Files
fantabeto/.ipynb_checkpoints/4_player_match_dataset_creation-checkpoint.ipynb
T
2023-09-21 07:51:22 +02:00

4473 lines
154 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "markdown",
"id": "8f597771",
"metadata": {},
"source": [
"Player/match dataset creation\n",
"\n",
"For each serie A (already happened) match and player, a database entry is generated, with this form:\n",
" \n",
"[y = player votes data, player data, team data, vs team data, opp team data, vs opp team data]"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3ecf3676",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"id": "a7d3a9d6",
"metadata": {},
"source": [
"Load team data from FBref"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8a6867a5",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>team</th>\n",
" <th>team_players_used</th>\n",
" <th>team_possession</th>\n",
" <th>team_games</th>\n",
" <th>team_games_starts</th>\n",
" <th>team_minutes</th>\n",
" <th>team_goals</th>\n",
" <th>team_assists</th>\n",
" <th>team_pens_made</th>\n",
" <th>team_pens_att</th>\n",
" <th>...</th>\n",
" <th>vs_team_fouls</th>\n",
" <th>vs_team_fouled</th>\n",
" <th>vs_team_offsides</th>\n",
" <th>vs_team_pens_won</th>\n",
" <th>vs_team_pens_conceded</th>\n",
" <th>vs_team_own_goals</th>\n",
" <th>vs_team_ball_recoveries</th>\n",
" <th>vs_team_aerials_won</th>\n",
" <th>vs_team_aerials_lost</th>\n",
" <th>vs_team_aerials_won_pct</th>\n",
" </tr>\n",
" <tr>\n",
" <th>team_idx</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Atalanta</th>\n",
" <td>Atalanta</td>\n",
" <td>23.0</td>\n",
" <td>49.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>8.0</td>\n",
" <td>8.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>36.0</td>\n",
" <td>47.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>212.0</td>\n",
" <td>65.0</td>\n",
" <td>60.0</td>\n",
" <td>52.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Bologna</th>\n",
" <td>Bologna</td>\n",
" <td>22.0</td>\n",
" <td>56.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>50.0</td>\n",
" <td>40.0</td>\n",
" <td>12.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>207.0</td>\n",
" <td>34.0</td>\n",
" <td>46.0</td>\n",
" <td>42.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cagliari</th>\n",
" <td>Cagliari</td>\n",
" <td>21.0</td>\n",
" <td>37.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>38.0</td>\n",
" <td>41.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>220.0</td>\n",
" <td>60.0</td>\n",
" <td>51.0</td>\n",
" <td>54.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Empoli</th>\n",
" <td>Empoli</td>\n",
" <td>27.0</td>\n",
" <td>47.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>60.0</td>\n",
" <td>42.0</td>\n",
" <td>8.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>203.0</td>\n",
" <td>54.0</td>\n",
" <td>39.0</td>\n",
" <td>58.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Fiorentina</th>\n",
" <td>Fiorentina</td>\n",
" <td>22.0</td>\n",
" <td>61.0</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>9.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>56.0</td>\n",
" <td>43.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>202.0</td>\n",
" <td>56.0</td>\n",
" <td>53.0</td>\n",
" <td>51.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Frosinone</th>\n",
" <td>Frosinone</td>\n",
" <td>23.0</td>\n",
" <td>48.3</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>7.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>50.0</td>\n",
" <td>39.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>212.0</td>\n",
" <td>53.0</td>\n",
" <td>52.0</td>\n",
" <td>50.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Genoa</th>\n",
" <td>Genoa</td>\n",
" <td>19.0</td>\n",
" <td>33.3</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>43.0</td>\n",
" <td>43.0</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>200.0</td>\n",
" <td>46.0</td>\n",
" <td>60.0</td>\n",
" <td>43.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Verona</th>\n",
" <td>Hellas Verona</td>\n",
" <td>21.0</td>\n",
" <td>43.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>47.0</td>\n",
" <td>63.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>190.0</td>\n",
" <td>71.0</td>\n",
" <td>82.0</td>\n",
" <td>46.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Inter</th>\n",
" <td>Inter</td>\n",
" <td>19.0</td>\n",
" <td>48.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>13.0</td>\n",
" <td>11.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>47.0</td>\n",
" <td>44.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>163.0</td>\n",
" <td>30.0</td>\n",
" <td>44.0</td>\n",
" <td>40.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Juventus</th>\n",
" <td>Juventus</td>\n",
" <td>21.0</td>\n",
" <td>48.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>9.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>52.0</td>\n",
" <td>49.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>173.0</td>\n",
" <td>26.0</td>\n",
" <td>38.0</td>\n",
" <td>40.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lazio</th>\n",
" <td>Lazio</td>\n",
" <td>20.0</td>\n",
" <td>56.0</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>49.0</td>\n",
" <td>44.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>196.0</td>\n",
" <td>51.0</td>\n",
" <td>30.0</td>\n",
" <td>63.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lecce</th>\n",
" <td>Lecce</td>\n",
" <td>19.0</td>\n",
" <td>43.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>7.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>64.0</td>\n",
" <td>53.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>203.0</td>\n",
" <td>43.0</td>\n",
" <td>54.0</td>\n",
" <td>44.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Milan</th>\n",
" <td>Milan</td>\n",
" <td>19.0</td>\n",
" <td>55.3</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>9.0</td>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>56.0</td>\n",
" <td>43.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>176.0</td>\n",
" <td>42.0</td>\n",
" <td>33.0</td>\n",
" <td>56.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Monza</th>\n",
" <td>Monza</td>\n",
" <td>22.0</td>\n",
" <td>56.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>37.0</td>\n",
" <td>52.0</td>\n",
" <td>6.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>187.0</td>\n",
" <td>45.0</td>\n",
" <td>37.0</td>\n",
" <td>54.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Napoli</th>\n",
" <td>Napoli</td>\n",
" <td>19.0</td>\n",
" <td>61.8</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>8.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>47.0</td>\n",
" <td>39.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>173.0</td>\n",
" <td>35.0</td>\n",
" <td>47.0</td>\n",
" <td>42.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Roma</th>\n",
" <td>Roma</td>\n",
" <td>23.0</td>\n",
" <td>57.0</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>10.0</td>\n",
" <td>8.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>46.0</td>\n",
" <td>51.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>159.0</td>\n",
" <td>54.0</td>\n",
" <td>76.0</td>\n",
" <td>41.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Salernitana</th>\n",
" <td>Salernitana</td>\n",
" <td>21.0</td>\n",
" <td>51.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>64.0</td>\n",
" <td>46.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>203.0</td>\n",
