanta Genoa\n", "81 9 Bologna Frosinone\n", "82 9 Fiorentina Empoli\n", "83 9 Verona Napoli\n", "84 9 Milan Juventus\n", "85 9 Roma Monza\n", "86 9 Salernitana Cagliari\n", "87 9 Sassuolo Lazio\n", "88 9 Torino Inter\n", "89 9 Udinese Lecce\n", "90 10 Cagliari Frosinone\n", "91 10 Empoli Atalanta\n", "92 10 Genoa Salernitana\n", "93 10 Inter Roma\n", "94 10 Juventus Verona\n", "95 10 Lazio Fiorentina\n", "96 10 Lecce Torino\n", "97 10 Monza Udinese\n", "98 10 Napoli Milan\n", "99 10 Sassuolo Bologna\n", "100 11 Atalanta Inter\n", "101 11 Bologna Lazio\n", "102 11 Cagliari Genoa\n", "103 11 Fiorentina Juventus\n", "104 11 Frosinone Empoli\n", "105 11 Verona Monza\n", "106 11 Milan Udinese\n", "107 11 Roma Lecce\n", "108 11 Salernitana Napoli\n", "109 11 Torino Sassuolo\n", "110 12 Fiorentina Bologna\n", "111 12 Genoa Verona\n", "112 12 Inter Frosinone\n", "113 12 Juventus Cagliari\n", "114 12 Lazio Roma\n", "115 12 Lecce Milan\n", "116 12 Monza Torino\n", "117 12 Napoli Empoli\n", "118 12 Sassuolo Salernitana\n", "119 12 Udinese Atalanta\n", "120 13 Atalanta Napoli\n", "121 13 Bologna Torino\n", "122 13 Cagliari Monza\n", "123 13 Empoli Sassuolo\n", "124 13 Frosinone Genoa\n", "125 13 Verona Lecce\n", "126 13 Juventus Inter\n", "127 13 Milan Fiorentina\n", "128 13 Roma Udinese\n", "129 13 Salernitana Lazio\n", "130 14 Fiorentina Salernitana\n", "131 14 Genoa Empoli\n", "132 14 Lazio Cagliari\n", "133 14 Lecce Bologna\n", "134 14 Milan Frosinone\n", "135 14 Monza Juventus\n", "136 14 Napoli Inter\n", "137 14 Sassuolo Roma\n", "138 14 Torino Atalanta\n", "139 14 Udinese Verona\n", "140 15 Atalanta Milan\n", "141 15 Cagliari Sassuolo\n", "142 15 Empoli Lecce\n", "143 15 Frosinone Torino\n", "144 15 Verona Lazio\n", "145 15 Inter Udinese\n", "146 15 Juventus Napoli\n", "147 15 Monza Genoa\n", "148 15 Roma Fiorentina\n", "149 15 Salernitana Bologna\n", "150 16 Atalanta Salernitana\n", "151 16 Bologna Roma\n", "152 16 Fiorentina Verona\n", "153 16 Genoa Juventus\n", "154 16 Lazio Inter\n", "155 16 Lecce Frosinone\n", "156 16 Milan Monza\n", "157 16 Napoli Cagliari\n", "158 16 Torino Empoli\n", "159 16 Udinese Sassuolo\n", "160 17 Bologna Atalanta\n", "161 17 Empoli Lazio\n", "162 17 Frosinone Juventus\n", "163 17 Verona Cagliari\n", "164 17 Inter Lecce\n", "165 17 Monza Fiorentina\n", "166 17 Roma Napoli\n", "167 17 Salernitana Milan\n", "168 17 Sassuolo Genoa\n", "169 17 Torino Udinese\n", "170 18 Atalanta Lecce\n", "171 18 Cagliari Empoli\n", "172 18 Fiorentina Torino\n", "173 18 Genoa Inter\n", "174 18 Verona Salernitana\n", "175 18 Juventus Roma\n", "176 18 Milan Sassuolo\n", "177 18 Udinese Bologna\n", "178 18 Lazio Frosinone\n", "179 18 Napoli Monza\n", "180 19 Bologna Genoa\n", "181 19 Empoli Milan\n", "182 19 Frosinone Monza\n", "183 19 Roma Atalanta\n", "184 19 Lecce Cagliari\n", "185 19 Sassuolo Fiorentina\n", "186 19 Inter Verona\n", "187 19 Salernitana Juventus\n", "188 19 Udinese Lazio\n", "189 19 Torino Napoli\n", "190 20 Atalanta Frosinone\n", "191 20 Cagliari Bologna\n", "192 20 Fiorentina Udinese\n", "193 20 Genoa Torino\n", "194 20 Verona Empoli\n", "195 20 Juventus Sassuolo\n", "196 20 Lazio Lecce\n", "197 20 Milan Roma\n", "198 20 Monza Inter\n", "199 20 Napoli Salernitana\n", "200 21 Bologna Fiorentina\n", "201 21 Empoli Monza\n", "202 21 Frosinone Cagliari\n", "203 21 Inter Atalanta\n", "204 21 Lecce Juventus\n", "205 21 Roma Verona\n", "206 21 Salernitana Genoa\n", "207 21 Sassuolo Napoli\n", "208 21 Torino Lazio\n", "209 21 Udinese Milan\n", "210 22 Atalanta Udinese\n", "211 22 Cagliari Torino\n", "212 22 Fiorentina Inter\n", "213 22 Genoa Lecce\n", "214 22 Verona Frosinone\n", "215 22 Juventus Empoli\n", "216 22 Lazio Napoli\n", "217 22 Milan Bologna\n", "218 22 Monza Sassuolo\n", "219 22 Salernitana Roma\n", "220 23 Atalanta Lazio\n", "221 23 Bologna Sassuolo\n", "222 23 Empoli Genoa\n", "223 23 Frosinone Milan\n", "224 23 Inter Juventus\n", "225 23 Lecce Fiorentina\n", "226 23 Napoli Verona\n", "227 23 Roma Cagliari\n", "228 23 Torino Salernitana\n", "229 23 Udinese Monza\n", "230 24 Bologna Lecce\n", "231 24 Cagliari Lazio\n", "232 24 Fiorentina Frosinone\n", "233 24 Genoa Atalanta\n", "234 24 Juventus Udinese\n", "235 24 Milan Napoli\n", "236 24 Monza Verona\n", "237 24 Roma Inter\n", "238 24 Salernitana Empoli\n", "239 24 Sassuolo Torino\n", "240 25 Atalanta Sassuolo\n", "241 25 Empoli Fiorentina\n", "242 25 Frosinone Roma\n", "243 25 Verona Juventus\n", "244 25 Inter Salernitana\n", "245 25 Lazio Bologna\n", "246 25 Monza Milan\n", "247 25 Napoli Genoa\n", "248 25 Torino Lecce\n", "249 25 Udinese Cagliari\n", "250 26 Bologna Verona\n", "251 26 Cagliari Napoli\n", "252 26 Fiorentina Lazio\n", "253 26 Genoa Udinese\n", "254 26 Juventus Frosinone\n", "255 26 Lecce Inter\n", "256 26 Milan Atalanta\n", "257 26 Roma Torino\n", "258 26 Salernitana Monza\n", "259 26 Sassuolo Empoli\n", "260 27 Atalanta Bologna\n", "261 27 Empoli Cagliari\n", "262 27 Frosinone Lecce\n", "263 27 Verona Sassuolo\n", "264 27 Inter Genoa\n", "265 27 Lazio Milan\n", "266 27 Monza Roma\n", "267 27 Napoli Juventus\n", "268 27 Torino Fiorentina\n", "269 27 Udinese Salernitana\n", "270 28 Bologna Inter\n", "271 28 Cagliari Salernitana\n", "272 28 Fiorentina Roma\n", "273 28 Genoa Monza\n", "274 28 Juventus Atalanta\n", "275 28 Lazio Udinese\n", "276 28 Lecce Verona\n", "277 28 Milan Empoli\n", "278 28 Napoli Torino\n", "279 28 Sassuolo Frosinone\n", "280 29 Atalanta Fiorentina\n", "281 29 Empoli Bologna\n", "282 29 Frosinone Lazio\n", "283 29 Verona Milan\n", "284 29 Inter Napoli\n", "285 29 Juventus Genoa\n", "286 29 Monza Cagliari\n", "287 29 Roma Sassuolo\n", "288 29 Salernitana Lecce\n", "289 29 Udinese Torino\n", "290 30 Bologna Salernitana\n", "291 30 Cagliari Verona\n", "292 30 Fiorentina Milan\n", "293 30 Genoa Frosinone\n", "294 30 Inter Empoli\n", "295 30 Lazio Juventus\n", "296 30 Lecce Roma\n", "297 30 Napoli Atalanta\n", "298 30 Sassuolo Udinese\n", "299 30 Torino Monza\n", "300 31 Cagliari Atalanta\n", "301 31 Empoli Torino\n", "302 31 Frosinone Bologna\n", "303 31 Verona Genoa\n", "304 31 Juventus Fiorentina\n", "305 31 Milan Lecce\n", "306 31 Monza Napoli\n", "307 31 Roma Lazio\n", "308 31 Salernitana Sassuolo\n", "309 31 Udinese Inter\n", "310 32 Atalanta Verona\n", "311 32 Bologna Monza\n", "312 32 Fiorentina Genoa\n", "313 32 Inter Cagliari\n", "314 32 Lazio Salernitana\n", "315 32 Lecce Empoli\n", "316 32 Napoli Frosinone\n", "317 32 Sassuolo Milan\n", "318 32 Torino Juventus\n", "319 32 Udinese Roma\n", "320 33 Cagliari Juventus\n", "321 33 Empoli Napoli\n", "322 33 Genoa Lazio\n", "323 33 Verona Udinese\n", "324 33 Milan Inter\n", "325 33 Monza Atalanta\n", "326 33 Roma Bologna\n", "327 33 Salernitana Fiorentina\n", "328 33 Sassuolo Lecce\n", "329 33 Torino Frosinone\n", "330 34 Atalanta Empoli\n", "331 34 Bologna Udinese\n", "332 34 Fiorentina Sassuolo\n", "333 34 Frosinone Salernitana\n", "334 34 Genoa Cagliari\n", "335 34 Inter Torino\n", "336 34 Juventus Milan\n", "337 34 Lazio Verona\n", "338 34 Lecce Monza\n", "339 34 Napoli Roma\n", "340 35 Cagliari Lecce\n", "341 35 Empoli Frosinone\n", "342 35 Verona Fiorentina\n", "343 35 Milan Genoa\n", "344 35 Monza Lazio\n", "345 35 Roma Juventus\n", "346 35 Salernitana Atalanta\n", "347 35 Sassuolo Inter\n", "348 35 Torino Bologna\n", "349 35 Udinese Napoli\n", "350 36 Atalanta Roma\n", "351 36 Fiorentina Monza\n", "352 36 Frosinone Inter\n", "353 36 Genoa Sassuolo\n", "354 36 Verona Torino\n", "355 36 Juventus Salernitana\n", "356 36 Lazio Empoli\n", "357 36 Lecce Udinese\n", "358 36 Milan Cagliari\n", "359 36 Napoli Bologna\n", "360 37 Bologna Juventus\n", "361 37 Fiorentina Napoli\n", "362 37 Inter Lazio\n", "363 37 Lecce Atalanta\n", "364 37 Monza Frosinone\n", "365 37 Roma Genoa\n", "366 37 Salernitana Verona\n", "367 37 Sassuolo Cagliari\n", "368 37 Torino Milan\n", "369 37 Udinese Empoli\n", "370 38 Atalanta Torino\n", "371 38 Cagliari Fiorentina\n", "372 38 Empoli Roma\n", "373 38 Frosinone Udinese\n", "374 38 Genoa Bologna\n", "375 38 Verona Inter\n", "376 38 Juventus Monza\n", "377 38 Lazio Sassuolo\n", "378 38 Milan Salernitana\n", "379 38 Napoli Lecce\n" ] } ], "source": [ "print(cal_df.to_string())" ] }, { "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": 30, "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": 31, "id": "f79792b6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
starterpercentage
player
Falcone1.090
Gendrey1.090
Baschirotto1.090
Pongracic1.080
Gallo0.660
.........
