Files
fantabeto/4b_player_match_dataset_creation_oldseasons.ipynb
T
Giuseppe Musicco b60a8a061c Release
2022-11-12 11:29:20 +01:00

3377 lines
115 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": "b22c6ee8",
"metadata": {},
"source": [
"player_match_dataset_creation code for past seasons\n",
"\n",
"Select the season in season variable, and repeat the code if needed"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "8a74364d",
"metadata": {},
"outputs": [],
"source": [
"season = '2122'"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "8a6867a5",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_1244\\813865162.py:21: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" team_data['team_idx'][i] = team_data['team_idx'][i].split(' ')[-1]\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>team</th>\n",
" <th>team_players_used</th>\n",
" <th>team_possession</th>\n",
" <th>team_games</th>\n",
" <th>team_games_starts</th>\n",
" <th>team_minutes</th>\n",
" <th>team_goals</th>\n",
" <th>team_assists</th>\n",
" <th>team_pens_made</th>\n",
" <th>team_pens_att</th>\n",
" <th>...</th>\n",
" <th>vs_team_fouls</th>\n",
" <th>vs_team_fouled</th>\n",
" <th>vs_team_offsides</th>\n",
" <th>vs_team_pens_won</th>\n",
" <th>vs_team_pens_conceded</th>\n",
" <th>vs_team_own_goals</th>\n",
" <th>vs_team_ball_recoveries</th>\n",
" <th>vs_team_aerials_won</th>\n",
" <th>vs_team_aerials_lost</th>\n",
" <th>vs_team_aerials_won_pct</th>\n",
" </tr>\n",
" <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>32.0</td>\n",
" <td>55.0</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>62.0</td>\n",
" <td>48.0</td>\n",
" <td>5.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>491.0</td>\n",
" <td>488.0</td>\n",
" <td>69.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>2240.0</td>\n",
" <td>518.0</td>\n",
" <td>685.0</td>\n",
" <td>43.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Bologna</th>\n",
" <td>Bologna</td>\n",
" <td>36.0</td>\n",
" <td>50.6</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>43.0</td>\n",
" <td>34.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>527.0</td>\n",
" <td>416.0</td>\n",
" <td>88.0</td>\n",
" <td>8.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>2032.0</td>\n",
" <td>520.0</td>\n",
" <td>492.0</td>\n",
" <td>51.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cagliari</th>\n",
" <td>Cagliari</td>\n",
" <td>33.0</td>\n",
" <td>44.5</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>34.0</td>\n",
" <td>26.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>526.0</td>\n",
" <td>524.0</td>\n",
" <td>76.0</td>\n",
" <td>6.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>2112.0</td>\n",
" <td>742.0</td>\n",
" <td>696.0</td>\n",
" <td>51.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Empoli</th>\n",
" <td>Empoli</td>\n",
" <td>28.0</td>\n",
" <td>47.4</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>47.0</td>\n",
" <td>27.0</td>\n",
" <td>7.0</td>\n",
" <td>7.0</td>\n",
" <td>...</td>\n",
" <td>488.0</td>\n",
" <td>482.0</td>\n",
" <td>66.0</td>\n",
" <td>7.0</td>\n",
" <td>7.0</td>\n",
" <td>3.0</td>\n",
" <td>2051.0</td>\n",
" <td>549.0</td>\n",
" <td>427.0</td>\n",
" <td>56.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Fiorentina</th>\n",
" <td>Fiorentina</td>\n",
" <td>28.0</td>\n",
" <td>57.7</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>59.0</td>\n",
" <td>33.0</td>\n",
" <td>9.0</td>\n",
" <td>12.0</td>\n",
" <td>...</td>\n",
" <td>585.0</td>\n",
" <td>441.0</td>\n",
" <td>119.0</td>\n",
" <td>4.0</td>\n",
" <td>12.0</td>\n",
" <td>0.0</td>\n",
" <td>1825.0</td>\n",
" <td>456.0</td>\n",
" <td>469.0</td>\n",
" <td>49.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Genoa</th>\n",
" <td>Genoa</td>\n",