" <td>86.0</td>\n",
" <td>54.0</td>\n",
" <td>61.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sassuolo</th>\n",
" <td>Sassuolo</td>\n",
" <td>24.0</td>\n",
" <td>43.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>45.0</td>\n",
" <td>34.0</td>\n",
" <td>15.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>207.0</td>\n",
" <td>50.0</td>\n",
" <td>37.0</td>\n",
" <td>57.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Torino</th>\n",
" <td>Torino</td>\n",
" <td>22.0</td>\n",
" <td>51.3</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>44.0</td>\n",
" <td>48.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>207.0</td>\n",
" <td>63.0</td>\n",
" <td>59.0</td>\n",
" <td>51.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Udinese</th>\n",
" <td>Udinese</td>\n",
" <td>22.0</td>\n",
" <td>48.5</td>\n",
" <td>4.0</td>\n",
" <td>44.0</td>\n",
" <td>360.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>43.0</td>\n",
" <td>51.0</td>\n",
" <td>10.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>188.0</td>\n",
" <td>52.0</td>\n",
" <td>64.0</td>\n",
" <td>44.8</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>20 rows × 303 columns</p>\n",
"</div>"
],
"text/plain": [
" team team_players_used team_possession team_games \\\n",
"team_idx \n",
"Atalanta Atalanta 23.0 49.5 4.0 \n",
"Bologna Bologna 22.0 56.5 4.0 \n",
"Cagliari Cagliari 21.0 37.8 4.0 \n",
"Empoli Empoli 27.0 47.8 4.0 \n",
"Fiorentina Fiorentina 22.0 61.0 4.0 \n",
"Frosinone Frosinone 23.0 48.3 4.0 \n",
"Genoa Genoa 19.0 33.3 4.0 \n",
"Verona Hellas Verona 21.0 43.5 4.0 \n",
"Inter Inter 19.0 48.8 4.0 \n",
"Juventus Juventus 21.0 48.8 4.0 \n",
"Lazio Lazio 20.0 56.0 4.0 \n",
"Lecce Lecce 19.0 43.5 4.0 \n",
"Milan Milan 19.0 55.3 4.0 \n",
"Monza Monza 22.0 56.8 4.0 \n",
"Napoli Napoli 19.0 61.8 4.0 \n",
"Roma Roma 23.0 57.0 4.0 \n",
"Salernitana Salernitana 21.0 51.5 4.0 \n",
"Sassuolo Sassuolo 24.0 43.5 4.0 \n",
"Torino Torino 22.0 51.3 4.0 \n",
"Udinese Udinese 22.0 48.5 4.0 \n",
"\n",
" team_games_starts team_minutes team_goals team_assists \\\n",
"team_idx \n",
"Atalanta 44.0 360.0 8.0 8.0 \n",
"Bologna 44.0 360.0 3.0 2.0 \n",
"Cagliari 44.0 360.0 1.0 1.0 \n",
"Empoli 44.0 360.0 0.0 0.0 \n",
"Fiorentina 44.0 360.0 9.0 7.0 \n",
"Frosinone 44.0 360.0 7.0 4.0 \n",
"Genoa 44.0 360.0 4.0 3.0 \n",
"Verona 44.0 360.0 4.0 2.0 \n",
"Inter 44.0 360.0 13.0 11.0 \n",
"Juventus 44.0 360.0 9.0 7.0 \n",
"Lazio 44.0 360.0 4.0 4.0 \n",
"Lecce 44.0 360.0 7.0 5.0 \n",
"Milan 44.0 360.0 9.0 6.0 \n",
"Monza 44.0 360.0 3.0 3.0 \n",
"Napoli 44.0 360.0 8.0 5.0 \n",
"Roma 44.0 360.0 10.0 8.0 \n",
"Salernitana 44.0 360.0 3.0 3.0 \n",
"Sassuolo 44.0 360.0 5.0 4.0 \n",
"Torino 44.0 360.0 5.0 3.0 \n",
"Udinese 44.0 360.0 1.0 1.0 \n",
"\n",
" team_pens_made team_pens_att ... vs_team_fouls \\\n",
"team_idx ... \n",
"Atalanta 0.0 0.0 ... 36.0 \n",
"Bologna 0.0 1.0 ... 50.0 \n",
"Cagliari 0.0 0.0 ... 38.0 \n",
"Empoli 0.0 0.0 ... 60.0 \n",
"Fiorentina 0.0 0.0 ... 56.0 \n",
"Frosinone 2.0 2.0 ... 50.0 \n",
"Genoa 0.0 0.0 ... 43.0 \n",
"Verona 0.0 0.0 ... 47.0 \n",
"Inter 2.0 2.0 ... 47.0 \n",
"Juventus 1.0 2.0 ... 52.0 \n",
"Lazio 0.0 0.0 ... 49.0 \n",
"Lecce 2.0 2.0 ... 64.0 \n",
"Milan 3.0 3.0 ... 56.0 \n",
"Monza 0.0 0.0 ... 37.0 \n",
"Napoli 1.0 2.0 ... 47.0 \n",
"Roma 1.0 1.0 ... 46.0 \n",
"Salernitana 0.0 0.0 ... 64.0 \n",
"Sassuolo 1.0 1.0 ... 45.0 \n",
"Torino 0.0 0.0 ... 44.0 \n",
"Udinese 0.0 0.0 ... 43.0 \n",
"\n",
" vs_team_fouled vs_team_offsides vs_team_pens_won \\\n",
"team_idx \n",
"Atalanta 47.0 2.0 0.0 \n",
"Bologna 40.0 12.0 0.0 \n",
"Cagliari 41.0 5.0 0.0 \n",
"Empoli 42.0 8.0 1.0 \n",
"Fiorentina 43.0 5.0 1.0 \n",
"Frosinone 39.0 6.0 0.0 \n",
"Genoa 43.0 9.0 0.0 \n",
"Verona 63.0 7.0 1.0 \n",
"Inter 44.0 5.0 0.0 \n",
"Juventus 49.0 5.0 0.0 \n",
"Lazio 44.0 7.0 0.0 \n",
"Lecce 53.0 5.0 0.0 \n",
"Milan 43.0 7.0 1.0 \n",
"Monza 52.0 6.0 1.0 \n",
"Napoli 39.0 7.0 1.0 \n",
"Roma 51.0 4.0 1.0 \n",
"Salernitana 46.0 4.0 0.0 \n",
"Sassuolo 34.0 15.0 2.0 \n",
"Torino 48.0 7.0 1.0 \n",
"Udinese 51.0 10.0 0.0 \n",
"\n",
" vs_team_pens_conceded vs_team_own_goals \\\n",
"team_idx \n",
"Atalanta 0.0 0.0 \n",
"Bologna 1.0 0.0 \n",
"Cagliari 0.0 0.0 \n",
"Empoli 0.0 0.0 \n",
"Fiorentina 0.0 0.0 \n",
"Frosinone 2.0 0.0 \n",
"Genoa 0.0 0.0 \n",
"Verona 0.0 0.0 \n",
"Inter 2.0 0.0 \n",
"Juventus 2.0 0.0 \n",
"Lazio 0.0 0.0 \n",
"Lecce 2.0 0.0 \n",
"Milan 3.0 0.0 \n",
"Monza 0.0 0.0 \n",
"Napoli 2.0 0.0 \n",
"Roma 1.0 1.0 \n",
"Salernitana 0.0 0.0 \n",
"Sassuolo 1.0 0.0 \n",
"Torino 0.0 0.0 \n",
"Udinese 0.0 0.0 \n",
"\n",
" vs_team_ball_recoveries vs_team_aerials_won \\\n",
"team_idx \n",
"Atalanta 212.0 65.0 \n",
"Bologna 207.0 34.0 \n",
"Cagliari 220.0 60.0 \n",
"Empoli 203.0 54.0 \n",
"Fiorentina 202.0 56.0 \n",
"Frosinone 212.0 53.0 \n",
"Genoa 200.0 46.0 \n",
"Verona 190.0 71.0 \n",
"Inter 163.0 30.0 \n",
"Juventus 173.0 26.0 \n",
"Lazio 196.0 51.0 \n",
"Lecce 203.0 43.0 \n",
"Milan 176.0 42.0 \n",
"Monza 187.0 45.0 \n",
"Napoli 173.0 35.0 \n",
"Roma 159.0 54.0 \n",
"Salernitana 203.0 86.0 \n",
"Sassuolo 207.0 50.0 \n",
"Torino 207.0 63.0 \n",
"Udinese 188.0 52.0 \n",
"\n",
" vs_team_aerials_lost vs_team_aerials_won_pct \n",
"team_idx \n",
"Atalanta 60.0 52.0 \n",
"Bologna 46.0 42.5 \n",
"Cagliari 51.0 54.1 \n",
"Empoli 39.0 58.1 \n",
"Fiorentina 53.0 51.4 \n",
"Frosinone 52.0 50.5 \n",
"Genoa 60.0 43.4 \n",
"Verona 82.0 46.4 \n",
"Inter 44.0 40.5 \n",
"Juventus 38.0 40.6 \n",
"Lazio 30.0 63.0 \n",
"Lecce 54.0 44.3 \n",
"Milan 33.0 56.0 \n",
"Monza 37.0 54.9 \n",
"Napoli 47.0 42.7 \n",
"Roma 76.0 41.5 \n",
"Salernitana 54.0 61.4 \n",
"Sassuolo 37.0 57.5 \n",
"Torino 59.0 51.6 \n",
"Udinese 64.0 44.8 \n",
"\n",
"[20 rows x 303 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rcsv = pd.read_csv('fbref_data/teams.csv') \n",
"team = pd.DataFrame(rcsv)\n",
"\n",
"rcsv = pd.read_csv('fbref_data/teams_vs.csv') \n",
"vs_team = pd.DataFrame(rcsv)\n",
"\n",
"for i in range(1, team.shape[1]):\n",
" team = team.rename(columns = {team.columns[i] : 'team_' + team.columns[i]})\n",
" \n",
"for i in range(1, vs_team.shape[1]):\n",
" vs_team = vs_team.rename(columns = {vs_team.columns[i] : 'vs_team_' + vs_team.columns[i]})\n",
" \n",
"vs_team.pop('team')\n",
"\n",
"team_data = pd.concat([team, vs_team], axis = 1)\n",
"\n",
"team_data['team_idx'] = team_data['team']\n",
"for i in range(team_data.shape[0]):\n",
" team_data.loc[i, 'team_idx'] = team_data.loc[i, 'team_idx'].split(' ')[-1]\n",
"\n",
"team_data = team_data.set_index('team_idx')\n",
"\n",
"team_data\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b6a3db98",
"metadata": {},
"outputs": [],
"source": [
"team_data.to_excel('mid_outputs/team_data.xlsx')"
]
},
{
"cell_type": "markdown",
"id": "cc50dde9",
"metadata": {},
"source": [
"Load data generated from players_dataset_creation"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "c34eb398",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>id</th>\n",
" <th>r</th>\n",
" <th>team</th>\n",
" <th>surname</th>\n",
" <th>initial</th>\n",
" <th>fb_ID</th>\n",
" <th>age</th>\n",
" <th>birth_year</th>\n",
" <th>games</th>\n",
" <th>...</th>\n",
" <th>gk_pct_goal_kicks_launched</th>\n",
" <th>gk_goal_kick_length_avg</th>\n",
" <th>gk_crosses</th>\n",
" <th>gk_crosses_stopped</th>\n",
" <th>gk_crosses_stopped_pct</th>\n",
" <th>gk_def_actions_outside_pen_area</th>\n",
" <th>gk_def_actions_outside_pen_area_per90</th>\n",
" <th>gk_avg_distance_def_actions</th>\n",