Oristanio0.050
Jankto0.015
Mancosu0.010
Pavoletti0.055
Shomurodov0.460
\n", "

467 rows × 2 columns

\n", "
" ], "text/plain": [ " starter percentage\n", "player \n", "Falcone 1.0 90\n", "Gendrey 1.0 90\n", "Baschirotto 1.0 90\n", "Pongracic 1.0 80\n", "Gallo 0.6 60\n", "... ... ...\n", "Oristanio 0.0 50\n", "Jankto 0.0 15\n", "Mancosu 0.0 10\n", "Pavoletti 0.0 55\n", "Shomurodov 0.4 60\n", "\n", "[467 rows x 2 columns]" ] }, "execution_count": 31, "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": 32, "id": "5e63c2b7", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sommer: MV 6.12 ± 0.86; FV 5.77 + 1.22 (56.3% cs)\n", "Szczesny: MV 5.98 ± 0.96; FV 4.94 + 1.44 (9.0% cs)\n", "Meret: MV 5.71 ± 1.07; FV 3.21 + 2.69 (1.1% cs)\n", "Provedel: MV 6.13 ± 0.97; FV 3.79 + 2.12 (2.5% cs)\n", "Maignan: MV 6.10 ± 0.92; FV 5.03 + 1.36 (22.9% cs)\n", "Rui Patricio: MV 6.01 ± 0.91; FV 4.39 + 1.69 (2.5% cs)\n", "Skorupski: MV 6.14 ± 0.82; FV 5.82 + 1.23 (71.9% cs)\n", "Milinkovic-Savic V.: MV 6.13 ± 0.88; FV 5.66 + 1.21 (54.3% cs)\n", "Di Gregorio: MV 6.27 ± 0.85; FV 5.05 + 1.41 (15.4% cs)\n", "Falcone: MV 6.16 ± 0.91; FV 4.94 + 1.43 (15.0% cs)\n", "Silvestri: MV 6.18 ± 0.91; FV 5.18 + 1.51 (32.2% cs)\n", "Terracciano: MV 6.16 ± 0.84; FV 5.75 + 1.22 (68.0% cs)\n", "Carnesecchi: MV 6.14 ± 0.96; FV 5.07 + 1.43 (20.7% cs)\n", "Radunovic: MV 5.74 ± 1.10; FV 3.20 + 2.62 (1.0% cs)\n", "Montipo': MV 6.20 ± 0.82; FV 5.69 + 1.22 (55.2% cs)\n", "Martinez Jo.: MV 6.21 ± 0.90; FV 5.05 + 1.38 (23.2% cs)\n", "Ochoa: MV 6.19 ± 0.98; FV 3.43 + 2.43 (1.3% cs)\n", "Caprile: MV 6.20 ± 0.91; FV 5.05 + 1.42 (21.4% cs)\n", "Turati: MV 6.10 ± 0.97; FV 4.14 + 1.98 (4.6% cs)\n", "Consigli: MV 6.13 ± 0.95; FV 4.94 + 1.47 (13.3% cs)\n", "Musso: MV 6.17 ± 0.96; FV 5.04 + 1.37 (28.8% cs)\n", "Cragno: MV 6.04 ± 0.98; FV 3.76 + 2.10 (2.3% cs)\n", "Perin: MV 6.16 ± 0.93; FV 5.04 + 1.37 (20.1% cs)\n", "Berisha: MV 6.23 ± 0.91; FV 5.04 + 1.38 (21.9% cs)\n", "Christensen O.: MV 6.19 ± 0.88; FV 5.14 + 1.31 (31.1% cs)\n", "Sportiello: MV 6.13 ± 0.92; FV 5.13 + 1.29 (32.9% cs)\n", "Mirante: MV 6.10 ± 0.92; FV 5.03 + 1.36 (22.9% cs)\n", "Sepe: MV 6.12 ± 0.97; FV 3.73 + 2.16 (2.3% cs)\n", "Leali: MV 6.21 ± 0.90; FV 5.05 + 1.38 (23.2% cs)\n", "Lamanna: MV 6.26 ± 0.85; FV 5.04 + 1.38 (15.3% cs)\n", "Sommariva: MV 6.21 ± 0.90; FV 5.05 + 1.38 (23.2% cs)\n", "Pegolo: MV 6.12 ± 0.95; FV 4.83 + 1.52 (12.1% cs)\n", "Perilli: MV 6.20 ± 0.82; FV 5.71 + 1.22 (57.3% cs)\n", "Padelli: MV 6.17 ± 0.91; FV 5.17 + 1.51 (31.5% cs)\n", "Scuffet: MV 5.74 ± 1.10; FV 3.20 + 2.62 (1.0% cs)\n", "Gollini: MV 5.71 ± 1.07; FV 3.21 + 2.69 (1.1% cs)\n", "Perisan: MV 6.19 ± 0.87; FV 5.05 + 1.42 (25.8% cs)\n", "Audero: MV 6.12 ± 0.86; FV 5.77 + 1.22 (56.3% cs)\n", "Di Gennaro: MV 6.12 ± 0.86; FV 5.77 + 1.22 (56.3% cs)\n", "Pinsoglio: MV 5.89 ± 0.98; FV 4.52 + 1.64 (3.3% cs)\n", "Aresti: MV 5.74 ± 1.10; FV 3.20 + 2.62 (1.0% cs)\n", "Fiorillo: MV 6.19 ± 0.98; FV 3.43 + 2.43 (1.3% cs)\n", "Cerofolini: MV 6.08 ± 0.99; FV 3.63 + 2.32 (1.9% cs)\n", "Rossi F.: MV 6.17 ± 0.96; FV 5.04 + 1.37 (28.9% cs)\n", "Costil: MV 6.19 ± 0.98; FV 3.43 + 2.43 (1.3% cs)\n", "Ravaglia F.: MV 6.13 ± 0.82; FV 5.82 + 1.23 (71.7% cs)\n", "Frattali: MV 6.10 ± 0.97; FV 4.14 + 1.98 (4.6% cs)\n", "Contini: MV 5.71 ± 1.07; FV 3.21 + 2.69 (1.1% cs)\n", "Brancolini: MV 6.16 ± 0.90; FV 4.96 + 1.41 (16.4% cs)\n", "Berardi A.: MV 6.20 ± 0.82; FV 5.71 + 1.22 (57.3% cs)\n", "Gemello: MV 6.13 ± 0.88; FV 5.66 + 1.21 (54.3% cs)\n", "Boer: MV 6.01 ± 0.91; FV 4.39 + 1.69 (2.5% cs)\n", "Bagnolini: MV 6.13 ± 0.82; FV 5.82 + 1.23 (71.7% cs)\n", "Svilar: MV 6.01 ± 0.91; FV 4.39 + 1.69 (2.5% cs)\n", "Sorrentino A.: MV 6.25 ± 0.85; FV 5.01 + 1.41 (10.6% cs)\n", "Martinelli T.: MV 6.16 ± 0.84; FV 5.75 + 1.22 (66.1% cs)\n", "Popa: MV 6.13 ± 0.88; FV 5.66 + 1.21 (54.3% cs)\n", "Stubljar: MV 6.23 ± 0.91; FV 5.04 + 1.38 (21.9% cs)\n", "Gori: MV 6.26 ± 0.85; FV 5.04 + 1.38 (15.3% cs)\n", "Borbei: MV 6.16 ± 0.90; FV 4.96 + 1.41 (16.4% cs)\n", "Okoye: MV 6.17 ± 0.91; FV 5.17 + 1.51 (31.5% cs)\n", "Mandas: MV 6.12 ± 0.97; FV 3.73 + 2.16 (2.3% cs)\n", "Dimarco: MV 6.35 ± 0.79; FV 6.69 + 1.42\n", "Di Lorenzo: MV 6.18 ± 0.97; FV 6.55 + 1.62\n", "Hernandez T.: MV 6.22 ± 1.10; FV 6.75 + 2.07\n", "Carlos Augusto: MV 6.24 ± 0.86; FV 6.63 + 1.47\n", "Danilo: MV 6.02 ± 1.03; FV 6.18 + 1.39\n", "Zappacosta: MV 5.99 ± 1.04; FV 6.21 + 1.47\n", "Schuurs: MV 6.14 ± 0.71; FV 6.31 + 0.96\n", "Posch: MV 6.21 ± 0.76; FV 6.52 + 1.38\n", "Bastoni: MV 6.26 ± 0.77; FV 6.44 + 0.99\n", "Smalling: MV 6.08 ± 0.85; FV 6.33 + 1.30\n", "Dumfries: MV 6.30 ± 0.93; FV 6.81 + 1.82\n", "Romagnoli: MV 5.95 ± 1.00; FV 6.01 + 1.24\n", "Pavard: MV 6.12 ± 0.64; FV 6.25 + 0.78\n", "Rrahmani: MV 6.00 ± 0.96; FV 6.13 + 1.24\n", "Spinazzola: MV 6.15 ± 0.76; FV 6.44 + 1.31\n", "Buongiorno: MV 6.11 ± 0.77; FV 6.35 + 1.22\n", "Bremer: MV 5.80 ± 1.20; FV 5.91 + 1.51\n", "Tomori: MV 6.22 ± 0.98; FV 6.58 + 1.69\n", "Biraghi: MV 6.23 ± 0.98; FV 6.85 + 2.11\n", "Mancini: MV 5.95 ± 1.02; FV 6.17 + 1.45\n", "Darmian: MV 6.21 ± 0.75; FV 6.43 + 1.02\n", "Bakker: MV 5.94 ± 0.66; FV 6.01 + 0.90\n", "Mazzocchi: MV 5.61 ± 0.72; FV 5.57 + 0.74\n", "Doig: MV 5.97 ± 0.96; FV 6.12 + 1.29\n", "Calabria: MV 6.06 ± 0.92; FV 6.27 + 1.33\n", "Acerbi: MV 6.13 ± 0.69; FV 6.20 + 0.71\n", "Cuadrado: MV 6.11 ± 0.81; FV 6.26 + 1.00\n", "Ebuehi: MV 5.90 ± 0.66; FV 5.91 + 0.74\n", "Casale: MV 5.70 ± 1.08; FV 5.69 + 1.26\n", "Holm: MV 5.98 ± 0.64; FV 6.05 + 0.82\n", "Baschirotto: MV 5.76 ± 1.21; FV 5.84 + 1.45\n", "Bijol: MV 5.83 ± 1.11; FV 5.97 + 1.52\n", "Thiaw: MV 5.89 ± 1.23; FV 5.87 + 1.32\n", "Mario Rui: MV 5.92 ± 0.67; FV 5.93 + 0.76\n", "Milenkovic: MV 6.04 ± 0.96; FV 6.16 + 1.22\n", "Rodriguez R.: MV 6.04 ± 0.64; FV 6.07 + 0.61\n", "Kolasinac: MV 5.94 ± 0.78; FV 6.07 + 1.08\n", "N'dicka: MV 5.91 ± 0.81; FV 5.93 + 0.98\n", "Scalvini: MV 5.95 ± 1.17; FV 6.14 + 1.52\n", "Perez N.: MV 5.78 ± 1.07; FV 5.78 + 1.25\n", "Kristensen: MV 6.02 ± 0.68; FV 6.20 + 1.05\n", "Izzo: MV 5.90 ± 0.93; FV 5.94 + 1.24\n", "De Vrij: MV 6.22 ± 0.74; FV 6.36 + 0.83\n", "Faraoni: MV 5.82 ± 0.70; FV 5.84 + 0.86\n", "Toloi: MV 6.00 ± 1.00; FV 6.20 + 1.40\n", "Kyriakopoulos: MV 6.03 ± 0.94; FV 6.20 + 1.44\n", "Bellanova: MV 5.95 ± 0.88; FV 6.00 + 1.07\n", "Mari': MV 5.84 ± 0.93; FV 5.87 + 1.20\n", "Dodo': MV 6.04 ± 0.94; FV 6.14 + 1.23\n", "Lucumi': MV 6.09 ± 0.64; FV 6.12 + 0.70\n", "Hien: MV 5.87 ± 0.84; FV 5.82 + 0.87\n", "Natan: MV 5.99 ± 0.76; FV 6.06 + 0.92\n", "Hysaj: MV 5.70 ± 0.99; FV 5.69 + 1.15\n", "D'ambrosio: MV 5.96 ± 0.72; FV 5.94 + 0.87\n", "Luperto: MV 5.79 ± 1.05; FV 5.66 + 1.07\n", "Djimsiti: MV 5.96 ± 0.77; FV 5.97 + 0.86\n", "Marusic: MV 5.68 ± 1.10; FV 5.65 + 1.28\n", "Martin: MV 6.02 ± 0.78; FV 6.11 + 1.02\n", "Mina: MV 6.14 ± 0.78; FV 6.45 + 1.38\n", "Toljan: MV 5.90 ± 0.80; FV 5.89 + 0.81\n", "Llorente D.: MV 5.90 ± 0.79; FV 5.92 + 0.91\n", "Martinez Quarta: MV 6.22 ± 1.04; FV 6.60 + 1.76\n", "Bastoni S.: MV 5.98 ± 0.85; FV 6.19 + 1.29\n", "Dragusin: MV 6.09 ± 0.75; FV 6.27 + 1.01\n", "Parisi: MV 6.12 ± 0.90; FV 6.26 + 1.31\n", "Bradaric: MV 5.61 ± 0.89; FV 5.58 + 0.96\n", "Kamara H.: MV 5.93 ± 0.60; FV 5.91 + 0.64\n", "Olivera: MV 5.95 ± 0.64; FV 6.00 + 0.77\n", "Gendrey: MV 5.90 ± 0.80; FV 5.87 + 0.91\n", "Kristiansen: MV 6.17 ± 0.68; FV 6.30 + 0.95\n", "Beukema: MV 6.18 ± 0.72; FV 6.30 + 0.89\n", "Dossena: MV 5.55 ± 1.06; FV 5.47 + 1.11\n", "Pedersen: MV 5.90 ± 0.59; FV 5.89 + 0.57\n", "Juan Jesus: MV 5.97 ± 0.64; FV 5.99 + 0.65\n", "Gyomber: MV 5.60 ± 0.99; FV 5.54 + 1.09\n", "Alex Sandro: MV 5.58 ± 1.23; FV 5.47 + 1.33\n", "Hateboer: MV 5.85 ± 0.89; FV 5.91 + 1.16\n", "Palomino: MV 5.98 ± 0.64; FV 6.02 + 0.80\n", "Marchizza: MV 6.07 ± 1.07; FV 6.22 + 1.48\n", "Zappa: MV 5.54 ± 1.01; FV 5.47 + 1.01\n", "Gallo: MV 5.82 ± 0.99; FV 5.77 + 1.07\n", "Caldirola: MV 5.73 ± 1.06; FV 5.79 + 1.39\n", "Kalulu: MV 5.94 ± 0.94; FV 5.97 + 1.12\n", "Erlic: MV 5.90 ± 0.83; FV 5.87 + 0.75\n", "Vojvoda: MV 5.97 ± 0.61; FV 6.00 + 0.66\n", "Vasquez: MV 6.14 ± 0.68; FV 6.18 + 0.66\n", "Cambiaso: MV 5.80 ± 1.05; FV 5.84 + 1.25\n", "Pongracic: MV 5.96 ± 0.90; FV 5.98 + 1.01\n", "Viti: MV 5.94 ± 0.83; FV 5.89 + 0.79\n", "Gatti: MV 5.62 ± 1.36; FV 5.55 + 1.49\n", "Birindelli: MV 5.93 ± 0.75; FV 5.95 + 0.96\n", "Azzi: MV 5.74 ± 0.76; FV 5.72 + 0.78\n", "Wieteska: MV 5.67 ± 1.14; FV 5.63 + 1.30\n", "Masina: MV 5.84 ± 1.09; FV 6.26 + 1.75\n", "Romagnoli S.: MV 5.98 ± 1.26; FV 5.97 + 1.64\n", "Pezzella Giu.: MV 5.67 ± 0.79; FV 5.60 + 0.72\n", "Sabelli: MV 6.01 ± 0.52; FV 6.07 + 0.58\n", "Lirola: MV 5.95 ± 1.16; FV 6.00 + 1.46\n", "Lazzari: MV 5.90 ± 0.88; FV 5.87 + 1.01\n", "Bani: MV 6.18 ± 0.92; FV 6.54 + 1.61\n", "Djidji: MV 5.94 ± 0.65; FV 5.96 + 0.67\n", "Kabasele: MV 5.88 ± 0.70; FV 5.82 + 0.79\n", "Lazaro: MV 6.07 ± 0.63; FV 6.13 + 0.66\n", "Augello: MV 5.62 ± 1.00; FV 5.64 + 1.06\n", "Zortea: MV 5.91 ± 0.87; FV 6.07 + 1.20\n", "Dawidowicz: MV 5.87 ± 0.76; FV 5.83 + 