" <td>40.0</td>\n",
" <td>43.9</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>26.0</td>\n",
" <td>19.0</td>\n",
" <td>6.0</td>\n",
" <td>7.0</td>\n",
" <td>...</td>\n",
" <td>523.0</td>\n",
" <td>530.0</td>\n",
" <td>59.0</td>\n",
" <td>4.0</td>\n",
" <td>7.0</td>\n",
" <td>1.0</td>\n",
" <td>2257.0</td>\n",
" <td>743.0</td>\n",
" <td>635.0</td>\n",
" <td>53.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Verona</th>\n",
" <td>Hellas Verona</td>\n",
" <td>31.0</td>\n",
" <td>50.6</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>63.0</td>\n",
" <td>44.0</td>\n",
" <td>7.0</td>\n",
" <td>8.0</td>\n",
" <td>...</td>\n",
" <td>463.0</td>\n",
" <td>534.0</td>\n",
" <td>32.0</td>\n",
" <td>3.0</td>\n",
" <td>8.0</td>\n",
" <td>2.0</td>\n",
" <td>2206.0</td>\n",
" <td>733.0</td>\n",
" <td>689.0</td>\n",
" <td>51.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Inter</th>\n",
" <td>Inter</td>\n",
" <td>27.0</td>\n",
" <td>56.5</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>83.0</td>\n",
" <td>57.0</td>\n",
" <td>7.0</td>\n",
" <td>11.0</td>\n",
" <td>...</td>\n",
" <td>440.0</td>\n",
" <td>441.0</td>\n",
" <td>34.0</td>\n",
" <td>3.0</td>\n",
" <td>11.0</td>\n",
" <td>1.0</td>\n",
" <td>1767.0</td>\n",
" <td>476.0</td>\n",
" <td>549.0</td>\n",
" <td>46.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Juventus</th>\n",
" <td>Juventus</td>\n",
" <td>32.0</td>\n",
" <td>51.5</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>56.0</td>\n",
" <td>37.0</td>\n",
" <td>5.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>525.0</td>\n",
" <td>471.0</td>\n",
" <td>35.0</td>\n",
" <td>5.0</td>\n",
" <td>6.0</td>\n",
" <td>1.0</td>\n",
" <td>1894.0</td>\n",
" <td>440.0</td>\n",
" <td>550.0</td>\n",
" <td>44.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lazio</th>\n",
" <td>Lazio</td>\n",
" <td>27.0</td>\n",
" <td>55.4</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>74.0</td>\n",
" <td>48.0</td>\n",
" <td>7.0</td>\n",
" <td>9.0</td>\n",
" <td>...</td>\n",
" <td>474.0</td>\n",
" <td>418.0</td>\n",
" <td>73.0</td>\n",
" <td>6.0</td>\n",
" <td>9.0</td>\n",
" <td>3.0</td>\n",
" <td>1956.0</td>\n",
" <td>427.0</td>\n",
" <td>411.0</td>\n",
" <td>51.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Milan</th>\n",
" <td>Milan</td>\n",
" <td>28.0</td>\n",
" <td>54.0</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>66.0</td>\n",
" <td>39.0</td>\n",
" <td>5.0</td>\n",
" <td>8.0</td>\n",
" <td>...</td>\n",
" <td>533.0</td>\n",
" <td>440.0</td>\n",
" <td>63.0</td>\n",
" <td>3.0</td>\n",
" <td>8.0</td>\n",
" <td>3.0</td>\n",
" <td>2106.0</td>\n",
" <td>517.0</td>\n",
" <td>521.0</td>\n",
" <td>49.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Napoli</th>\n",
" <td>Napoli</td>\n",
" <td>27.0</td>\n",
" <td>58.3</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>74.0</td>\n",
" <td>46.0</td>\n",
" <td>10.0</td>\n",
" <td>14.0</td>\n",
" <td>...</td>\n",
" <td>517.0</td>\n",
" <td>415.0</td>\n",
" <td>60.0</td>\n",
" <td>0.0</td>\n",
" <td>14.0</td>\n",
" <td>0.0</td>\n",
" <td>1963.0</td>\n",
" <td>403.0</td>\n",
" <td>393.0</td>\n",
" <td>50.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Roma</th>\n",
" <td>Roma</td>\n",
" <td>29.0</td>\n",
" <td>51.4</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>58.0</td>\n",
" <td>31.0</td>\n",
" <td>7.0</td>\n",
" <td>9.0</td>\n",
" <td>...</td>\n",
" <td>497.0</td>\n",
" <td>477.0</td>\n",
" <td>81.0</td>\n",
" <td>5.0</td>\n",
" <td>9.0</td>\n",
" <td>1.0</td>\n",
" <td>1970.0</td>\n",
" <td>441.0</td>\n",
" <td>524.0</td>\n",
" <td>45.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Salernitana</th>\n",
" <td>Salernitana</td>\n",
" <td>42.0</td>\n",
" <td>41.2</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>32.0</td>\n",