" <th>vote_avg</th>\n",
" <th>vote_std</th>\n",
" </tr>\n",
" <tr>\n",
" <th>name</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Sommer</th>\n",
" <td>0</td>\n",
" <td>2428</td>\n",
" <td>P</td>\n",
" <td>Inter</td>\n",
" <td>Sommer</td>\n",
" <td>NaN</td>\n",
" <td>452</td>\n",
" <td>34-278</td>\n",
" <td>1988</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>20.7</td>\n",
" <td>28.3</td>\n",
" <td>41</td>\n",
" <td>2</td>\n",
" <td>4.9</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>6.5</td>\n",
" <td>6.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Szczesny</th>\n",
" <td>1</td>\n",
" <td>453</td>\n",
" <td>P</td>\n",
" <td>Juventus</td>\n",
" <td>Szczesny</td>\n",
" <td>NaN</td>\n",
" <td>454</td>\n",
" <td>33-156</td>\n",
" <td>1990</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>66.7</td>\n",
" <td>52.0</td>\n",
" <td>33</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>9.6</td>\n",
" <td>6.750000</td>\n",
" <td>0.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Meret</th>\n",
" <td>2</td>\n",
" <td>572</td>\n",
" <td>P</td>\n",
" <td>Napoli</td>\n",
" <td>Meret</td>\n",
" <td>NaN</td>\n",
" <td>440</td>\n",
" <td>26-183</td>\n",
" <td>1997</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>20.4</td>\n",
" <td>27</td>\n",
" <td>1</td>\n",
" <td>3.7</td>\n",
" <td>7</td>\n",
" <td>1.75</td>\n",
" <td>18.2</td>\n",
" <td>5.750000</td>\n",
" <td>0.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Provedel</th>\n",
" <td>3</td>\n",
" <td>2814</td>\n",
" <td>P</td>\n",
" <td>Lazio</td>\n",
" <td>Provedel</td>\n",
" <td>NaN</td>\n",
" <td>448</td>\n",
" <td>29-188</td>\n",
" <td>1994</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>20.0</td>\n",
" <td>27.9</td>\n",
" <td>48</td>\n",
" <td>2</td>\n",
" <td>4.2</td>\n",
" <td>6</td>\n",
" <td>1.50</td>\n",
" <td>15.7</td>\n",
" <td>6.375000</td>\n",
" <td>0.414578</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Maignan</th>\n",
" <td>4</td>\n",
" <td>4312</td>\n",
" <td>P</td>\n",
" <td>Milan</td>\n",
" <td>Maignan</td>\n",
" <td>NaN</td>\n",
" <td>438</td>\n",
" <td>28-080</td>\n",
" <td>1995</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>60.9</td>\n",
" <td>47.0</td>\n",
" <td>52</td>\n",
" <td>12</td>\n",
" <td>23.1</td>\n",
" <td>3</td>\n",
" <td>0.75</td>\n",
" <td>9.8</td>\n",
" <td>6.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Shpendi S.</th>\n",
" <td>534</td>\n",
" <td>6395</td>\n",
" <td>A</td>\n",
" <td>Empoli</td>\n",
" <td>Shpendi</td>\n",
" <td>S</td>\n",
" <td>361</td>\n",
" <td>20-125</td>\n",
" <td>2003</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>5.750000</td>\n",
" <td>0.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Burnete</th>\n",
" <td>535</td>\n",
" <td>6418</td>\n",
" <td>A</td>\n",
" <td>Lecce</td>\n",
" <td>Burnete</td>\n",
" <td>NaN</td>\n",
" <td>55</td>\n",
" <td>19-233</td>\n",
" <td>2004</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Corfitzen</th>\n",
" <td>536</td>\n",
" <td>6419</td>\n",
" <td>A</td>\n",
" <td>Lecce</td>\n",
" <td>Corfitzen</td>\n",
" <td>NaN</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>5.799850</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Stewart</th>\n",
" <td>537</td>\n",
" <td>6427</td>\n",
" <td>A</td>\n",
" <td>Salernitana</td>\n",
" <td>Stewart</td>\n",
" <td>NaN</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.447669</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Yildiz</th>\n",
" <td>538</td>\n",
" <td>6434</td>\n",
" <td>A</td>\n",
" <td>Juventus</td>\n",
" <td>Yildiz</td>\n",
" <td>NaN</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.437600</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>539 rows × 160 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 id r team surname initial fb_ID \\\n",
"name \n",
"Sommer 0 2428 P Inter Sommer NaN 452 \n",
"Szczesny 1 453 P Juventus Szczesny NaN 454 \n",
"Meret 2 572 P Napoli Meret NaN 440 \n",
"Provedel 3 2814 P Lazio Provedel NaN 448 \n",
"Maignan 4 4312 P Milan Maignan NaN 438 \n",
"... ... ... .. ... ... ... ... \n",
"Shpendi S. 534 6395 A Empoli Shpendi S 361 \n",
"Burnete 535 6418 A Lecce Burnete NaN 55 \n",
"Corfitzen 536 6419 A Lecce Corfitzen NaN -1 \n",
"Stewart 537 6427 A Salernitana Stewart NaN -1 \n",
"Yildiz 538 6434 A Juventus Yildiz NaN -1 \n",
"\n",
" age birth_year games ... gk_pct_goal_kicks_launched \\\n",
"name ... \n",
"Sommer 34-278 1988 0 ... 20.7 \n",
"Szczesny 33-156 1990 0 ... 66.7 \n",
"Meret 26-183 1997 0 ... 0.0 \n",
"Provedel 29-188 1994 0 ... 20.0 \n",
"Maignan 28-080 1995 0 ... 60.9 \n",
"... ... ... ... ... ... \n",
"Shpendi S. 20-125 2003 3 ... 0.0 \n",
"Burnete 19-233 2004 1 ... 0.0 \n",
"Corfitzen 0 0 0 ... 0.0 \n",
"Stewart 0 0 0 ... 0.0 \n",
"Yildiz 0 0 0 ... 0.0 \n",
"\n",
" gk_goal_kick_length_avg gk_crosses gk_crosses_stopped \\\n",
"name \n",
"Sommer 28.3 41 2 \n",
"Szczesny 52.0 33 1 \n",
"Meret 20.4 27 1 \n",
"Provedel 27.9 48 2 \n",
"Maignan 47.0 52 12 \n",
"... ... ... ... \n",
"Shpendi S. 0.0 0 0 \n",
"Burnete 0.0 0 0 \n",
"Corfitzen 0.0 0 0 \n",
"Stewart 0.0 0 0 \n",
"Yildiz 0.0 0 0 \n",
"\n",
" gk_crosses_stopped_pct gk_def_actions_outside_pen_area \\\n",
"name \n",
"Sommer 4.9 0 \n",
"Szczesny 3.0 0 \n",
"Meret 3.7 7 \n",
"Provedel 4.2 6 \n",
"Maignan 23.1 3 \n",
"... ... ... \n",
"Shpendi S. 0.0 0 \n",
"Burnete 0.0 0 \n",
"Corfitzen 0.0 0 \n",
"Stewart 0.0 0 \n",
"Yildiz 0.0 0 \n",
"\n",
" gk_def_actions_outside_pen_area_per90 \\\n",
"name \n",
"Sommer 0.00 \n",
"Szczesny 0.00 \n",
"Meret 1.75 \n",
"Provedel 1.50 \n",
"Maignan 0.75 \n",
"... ... \n",
"Shpendi S. 0.00 \n",
"Burnete 0.00 \n",
"Corfitzen 0.00 \n",
"Stewart 0.00 \n",
"Yildiz 0.00 \n",
"\n",
" gk_avg_distance_def_actions vote_avg vote_std \n",
"name \n",
"Sommer 6.5 6.000000 0.000000 \n",
"Szczesny 9.6 6.750000 0.250000 \n",
"Meret 18.2 5.750000 0.250000 \n",
"Provedel 15.7 6.375000 0.414578 \n",
"Maignan 9.8 6.000000 0.000000 \n",
"... ... ... ... \n",
"Shpendi S. 0.0 5.750000 0.250000 \n",
"Burnete 0.0 6.000000 0.000000 \n",
"Corfitzen 0.0 5.799850 0.000000 \n",
"Stewart 0.0 6.447669 0.000000 \n",
"Yildiz 0.0 6.437600 0.000000 \n",
"\n",
"[539 rows x 160 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rx = pd.read_excel('mid_outputs/players_stats.xlsx', index_col = 3) \n",
"players = pd.DataFrame(rx)\n",
"\n",
"players\n"
]
},
{
"cell_type": "markdown",
"id": "ae37dfe3",
"metadata": {},
"source": [
"Function for merging match data (player, team, opponent team)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "71c8804e",
"metadata": {},
"outputs": [],
"source": [
"def player_match_data(player, pteam, oppteam):\n",
" if(not(player in players.index)):\n",
" return None\n",
" \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",
" "
]
},
{
"cell_type": "markdown",
"id": "a6fdd15b",
"metadata": {},
"source": [
"Output to excel file data for a player. \n",
"\n",
"The file is copied and there the desired features are manually selected and printed."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7eb4e666",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>id</th>\n",
" <th>r</th>\n",
" <th>team</th>\n",
" <th>surname</th>\n",
" <th>initial</th>\n",
" <th>fb_ID</th>\n",
" <th>age</th>\n",
" <th>birth_year</th>\n",
" <th>games</th>\n",
" <th>...</th>\n",
" <th>opp_vs_team_fouls</th>\n",
" <th>opp_vs_team_fouled</th>\n",
" <th>opp_vs_team_offsides</th>\n",
" <th>opp_vs_team_pens_won</th>\n",