0.83\n", "Pirola: MV 5.55 ± 0.90; FV 5.50 + 0.91\n", "Lovato: MV 5.54 ± 0.88; FV 5.47 + 0.89\n", "Ruggeri: MV 5.96 ± 1.14; FV 6.18 + 1.53\n", "Vina: MV 5.77 ± 1.06; FV 5.74 + 1.20\n", "Obert: MV 5.54 ± 1.08; FV 5.47 + 1.10\n", "Terracciano F.: MV 6.03 ± 0.70; FV 6.09 + 0.77\n", "Ebosele: MV 5.83 ± 0.89; FV 5.77 + 0.99\n", "Zemura: MV 5.89 ± 0.61; FV 5.85 + 0.64\n", "Hatzidiakos: MV 5.64 ± 1.13; FV 5.60 + 1.24\n", "Patric: MV 5.78 ± 0.84; FV 5.70 + 0.89\n", "Lykogiannis: MV 6.00 ± 0.49; FV 6.06 + 0.52\n", "Pellegrini Lu.: MV 5.61 ± 0.86; FV 5.50 + 0.88\n", "Magnani: MV 5.89 ± 0.93; FV 5.85 + 1.01\n", "Ranieri L.: MV 5.98 ± 0.84; FV 6.03 + 1.04\n", "Carboni A.: MV 5.96 ± 0.76; FV 6.02 + 1.02\n", "Calafiori: MV 6.05 ± 0.70; FV 6.10 + 0.86\n", "Monterisi: MV 5.92 ± 1.35; FV 6.08 + 2.01\n", "Ismajli: MV 5.84 ± 0.80; FV 5.79 + 0.73\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "De Winter: MV 6.07 ± 0.86; FV 6.09 + 0.87\n", "Tressoldi: MV 5.97 ± 0.85; FV 6.01 + 1.01\n", "Ehizibue: MV 5.78 ± 0.92; FV 5.88 + 1.30\n", "Vogliacco: MV 6.04 ± 0.82; FV 6.06 + 0.86\n", "Ferrari G.: MV 6.01 ± 0.87; FV 6.14 + 1.18\n", "Venuti: MV 5.78 ± 0.84; FV 5.74 + 0.91\n", "Karsdorp: MV 5.91 ± 0.57; FV 5.91 + 0.61\n", "Kjaer: MV 5.69 ± 0.91; FV 5.60 + 0.91\n", "Gunter: MV 5.69 ± 1.03; FV 5.58 + 1.07\n", "Soumaoro: MV 6.13 ± 0.77; FV 6.19 + 0.95\n", "Di Pardo: MV 5.58 ± 1.09; FV 5.51 + 1.14\n", "Zanoli: MV 6.00 ± 0.89; FV 6.20 + 1.28\n", "Zima: MV 6.05 ± 0.77; FV 6.09 + 0.77\n", "Hefti: MV 5.91 ± 0.65; FV 5.88 + 0.56\n", "Ostigard: MV 5.82 ± 0.72; FV 5.79 + 0.74\n", "Sambia: MV 5.70 ± 0.77; FV 5.68 + 0.85\n", "Bisseck: MV 6.07 ± 0.81; FV 6.20 + 0.99\n", "Oyono: MV 5.79 ± 1.02; FV 5.64 + 1.13\n", "Ferreira J.: MV 5.84 ± 0.66; FV 5.78 + 0.74\n", "Dorgu: MV 5.91 ± 0.55; FV 5.87 + 0.53\n", "Touba: MV 5.82 ± 1.03; FV 5.84 + 1.20\n", "Sazonov: MV 6.01 ± 0.68; FV 6.06 + 0.74\n", "Rugani: MV 5.92 ± 0.55; FV 5.92 + 0.57\n", "De Sciglio: MV 5.72 ± 0.75; FV 5.64 + 0.76\n", "Goldaniga: MV 5.55 ± 1.26; FV 5.46 + 1.44\n", "Florenzi: MV 6.07 ± 0.75; FV 6.15 + 0.89\n", "De Silvestri: MV 6.11 ± 0.51; FV 6.18 + 0.53\n", "Pereira P.: MV 5.96 ± 0.81; FV 6.02 + 1.10\n", "Fazio: MV 5.66 ± 1.26; FV 5.65 + 1.48\n", "Bereszynski: MV 5.66 ± 0.88; FV 5.58 + 0.91\n", "Bonifazi: MV 6.00 ± 0.61; FV 6.01 + 0.59\n", "Walukiewicz: MV 5.75 ± 0.95; FV 5.69 + 1.00\n", "Okoli: MV 5.65 ± 1.12; FV 5.49 + 1.24\n", "Kumbulla: MV 5.55 ± 1.47; FV 5.32 + 1.45\n", "Celik: MV 5.73 ± 0.91; FV 5.65 + 1.02\n", "Amione: MV 5.66 ± 0.94; FV 5.63 + 1.06\n", "Daniliuc: MV 5.58 ± 0.97; FV 5.54 + 1.08\n", "Soppy: MV 5.97 ± 0.59; FV 5.98 + 0.62\n", "Haps: MV 6.06 ± 0.83; FV 6.15 + 1.01\n", "Cittadini: MV 5.92 ± 0.86; FV 5.96 + 1.19\n", "Coppola D.: MV 5.82 ± 0.72; FV 5.76 + 0.72\n", "Cacace: MV 5.76 ± 0.70; FV 5.71 + 0.66\n", "Ebosse: MV 5.85 ± 0.75; FV 5.78 + 0.81\n", "Guessand A.: MV 5.91 ± 0.91; FV 5.93 + 1.13\n", "Cabal: MV 6.00 ± 0.89; FV 6.02 + 1.00\n", "Missori: MV 6.00 ± 0.87; FV 6.06 + 1.05\n", "Kayode: MV 6.14 ± 0.91; FV 6.25 + 1.14\n", "Corazza: MV 6.00 ± 0.58; FV 6.01 + 0.64\n", "Kristensen T.: MV 5.81 ± 0.81; FV 5.76 + 0.97\n", "Dermaku: MV 5.79 ± 1.01; FV 5.84 + 1.22\n", "Tonelli: MV 5.73 ± 0.85; FV 5.65 + 0.82\n", "Capradossi: MV 5.66 ± 1.16; FV 5.64 + 1.29\n", "Bettella: MV 5.92 ± 0.86; FV 5.96 + 1.19\n", "Amey: MV 6.10 ± 0.70; FV 6.20 + 0.93\n", "Gila: MV 5.69 ± 1.04; FV 5.64 + 1.17\n", "Bronn: MV 5.52 ± 1.00; FV 5.44 + 1.09\n", "Guarino: MV 5.89 ± 0.77; FV 5.88 + 0.84\n", "Carboni F.: MV 6.01 ± 0.87; FV 6.13 + 1.25\n", "Smajlovic: MV 5.80 ± 1.05; FV 5.87 + 1.30\n", "Matturro: MV 6.03 ± 0.80; FV 6.04 + 0.80\n", "N'guessan: MV 6.00 ± 0.73; FV 6.06 + 0.81\n", "Mateus Lusuardi: MV 5.78 ± 1.20; FV 5.72 + 1.43\n", "Kalaj: MV 5.78 ± 1.20; FV 5.72 + 1.43\n", "Pierozzi: MV 6.05 ± 0.85; FV 6.12 + 1.04\n", "Huijsen: MV 5.76 ± 1.10; FV 5.81 + 1.34\n", "Bonfanti: MV 5.90 ± 1.04; FV 6.01 + 1.33\n", "Pellegrino: MV 5.98 ± 0.88; FV 6.06 + 1.11\n", "Comuzzo: MV 6.05 ± 0.85; FV 6.12 + 1.04\n", "Zaccagni: MV 6.25 ± 1.08; FV 6.80 + 2.13\n", "Koopmeiners: MV 6.30 ± 1.07; FV 6.90 + 2.21\n", "Luis Alberto: MV 6.20 ± 1.10; FV 6.77 + 2.14\n", "Felipe Anderson: MV 6.00 ± 1.06; FV 6.39 + 1.70\n", "Rabiot: MV 6.07 ± 1.12; FV 6.54 + 1.93\n", "Zielinski: MV 6.19 ± 0.87; FV 6.57 + 1.52\n", "Barella: MV 6.29 ± 0.89; FV 6.73 + 1.65\n", "Pulisic: MV 6.32 ± 1.15; FV 7.11 + 2.64\n", "Orsolini: MV 6.25 ± 0.91; FV 6.88 + 2.16\n", "Calhanoglu: MV 6.38 ± 0.78; FV 6.65 + 1.28\n", "Strefezza: MV 6.00 ± 0.95; FV 6.28 + 1.49\n", "Chukwueze: MV 5.93 ± 0.81; FV 6.17 + 1.14\n", "Ferguson: MV 6.25 ± 0.74; FV 6.60 + 1.38\n", "Candreva: MV 6.03 ± 1.24; FV 6.33 + 1.84\n", "Frattesi: MV 6.30 ± 1.02; FV 6.93 + 2.18\n", "Samardzic: MV 6.19 ± 0.99; FV 6.69 + 1.94\n", "Vlasic: MV 6.10 ± 0.78; FV 6.35 + 1.22\n", "Bonaventura: MV 6.40 ± 1.13; FV 7.25 + 2.73\n", "Politano: MV 6.25 ± 0.91; FV 6.71 + 1.79\n", "El Shaarawy: MV 6.17 ± 0.85; FV 6.53 + 1.56\n", "Mkhitaryan: MV 6.35 ± 1.00; FV 6.99 + 2.19\n", "Aouar: MV 6.07 ± 1.04; FV 6.58 + 1.92\n", "Malinovskyi: MV 6.18 ± 0.90; FV 6.65 + 1.82\n", "Gudmundsson A.: MV 6.30 ± 0.94; FV 6.86 + 1.99\n", "Kamada: MV 5.98 ± 1.03; FV 6.33 + 1.59\n", "Pellegrini Lo.: MV 5.98 ± 1.09; FV 6.45 + 1.89\n", "Kostic: MV 6.07 ± 0.92; FV 6.36 + 1.44\n", "Radonjic: MV 6.30 ± 1.08; FV 6.99 + 2.38\n", "Baldanzi: MV 5.90 ± 0.98; FV 6.25 + 1.56\n", "Lovric: MV 6.07 ± 0.84; FV 6.40 + 1.48\n", "Lindstrom: MV 5.94 ± 0.73; FV 6.18 + 1.15\n", "Lazovic: MV 6.10 ± 0.84; FV 6.37 + 1.36\n", "Pereyra: MV 6.18 ± 1.23; FV 6.88 + 2.56\n", "Renato Sanches: MV 6.16 ± 0.73; FV 6.43 + 1.22\n", "Pessina: MV 6.07 ± 0.92; FV 6.39 + 1.58\n", "Guendouzi: MV 5.86 ± 0.84; FV 6.00 + 1.07\n", "Loftus-Cheek: MV 6.25 ± 0.91; FV 6.68 + 1.68\n", "Zambo Anguissa: MV 6.03 ± 0.92; FV 6.23 + 1.29\n", "Elmas: MV 5.93 ± 0.95; FV 6.23 + 1.48\n", "Bajrami: MV 6.03 ± 0.68; FV 6.21 + 0.90\n", "Ricci S.: MV 6.04 ± 0.73; FV 6.13 + 0.88\n", "Colpani: MV 6.38 ± 1.13; FV 7.19 + 2.68\n", "Ciurria: MV 6.02 ± 1.05; FV 6.47 + 1.94\n", "De Roon: MV 6.06 ± 1.00; FV 6.33 + 1.51\n", "Pogba: MV 5.94 ± 0.88; FV 6.00 + 1.15\n", "Cristante: MV 6.12 ± 0.99; FV 6.50 + 1.66\n", "Locatelli: MV 5.88 ± 0.82; FV 5.90 + 1.03\n", "Pasalic: MV 5.97 ± 1.01; FV 6.35 + 1.63\n", "Lobotka: MV 6.01 ± 0.72; FV 6.08 + 0.85\n", "Fagioli: MV 5.95 ± 1.02; FV 6.23 + 1.53\n", "Ikone': MV 6.21 ± 1.03; FV 6.76 + 2.04\n", "Ilic: MV 6.05 ± 0.66; FV 6.11 + 0.74\n", "Ndoye: MV 6.09 ± 0.64; FV 6.21 + 0.83\n", "Ederson D.s.: MV 6.05 ± 1.00; FV 6.36 + 1.56\n", "Reijnders: MV 6.18 ± 0.90; FV 6.56 + 1.57\n", "Barak: MV 5.99 ± 0.78; FV 6.15 + 1.04\n", "Saponara: MV 6.06 ± 0.76; FV 6.27 + 1.14\n", "Mandragora: MV 6.14 ± 1.01; FV 6.59 + 1.81\n", "Weah: MV 5.88 ± 0.57; FV 5.90 + 0.63\n", "Bennacer: MV 6.21 ± 0.89; FV 6.60 + 1.58\n", "Duda: MV 6.22 ± 1.00; FV 6.71 + 1.91\n", "Castrovilli: MV 6.20 ± 1.08; FV 6.79 + 2.13\n", "Mckennie: MV 6.13 ± 0.78; FV 6.34 + 1.11\n", "Miranchuk: MV 6.17 ± 0.91; FV 6.52 + 1.57\n", "Matheus Henrique: MV 6.03 ± 0.88; FV 6.23 + 1.28\n", "De Ketelaere: MV 6.06 ± 1.01; FV 6.40 + 1.61\n", "Mboula: MV 5.90 ± 0.76; FV 5.88 + 0.86\n", "Paredes: MV 5.85 ± 0.99; FV 5.87 + 1.21\n", "Sottil: MV 6.01 ± 0.63; FV 6.10 + 0.74\n", "Klaassen: MV 6.21 ± 0.86; FV 6.60 + 1.54\n", "Arthur Melo: MV 6.11 ± 0.76; FV 6.21 + 0.86\n", "Thorsby: MV 6.16 ± 0.95; FV 6.64 + 1.82\n", "Nandez: MV 5.94 ± 0.81; FV 6.09 + 1.12\n", "Tameze: MV 5.93 ± 0.57; FV 5.91 + 0.52\n", "Marin: MV 5.94 ± 0.67; FV 5.96 + 0.77\n", "Messias: MV 6.18 ± 0.89; FV 6.65 + 1.79\n", "Musah: MV 6.03 ± 0.70; FV 6.07 + 0.82\n", "Coulibaly L.: MV 5.82 ± 0.93; FV 5.96 + 1.27\n", "Krunic: MV 5.98 ± 0.74; FV 5.99 + 0.81\n", "Cataldi: MV 5.89 ± 0.84; FV 5.85 + 0.97\n", "Strootman: MV 6.04 ± 0.61; FV 6.14 + 0.75\n", "Duncan: MV 6.25 ± 0.86; FV 6.68 + 1.62\n", "Freuler: MV 6.00 ± 0.49; FV 6.03 + 0.50\n", "Gagliardini: MV 6.15 ± 0.92; FV 6.53 + 1.69\n", "Mazzitelli: MV 6.14 ± 1.39; FV 6.65 + 2.59\n", "Jankto: MV 5.79 ± 0.80; FV 5.81 + 0.91\n", "Kastanos: MV 5.86 ± 0.55; FV 5.96 + 0.72\n", "Gyasi: MV 5.68 ± 0.77; FV 5.66 + 0.84\n", "Reinier: MV 5.85 ± 1.14; FV 5.85 + 1.41\n", "Zalewski: MV 5.89 ± 0.68; FV 5.99 + 0.83\n", "Harroui: MV 6.18 ± 1.07; FV 6.67 + 1.92\n", "Frendrup: MV 6.10 ± 0.61; FV 6.24 + 0.73\n", "Blin: MV 5.92 ± 0.57; FV 5.92 + 0.62\n", "Fabbian: MV 6.14 ± 0.75; FV 6.54 + 1.52\n", "Ramadani: MV 6.05 ± 0.87; FV 6.17 + 1.12\n", "Cajuste : MV 5.95 ± 0.89; FV 5.99 + 1.12\n", "Mancosu: MV 5.68 ± 1.15; FV 5.69 + 1.31\n", "Vecino: MV 5.86 ± 1.02; FV 6.02 + 1.39\n", "Sensi: MV 6.19 ± 0.87; FV 6.59 + 1.47\n", "Walace: MV 5.82 ± 0.75; FV 5.74 + 0.84\n", "Lopez M.: MV 5.97 ± 0.76; FV 5.96 + 0.77\n", "Brescianini: MV 5.93 ± 0.88; FV 5.89 + 1.04\n", "Bove: MV 5.91 ± 0.87; FV 6.13 + 1.27\n", "Aebischer: MV 6.05 ± 0.53; FV 6.14 + 0.60\n", "Thorstvedt: MV 5.95 ± 0.66; FV 5.97 + 0.70\n", "Gonzalez J.: MV 5.82 ± 0.83; FV 5.89 + 1.10\n", "Moro N.: MV 6.14 ± 0.62; FV 6.31 + 0.83\n", "Oudin: MV 5.97 ± 1.02; FV 6.30 + 1.61\n", "Boloca: MV 6.04 ± 0.96; FV 6.12 + 1.20\n", "Rafia: MV 5.80 ± 0.76; FV 5.94 + 1.05\n", "Makoumbou: MV 5.71 ± 0.75; FV 5.77 + 0.86\n", "Kaba: MV 5.78 ± 0.85; FV 5.66 + 0.95\n", "Badelj: MV 5.96 ± 0.73; FV 5.96 + 0.72\n", "Machin: MV 5.91 ± 0.87; FV 5.96 + 1.22\n", "Linetty: MV 5.94 ± 0.62; FV 5.94 + 0.63\n", "Castillejo: MV 5.99 ± 0.66; FV 6.12 + 0.91\n", "Rovella: MV 5.97 ± 1.04; FV 6.06 + 1.32\n", "Pobega: MV 5.94 ± 0.52; FV 5.97 + 0.57\n", "Hongla: MV 5.90 ± 0.62; FV 5.88 + 0.62\n", "Miretti: MV 5.77 ± 0.72; FV 5.79 + 0.83\n", "Fazzini: MV 5.81 ± 0.63; FV 5.76 + 0.60\n", "Iling Junior: MV 5.78 ± 1.06; FV 5.85 + 1.32\n", "Oristanio: MV 5.71 ± 0.80; FV 5.71 + 0.85\n", "Serdar: MV 5.91 ± 0.65; FV 5.89 + 0.69\n", "Payero: MV 5.88 ± 0.75; FV 5.84 + 0.89\n", "Grassi: MV 5.86 ± 0.70; FV 5.81 + 0.67\n", "Baez: MV 5.86 ± 0.79; FV 5.88 + 0.92\n", "Deiola: MV 5.52 ± 0.97; FV 5.49 + 0.90\n", "Garritano: MV 6.09 ± 0.99; FV 6.20 + 1.30\n", "Bourabia: MV 5.95 ± 0.95; FV 6.07 + 1.27\n", "Saelemaekers: MV 6.09 ± 0.70; FV 6.31 + 1.08\n", "Maldini: MV 5.96 ± 0.74; FV 6.15 + 1.06\n", "Racic: MV 5.95 ± 0.69; FV 5.95 + 0.70\n", "Kovalenko: MV 5.90 ± 0.68; FV 5.86 + 0.67\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Maleh: MV 5.74 ± 0.91; FV 5.69 + 1.07\n", "Bohinen: MV 5.82 ± 0.55; FV 5.77 + 0.56\n", "Ranocchia F.: MV 5.99 ± 0.67; FV 6.13 + 0.84\n", "Folorunsho: MV 5.83 ± 0.91; FV 6.06 + 1.31\n", "Infantino: MV 6.00 ± 0.81; FV 6.03 + 0.89\n", "Martegani: MV 5.90 ± 0.74; FV 5.94 + 0.97\n", "Kutlu: MV 6.03 ± 0.80; FV 6.04 + 0.79\n", "Tchatchoua: MV 5.93 ± 0.87; FV 5.95 + 1.06\n", "Quina: MV 6.02 ± 0.81; FV 6.15 + 1.14\n", "Adopo: MV 5.91 ± 1.10; FV 6.04 + 1.39\n", "Romero L.: MV 6.01 ± 0.82; FV 6.12 + 1.06\n", "Basic: MV 5.90 ± 0.79; FV 6.02 + 1.01\n", "Asllani: MV 6.14 ± 0.76; FV 6.28 + 0.88\n", "Tchaouna: MV 5.70 ± 0.76; FV 5.67 + 0.88\n", "Sulemana I.: MV 5.58 ± 0.86; FV 5.56 + 0.86\n", "Barrenechea: MV 5.92 ± 0.91; FV 5.87 + 1.10\n", "Gelli: MV 5.88 ± 1.19; FV 5.89 + 1.46\n", "Suslov: MV 5.92 ± 0.65; FV 5.91 + 0.72\n", "Gaetano: MV 5.95 ± 0.89; FV 6.31 + 1.46\n", "Jagiello: MV 6.04 ± 0.82; FV 6.08 + 0.86\n", "Obiang: MV 5.91 ± 0.57; FV 5.88 + 0.53\n", "Maggiore: MV 5.83 ± 0.55; FV 5.80 + 0.64\n", "Akpa Akpro: MV 5.91 ± 0.87; FV 5.96 + 1.22\n", "Urbanski: MV 6.04 ± 0.67; FV 6.11 + 0.86\n", "Volpato: MV 6.02 ± 0.87; FV 6.16 + 1.23\n", "Vignato S.: MV 5.77 ± 0.84; FV 5.70 + 1.01\n", "Hrustic: MV 5.70 ± 0.60; FV 5.64 + 0.57\n", "Zarraga: MV 5.80 ± 0.83; FV 5.76 + 1.02\n", "Camara E.: MV 5.90 ± 0.94; FV 6.02 + 1.34\n", "Amatucci: MV 6.03 ± 0.87; FV 6.10 + 1.04\n", "Pagano: MV 6.13 ± 0.81; FV 6.31 + 1.13\n", "Prati: MV 5.71 ± 1.14; FV 5.72 + 1.33\n", "Viola: MV 5.70 ± 1.01; FV 5.69 + 1.14\n", "Lulic K.: MV 5.85 ± 1.14; FV 5.85 + 1.41\n", "Rog: MV 5.67 ± 0.96; FV 5.71 + 1.02\n", "Nicolussi Caviglia: MV 5.70 ± 1.11; FV 5.73 + 1.27\n", "Demme: MV 5.96 ± 0.51; FV 5.95 + 0.46\n", "Pafundi: MV 5.98 ± 0.84; FV 6.02 + 1.01\n", "Adli: MV 5.91 ± 0.85; FV 5.92 + 0.97\n", "Bondo: MV 5.94 ± 0.84; FV 6.00 + 1.15\n", "Zerbin: MV 5.90 ± 0.72; FV 5.88 + 0.86\n", "Carboni V.: MV 5.81 ± 0.91; FV 5.83 + 1.20\n", "Faticanti: MV 5.79 ± 1.02; FV 5.88 + 1.31\n", "Gineitis: MV 5.99 ± 0.74; FV 6.03 + 0.82\n", "Belardinelli: MV 5.91 ± 0.77; FV 5.89 + 0.85\n", "El Azzouzi: MV 5.99 ± 0.58; FV 6.00 + 0.58\n", "Lipani: MV 5.97 ± 0.86; FV 6.01 + 1.02\n", "Joselito: MV 5.93 ± 0.87; FV 5.95 + 1.06\n", "Legowski: MV 5.78 ± 0.90; FV 5.84 + 1.18\n", "Ibrahimovic A.: MV 5.85 ± 1.14; FV 5.85 + 1.41\n", "Osimhen: MV 6.44 ± 1.56; FV 7.80 + 3.97\n", "Martinez L.: MV 6.51 ± 1.37; FV 8.00 + 4.04\n", "Rafael Leao: MV 6.49 ± 1.25; FV 7.59 + 3.28\n", "Lukaku: MV 6.32 ± 1.49; FV 7.50 + 3.55\n", "Berardi: MV 6.49 ± 1.33; FV 7.84 + 3.77\n", "Immobile: MV 5.99 ± 1.26; FV 6.62 + 2.25\n", "Vlahovic: MV 6.16 ± 1.45; FV 7.09 + 3.05\n", "Dybala: MV 6.36 ± 1.47; FV 7.58 + 3.67\n", "Kvaratskhelia: MV 6.35 ± 1.22; FV 7.31 + 3.03\n", "Giroud: MV 6.42 ± 1.30; FV 7.65 + 3.55\n", "Scamacca: MV 6.24 ± 1.39; FV 7.22 + 3.16\n", "Thuram: MV 6.47 ± 1.15; FV 7.46 + 3.04\n", "Lookman: MV 6.30 ± 1.33; FV 7.32 + 3.20\n", "Dia: MV 6.00 ± 1.33; FV 6.77 + 2.48\n", "Arnautovic: MV 6.33 ± 1.03; FV 6.97 + 2.21\n", "Retegui: MV 6.27 ± 1.30; FV 7.36 + 3.29\n", "Sanabria: MV 6.13 ± 1.02; FV 6.79 + 2.22\n", "Nzola: MV 6.01 ± 1.21; FV 6.72 + 2.36\n", "Lauriente': MV 6.32 ± 1.20; FV 7.21 + 2.87\n", "Zapata D.: MV 6.09 ± 0.71; FV 6.32 + 1.10\n", "Chiesa: MV 6.33 ± 1.15; FV 7.13 + 2.66\n", "Milik: MV 6.11 ± 0.93; FV 6.50 + 1.62\n", "Gonzalez N.: MV 6.44 ± 1.19; FV 7.48 + 3.14\n", "Okafor: MV 6.19 ± 0.96; FV 6.67 + 1.89\n", "Pinamonti: MV 6.02 ± 1.22; FV 6.70 + 2.41\n", "Beltran L.: MV 6.10 ± 0.84; FV 6.47 + 1.48\n", "Caprari: MV 6.05 ± 1.02; FV 6.47 + 1.82\n", "Sanchez: MV 6.21 ± 0.92; FV 6.70 + 1.82\n", "Caputo: MV 5.74 ± 0.87; FV 6.02 + 1.25\n", "Toure' E.: MV 5.92 ± 1.01; FV 6.07 + 1.34\n", "Krstovic: MV 6.21 ± 1.11; FV 6.79 + 2.22\n", "Belotti: MV 6.10 ± 1.04; FV 6.68 + 2.07\n", "Muriel: MV 6.15 ± 0.89; FV 6.48 + 1.59\n", "Lapadula: MV 5.92 ± 1.14; FV 6.44 + 1.87\n", "Jovic: MV 6.09 ± 1.20; FV 6.76 + 2.37\n", "Abraham: MV 6.17 ± 1.16; FV 6.98 + 2.61\n", "Zirkzee: MV 6.37 ± 0.85; FV 6.87 + 1.87\n", "Ngonge: MV 5.90 ± 1.11; FV 6.36 + 1.76\n", "Petagna: MV 5.82 ± 1.09; FV 6.18 + 1.51\n", "Simeone: MV 5.99 ± 1.11; FV 6.50 + 1.90\n", "Deulofeu: MV 6.34 ± 1.23; FV 7.32 + 3.08\n", "Pedro: MV 5.96 ± 0.98; FV 6.26 + 1.48\n", "Shomurodov: MV 5.52 ± 0.78; FV 5.56 + 0.71\n", "Azmoun: MV 5.97 ± 0.74; FV 6.24 + 1.23\n", "Castellanos: MV 6.00 ± 0.78; FV 6.06 + 0.96\n", "Cheddira: MV 6.14 ± 1.38; FV 6.99 + 2.78\n", "Karlsson: MV 6.19 ± 0.76; FV 6.61 + 1.60\n", "Brekalo: MV 6.22 ± 1.04; FV 6.83 + 2.14\n", "Cambiaghi: MV 5.91 ± 0.86; FV 6.10 + 1.18\n", "Henry: MV 5.84 ± 0.89; FV 6.12 + 1.34\n", "Mulattieri: MV 6.01 ± 0.72; FV 6.32 + 1.33\n", "Almqvist: MV 6.11 ± 1.13; FV 6.61 + 2.01\n", "Isaksen: MV 5.75 ± 1.07; FV 5.79 + 1.28\n", "Kean: MV 5.84 ± 1.09; FV 6.19 + 1.70\n", "Karamoh: MV 6.09 ± 0.63; FV 6.26 + 0.87\n", "Thauvin: MV 5.71 ± 0.70; FV 5.85 + 0.96\n", "Kouame': MV 6.23 ± 1.19; FV 7.12 + 2.84\n", "Raspadori: MV 5.94 ± 0.94; FV 6.30 + 1.53\n", "Colombo: MV 5.88 ± 1.03; FV 6.31 + 1.72\n", "Luvumbo: MV 5.85 ± 0.80; FV 6.08 + 1.13\n", "Mota: MV 5.87 ± 0.99; FV 6.23 + 1.59\n", "Brenner: MV 5.90 ± 0.95; FV 6.08 + 1.41\n", "Bonazzoli: MV 5.91 ± 0.90; FV 6.24 + 1.40\n", "Djuric: MV 5.99 ± 0.51; FV 6.06 + 0.59\n", "Davis K.: MV 5.90 ± 0.95; FV 6.08 + 1.41\n", "Banda: MV 5.97 ± 0.92; FV 6.25 + 1.39\n", "Defrel: MV 5.76 ± 0.82; FV 5.94 + 1.11\n", "Sansone: MV 6.03 ± 0.97; FV 6.41 + 1.61\n", "Pellegri: MV 5.95 ± 0.61; FV 5.98 + 0.66\n", "Piccoli: MV 5.84 ± 0.78; FV 5.85 + 0.90\n", "Success: MV 5.91 ± 0.81; FV 6.16 + 1.28\n", "Botheim: MV 5.57 ± 0.65; FV 5.57 + 0.64\n", "Lucca: MV 5.76 ± 0.88; FV 6.01 + 1.34\n", "Caso: MV 6.13 ± 1.03; FV 6.64 + 1.94\n", "Jovane: MV 5.76 ± 0.91; FV 5.84 + 1.16\n", "Soule': MV 6.27 ± 0.98; FV 6.72 + 1.76\n", "Pavoletti: MV 5.70 ± 0.85; FV 5.93 + 1.10\n", "Cancellieri: MV 5.77 ± 0.88; FV 5.86 + 1.11\n", "Seck: MV 6.10 ± 0.60; FV 6.21 + 0.66\n", "Alvarez A.: MV 5.95 ± 0.78; FV 6.16 + 1.10\n", "Cuni: MV 5.73 ± 1.02; FV 5.67 + 1.17\n", "Ekuban: MV 6.02 ± 0.54; FV 6.10 + 0.58\n", "Maric: MV 5.96 ± 0.51; FV 5.97 + 0.58\n", "Cruz: MV 5.93 ± 0.87; FV 5.99 + 1.08\n", "Destro: MV 5.66 ± 0.79; FV 5.68 + 0.88\n", "Van Hooijdonk: MV 6.13 ± 0.64; FV 6.25 + 0.84\n", "Ceide: MV 5.86 ± 0.72; FV 5.86 + 0.68\n", "Kvernadze: MV 5.74 ± 1.15; FV 5.69 + 1.39\n", "Ikwuemesi: MV 5.65 ± 0.72; FV 5.60 + 0.74\n", "Puscas: MV 6.04 ± 0.77; FV 6.11 + 0.86\n", "Ake' M.: MV 5.94 ± 0.75; FV 5.96 + 0.95\n", "Braaf: MV 5.67 ± 0.68; FV 5.73 + 0.74\n", "Kallon: MV 5.86 ± 0.78; FV 6.04 + 1.05\n", "Kaio Jorge: MV 5.92 ± 0.64; FV 5.99 + 0.74\n", "Vivaldo: MV 5.90 ± 0.95; FV 6.08 + 1.41\n", "Bidaoui: MV 5.84 ± 1.17; FV 5.86 + 1.45\n", "Shpendi S.: MV 5.91 ± 0.53; FV 5.90 + 0.53\n", "Burnete: MV 5.81 ± 1.00; FV 5.93 + 1.35\n", "Corfitzen: MV 5.79 ± 1.02; FV 5.90 + 1.33\n", "Stewart: MV 5.76 ± 0.91; FV 5.84 + 1.16\n", "Yildiz: MV 5.78 ± 1.06; FV 5.88 + 1.32\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
CarnesecchiPAtalantaJuventus10.056.1405900.4817075.0701390.7159235.9802160.5098920.2303961.0860845.3214551.055452-0.1747960.96532020.727640
MussoPAtalantaJuventus11.0706.1711500.4802945.0388670.6849765.9860300.4948520.2728831.0840605.2558831.019420-0.1564790.98344628.833491
Rossi F.PAtalantaJuventus10.016.1702960.4804705.0378720.6844385.9844730.4946520.2739991.0843745.2543711.018776-0.1562090.98378028.943959
ZappacostaDAtalantaJuventus11.0905.9852590.5220626.2069510.7332746.0015760.613546-0.0195590.8816055.7605961.0504390.3079811.2998150.000000
ToloiDAtalantaJuventus11.0906.0028940.4998776.1960840.6999526.0352640.591494-0.0402560.8923045.8047921.0250370.2780351.2998140.000000
............................................................