" <th>opp_vs_team_pens_conceded</th>\n",
" <th>opp_vs_team_own_goals</th>\n",
" <th>opp_vs_team_ball_recoveries</th>\n",
" <th>opp_vs_team_aerials_won</th>\n",
" <th>opp_vs_team_aerials_lost</th>\n",
" <th>opp_vs_team_aerials_won_pct</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Barella</th>\n",
" <td>260</td>\n",
" <td>1870</td>\n",
" <td>C</td>\n",
" <td>Inter</td>\n",
" <td>Barella</td>\n",
" <td>NaN</td>\n",
" <td>23</td>\n",
" <td>26-226</td>\n",
" <td>1997</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>36.0</td>\n",
" <td>47.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>212.0</td>\n",
" <td>65.0</td>\n",
" <td>60.0</td>\n",
" <td>52.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 766 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 id r team surname initial fb_ID age \\\n",
"Barella 260 1870 C Inter Barella NaN 23 26-226 \n",
"\n",
" birth_year games ... opp_vs_team_fouls opp_vs_team_fouled \\\n",
"Barella 1997 4 ... 36.0 47.0 \n",
"\n",
" opp_vs_team_offsides opp_vs_team_pens_won \\\n",
"Barella 2.0 0.0 \n",
"\n",
" opp_vs_team_pens_conceded opp_vs_team_own_goals \\\n",
"Barella 0.0 0.0 \n",
"\n",
" opp_vs_team_ball_recoveries opp_vs_team_aerials_won \\\n",
"Barella 212.0 65.0 \n",
"\n",
" opp_vs_team_aerials_lost opp_vs_team_aerials_won_pct \n",
"Barella 60.0 52.0 \n",
"\n",
"[1 rows x 766 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test = player_match_data('Barella', 'Inter', 'Atalanta')\n",
"test.to_excel('tmp/playermatchdata.xlsx')\n",
"\n",
"test"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "6b4c1b00",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Inter'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pteam = 'Inter'\n",
"pteam_stats = team_data.loc[[pteam]]\n",
"pteam_stats.index[0]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "6ea6df1f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['r',\n",
" 'fb_ID',\n",
" 'games',\n",
" 'games_starts',\n",
" 'minutes',\n",
" 'goals',\n",
" 'assists',\n",
" 'cards_yellow',\n",
" 'cards_red',\n",
" 'xg',\n",
" 'npxg',\n",
" 'shots_on_target',\n",
" 'shots_on_target_pct',\n",
" 'goals_per_shot',\n",
" 'goals_per_shot_on_target',\n",
" 'passes_completed',\n",
" 'passes_pct',\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",
" 'dribble_tackles_pct',\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",
" 'dribbles_completed_pct',\n",
" 'carries',\n",
" 'progressive_carries',\n",
" 'carries_into_final_third',\n",
" 'carries_into_penalty_area',\n",
" 'passes_received',\n",
" 'miscontrols',\n",
" 'dispossessed',\n",
" 'fouls',\n",
" 'fouled',\n",
" 'aerials_won',\n",
" 'aerials_lost',\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']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rx = pd.read_excel('tmp/playermatchdata_sel.xlsx', index_col = 0, header = None) \n",
"\n",
"out = list()\n",
"\n",
"for i in range(1, rx.shape[1]):\n",
" if(rx[i][2] == \"x\"):\n",
" out.append(rx[i][0])\n",
" \n",
"out"
]
},
{
"cell_type": "markdown",
"id": "d4097382",
"metadata": {},
"source": [
"Define and select the dataset features: abs features and rel features.\n",
" \n",
"Rel features are divided by the player minutes played.\n",
"\n",
"Rel features (game corrected) are divided by the player number of games instead of minutes. \n",
"For example, a player who plays 20 minutes and scores, would be to match for stats averaging. It is better to consider the goals made per match."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "47bc651f",
"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": "markdown",
"id": "ced70285",
"metadata": {},
"source": [
"Function for merging match data (player, team, opponent team) and select only the desired features, applying the desired corrections."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "3f43d509",
"metadata": {},
"outputs": [],
"source": [
"def player_match_data_ext(player, pteam, oppteam):\n",
" pdata = player_match_data(player, pteam, oppteam)\n",
" \n",
" if(not isinstance(pdata, pd.DataFrame)):\n",
" return None\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",
" return out\n",
" "
]
},
{
"cell_type": "markdown",
"id": "959bf152",
"metadata": {},
"source": [
"Columns variable for the match data, to be then added to votes data."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "930d00c7",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>r</th>\n",
" <th>games</th>\n",
" <th>games_starts</th>\n",
" <th>minutes</th>\n",
" <th>shots_on_target_pct</th>\n",
" <th>goals_per_shot</th>\n",
" <th>goals_per_shot_on_target</th>\n",
" <th>passes_pct</th>\n",
" <th>aerials_won_pct</th>\n",
" <th>team_possession</th>\n",
" <th>...</th>\n",
" <th>miscontrols</th>\n",
" <th>dispossessed</th>\n",
" <th>fouls</th>\n",
" <th>fouled</th>\n",
" <th>aerials_won</th>\n",
" <th>aerials_lost</th>\n",
" <th>carries</th>\n",
" <th>progressive_carries</th>\n",
" <th>carries_into_final_third</th>\n",
" <th>carries_into_penalty_area</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Barella</th>\n",
" <td>C</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>281</td>\n",
" <td>25.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>86.2</td>\n",
" <td>100.0</td>\n",
" <td>48.8</td>\n",
" <td>...</td>\n",
" <td>0.003559</td>\n",
" <td>0.0</td>\n",
" <td>0.010676</td>\n",
" <td>0.010676</td>\n",
" <td>0.007117</td>\n",
" <td>0.0</td>\n",
" <td>0.494662</td>\n",
" <td>0.024911</td>\n",
" <td>0.021352</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 112 columns</p>\n",
"</div>"
],
"text/plain": [
" r games games_starts minutes shots_on_target_pct goals_per_shot \\\n",
"Barella C 4 4 281 25.0 0.0 \n",
"\n",
" goals_per_shot_on_target passes_pct aerials_won_pct \\\n",
"Barella 0.0 86.2 100.0 \n",
"\n",
" team_possession ... miscontrols dispossessed fouls fouled \\\n",
"Barella 48.8 ... 0.003559 0.0 0.010676 0.010676 \n",
"\n",
" aerials_won aerials_lost carries progressive_carries \\\n",
"Barella 0.007117 0.0 0.494662 0.024911 \n",
"\n",
" carries_into_final_third carries_into_penalty_area \n",
"Barella 0.021352 0.0 \n",
"\n",
"[1 rows x 112 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test = player_match_data_ext('Barella', 'Inter', 'Atalanta')\n",
"\n",
"add_columns = test.columns\n",
"\n",
"test"
]
},
{
"cell_type": "markdown",
"id": "8d95c9ef",
"metadata": {},
"source": [
"Load Fantacalcio votes data for each match of the season."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "3ae718d2",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Musso</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Zappacosta</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Kolasinac</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Zortea</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1154</th>\n",
" <td>4</td>\n",
" <td>Serdar</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1155</th>\n",
" <td>4</td>\n",
" <td>Suslov</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1156</th>\n",
" <td>4</td>\n",
" <td>Bonazzoli</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1157</th>\n",
" <td>4</td>\n",
" <td>Djuric</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1158</th>\n",
" <td>4</td>\n",
" <td>Ngonge</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1159 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"0 1 Musso Atalanta Sassuolo 0 6.5 0 0 \n",
"1 1 Zappacosta Atalanta Sassuolo 0 6.5 0 0 \n",
"2 1 Djimsiti Atalanta Sassuolo 0 6.0 0 0 \n",
"3 1 Kolasinac Atalanta Sassuolo 0 6.5 0 0 \n",
"4 1 Zortea Atalanta Sassuolo 0 7.0 1 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"1154 4 Serdar Verona Bologna 1 6.0 0 0 \n",
"1155 4 Suslov Verona Bologna 1 6.0 0 0 \n",
"1156 4 Bonazzoli Verona Bologna 1 6.0 0 0 \n",
"1157 4 Djuric Verona Bologna 1 5.5 0 0 \n",
"1158 4 Ngonge Verona Bologna 1 5.5 0 0 \n",
"\n",
" cards_malus fantavote \n",
"0 0.0 6.5 \n",
"1 0.0 6.5 \n",
"2 0.0 6.0 \n",
"3 0.0 6.5 \n",
"4 0.0 10.0 \n",
"... ... ... \n",
"1154 0.5 5.5 \n",
"1155 0.5 5.5 \n",
"1156 0.0 6.0 \n",
"1157 0.0 5.5 \n",
"1158 0.0 5.5 \n",
"\n",
"[1159 rows x 10 columns]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"votes = pd.read_excel('mid_outputs/players_votes.xlsx', index_col = 0)\n",
"votes"
]
},
{
"cell_type": "markdown",
"id": "8cf677e4",
"metadata": {},
"source": [
"Merge votes data with match data for the player."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "ec0bc56b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0\n",
"100\n",
"200\n",
"300\n",
"400\n",
"500\n",
"600\n",
"700\n",
"800\n",
"900\n",
"1000\n",
"1100\n"
]
}
],
"source": [
"db = votes.copy()\n",
"\n",
"delta = pd.DataFrame(columns = add_columns)\n",
"\n",
"for i in range(db.shape[0]):\n",
" ext_data = player_match_data_ext(db['player'][i], db['team'][i], db['oppteam'][i])\n",
" \n",
" if(not isinstance(ext_data, pd.DataFrame)):\n",
" continue\n",
" \n",
" ext_data = ext_data.rename(index = {db['player'][i] : i})\n",
" \n",
" delta = pd.concat([delta, ext_data], axis = 0)\n",
" \n",
" if(i % 100 == 0):\n",
" print(i)\n",
" \n",
"db = pd.concat([db, delta], axis = 1)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "b292f9f9",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>miscontrols</th>\n",
" <th>dispossessed</th>\n",
" <th>fouls</th>\n",
" <th>fouled</th>\n",
" <th>aerials_won</th>\n",
" <th>aerials_lost</th>\n",
" <th>carries</th>\n",
" <th>progressive_carries</th>\n",
" <th>carries_into_final_third</th>\n",
" <th>carries_into_penalty_area</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Musso</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Zappacosta</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>0.020161</td>\n",
" <td>0.012097</td>\n",
" <td>0.012097</td>\n",
" <td>0.016129</td>\n",
" <td>0.008065</td>\n",
" <td>0.016129</td>\n",
" <td>0.391129</td>\n",
" <td>0.040323</td>\n",
" <td>0.020161</td>\n",
" <td>0.012097</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.007874</td>\n",
" <td>0.000000</td>\n",
" <td>0.007874</td>\n",
" <td>0.000000</td>\n",
" <td>0.019685</td>\n",
" <td>0.027559</td>\n",
" <td>0.350394</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Kolasinac</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>0.002786</td>\n",
" <td>0.002786</td>\n",
" <td>0.002786</td>\n",
" <td>0.011142</td>\n",
" <td>0.013928</td>\n",
" <td>0.022284</td>\n",
" <td>0.412256</td>\n",
" <td>0.019499</td>\n",
" <td>0.025070</td>\n",
" <td>0.002786</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Zortea</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.020833</td>\n",
" <td>0.031250</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.010417</td>\n",
" <td>0.447917</td>\n",
" <td>0.062500</td>\n",
" <td>0.041667</td>\n",
" <td>0.010417</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1154</th>\n",
" <td>4</td>\n",
" <td>Serdar</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.028846</td>\n",
" <td>0.009615</td>\n",
" <td>0.019231</td>\n",
" <td>0.000000</td>\n",
" <td>0.009615</td>\n",
" <td>0.038462</td>\n",
" <td>0.182692</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1155</th>\n",
" <td>4</td>\n",
" <td>Suslov</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.095238</td>\n",
" <td>0.047619</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.142857</td>\n",
" <td>0.000000</td>\n",
" <td>0.047619</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1156</th>\n",
" <td>4</td>\n",
" <td>Bonazzoli</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.047297</td>\n",
" <td>0.006757</td>\n",
" <td>0.006757</td>\n",
" <td>0.040541</td>\n",
" <td>0.013514</td>\n",
" <td>0.020270</td>\n",
" <td>0.324324</td>\n",
" <td>0.020270</td>\n",
" <td>0.013514</td>\n",
" <td>0.013514</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1157</th>\n",
" <td>4</td>\n",
" <td>Djuric</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.026316</td>\n",
" <td>0.006579</td>\n",
" <td>0.046053</td>\n",
" <td>0.006579</td>\n",
" <td>0.138158</td>\n",
" <td>0.092105</td>\n",
" <td>0.171053</td>\n",
" <td>0.000000</td>\n",
" <td>0.013158</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1158</th>\n",
" <td>4</td>\n",
" <td>Ngonge</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.019355</td>\n",
" <td>0.012903</td>\n",
" <td>0.032258</td>\n",
" <td>0.009677</td>\n",
" <td>0.012903</td>\n",
" <td>0.022581</td>\n",
" <td>0.206452</td>\n",
" <td>0.035484</td>\n",
" <td>0.012903</td>\n",
" <td>0.016129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1159 rows × 122 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"0 1 Musso Atalanta Sassuolo 0 6.5 0 0 \n",
"1 1 Zappacosta Atalanta Sassuolo 0 6.5 0 0 \n",
"2 1 Djimsiti Atalanta Sassuolo 0 6.0 0 0 \n",
"3 1 Kolasinac Atalanta Sassuolo 0 6.5 0 0 \n",
"4 1 Zortea Atalanta Sassuolo 0 7.0 1 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"1154 4 Serdar Verona Bologna 1 6.0 0 0 \n",
"1155 4 Suslov Verona Bologna 1 6.0 0 0 \n",
"1156 4 Bonazzoli Verona Bologna 1 6.0 0 0 \n",
"1157 4 Djuric Verona Bologna 1 5.5 0 0 \n",
"1158 4 Ngonge Verona Bologna 1 5.5 0 0 \n",
"\n",
" cards_malus fantavote ... miscontrols dispossessed fouls \\\n",
"0 0.0 6.5 ... 0.000000 0.000000 0.000000 \n",
"1 0.0 6.5 ... 0.020161 0.012097 0.012097 \n",
"2 0.0 6.0 ... 0.007874 0.000000 0.007874 \n",
"3 0.0 6.5 ... 0.002786 0.002786 0.002786 \n",
"4 0.0 10.0 ... 0.000000 0.020833 0.031250 \n",
"... ... ... ... ... ... ... \n",
"1154 0.5 5.5 ... 0.028846 0.009615 0.019231 \n",
"1155 0.5 5.5 ... 0.000000 0.000000 0.095238 \n",
"1156 0.0 6.0 ... 0.047297 0.006757 0.006757 \n",
"1157 0.0 5.5 ... 0.026316 0.006579 0.046053 \n",
"1158 0.0 5.5 ... 0.019355 0.012903 0.032258 \n",
"\n",
" fouled aerials_won aerials_lost carries progressive_carries \\\n",
"0 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"1 0.016129 0.008065 0.016129 0.391129 0.040323 \n",
"2 0.000000 0.019685 0.027559 0.350394 0.000000 \n",
"3 0.011142 0.013928 0.022284 0.412256 0.019499 \n",
"4 0.000000 0.000000 0.010417 0.447917 0.062500 \n",
"... ... ... ... ... ... \n",
"1154 0.000000 0.009615 0.038462 0.182692 0.000000 \n",
"1155 0.047619 0.000000 0.000000 0.142857 0.000000 \n",
"1156 0.040541 0.013514 0.020270 0.324324 0.020270 \n",
"1157 0.006579 0.138158 0.092105 0.171053 0.000000 \n",
"1158 0.009677 0.012903 0.022581 0.206452 0.035484 \n",
"\n",
" carries_into_final_third carries_into_penalty_area \n",
"0 0.000000 0.000000 \n",
"1 0.020161 0.012097 \n",
"2 0.000000 0.000000 \n",
"3 0.025070 0.002786 \n",
"4 0.041667 0.010417 \n",
"... ... ... \n",
"1154 0.000000 0.000000 \n",
"1155 0.047619 0.000000 \n",
"1156 0.013514 0.013514 \n",
"1157 0.013158 0.000000 \n",
"1158 0.012903 0.016129 \n",
"\n",
"[1159 rows x 122 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db"
]
},
{
"cell_type": "markdown",
"id": "d237f87b",
"metadata": {},
"source": [
"Remove undesired database entries."