HenryAVeronaTorino00.4605.8399200.4442406.1166770.6692895.6319520.4535450.3324640.9069135.4740790.7557540.5771761.2998520.000000
DjuricAVeronaTorino00.005.9887540.2566116.0650000.2932576.0351560.320372-0.1070451.1156075.9775990.4691250.1379291.2997580.000000
KallonAVeronaTorino00.005.8636740.3922026.0448290.5228015.7195280.4140420.2541750.9620035.5927720.6418980.4903061.2998330.000000
CruzAVeronaTorino00.0155.9326670.4346995.9901850.5382536.0152190.528602-0.1148880.9511505.8784940.8803380.0941971.2997730.000000
BraafAVeronaTorino00.005.6656970.3410065.7253230.3700405.5617850.3675060.2073201.0191255.5069730.5346180.2965891.2997930.000000
\n", "

539 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Carnesecchi P Atalanta Juventus 1 0.0 5 6.140590 0.481707 \n", "Musso P Atalanta Juventus 1 1.0 70 6.171150 0.480294 \n", "Rossi F. P Atalanta Juventus 1 0.0 1 6.170296 0.480470 \n", "Zappacosta D Atalanta Juventus 1 1.0 90 5.985259 0.522062 \n", "Toloi D Atalanta Juventus 1 1.0 90 6.002894 0.499877 \n", "... ... ... ... ... ... ... ... ... \n", "Henry A Verona Torino 0 0.4 60 5.839920 0.444240 \n", "Djuric A Verona Torino 0 0.0 0 5.988754 0.256611 \n", "Kallon A Verona Torino 0 0.0 0 5.863674 0.392202 \n", "Cruz A Verona Torino 0 0.0 15 5.932667 0.434699 \n", "Braaf A Verona Torino 0 0.0 0 5.665697 0.341006 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Carnesecchi 5.070139 0.715923 5.980216 0.509892 0.230396 \n", "Musso 5.038867 0.684976 5.986030 0.494852 0.272883 \n", "Rossi F. 5.037872 0.684438 5.984473 0.494652 0.273999 \n", "Zappacosta 6.206951 0.733274 6.001576 0.613546 -0.019559 \n", "Toloi 6.196084 0.699952 6.035264 0.591494 -0.040256 \n", "... ... ... ... ... ... \n", "Henry 6.116677 0.669289 5.631952 0.453545 0.332464 \n", "Djuric 6.065000 0.293257 6.035156 0.320372 -0.107045 \n", "Kallon 6.044829 0.522801 5.719528 0.414042 0.254175 \n", "Cruz 5.990185 0.538253 6.015219 0.528602 -0.114888 \n", "Braaf 5.725323 0.370040 5.561785 0.367506 0.207320 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Carnesecchi 1.086084 5.321455 1.055452 -0.174796 0.965320 \n", "Musso 1.084060 5.255883 1.019420 -0.156479 0.983446 \n", "Rossi F. 1.084374 5.254371 1.018776 -0.156209 0.983780 \n", "Zappacosta 0.881605 5.760596 1.050439 0.307981 1.299815 \n", "Toloi 0.892304 5.804792 1.025037 0.278035 1.299814 \n", "... ... ... ... ... ... \n", "Henry 0.906913 5.474079 0.755754 0.577176 1.299852 \n", "Djuric 1.115607 5.977599 0.469125 0.137929 1.299758 \n", "Kallon 0.962003 5.592772 0.641898 0.490306 1.299833 \n", "Cruz 0.951150 5.878494 0.880338 0.094197 1.299773 \n", "Braaf 1.019125 5.506973 0.534618 0.296589 1.299793 \n", "\n", " Clean Sheet % \n", "player \n", "Carnesecchi 20.727640 \n", "Musso 28.833491 \n", "Rossi F. 28.943959 \n", "Zappacosta 0.000000 \n", "Toloi 0.000000 \n", "... ... \n", "Henry 0.000000 \n", "Djuric 0.000000 \n", "Kallon 0.000000 \n", "Cruz 0.000000 \n", "Braaf 0.000000 \n", "\n", "[539 rows x 19 columns]" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matchday_out = 7\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": 33, "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": 34, "id": "2b637a15", "metadata": {}, "outputs": [], "source": [ "gk_starters = ['Maignan', 'Ochoa', 'Silvestri', 'Consigli', 'Provedel', 'Di Gregorio', 'Meret', 'Milinkovic-Savic V.',\n", " 'Terracciano', 'Sommer', 'Szczesny', 'Skorupski', 'Berisha', 'Musso', 'Radunovic', 'Rui Patricio',\n", " 'Montipo\\'', 'Falcone', 'Martinez Jo.', 'Turati']" ] }, { "cell_type": "code", "execution_count": 35, "id": "60d73507", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sommer (6.16, 0.44); (5.74, 0.61)\n", "Szczesny (6.18, 0.43); (5.77, 0.63)\n", "Meret (5.86, 0.50); (4.14, 1.03)\n", "Provedel (6.18, 0.46); (4.76, 0.82)\n", "Maignan (6.14, 0.47); (4.99, 0.69)\n", "Rui Patricio (5.82, 0.52); (3.28, 1.26)\n", "Skorupski (6.12, 0.43); (5.58, 0.61)\n", "Milinkovic-Savic V. (6.20, 0.44); (5.13, 0.68)\n", "Di Gregorio (6.21, 0.46); (5.06, 0.69)\n", "Falcone (6.18, 0.44); (5.10, 0.67)\n", "Silvestri (5.93, 0.48); (4.16, 1.05)\n", "Terracciano (6.20, 0.45); (5.08, 0.71)\n", "Carnesecchi (6.12, 0.45); (5.20, 0.66)\n", "Radunovic (6.17, 0.44); (5.04, 0.74)\n", "Montipo' (6.19, 0.43); (5.25, 0.62)\n", "Martinez Jo. (6.15, 0.47); (4.63, 0.86)\n", "Ochoa (6.14, 0.47); (3.71, 1.14)\n", "Caprile (6.06, 0.47); (4.00, 1.05)\n", "Turati (6.22, 0.47); (5.05, 0.70)\n", "Consigli (6.04, 0.49); (4.11, 1.00)\n", "Musso (6.15, 0.43); (5.71, 0.61)\n", "Cragno (6.04, 0.49); (3.72, 1.10)\n", "Perin (6.17, 0.44); (5.57, 0.61)\n", "Berisha (6.05, 0.49); (3.77, 1.13)\n", "Christensen O. (6.12, 0.47); (4.45, 0.85)\n", "Sportiello (6.16, 0.45); (5.28, 0.63)\n", "Mirante (6.14, 0.47); (4.99, 0.69)\n", "Sepe (6.16, 0.46); (4.55, 0.87)\n", "Leali (6.15, 0.47); (4.63, 0.86)\n", "Lamanna (6.19, 0.46); (5.04, 0.69)\n", "Sommariva (6.15, 0.47); (4.63, 0.86)\n", "Pegolo (6.06, 0.49); (3.98, 1.04)\n", "Perilli (6.19, 0.42); (5.28, 0.62)\n", "Padelli (5.92, 0.48); (3.93, 1.11)\n", "Scuffet (6.17, 0.44); (5.04, 0.74)\n", "Gollini (5.86, 0.50); (4.14, 1.03)\n", "Perisan (5.90, 0.49); (3.73, 1.17)\n", "Audero (6.16, 0.44); (5.74, 0.61)\n", "Di Gennaro (6.16, 0.44); (5.74, 0.61)\n", "Pinsoglio (6.18, 0.43); (5.78, 0.63)\n", "Aresti (6.17, 0.44); (5.04, 0.74)\n", "Fiorillo (6.14, 0.47); (3.71, 1.14)\n", "Cerofolini (6.23, 0.47); (5.05, 0.70)\n", "Rossi F. (6.15, 0.43); (5.71, 0.61)\n", "Costil (6.14, 0.47); (3.71, 1.14)\n", "Ravaglia F. (6.12, 0.43); (5.58, 0.61)\n", "Frattali (6.22, 0.47); (5.05, 0.70)\n", "Contini (5.86, 0.50); (4.14, 1.03)\n", "Brancolini (6.17, 0.44); (5.10, 0.66)\n", "Berardi A. (6.19, 0.42); (5.28, 0.62)\n", "Gemello (6.21, 0.43); (5.16, 0.67)\n", "Boer (5.82, 0.52); (3.28, 1.26)\n", "Bagnolini (6.12, 0.43); (5.58, 0.61)\n", "Svilar (5.82, 0.52); (3.28, 1.26)\n", "Sorrentino A. (6.20, 0.46); (5.04, 0.69)\n", "Martinelli T. (6.20, 0.45); (5.07, 0.70)\n", "Popa (6.21, 0.43); (5.16, 0.67)\n", "Stubljar (6.05, 0.49); (3.77, 1.13)\n", "Gori (6.19, 0.46); (5.04, 0.69)\n", "Borbei (6.17, 0.44); (5.10, 0.66)\n", "Okoye (5.92, 0.48); (3.93, 1.11)\n", "Mandas (6.16, 0.46); (4.55, 0.87)\n", "Dimarco (6.28, 0.38); (6.61, 0.67)\n", "Di Lorenzo (6.25, 0.51); (6.74, 0.94)\n", "Hernandez T. (6.16, 0.55); (6.59, 0.95)\n", "Carlos Augusto (6.15, 0.41); (6.46, 0.66)\n", "Danilo (6.17, 0.47); (6.48, 0.75)\n", "Zappacosta (6.11, 0.49); (6.43, 0.78)\n", "Schuurs (6.08, 0.44); (6.27, 0.63)\n", "Posch (5.98, 0.41); (6.10, 0.59)\n", "Bastoni (6.22, 0.41); (6.38, 0.52)\n", "Smalling (6.03, 0.42); (6.23, 0.60)\n", "Dumfries (6.21, 0.45); (6.64, 0.82)\n", "Romagnoli (6.08, 0.47); (6.20, 0.59)\n", "Pavard (6.04, 0.31); (6.13, 0.37)\n", "Rrahmani (6.05, 0.50); (6.22, 0.66)\n", "Spinazzola (6.10, 0.37); (6.35, 0.61)\n", "Buongiorno (6.04, 0.47); (6.26, 0.72)\n", "Bremer (6.04, 0.48); (6.19, 0.66)\n", "Tomori (6.15, 0.49); (6.41, 0.75)\n", "Biraghi (6.09, 0.50); (6.54, 0.92)\n", "Mancini (5.88, 0.52); (6.07, 0.72)\n", "Darmian (6.14, 0.37); (6.33, 0.50)\n", "Bakker (6.00, 0.32); (6.10, 0.44)\n", "Mazzocchi (5.72, 0.39); (5.74, 0.43)\n", "Doig (6.01, 0.49); (6.24, 0.72)\n", "Calabria (6.02, 0.45); (6.17, 0.62)\n", "Acerbi (6.04, 0.32); (6.09, 0.33)\n", "Cuadrado (6.03, 0.39); (6.12, 0.48)\n", "Ebuehi (5.78, 0.41); (5.81, 0.50)\n", "Casale (5.94, 0.44); (5.96, 0.53)\n", "Holm (6.03, 0.33); (6.14, 0.42)\n", "Baschirotto (5.92, 0.53); (6.02, 0.66)\n", "Bijol (5.77, 0.52); (5.83, 0.65)\n", "Thiaw (5.82, 0.62); (5.77, 0.65)\n", "Mario Rui (5.93, 0.36); (5.95, 0.40)\n", "Milenkovic (5.85, 0.56); (5.90, 0.68)\n", "Rodriguez R. (5.98, 0.37); (5.98, 0.38)\n", "Kolasinac (6.00, 0.37); (6.12, 0.49)\n", "N'dicka (5.86, 0.42); (5.85, 0.48)\n", "Scalvini (6.01, 0.51); (6.16, 0.67)\n", "Perez N. (5.80, 0.50); (5.81, 0.61)\n", "Kristensen (5.97, 0.33); (6.14, 0.49)\n", "Izzo (5.93, 0.46); (5.97, 0.56)\n", "De Vrij (6.17, 0.38); (6.27, 0.42)\n", "Faraoni (5.78, 0.37); (5.80, 0.45)\n", "Toloi (6.05, 0.46); (6.18, 0.61)\n", "Kyriakopoulos (6.05, 0.48); (6.22, 0.68)\n", "Bellanova (5.73, 0.56); (5.77, 0.65)\n", "Mari' (5.89, 0.47); (5.90, 0.56)\n", "Dodo' (5.85, 0.54); (5.93, 0.69)\n", "Lucumi' (5.93, 0.38); (5.92, 0.43)\n", "Hien (5.91, 0.41); (5.87, 0.44)\n", "Natan (6.03, 0.41); (6.12, 0.49)\n", "Hysaj (5.92, 0.39); (5.95, 0.49)\n", "D'ambrosio (5.93, 0.34); (5.90, 0.35)\n", "Luperto (5.64, 0.59); (5.58, 0.66)\n", "Djimsiti (6.01, 0.36); (6.03, 0.38)\n", "Marusic (5.88, 0.46); (5.84, 0.52)\n", "Martin (5.87, 0.45); (5.91, 0.57)\n", "Mina (6.03, 0.41); (6.26, 0.63)\n", "Toljan (5.86, 0.44); (5.86, 0.50)\n", "Llorente D. (5.85, 0.39); (5.81, 0.40)\n", "Martinez Quarta (6.06, 0.58); (6.30, 0.83)\n", "Bastoni S. (5.94, 0.50); (6.20, 0.79)\n", "Dragusin (6.03, 0.44); (6.19, 0.62)\n", "Parisi (6.05, 0.50); (6.24, 