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "1db9f77f",
"metadata": {},
"outputs": [],
"source": [
"db = db.drop(db[db.r == 'P'].index) # remove goalkeepers\n",
"db = db.drop(db[db.r != db.r].index) # remove non existing players (by searching NaN values)\n",
"db = db.drop(db[db.xg != db.xg].index)\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "f56df3ca",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>miscontrols</th>\n",
" <th>dispossessed</th>\n",
" <th>fouls</th>\n",
" <th>fouled</th>\n",
" <th>aerials_won</th>\n",
" <th>aerials_lost</th>\n",
" <th>carries</th>\n",
" <th>progressive_carries</th>\n",
" <th>carries_into_final_third</th>\n",
" <th>carries_into_penalty_area</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Zappacosta</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>0.020161</td>\n",
" <td>0.012097</td>\n",
" <td>0.012097</td>\n",
" <td>0.016129</td>\n",
" <td>0.008065</td>\n",
" <td>0.016129</td>\n",
" <td>0.391129</td>\n",
" <td>0.040323</td>\n",
" <td>0.020161</td>\n",
" <td>0.012097</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.007874</td>\n",
" <td>0.000000</td>\n",
" <td>0.007874</td>\n",
" <td>0.000000</td>\n",
" <td>0.019685</td>\n",
" <td>0.027559</td>\n",
" <td>0.350394</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Kolasinac</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>0.002786</td>\n",
" <td>0.002786</td>\n",
" <td>0.002786</td>\n",
" <td>0.011142</td>\n",
" <td>0.013928</td>\n",
" <td>0.022284</td>\n",
" <td>0.412256</td>\n",
" <td>0.019499</td>\n",
" <td>0.025070</td>\n",
" <td>0.002786</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Zortea</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.020833</td>\n",
" <td>0.031250</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.010417</td>\n",
" <td>0.447917</td>\n",
" <td>0.062500</td>\n",
" <td>0.041667</td>\n",
" <td>0.010417</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1</td>\n",
" <td>Ruggeri</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>7.5</td>\n",
" <td>...</td>\n",
" <td>0.012384</td>\n",
" <td>0.003096</td>\n",
" <td>0.012384</td>\n",
" <td>0.006192</td>\n",
" <td>0.003096</td>\n",
" <td>0.027864</td>\n",
" <td>0.408669</td>\n",
" <td>0.015480</td>\n",
" <td>0.012384</td>\n",
" <td>0.003096</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1154</th>\n",
" <td>4</td>\n",
" <td>Serdar</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.028846</td>\n",
" <td>0.009615</td>\n",
" <td>0.019231</td>\n",
" <td>0.000000</td>\n",
" <td>0.009615</td>\n",
" <td>0.038462</td>\n",
" <td>0.182692</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1155</th>\n",
" <td>4</td>\n",
" <td>Suslov</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.095238</td>\n",
" <td>0.047619</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.142857</td>\n",
" <td>0.000000</td>\n",
" <td>0.047619</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1156</th>\n",
" <td>4</td>\n",
" <td>Bonazzoli</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.047297</td>\n",
" <td>0.006757</td>\n",
" <td>0.006757</td>\n",
" <td>0.040541</td>\n",
" <td>0.013514</td>\n",
" <td>0.020270</td>\n",
" <td>0.324324</td>\n",
" <td>0.020270</td>\n",
" <td>0.013514</td>\n",
" <td>0.013514</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1157</th>\n",
" <td>4</td>\n",
" <td>Djuric</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.026316</td>\n",
" <td>0.006579</td>\n",
" <td>0.046053</td>\n",
" <td>0.006579</td>\n",
" <td>0.138158</td>\n",
" <td>0.092105</td>\n",
" <td>0.171053</td>\n",
" <td>0.000000</td>\n",
" <td>0.013158</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1158</th>\n",
" <td>4</td>\n",
" <td>Ngonge</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.019355</td>\n",
" <td>0.012903</td>\n",
" <td>0.032258</td>\n",
" <td>0.009677</td>\n",
" <td>0.012903</td>\n",
" <td>0.022581</td>\n",
" <td>0.206452</td>\n",
" <td>0.035484</td>\n",
" <td>0.012903</td>\n",
" <td>0.016129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1070 rows × 122 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"1 1 Zappacosta Atalanta Sassuolo 0 6.5 0 0 \n",
"2 1 Djimsiti Atalanta Sassuolo 0 6.0 0 0 \n",
"3 1 Kolasinac Atalanta Sassuolo 0 6.5 0 0 \n",
"4 1 Zortea Atalanta Sassuolo 0 7.0 1 0 \n",
"5 1 Ruggeri Atalanta Sassuolo 0 6.5 0 1 \n",
"... ... ... ... ... ... ... ... ... \n",
"1154 4 Serdar Verona Bologna 1 6.0 0 0 \n",
"1155 4 Suslov Verona Bologna 1 6.0 0 0 \n",
"1156 4 Bonazzoli Verona Bologna 1 6.0 0 0 \n",
"1157 4 Djuric Verona Bologna 1 5.5 0 0 \n",
"1158 4 Ngonge Verona Bologna 1 5.5 0 0 \n",
"\n",
" cards_malus fantavote ... miscontrols dispossessed fouls \\\n",
"1 0.0 6.5 ... 0.020161 0.012097 0.012097 \n",
"2 0.0 6.0 ... 0.007874 0.000000 0.007874 \n",
"3 0.0 6.5 ... 0.002786 0.002786 0.002786 \n",
"4 0.0 10.0 ... 0.000000 0.020833 0.031250 \n",
"5 0.0 7.5 ... 0.012384 0.003096 0.012384 \n",
"... ... ... ... ... ... ... \n",
"1154 0.5 5.5 ... 0.028846 0.009615 0.019231 \n",
"1155 0.5 5.5 ... 0.000000 0.000000 0.095238 \n",
"1156 0.0 6.0 ... 0.047297 0.006757 0.006757 \n",
"1157 0.0 5.5 ... 0.026316 0.006579 0.046053 \n",
"1158 0.0 5.5 ... 0.019355 0.012903 0.032258 \n",
"\n",
" fouled aerials_won aerials_lost carries progressive_carries \\\n",
"1 0.016129 0.008065 0.016129 0.391129 0.040323 \n",
"2 0.000000 0.019685 0.027559 0.350394 0.000000 \n",
"3 0.011142 0.013928 0.022284 0.412256 0.019499 \n",
"4 0.000000 0.000000 0.010417 0.447917 0.062500 \n",
"5 0.006192 0.003096 0.027864 0.408669 0.015480 \n",
"... ... ... ... ... ... \n",
"1154 0.000000 0.009615 0.038462 0.182692 0.000000 \n",
"1155 0.047619 0.000000 0.000000 0.142857 0.000000 \n",
"1156 0.040541 0.013514 0.020270 0.324324 0.020270 \n",
"1157 0.006579 0.138158 0.092105 0.171053 0.000000 \n",
"1158 0.009677 0.012903 0.022581 0.206452 0.035484 \n",
"\n",
" carries_into_final_third carries_into_penalty_area \n",
"1 0.020161 0.012097 \n",
"2 0.000000 0.000000 \n",
"3 0.025070 0.002786 \n",
"4 0.041667 0.010417 \n",
"5 0.012384 0.003096 \n",
"... ... ... \n",
"1154 0.000000 0.000000 \n",
"1155 0.047619 0.000000 \n",
"1156 0.013514 0.013514 \n",
"1157 0.013158 0.000000 \n",
"1158 0.012903 0.016129 \n",
"\n",
"[1070 rows x 122 columns]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db"
]
},
{
"cell_type": "markdown",
"id": "ab69d09e",
"metadata": {},
"source": [
"Save outfield players database to file."
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "df26c8e0",
"metadata": {},
"outputs": [],
"source": [
"db.to_excel('mid_outputs/database_entries.xlsx')"
]
},
{
"cell_type": "markdown",
"id": "38b564d2",
"metadata": {},
"source": [
"Do the same process for goalkeepers, generating a different database."