0.72)\n", "Bradaric (5.80, 0.44); (5.81, 0.52)\n", "Kamara H. (5.92, 0.27); (5.92, 0.29)\n", "Olivera (5.97, 0.34); (6.03, 0.41)\n", "Gendrey (5.93, 0.35); (5.93, 0.38)\n", "Kristiansen (6.00, 0.38); (6.07, 0.49)\n", "Beukema (5.98, 0.41); (6.03, 0.49)\n", "Dossena (5.73, 0.42); (5.66, 0.43)\n", "Pedersen (5.91, 0.30); (5.90, 0.31)\n", "Juan Jesus (6.00, 0.34); (6.05, 0.35)\n", "Gyomber (5.80, 0.46); (5.74, 0.49)\n", "Alex Sandro (5.82, 0.51); (5.70, 0.54)\n", "Hateboer (5.92, 0.45); (6.07, 0.65)\n", "Palomino (6.01, 0.31); (6.06, 0.35)\n", "Marchizza (6.10, 0.43); (6.31, 0.62)\n", "Zappa (5.75, 0.38); (5.69, 0.38)\n", "Gallo (5.93, 0.42); (5.91, 0.45)\n", "Caldirola (5.82, 0.51); (5.87, 0.64)\n", "Kalulu (5.92, 0.50); (5.95, 0.59)\n", "Erlic (5.89, 0.46); (5.83, 0.46)\n", "Vojvoda (5.93, 0.36); (5.97, 0.44)\n", "Vasquez (6.09, 0.36); (6.15, 0.37)\n", "Cambiaso (6.00, 0.43); (6.07, 0.50)\n", "Pongracic (6.03, 0.40); (6.06, 0.44)\n", "Viti (5.89, 0.45); (5.82, 0.43)\n", "Gatti (5.76, 0.62); (5.69, 0.64)\n", "Birindelli (5.93, 0.35); (5.92, 0.39)\n", "Azzi (5.90, 0.28); (5.89, 0.28)\n", "Wieteska (5.92, 0.44); (5.92, 0.52)\n", "Masina (5.78, 0.49); (6.08, 0.69)\n", "Romagnoli S. (6.08, 0.53); (6.32, 0.81)\n", "Pezzella Giu. (5.64, 0.44); (5.55, 0.46)\n", "Sabelli (5.98, 0.28); (6.02, 0.34)\n", "Lirola (6.03, 0.49); (6.21, 0.69)\n", "Lazzari (5.99, 0.37); (6.01, 0.40)\n", "Bani (6.07, 0.53); (6.31, 0.80)\n", "Djidji (5.88, 0.38); (5.90, 0.45)\n", "Kabasele (5.86, 0.35); (5.83, 0.41)\n", "Lazaro (6.00, 0.35); (6.04, 0.40)\n", "Augello (5.87, 0.36); (5.92, 0.45)\n", "Zortea (6.04, 0.43); (6.29, 0.65)\n", "Dawidowicz (5.90, 0.39); (5.86, 0.44)\n", "Pirola (5.70, 0.45); (5.69, 0.51)\n", "Lovato (5.69, 0.44); (5.60, 0.47)\n", "Ruggeri (6.10, 0.53); (6.43, 0.83)\n", "Vina (5.67, 0.56); (5.67, 0.63)\n", "Obert (5.75, 0.42); (5.69, 0.44)\n", "Terracciano F. (6.02, 0.36); (6.08, 0.42)\n", "Ebosele (5.80, 0.41); (5.75, 0.46)\n", "Zemura (5.89, 0.29); (5.86, 0.31)\n", "Hatzidiakos (5.89, 0.42); (5.88, 0.46)\n", "Patric (5.94, 0.33); (5.92, 0.33)\n", "Lykogiannis (5.92, 0.27); (5.92, 0.32)\n", "Pellegrini Lu. (5.81, 0.34); (5.74, 0.34)\n", "Magnani (5.93, 0.46); (5.92, 0.52)\n", "Ranieri L. (5.78, 0.50); (5.82, 0.61)\n", "Carboni A. (5.97, 0.37); (6.01, 0.44)\n", "Calafiori (5.84, 0.44); (5.82, 0.53)\n", "Monterisi (5.98, 0.62); (6.40, 1.05)\n", "Ismajli (5.78, 0.48); (5.69, 0.49)\n", "De Winter (5.93, 0.46); (5.90, 0.50)\n", "Tressoldi (5.91, 0.45); (5.94, 0.53)\n", "Ehizibue (5.77, 0.44); (5.77, 0.56)\n", "Vogliacco (5.94, 0.46); (5.94, 0.52)\n", "Ferrari G. (5.91, 0.50); (5.97, 0.62)\n", "Venuti (5.89, 0.36); (5.86, 0.39)\n", "Karsdorp (5.89, 0.29); (5.87, 0.30)\n", "Kjaer (5.67, 0.49); (5.54, 0.50)\n", "Gunter (5.74, 0.52); (5.64, 0.55)\n", "Soumaoro (5.88, 0.47); (5.84, 0.54)\n", "Di Pardo (5.80, 0.41); (5.75, 0.43)\n", "Zanoli (6.07, 0.48); (6.35, 0.75)\n", "Zima (5.97, 0.46); (5.97, 0.50)\n", "Hefti (5.84, 0.38); (5.79, 0.36)\n", "Ostigard (5.83, 0.38); (5.79, 0.38)\n", "Sambia (5.89, 0.38); (5.88, 0.41)\n", "Bisseck (5.99, 0.42); (6.08, 0.52)\n", "Oyono (5.89, 0.35); (5.85, 0.35)\n", "Ferreira J. (5.82, 0.33); (5.77, 0.36)\n", "Dorgu (5.95, 0.24); (5.94, 0.23)\n", "Touba (5.96, 0.43); (6.02, 0.52)\n", "Sazonov (5.96, 0.40); (5.99, 0.48)\n", "Rugani (5.98, 0.26); (5.99, 0.25)\n", "De Sciglio (5.88, 0.32); (5.86, 0.31)\n", "Goldaniga (5.65, 0.58); (5.56, 0.62)\n", "Florenzi (6.06, 0.38); (6.14, 0.45)\n", "De Silvestri (6.02, 0.28); (6.06, 0.31)\n", "Pereira P. (5.97, 0.42); (6.02, 0.51)\n", "Fazio (5.86, 0.61); (5.96, 0.77)\n", "Bereszynski (5.64, 0.48); (5.58, 0.54)\n", "Bonifazi (5.84, 0.40); (5.79, 0.43)\n", "Walukiewicz (5.70, 0.55); (5.69, 0.64)\n", "Okoli (5.86, 0.41); (5.81, 0.42)\n", "Kumbulla (5.50, 0.73); (5.27, 0.69)\n", "Celik (5.75, 0.45); (5.68, 0.50)\n", "Amione (5.72, 0.44); (5.70, 0.53)\n", "Daniliuc (5.77, 0.47); (5.74, 0.56)\n", "Soppy (5.93, 0.34); (5.93, 0.40)\n", "Haps (5.96, 0.46); (6.02, 0.58)\n", "Cittadini (5.95, 0.44); (6.02, 0.57)\n", "Coppola D. (5.85, 0.35); (5.78, 0.36)\n", "Cacace (5.64, 0.43); (5.54, 0.43)\n", "Ebosse (5.83, 0.35); (5.76, 0.39)\n", "Guessand A. (5.89, 0.43); (5.92, 0.55)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Cabal (6.04, 0.46); (6.10, 0.55)\n", "Missori (5.95, 0.45); (5.99, 0.54)\n", "Kayode (6.03, 0.48); (6.10, 0.59)\n", "Corazza (5.84, 0.37); (5.81, 0.42)\n", "Kristensen T. (5.77, 0.41); (5.74, 0.47)\n", "Dermaku (5.95, 0.42); (5.99, 0.52)\n", "Tonelli (5.64, 0.49); (5.53, 0.51)\n", "Capradossi (5.90, 0.44); (5.93, 0.53)\n", "Bettella (5.95, 0.44); (6.02, 0.57)\n", "Amey (5.92, 0.41); (5.97, 0.54)\n", "Gila (5.89, 0.42); (5.86, 0.46)\n", "Bronn (5.68, 0.45); (5.56, 0.47)\n", "Guarino (5.78, 0.48); (5.81, 0.59)\n", "Carboni F. (6.04, 0.44); (6.18, 0.59)\n", "Smajlovic (5.96, 0.44); (6.03, 0.55)\n", "Matturro (5.93, 0.45); (5.91, 0.48)\n", "N'guessan (5.95, 0.43); (6.00, 0.53)\n", "Mateus Lusuardi (5.95, 0.46); (6.01, 0.57)\n", "Kalaj (5.95, 0.46); (6.01, 0.57)\n", "Pierozzi (5.97, 0.47); (6.03, 0.59)\n", "Huijsen (6.00, 0.44); (6.11, 0.56)\n", "Bonfanti (6.00, 0.45); (6.10, 0.58)\n", "Pellegrino (5.97, 0.46); (6.03, 0.57)\n", "Comuzzo (5.97, 0.47); (6.03, 0.59)\n", "Zaccagni (6.30, 0.53); (6.91, 1.12)\n", "Koopmeiners (6.37, 0.55); (7.10, 1.25)\n", "Luis Alberto (6.30, 0.54); (6.98, 1.19)\n", "Felipe Anderson (6.10, 0.55); (6.60, 1.01)\n", "Rabiot (6.23, 0.55); (6.86, 1.16)\n", "Zielinski (6.28, 0.47); (6.77, 0.93)\n", "Barella (6.23, 0.45); (6.64, 0.80)\n", "Pulisic (6.26, 0.59); (7.02, 1.31)\n", "Orsolini (6.03, 0.52); (6.48, 0.98)\n", "Calhanoglu (6.34, 0.40); (6.63, 0.66)\n", "Strefezza (6.09, 0.44); (6.42, 0.76)\n", "Chukwueze (5.94, 0.39); (6.17, 0.57)\n", "Ferguson (6.13, 0.43); (6.46, 0.75)\n", "Candreva (6.21, 0.63); (6.94, 1.30)\n", "Frattesi (6.22, 0.51); (6.75, 1.00)\n", "Samardzic (6.11, 0.47); (6.53, 0.85)\n", "Vlasic (6.04, 0.47); (6.40, 0.79)\n", "Bonaventura (6.32, 0.55); (7.00, 1.20)\n", "Politano (6.33, 0.50); (6.92, 1.07)\n", "El Shaarawy (6.10, 0.40); (6.40, 0.69)\n", "Mkhitaryan (6.29, 0.51); (6.90, 1.06)\n", "Aouar (5.97, 0.53); (6.43, 0.89)\n", "Malinovskyi (6.04, 0.56); (6.63, 1.11)\n", "Gudmundsson A. (6.25, 0.49); (6.79, 0.99)\n", "Kamada (6.07, 0.48); (6.42, 0.80)\n", "Pellegrini Lo. (5.93, 0.53); (6.35, 0.87)\n", "Kostic (6.14, 0.44); (6.49, 0.74)\n", "Radonjic (6.26, 0.59); (7.04, 1.33)\n", "Baldanzi (5.95, 0.53); (6.37, 0.88)\n", "Lovric (6.00, 0.41); (6.27, 0.66)\n", "Lindstrom (6.04, 0.39); (6.33, 0.66)\n", "Lazovic (6.12, 0.44); (6.43, 0.73)\n", "Pereyra (6.05, 0.56); (6.55, 1.01)\n", "Renato Sanches (6.10, 0.36); (6.32, 0.56)\n", "Pessina (6.07, 0.48); (6.31, 0.73)\n", "Guendouzi (5.97, 0.36); (6.06, 0.47)\n", "Loftus-Cheek (6.19, 0.45); (6.54, 0.75)\n", "Zambo Anguissa (6.05, 0.46); (6.26, 0.65)\n", "Elmas (6.00, 0.50); (6.35, 0.81)\n", "Bajrami (6.08, 0.36); (6.28, 0.54)\n", "Ricci S. (5.99, 0.41); (6.10, 0.55)\n", "Colpani (6.34, 0.53); (7.03, 1.19)\n", "Ciurria (6.03, 0.51); (6.39, 0.85)\n", "De Roon (6.12, 0.47); (6.41, 0.73)\n", "Pogba (6.04, 0.42); (6.15, 0.52)\n", "Cristante (6.08, 0.50); (6.38, 0.78)\n", "Locatelli (5.98, 0.38); (6.03, 0.45)\n", "Pasalic (6.00, 0.52); (6.47, 0.91)\n", "Lobotka (6.06, 0.40); (6.16, 0.48)\n", "Fagioli (6.07, 0.49); (6.40, 0.78)\n", "Ikone' (6.08, 0.53); (6.56, 0.96)\n", "Ilic (6.00, 0.37); (6.05, 0.46)\n", "Ndoye (5.94, 0.35); (5.99, 0.43)\n", "Ederson D.s. (6.09, 0.46); (6.38, 0.72)\n", "Reijnders (6.13, 0.44); (6.43, 0.70)\n", "Barak (5.87, 0.44); (6.07, 0.61)\n", "Saponara (6.06, 0.40); (6.31, 0.63)\n", "Mandragora (6.02, 0.51); (6.36, 0.82)\n", "Weah (5.96, 0.27); (5.99, 0.29)\n", "Bennacer (6.16, 0.44); (6.49, 0.71)\n", "Duda (6.26, 0.52); (6.82, 1.06)\n", "Castrovilli (6.08, 0.54); (6.56, 0.97)\n", "Mckennie (6.21, 0.39); (6.39, 0.52)\n", "Miranchuk (6.24, 0.49); (6.69, 0.91)\n", "Matheus Henrique (5.99, 0.46); (6.25, 0.69)\n", "De Ketelaere (6.08, 0.51); (6.47, 0.85)\n", "Mboula (5.92, 0.39); (5.93, 0.47)\n", "Paredes (5.82, 0.49); (5.85, 0.60)\n", "Sottil (5.94, 0.35); (6.08, 0.43)\n", "Klaassen (6.10, 0.39); (6.38, 0.66)\n", "Arthur Melo (6.06, 0.40); (6.15, 0.50)\n", "Thorsby (5.92, 0.60); (6.36, 0.99)\n", "Nandez (5.99, 0.34); (6.11, 0.48)\n", "Tameze (5.92, 0.31); (5.90, 0.33)\n", "Marin (5.89, 0.39); (5.97, 0.52)\n", "Messias (6.03, 0.56); (6.59, 1.07)\n", "Musah (6.01, 0.34); (6.06, 0.40)\n", "Coulibaly L. (5.99, 0.49); (6.22, 0.73)\n", "Krunic (5.97, 0.38); (5.99, 0.43)\n", "Cataldi (5.98, 0.35); (5.98, 0.38)\n", "Strootman (5.96, 0.34); (6.01, 0.44)\n", "Duncan (6.17, 0.43); (6.51, 0.74)\n", "Freuler (5.94, 0.28); (5.94, 0.33)\n", "Gagliardini (6.14, 0.47); (6.48, 0.77)\n", "Mazzitelli (6.10, 0.68); (6.75, 1.31)\n", "Jankto (5.94, 0.30); (5.94, 0.33)\n", "Kastanos (5.94, 0.30); (6.02, 0.36)\n", "Gyasi (5.69, 0.40); (5.70, 0.47)\n", "Reinier (5.96, 0.47); (6.05, 0.59)\n", "Zalewski (5.86, 0.34); (5.94, 0.41)\n", "Harroui (6.17, 0.45); (6.52, 0.76)\n", "Frendrup (6.04, 0.33); (6.14, 0.41)\n", "Blin (5.95, 0.26); (5.95, 0.27)\n", "Fabbian (5.94, 0.39); (6.17, 0.67)\n", "Ramadani (6.09, 0.41); (6.21, 0.50)\n", "Cajuste (5.96, 0.47); (6.02, 0.58)\n", "Mancosu (5.89, 0.45); (5.92, 0.55)\n", "Vecino (6.00, 0.48); (6.16, 0.68)\n", "Sensi (6.14, 0.45); (6.48, 0.72)\n", "Walace (5.81, 0.37); (5.76, 0.43)\n", "Lopez M. (5.92, 0.42); (5.89, 0.47)\n", "Brescianini (5.94, 0.32); (5.93, 0.34)\n", "Bove (5.88, 0.41); (6.07, 0.58)\n", "Aebischer (5.95, 0.30); (6.00, 0.37)\n", "Thorstvedt (5.95, 0.33); (6.01, 0.39)\n", "Gonzalez J. (5.89, 0.38); (5.95, 0.49)\n", "Moro N. (6.02, 0.35); (6.17, 0.51)\n", "Oudin (6.07, 0.46); (6.38, 0.75)\n", "Boloca (5.99, 0.49); (6.05, 0.60)\n", "Rafia (5.94, 0.33); (6.09, 0.47)\n", "Makoumbou (5.90, 0.30); (5.92, 0.36)\n", "Kaba (5.85, 0.37); (5.76, 0.39)\n", "Badelj (5.87, 0.44); (5.83, 0.47)\n", "Machin (5.94, 0.45); (6.02, 0.59)\n", "Linetty (5.93, 0.35); (5.94, 0.40)\n", "Castillejo (5.91, 0.34); (6.07, 0.46)\n", "Rovella (6.04, 0.45); (6.13, 0.57)\n", "Pobega (5.94, 0.26); (5.97, 0.30)\n", "Hongla (5.93, 0.31); (5.92, 0.33)\n", "Miretti (5.92, 0.32); (5.94, 0.37)\n", "Fazzini (5.74, 0.36); (5.67, 0.37)\n", "Iling Junior (6.00, 0.45); (6.12, 0.58)\n", "Oristanio (5.90, 0.30); (5.88, 0.31)\n", "Serdar (5.93, 0.33); (5.93, 0.37)\n", "Payero (5.82, 0.38); (5.80, 0.45)\n", "Grassi (5.76, 0.43); (5.68, 0.46)\n", "Baez (5.89, 0.32); (5.86, 0.35)\n", "Deiola (5.66, 0.40); (5.62, 0.43)\n", "Garritano (6.10, 0.40); (6.18, 0.47)\n", "Bourabia (5.96, 0.38); (6.01, 0.47)\n", "Saelemaekers (5.86, 0.39); (6.00, 0.54)\n", "Maldini (5.93, 0.42); (6.21, 0.67)\n", "Racic (5.97, 0.35); (5.99, 0.39)\n", "Kovalenko (5.86, 0.39); (5.83, 0.43)\n", "Maleh (5.70, 0.47); (5.67, 0.56)\n", "Bohinen (5.91, 0.26); (5.88, 0.26)\n", "Ranocchia F. (6.01, 0.41); (6.25, 0.61)\n", "Folorunsho (5.86, 0.43); (6.08, 0.64)\n", "Infantino (5.96, 0.44); (5.99, 0.52)\n", "Martegani (5.98, 0.37); (6.02, 0.45)\n", "Kutlu (5.98, 0.44); (5.99, 0.48)\n", "Tchatchoua (5.95, 0.44); (6.02, 0.57)\n", "Quina (5.99, 0.40); (6.08, 0.52)\n", "Adopo (6.00, 0.49); (6.10, 0.62)\n", "Romero L. (6.00, 0.41); (6.12, 0.55)\n", "Basic (5.97, 0.36); (6.03, 0.44)\n", "Asllani (6.08, 0.40); (6.16, 0.46)\n", "Tchaouna (5.88, 0.39); (5.89, 0.48)\n", "Sulemana I. (5.75, 0.34); (5.69, 0.34)\n", "Barrenechea (5.93, 0.34); (5.90, 0.35)\n", "Gelli (5.97, 0.47); (6.03, 0.57)\n", "Suslov (5.94, 0.33); (5.95, 0.38)\n", "Gaetano (6.05, 0.47); (6.53, 0.90)\n", "Jagiello (5.96, 0.46); (5.97, 0.51)\n", "Obiang (5.92, 0.28); (5.90, 0.29)\n", "Maggiore (5.91, 0.27); (5.88, 0.29)\n", "Akpa Akpro (5.94, 0.45); (6.02, 0.59)\n", "Urbanski (5.85, 0.42); (5.87, 0.54)\n", "Volpato (5.96, 0.45); (6.10, 0.62)\n", "Vignato S. (5.85, 0.39); (5.82, 0.45)\n", "Hrustic (5.69, 0.30); (5.65, 0.30)\n", "Zarraga (5.76, 0.43); (5.75, 0.51)\n", "Camara E. (5.85, 0.45); (5.91, 0.60)\n", "Amatucci (5.98, 0.47); (6.07, 0.60)\n", "Pagano (6.09, 0.39); (6.23, 0.50)\n", "Prati (5.92, 0.45); (5.95, 0.53)\n", "Viola (5.92, 0.37); (5.92, 0.41)\n", "Lulic K. (5.96, 0.47); (6.05, 0.59)\n", "Rog (5.87, 0.36); (5.85, 0.39)\n", "Nicolussi Caviglia (5.83, 0.49); (5.91, 0.63)\n", "Demme (5.99, 0.27); (5.98, 0.24)\n", "Pafundi (5.93, 0.40); (5.93, 0.45)\n", "Adli (5.91, 0.44); (5.91, 0.52)\n", "Bondo (5.96, 0.43); (6.03, 0.56)\n", "Zerbin (5.93, 0.38); (5.93, 0.45)\n", "Carboni V. (5.89, 0.46); (5.94, 0.59)\n", "Faticanti (5.96, 0.45); (6.03, 0.58)\n", "Gineitis (5.96, 0.42); (6.02, 0.53)\n", "Belardinelli (5.81, 0.47); (5.86, 0.60)\n", "El Azzouzi (5.88, 0.36); (5.84, 0.39)\n", "Lipani (5.95, 0.44); (6.00, 0.55)\n", "Joselito (5.95, 0.44); (6.02, 0.57)\n", "Legowski (5.95, 0.47); (6.07, 0.64)\n", "Ibrahimovic A. (5.96, 0.47); (6.05, 0.59)\n", "Osimhen (6.47, 0.76); (7.90, 2.05)\n", "Martinez L. (6.47, 0.71); (7.97, 2.04)\n", "Rafael Leao (6.45, 0.63); (7.59, 1.68)\n", "Lukaku (6.25, 0.74); (7.33, 1.65)\n", "Berardi (6.48, 0.66); (7.77, 1.83)\n", "Immobile (6.15, 0.65); (7.02, 1.41)\n", "Vlahovic (6.34, 0.75); (7.49, 1.78)\n", "Dybala (6.32, 0.76); (7.48, 1.77)\n", "Kvaratskhelia (6.39, 0.64); (7.46, 1.64)\n", "Giroud (6.38, 0.65); (7.56, 1.74)\n", "Scamacca (6.31, 0.72); (7.47, 1.74)\n", "Thuram (6.43, 0.58); (7.37, 1.47)\n", "Lookman (6.37, 0.68); (7.55, 1.75)\n", "Dia (6.26, 0.72); (7.39, 1.68)\n", "Arnautovic (6.25, 0.50); (6.81, 1.02)\n", "Retegui (6.15, 0.69); (7.05, 1.49)\n", "Sanabria (6.04, 0.56); (6.68, 1.10)\n", "Nzola (5.95, 0.54); (6.43, 0.91)\n", "Lauriente' (6.32, 0.59); (7.11, 1.35)\n", "Zapata D. (6.03, 0.44); (6.36, 0.74)\n", "Chiesa (6.42, 0.59); (7.39, 1.50)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Milik (6.18, 0.46); (6.62, 0.88)\n", "Gonzalez N. (6.37, 0.58); (7.27, 1.42)\n", "Okafor (6.14, 0.46); (6.55, 0.84)\n", "Pinamonti (5.99, 0.59); (6.57, 1.07)\n", "Beltran L. (5.96, 0.45); (6.34, 0.76)\n", "Caprari (6.04, 0.50); (6.40, 0.82)\n", "Sanchez (6.03, 0.44); (6.45, 0.81)\n", "Caputo (5.77, 0.46); (6.08, 0.68)\n", "Toure' E. (6.00, 0.45); (6.14, 0.60)\n", "Krstovic (6.27, 0.52); (6.87, 1.09)\n", "Belotti (6.04, 0.51); (6.57, 0.96)\n", "Muriel (6.19, 0.46); (6.58, 0.86)\n", "Lapadula (5.99, 0.50); (6.52, 0.97)\n", "Jovic (6.03, 0.58); (6.61, 1.06)\n", "Abraham (6.07, 0.58); (6.78, 1.16)\n", "Zirkzee (6.22, 0.47); (6.68, 0.92)\n", "Ngonge (5.94, 0.54); (6.41, 0.91)\n", "Petagna (5.95, 0.52); (6.39, 0.90)\n", "Simeone (6.08, 0.61); (6.78, 1.20)\n", "Deulofeu (6.29, 0.58); (7.11, 1.37)\n", "Pedro (6.00, 0.45); (6.27, 0.69)\n", "Shomurodov (5.72, 0.29); (5.68, 0.27)\n", "Azmoun (5.88, 0.36); (6.14, 0.57)\n", "Castellanos (6.06, 0.36); (6.13, 0.42)\n", "Cheddira (6.14, 0.63); (6.89, 1.30)\n", "Karlsson (5.95, 0.41); (6.26, 0.69)\n", "Brekalo (6.08, 0.56); (6.64, 1.04)\n", "Cambiaghi (5.92, 0.48); (6.20, 0.76)\n", "Henry (5.83, 0.43); (6.09, 0.64)\n", "Mulattieri (6.02, 0.35); (6.32, 0.65)\n", "Almqvist (6.15, 0.53); (6.61, 0.96)\n", "Isaksen (5.87, 0.45); (5.89, 0.55)\n", "Kean (5.99, 0.57); (6.48, 1.02)\n", "Karamoh (6.03, 0.39); (6.27, 0.60)\n", "Thauvin (5.70, 0.34); (5.81, 0.44)\n", "Kouame' (6.09, 0.59); (6.79, 1.20)\n", "Raspadori (5.97, 0.50); (6.40, 0.85)\n", "Colombo (5.87, 0.50); (6.25, 0.82)\n", "Luvumbo (5.97, 0.33); (6.14, 0.50)\n", "Mota (5.84, 0.49); (6.15, 0.74)\n", "Brenner (5.87, 0.44); (5.95, 0.59)\n", "Bonazzoli (5.94, 0.45); (6.27, 0.72)\n", "Djuric (5.98, 0.26); (6.06, 0.30)\n", "Davis K. (5.87, 0.44); (5.95, 0.59)\n", "Banda (6.06, 0.40); (6.28, 0.60)\n", "Defrel (5.75, 0.40); (5.94, 0.55)\n", "Sansone (6.12, 0.46); (6.53, 0.84)\n", "Pellegri (5.85, 0.34); (5.88, 0.39)\n", "Piccoli (5.95, 0.32); (5.99, 0.37)\n", "Success (5.85, 0.39); (6.05, 0.58)\n", "Botheim (5.63, 0.35); (5.67, 0.38)\n", "Lucca (5.73, 0.42); (5.94, 0.59)\n", "Caso (6.09, 0.45); (6.48, 0.82)\n", "Jovane (5.94, 0.47); (6.09, 0.66)\n", "Soule' (6.30, 0.40); (6.65, 0.73)\n", "Pavoletti (5.81, 0.37); (6.01, 0.56)\n", "Cancellieri (5.78, 0.46); (5.88, 0.62)\n", "Seck (6.09, 0.33); (6.21, 0.40)\n", "Alvarez A. (5.92, 0.41); (6.17, 0.62)\n", "Cuni (5.84, 0.38); (5.80, 0.40)\n", "Ekuban (5.94, 0.30); (5.97, 0.30)\n", "Maric (5.95, 0.24); (5.95, 0.25)\n", "Cruz (5.94, 0.44); (6.07, 0.60)\n", "Destro (5.67, 0.41); (5.73, 0.48)\n", "Van Hooijdonk (6.00, 0.36); (6.09, 0.48)\n", "Ceide (5.81, 0.38); (5.85, 0.39)\n", "Kvernadze (5.89, 0.44); (5.91, 0.53)\n", "Ikwuemesi (5.81, 0.36); (5.81, 0.40)\n", "Puscas (5.94, 0.45); (5.96, 0.51)\n", "Ake' M. (5.92, 0.37); (5.96, 0.46)\n", "Braaf (5.68, 0.33); (5.78, 0.40)\n", "Kallon (5.85, 0.40); (6.05, 0.55)\n", "Kaio Jorge (5.92, 0.27); (5.92, 0.28)\n", "Vivaldo (5.87, 0.44); (5.95, 0.59)\n", "Bidaoui (5.96, 0.47); (6.08, 0.62)\n", "Shpendi S. (5.88, 0.29); (5.90, 0.33)\n", "Burnete (6.01, 0.45); (6.16, 0.61)\n", "Corfitzen (5.97, 0.45); (6.10, 0.61)\n", "Stewart (5.94, 0.47); (6.09, 0.66)\n", "Yildiz (6.01, 0.46); (6.16, 0.60)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
Rossi F.PAtalantaAvg1006.1545250.4297695.7103400.6084286.0610850.4786730.1438721.0923866.4153440.598177-0.7697861.14894956.114355
MussoPAtalantaAvg111006.1545170.4301995.7078460.6083436.0602650.4788300.1450621.0923296.4119380.599186-0.7679921.14858156.005341
CarnesecchiPAtalantaAvg1006.1215010.4498495.1993590.6644096.0492850.5107740.1062781.0921195.6468190.903720-0.3643651.02785927.208376
ZappacostaDAtalantaAvg11836.1062010.4891436.4309540.7845396.0567910.5601620.0649600.8773535.8464071.0455970.3980341.2998410.000000
RuggeriDAtalantaAvg111006.1001990.5259286.4278300.8293786.0770050.6081890.0281100.8538735.8375521.1270700.3748611.2998390.000000
............................................................