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "4d06576a",
"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\n",
"82 - assists\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": "code",
"execution_count": 19,
"id": "01bb7413",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['r',\n",
" 'fb_ID',\n",
" 'gk_games',\n",
" 'gk_games_starts',\n",
" 'gk_minutes',\n",
" 'gk_goals_against_per90',\n",
" 'gk_shots_on_target_against',\n",
" 'gk_saves',\n",
" 'gk_save_pct',\n",
" 'gk_clean_sheets_pct',\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_psxg_net_per90',\n",
" 'gk_passes_completed_launched',\n",
" 'gk_passes_launched',\n",
" 'gk_passes_pct_launched',\n",
" 'gk_passes',\n",
" 'gk_passes_throws',\n",
" 'gk_pct_passes_launched',\n",
" 'gk_passes_length_avg',\n",
" 'gk_goal_kicks',\n",
" 'gk_pct_goal_kicks_launched',\n",
" 'gk_goal_kick_length_avg',\n",
" 'gk_crosses',\n",
" 'gk_crosses_stopped',\n",
" 'gk_crosses_stopped_pct',\n",
" 'gk_def_actions_outside_pen_area',\n",
" 'gk_def_actions_outside_pen_area_per90',\n",
" 'gk_avg_distance_def_actions',\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']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rx = pd.read_excel('tmp/playermatchdata_sel_gk.xlsx', index_col = 0, header = None) \n",
"\n",
"out = list()\n",
"\n",
"for i in range(1, rx.shape[1]):\n",
" if(rx[i][2] == \"x\"):\n",
" out.append(rx[i][0])\n",
" \n",
"out"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "02f961d8",
"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": 21,
"id": "5e3694a0",
"metadata": {},
"outputs": [],
"source": [
"def player_match_data_ext_gk(player, pteam, oppteam):\n",
" pdata = player_match_data(player, pteam, oppteam)\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": "code",
"execution_count": 22,
"id": "9b671646",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gk_games</th>\n",
" <th>gk_games_starts</th>\n",
" <th>gk_minutes</th>\n",
" <th>gk_goals_against_per90</th>\n",
" <th>gk_save_pct</th>\n",
" <th>gk_clean_sheets_pct</th>\n",
" <th>gk_psxg_net_per90</th>\n",
" <th>gk_passes_pct_launched</th>\n",
" <th>gk_pct_passes_launched</th>\n",
" <th>gk_passes_length_avg</th>\n",
" <th>...</th>\n",
" <th>gk_psxg</th>\n",
" <th>gk_psnpxg_per_shot_on_target_against</th>\n",
" <th>gk_psxg_net</th>\n",
" <th>gk_passes_completed_launched</th>\n",
" <th>gk_passes_launched</th>\n",
" <th>gk_passes</th>\n",
" <th>gk_passes_throws</th>\n",
" <th>gk_goal_kicks</th>\n",
" <th>gk_crosses</th>\n",
" <th>gk_crosses_stopped</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Consigli</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>270</td>\n",
" <td>1.67</td>\n",
" <td>66.7</td>\n",
" <td>0.0</td>\n",
" <td>-0.58</td>\n",
" <td>23.9</td>\n",
" <td>38.9</td>\n",
" <td>37.1</td>\n",
" <td>...</td>\n",
" <td>3.3</td>\n",
" <td>0.19</td>\n",
" <td>-1.7</td>\n",
" <td>11.0</td>\n",
" <td>46.0</td>\n",
" <td>95.0</td>\n",
" <td>10.0</td>\n",
" <td>34.0</td>\n",
" <td>46.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 92 columns</p>\n",
"</div>"
],
"text/plain": [
" gk_games gk_games_starts gk_minutes gk_goals_against_per90 \\\n",
"Consigli 3 3 270 1.67 \n",
"\n",
" gk_save_pct gk_clean_sheets_pct gk_psxg_net_per90 \\\n",
"Consigli 66.7 0.0 -0.58 \n",
"\n",
" gk_passes_pct_launched gk_pct_passes_launched \\\n",
"Consigli 23.9 38.9 \n",
"\n",
" gk_passes_length_avg ... gk_psxg \\\n",
"Consigli 37.1 ... 3.3 \n",
"\n",
" gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n",
"Consigli 0.19 -1.7 \n",
"\n",
" gk_passes_completed_launched gk_passes_launched gk_passes \\\n",
"Consigli 11.0 46.0 95.0 \n",
"\n",
" gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n",
"Consigli 10.0 34.0 46.0 2.0 \n",
"\n",
"[1 rows x 92 columns]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test = player_match_data_ext_gk('Consigli', 'Sassuolo', 'Atalanta')\n",
"\n",
"add_columns_gk = test.columns\n",
"\n",
"test"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "33f805a9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0\n",
"100\n",
"200\n",
"300\n",
"400\n",
"500\n",
"600\n",
"700\n",
"800\n",
"900\n",
"1000\n",
"1100\n"
]
}
],
"source": [
"db_gk = votes.copy()\n",
"\n",
"delta = pd.DataFrame(columns = add_columns_gk)\n",
"\n",
"for i in range(db_gk.shape[0]):\n",
" ext_data = player_match_data_ext_gk(db_gk['player'][i], db_gk['team'][i], db_gk['oppteam'][i])\n",
" \n",
" if(i % 100 == 0):\n",
" print(i)\n",
" \n",
" if(not isinstance(ext_data, pd.DataFrame)):\n",
" continue\n",
" \n",
" ext_data = ext_data.rename(index = {db_gk['player'][i] : i})\n",
" \n",
" delta = pd.concat([delta, ext_data], axis = 0)\n",
" \n",
" \n",
" \n",
"db_gk = pd.concat([db_gk, delta], axis = 1)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "4d484846",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>gk_psxg</th>\n",
" <th>gk_psnpxg_per_shot_on_target_against</th>\n",
" <th>gk_psxg_net</th>\n",
" <th>gk_passes_completed_launched</th>\n",
" <th>gk_passes_launched</th>\n",
" <th>gk_passes</th>\n",
" <th>gk_passes_throws</th>\n",
" <th>gk_goal_kicks</th>\n",
" <th>gk_crosses</th>\n",
" <th>gk_crosses_stopped</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Musso</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>2.1</td>\n",
" <td>0.21</td>\n",
" <td>0.1</td>\n",
" <td>11.0</td>\n",
" <td>34.0</td>\n",
" <td>88.0</td>\n",
" <td>18.0</td>\n",
" <td>18.0</td>\n",
" <td>28.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Zappacosta</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Kolasinac</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Zortea</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1154</th>\n",
" <td>4</td>\n",
" <td>Serdar</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1155</th>\n",
" <td>4</td>\n",
" <td>Suslov</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1156</th>\n",
" <td>4</td>\n",
" <td>Bonazzoli</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1157</th>\n",
" <td>4</td>\n",
" <td>Djuric</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1158</th>\n",
" <td>4</td>\n",
" <td>Ngonge</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1159 rows × 102 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"0 1 Musso Atalanta Sassuolo 0 6.5 0 0 \n",
"1 1 Zappacosta Atalanta Sassuolo 0 6.5 0 0 \n",
"2 1 Djimsiti Atalanta Sassuolo 0 6.0 0 0 \n",
"3 1 Kolasinac Atalanta Sassuolo 0 6.5 0 0 \n",
"4 1 Zortea Atalanta Sassuolo 0 7.0 1 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"1154 4 Serdar Verona Bologna 1 6.0 0 0 \n",
"1155 4 Suslov Verona Bologna 1 6.0 0 0 \n",
"1156 4 Bonazzoli Verona Bologna 1 6.0 0 0 \n",
"1157 4 Djuric Verona Bologna 1 5.5 0 0 \n",
"1158 4 Ngonge Verona Bologna 1 5.5 0 0 \n",
"\n",
" cards_malus fantavote ... gk_psxg \\\n",
"0 0.0 6.5 ... 2.1 \n",
"1 0.0 6.5 ... NaN \n",
"2 0.0 6.0 ... NaN \n",
"3 0.0 6.5 ... NaN \n",
"4 0.0 10.0 ... NaN \n",
"... ... ... ... ... \n",
"1154 0.5 5.5 ... NaN \n",
"1155 0.5 5.5 ... NaN \n",
"1156 0.0 6.0 ... NaN \n",
"1157 0.0 5.5 ... NaN \n",
"1158 0.0 5.5 ... NaN \n",
"\n",
" gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n",
"0 0.21 0.1 \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"1154 NaN NaN \n",
"1155 NaN NaN \n",
"1156 NaN NaN \n",
"1157 NaN NaN \n",
"1158 NaN NaN \n",
"\n",
" gk_passes_completed_launched gk_passes_launched gk_passes \\\n",
"0 11.0 34.0 88.0 \n",
"1 NaN NaN NaN \n",
"2 NaN NaN NaN \n",
"3 NaN NaN NaN \n",
"4 NaN NaN NaN \n",
"... ... ... ... \n",
"1154 NaN NaN NaN \n",
"1155 NaN NaN NaN \n",
"1156 NaN NaN NaN \n",
"1157 NaN NaN NaN \n",