HenryAVeronaAvg10165.8285180.4289706.0863430.6425575.6312630.4381630.3265360.9226815.4741990.7308400.5697871.2998490.000000
CruzAVeronaAvg1005.9433050.4443526.0657400.5980425.9491320.523503-0.0090820.9387805.7469090.8841580.2626321.2998020.000000
DjuricAVeronaAvg10835.9822390.2589926.0616400.3049346.0233190.321768-0.0944471.1126155.9560680.4812840.1619871.2997650.000000
KallonAVeronaAvg1005.8514570.4004506.0507250.5516215.6900240.4169880.2818360.9531695.5518190.6554380.5245931.2998380.000000
BraafAVeronaAvg1005.6754300.3319335.7833490.4010815.5545060.3481080.2537661.0310605.4871670.5366150.3933381.2998120.000000
\n", "

539 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Rossi F. P Atalanta Avg 1 0 0 6.154525 0.429769 \n", "Musso P Atalanta Avg 1 1 100 6.154517 0.430199 \n", "Carnesecchi P Atalanta Avg 1 0 0 6.121501 0.449849 \n", "Zappacosta D Atalanta Avg 1 1 83 6.106201 0.489143 \n", "Ruggeri D Atalanta Avg 1 1 100 6.100199 0.525928 \n", "... ... ... ... ... ... ... ... ... \n", "Henry A Verona Avg 1 0 16 5.828518 0.428970 \n", "Cruz A Verona Avg 1 0 0 5.943305 0.444352 \n", "Djuric A Verona Avg 1 0 83 5.982239 0.258992 \n", "Kallon A Verona Avg 1 0 0 5.851457 0.400450 \n", "Braaf A Verona Avg 1 0 0 5.675430 0.331933 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Rossi F. 5.710340 0.608428 6.061085 0.478673 0.143872 \n", "Musso 5.707846 0.608343 6.060265 0.478830 0.145062 \n", "Carnesecchi 5.199359 0.664409 6.049285 0.510774 0.106278 \n", "Zappacosta 6.430954 0.784539 6.056791 0.560162 0.064960 \n", "Ruggeri 6.427830 0.829378 6.077005 0.608189 0.028110 \n", "... ... ... ... ... ... \n", "Henry 6.086343 0.642557 5.631263 0.438163 0.326536 \n", "Cruz 6.065740 0.598042 5.949132 0.523503 -0.009082 \n", "Djuric 6.061640 0.304934 6.023319 0.321768 -0.094447 \n", "Kallon 6.050725 0.551621 5.690024 0.416988 0.281836 \n", "Braaf 5.783349 0.401081 5.554506 0.348108 0.253766 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Rossi F. 1.092386 6.415344 0.598177 -0.769786 1.148949 \n", "Musso 1.092329 6.411938 0.599186 -0.767992 1.148581 \n", "Carnesecchi 1.092119 5.646819 0.903720 -0.364365 1.027859 \n", "Zappacosta 0.877353 5.846407 1.045597 0.398034 1.299841 \n", "Ruggeri 0.853873 5.837552 1.127070 0.374861 1.299839 \n", "... ... ... ... ... ... \n", "Henry 0.922681 5.474199 0.730840 0.569787 1.299849 \n", "Cruz 0.938780 5.746909 0.884158 0.262632 1.299802 \n", "Djuric 1.112615 5.956068 0.481284 0.161987 1.299765 \n", "Kallon 0.953169 5.551819 0.655438 0.524593 1.299838 \n", "Braaf 1.031060 5.487167 0.536615 0.393338 1.299812 \n", "\n", " Clean Sheet % \n", "player \n", "Rossi F. 56.114355 \n", "Musso 56.005341 \n", "Carnesecchi 27.208376 \n", "Zappacosta 0.000000 \n", "Ruggeri 0.000000 \n", "... ... \n", "Henry 0.000000 \n", "Cruz 0.000000 \n", "Djuric 0.000000 \n", "Kallon 0.000000 \n", "Braaf 0.000000 \n", "\n", "[539 rows x 19 columns]" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "tot_matches = 2 # home and not home\n", "\n", "current_season_games = max(players_orig['games'])\n", "\n", "for i in range(players.shape[0]):\n", " try:\n", " home = 0\n", "\n", " for k in range(tot_matches):\n", " #matchday_out = k + 1\n", " #[player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", "\n", " player = players.index[i]\n", " team = players['team'][i]\n", " oppteam = 'Avg'\n", " home = not home\n", "\n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home)\n", "\n", " role = players['r'][player] \n", "\n", " starter = 0\n", " voteperc = 0\n", "\n", " games = max( players_orig['games'][i], players_orig['gk_games'][i] )\n", " mins = max( players_orig['minutes'][i], players_orig['gk_minutes'][i] )\n", "\n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", "\n", " starter = int( player in gk_starters )\n", " if(starter):\n", " voteperc = 100\n", " else:\n", " voteperc = 0\n", " else:\n", " starter = int ( 1 * (games >= current_season_games * 2/3 and mins / games >= 45 ) )\n", " voteperc = int( min( 1, games / current_season_games ) * 100) \n", "\n", " if(k == 0):\n", " row = [player, role, team, 'Avg', 1, starter, voteperc]\n", "\n", " numrow_ = [mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs] \n", "\n", " if(k == 0):\n", " numrow = numrow_\n", " else:\n", " for j in range(len(numrow)):\n", " numrow[j] += numrow_[j]\n", "\n", " for j in range(len(numrow)):\n", " numrow[j] /= tot_matches\n", "\n", " print(players.index[i] + ' (' + \"{:.2f}\".format(numrow[0]) + ', ' + \"{:.2f}\".format(numrow[1]) + \n", " '); (' + \"{:.2f}\".format(numrow[2]) + ', ' + \"{:.2f}\".format(numrow[3]) + ')' )\n", "\n", " row += numrow # list concat\n", "\n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", "\n", " output = pd.concat([output, row_df])\n", " except:\n", " print(players.index[i] + ' no data')\n", " \n", " \n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['team', 'role', 'FV'], ascending = [True, False, False])\n", "#output.to_excel('outputs/pred_matchday_' + str(matchday_out) + '.xlsx')\n", "\n", "output" ] }, { "cell_type": "code", "execution_count": 36, "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": 54, "id": "7300f3c2", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 5.90 ± 1.55; FV 5.53 + 1.18 (43.4% cs)\n", "Szczesny: MV 5.90 ± 1.55; FV 5.54 + 1.23 (53.7% cs)\n", "Provedel: MV 5.89 ± 1.56; FV 5.03 + 1.63 (28.1% cs)\n", "Maignan: MV 5.90 ± 1.55; FV 5.21 + 1.44 (29.1% cs)\n", "Rui Patricio: MV 5.84 ± 1.66; FV 3.89 + 2.53 (10.0% cs)\n", "Sommer: MV 5.90 ± 1.55; FV 5.57 + 1.20 (57.7% cs)\n", "Milinkovic-Savic V.: MV 5.85 ± 1.64; FV 5.11 + 1.72 (40.7% cs)\n", "Musso: MV 5.90 ± 1.55; FV 5.60 + 1.35 (58.3% cs)\n", "Caprile: MV 5.86 ± 1.61; FV 3.99 + 2.22 (6.3% cs)\n", "Silvestri: MV 5.90 ± 1.55; FV 5.19 + 1.44 (32.8% cs)\n", "Terracciano: MV 5.88 ± 1.58; FV 4.24 + 2.15 (16.7% cs)\n", "Skorupski: MV 5.89 ± 1.57; FV 4.48 + 2.02 (22.3% cs)\n", "Falcone: MV 5.90 ± 1.55; FV 5.32 + 1.44 (38.7% cs)\n", "Di Gregorio: MV 5.90 ± 1.55; FV 5.21 + 1.54 (32.9% cs)\n", "Consigli: MV 5.79 ± 1.73; FV 3.82 + 2.56 (8.2% cs)\n", "Radunovic: MV 5.71 ± 1.90; FV 4.24 + 2.26 (21.5% cs)\n", "Montipo': MV 5.87 ± 1.59; FV 4.34 + 2.10 (16.6% cs)\n", "Martinez Jo.: MV 5.90 ± 1.55; FV 5.24 + 1.34 (27.6% cs)\n", "Turati: MV 5.90 ± 1.55; FV 5.04 + 1.48 (22.6% cs)\n", "Ochoa: MV 5.90 ± 1.55; FV 4.95 + 1.55 (19.2% cs)\n" ] }, { "data": { "text/plain": [ "[array([5.89767402, 4.95480099]),\n", " array([0.7759559 , 0.77737534], dtype=float32),\n", " [,\n", " ,\n", " ]]" ] }, "execution_count": 54, "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('Sommer', 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('Caprile', 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('Radunovic', log = 1, plot = 0)\n", "predict_player('Montipo\\'', log = 1, plot = 0)\n", "predict_player('Martinez Jo.', log = 1, plot = 0)\n", "predict_player('Turati', log = 1, plot = 0)\n", "predict_player('Ochoa', log = 1, plot = 0)" ] }, { "cell_type": "code", "execution_count": 37, "id": "4b9f5a7d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Osimhen: MV 6.47 ± 1.49; FV 7.95 + 4.15\n", "Osimhen: MV 6.48 ± 1.46; FV 8.08 + 4.29\n" ] }, { "data": { "text/plain": [ "[array([6.48246781, 8.07706693]),\n", " array([0.72848487, 2.14604 ], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Osimhen', log = 1)\n", "predict_player('Osimhen', log = 1, oldseason= True)" ] }, { "cell_type": "code", "execution_count": 56, "id": "10c7ad3e", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Rafael Leao: MV 6.48 ± 1.37; FV 7.84 + 4.05\n" ] }, { "data": { "text/plain": [ "[array([6.48351824, 7.84102121]),\n", " array([0.6832447, 2.0243561], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Rafael Leao', plot = 1, log = 1)" ] }, { "cell_type": "markdown", "id": "30744d7a", "metadata": {}, "source": [ "Tensorflow seems to have a custom definition for SinhArcsinh distribution. \n", "\n", "Here the code to generate the probability density function is reproduced." ] }, { "cell_type": "code", "execution_count": 110, "id": "3ec6c3dc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 110, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# custom franction to calculate the probability density function\n", "\n", "def sinh_archsinh_pdf(x, mu, sigma, eps, delta):\n", "\n", " mul = np.sinh( np.arcsinh(2) * delta)\n", " \n", " mul = 2 / mul\n", " \n", " sigma_corr = sigma * mul\n", " \n", " z = (x - mu) / sigma_corr\n", " \n", " \n", " \n", " S = np.sinh( -eps + (1/delta) * np.arcsinh(z))\n", " \n", " f = np.exp(-0.5 * S * S)\n", "\n", " f /= np.sqrt(2 * np.pi)\n", " \n", " f *= 1 / ( sigma_corr * delta )\n", " \n", " f *= np.sqrt(1 + S * S)\n", " \n", " f /= np.sqrt(1 + z * z)\n", " \n", " return f\n", " \n", "\n", "x = np.arange(start = 0, stop = 15, step = 0.001)\n", "\n", "\n", "plt.plot(x, sinh_archsinh_pdf(x, 5.54, 1.4, 0.8, 1.68))\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "605dc968", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.13" } }, "nbformat": 4, "nbformat_minor": 5 }