"1158 NaN NaN NaN \n",
"\n",
" gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n",
"0 18.0 18.0 28.0 2.0 \n",
"1 NaN NaN NaN NaN \n",
"2 NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN \n",
"... ... ... ... ... \n",
"1154 NaN NaN NaN NaN \n",
"1155 NaN NaN NaN NaN \n",
"1156 NaN NaN NaN NaN \n",
"1157 NaN NaN NaN NaN \n",
"1158 NaN NaN NaN NaN \n",
"\n",
"[1159 rows x 102 columns]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db_gk"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "adab3577",
"metadata": {},
"outputs": [],
"source": [
"db_gk = db_gk.drop(db_gk[db_gk.gk_games != db_gk.gk_games].index) # remove non extisting players"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "e7ae792d",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>player</th>\n",
" <th>team</th>\n",
" <th>oppteam</th>\n",
" <th>home</th>\n",
" <th>vote</th>\n",
" <th>goals</th>\n",
" <th>assists</th>\n",
" <th>cards_malus</th>\n",
" <th>fantavote</th>\n",
" <th>...</th>\n",
" <th>gk_psxg</th>\n",
" <th>gk_psnpxg_per_shot_on_target_against</th>\n",
" <th>gk_psxg_net</th>\n",
" <th>gk_passes_completed_launched</th>\n",
" <th>gk_passes_launched</th>\n",
" <th>gk_passes</th>\n",
" <th>gk_passes_throws</th>\n",
" <th>gk_goal_kicks</th>\n",
" <th>gk_crosses</th>\n",
" <th>gk_crosses_stopped</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Musso</td>\n",
" <td>Atalanta</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>2.1</td>\n",
" <td>0.21</td>\n",
" <td>0.1</td>\n",
" <td>11.0</td>\n",
" <td>34.0</td>\n",
" <td>88.0</td>\n",
" <td>18.0</td>\n",
" <td>18.0</td>\n",
" <td>28.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1</td>\n",
" <td>Skorupski</td>\n",
" <td>Bologna</td>\n",
" <td>Milan</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>-2</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>3.2</td>\n",
" <td>0.32</td>\n",
" <td>-0.8</td>\n",
" <td>17.0</td>\n",
" <td>45.0</td>\n",
" <td>106.0</td>\n",
" <td>17.0</td>\n",
" <td>22.0</td>\n",
" <td>57.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1</td>\n",
" <td>Radunovic</td>\n",
" <td>Cagliari</td>\n",
" <td>Torino</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.5</td>\n",
" <td>...</td>\n",
" <td>4.1</td>\n",
" <td>0.33</td>\n",
" <td>0.1</td>\n",
" <td>24.0</td>\n",
" <td>54.0</td>\n",
" <td>76.0</td>\n",
" <td>18.0</td>\n",
" <td>40.0</td>\n",
" <td>62.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>1</td>\n",
" <td>Caprile</td>\n",
" <td>Empoli</td>\n",
" <td>Verona</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>0.4</td>\n",
" <td>0.11</td>\n",
" <td>-0.6</td>\n",
" <td>4.0</td>\n",
" <td>20.0</td>\n",
" <td>37.0</td>\n",
" <td>9.0</td>\n",
" <td>4.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>1</td>\n",
" <td>Terracciano</td>\n",
" <td>Fiorentina</td>\n",
" <td>Genoa</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>0.17</td>\n",
" <td>-2.0</td>\n",
" <td>13.0</td>\n",
" <td>20.0</td>\n",
" <td>85.0</td>\n",
" <td>10.0</td>\n",
" <td>9.0</td>\n",
" <td>16.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1085</th>\n",
" <td>4</td>\n",
" <td>Ochoa</td>\n",
" <td>Salernitana</td>\n",
" <td>Torino</td>\n",
" <td>1</td>\n",
" <td>5.0</td>\n",
" <td>-3</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>4.7</td>\n",
" <td>0.21</td>\n",
" <td>-3.3</td>\n",
" <td>13.0</td>\n",
" <td>55.0</td>\n",
" <td>89.0</td>\n",
" <td>14.0</td>\n",
" <td>35.0</td>\n",
" <td>63.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1101</th>\n",
" <td>4</td>\n",
" <td>Cragno</td>\n",
" <td>Sassuolo</td>\n",
" <td>Frosinone</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>-4</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>2.5</td>\n",
" <td>...</td>\n",
" <td>2.8</td>\n",
" <td>0.30</td>\n",
" <td>-1.2</td>\n",
" <td>5.0</td>\n",
" <td>15.0</td>\n",
" <td>24.0</td>\n",
" <td>3.0</td>\n",
" <td>9.0</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1117</th>\n",
" <td>4</td>\n",
" <td>Milinkovic-Savic V.</td>\n",
" <td>Torino</td>\n",
" <td>Salernitana</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>4.6</td>\n",
" <td>0.18</td>\n",
" <td>0.6</td>\n",
" <td>29.0</td>\n",
" <td>79.0</td>\n",
" <td>117.0</td>\n",
" <td>23.0</td>\n",
" <td>36.0</td>\n",
" <td>33.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1129</th>\n",
" <td>4</td>\n",
" <td>Silvestri</td>\n",
" <td>Udinese</td>\n",
" <td>Cagliari</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>3.9</td>\n",
" <td>0.29</td>\n",
" <td>-0.1</td>\n",
" <td>11.0</td>\n",
" <td>34.0</td>\n",
" <td>94.0</td>\n",
" <td>14.0</td>\n",
" <td>32.0</td>\n",
" <td>49.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1143</th>\n",
" <td>4</td>\n",
" <td>Montipo'</td>\n",
" <td>Verona</td>\n",
" <td>Bologna</td>\n",
" <td>1</td>\n",
" <td>7.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>...</td>\n",
" <td>4.9</td>\n",
" <td>0.19</td>\n",
" <td>0.9</td>\n",
" <td>35.0</td>\n",
" <td>93.0</td>\n",
" <td>109.0</td>\n",
" <td>8.0</td>\n",
" <td>35.0</td>\n",
" <td>54.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>80 rows × 102 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote \\\n",
"0 1 Musso Atalanta Sassuolo 0 6.5 \n",
"16 1 Skorupski Bologna Milan 1 6.0 \n",
"29 1 Radunovic Cagliari Torino 0 6.5 \n",
"44 1 Caprile Empoli Verona 1 5.0 \n",
"57 1 Terracciano Fiorentina Genoa 0 6.0 \n",
"... ... ... ... ... ... ... \n",
"1085 4 Ochoa Salernitana Torino 1 5.0 \n",
"1101 4 Cragno Sassuolo Frosinone 0 6.5 \n",
"1117 4 Milinkovic-Savic V. Torino Salernitana 0 6.0 \n",
"1129 4 Silvestri Udinese Cagliari 0 6.0 \n",
"1143 4 Montipo' Verona Bologna 1 7.0 \n",
"\n",
" goals assists cards_malus fantavote ... gk_psxg \\\n",
"0 0 0 0.0 6.5 ... 2.1 \n",
"16 -2 0 0.0 4.0 ... 3.2 \n",
"29 0 0 0.0 6.5 ... 4.1 \n",
"44 -1 0 0.0 4.0 ... 0.4 \n",
"57 -1 0 0.0 5.0 ... 1.0 \n",
"... ... ... ... ... ... ... \n",
"1085 -3 0 0.0 2.0 ... 4.7 \n",
"1101 -4 0 0.0 2.5 ... 2.8 \n",
"1117 0 0 0.0 6.0 ... 4.6 \n",
"1129 0 0 0.0 6.0 ... 3.9 \n",
"1143 0 0 0.0 7.0 ... 4.9 \n",
"\n",
" gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n",
"0 0.21 0.1 \n",
"16 0.32 -0.8 \n",
"29 0.33 0.1 \n",
"44 0.11 -0.6 \n",
"57 0.17 -2.0 \n",
"... ... ... \n",
"1085 0.21 -3.3 \n",
"1101 0.30 -1.2 \n",
"1117 0.18 0.6 \n",
"1129 0.29 -0.1 \n",
"1143 0.19 0.9 \n",
"\n",
" gk_passes_completed_launched gk_passes_launched gk_passes \\\n",
"0 11.0 34.0 88.0 \n",
"16 17.0 45.0 106.0 \n",
"29 24.0 54.0 76.0 \n",
"44 4.0 20.0 37.0 \n",
"57 13.0 20.0 85.0 \n",
"... ... ... ... \n",
"1085 13.0 55.0 89.0 \n",
"1101 5.0 15.0 24.0 \n",
"1117 29.0 79.0 117.0 \n",
"1129 11.0 34.0 94.0 \n",
"1143 35.0 93.0 109.0 \n",
"\n",
" gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n",
"0 18.0 18.0 28.0 2.0 \n",
"16 17.0 22.0 57.0 2.0 \n",
"29 18.0 40.0 62.0 4.0 \n",
"44 9.0 4.0 10.0 2.0 \n",
"57 10.0 9.0 16.0 1.0 \n",
"... ... ... ... ... \n",
"1085 14.0 35.0 63.0 4.0 \n",
"1101 3.0 9.0 9.0 0.0 \n",
"1117 23.0 36.0 33.0 3.0 \n",
"1129 14.0 32.0 49.0 0.0 \n",
"1143 8.0 35.0 54.0 1.0 \n",
"\n",
"[80 rows x 102 columns]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db_gk"
]
},
{
"cell_type": "markdown",
"id": "8dbb7476",
"metadata": {},
"source": [
"Save goalkeepers players database to file."
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "d8b8b6da",
"metadata": {},
"outputs": [],
"source": [
"db_gk.to_excel('mid_outputs/database_entries_gk.xlsx')"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "54519b24",
"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]))"
]
}
],
"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
}