" <td>19.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>546.0</td>\n",
" <td>463.0</td>\n",
" <td>63.0</td>\n",
" <td>6.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>2043.0</td>\n",
" <td>506.0</td>\n",
" <td>657.0</td>\n",
" <td>43.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sampdoria</th>\n",
" <td>Sampdoria</td>\n",
" <td>34.0</td>\n",
" <td>46.1</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>42.0</td>\n",
" <td>29.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>538.0</td>\n",
" <td>471.0</td>\n",
" <td>64.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>2174.0</td>\n",
" <td>506.0</td>\n",
" <td>609.0</td>\n",
" <td>45.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sassuolo</th>\n",
" <td>Sassuolo</td>\n",
" <td>29.0</td>\n",
" <td>54.9</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>60.0</td>\n",
" <td>39.0</td>\n",
" <td>7.0</td>\n",
" <td>7.0</td>\n",
" <td>...</td>\n",
" <td>519.0</td>\n",
" <td>434.0</td>\n",
" <td>142.0</td>\n",
" <td>6.0</td>\n",
" <td>7.0</td>\n",
" <td>4.0</td>\n",
" <td>2041.0</td>\n",
" <td>404.0</td>\n",
" <td>343.0</td>\n",
" <td>54.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Spezia</th>\n",
" <td>Spezia</td>\n",
" <td>30.0</td>\n",
" <td>42.7</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>38.0</td>\n",
" <td>25.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>474.0</td>\n",
" <td>477.0</td>\n",
" <td>62.0</td>\n",
" <td>8.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2064.0</td>\n",
" <td>589.0</td>\n",
" <td>530.0</td>\n",
" <td>52.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Torino</th>\n",
" <td>Torino</td>\n",
" <td>31.0</td>\n",
" <td>53.3</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>43.0</td>\n",
" <td>27.0</td>\n",
" <td>6.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>485.0</td>\n",
" <td>611.0</td>\n",
" <td>60.0</td>\n",
" <td>10.0</td>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>1989.0</td>\n",
" <td>891.0</td>\n",
" <td>781.0</td>\n",
" <td>53.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Udinese</th>\n",
" <td>Udinese</td>\n",
" <td>29.0</td>\n",
" <td>42.7</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>58.0</td>\n",
" <td>36.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>494.0</td>\n",
" <td>537.0</td>\n",
" <td>57.0</td>\n",
" <td>6.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2010.0</td>\n",
" <td>534.0</td>\n",
" <td>453.0</td>\n",
" <td>54.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Venezia</th>\n",
" <td>Venezia</td>\n",
" <td>39.0</td>\n",
" <td>42.3</td>\n",
" <td>38.0</td>\n",
" <td>418.0</td>\n",
" <td>3420.0</td>\n",
" <td>34.0</td>\n",
" <td>23.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>476.0</td>\n",
" <td>492.0</td>\n",
" <td>48.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>2059.0</td>\n",
" <td>583.0</td>\n",
" <td>564.0</td>\n",
" <td>50.8</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>20 rows × 313 columns</p>\n",
"</div>"
],
"text/plain": [
" team team_players_used team_possession team_games \\\n",
"team_idx \n",
"Atalanta Atalanta 32.0 55.0 38.0 \n",
"Bologna Bologna 36.0 50.6 38.0 \n",
"Cagliari Cagliari 33.0 44.5 38.0 \n",
"Empoli Empoli 28.0 47.4 38.0 \n",
"Fiorentina Fiorentina 28.0 57.7 38.0 \n",
"Genoa Genoa 40.0 43.9 38.0 \n",
"Verona Hellas Verona 31.0 50.6 38.0 \n",
"Inter Inter 27.0 56.5 38.0 \n",
"Juventus Juventus 32.0 51.5 38.0 \n",
"Lazio Lazio 27.0 55.4 38.0 \n",
"Milan Milan 28.0 54.0 38.0 \n",
"Napoli Napoli 27.0 58.3 38.0 \n",
"Roma Roma 29.0 51.4 38.0 \n",
"Salernitana Salernitana 42.0 41.2 38.0 \n",
"Sampdoria Sampdoria 34.0 46.1 38.0 \n",
"Sassuolo Sassuolo 29.0 54.9 38.0 \n",
"Spezia Spezia 30.0 42.7 38.0 \n",
"Torino Torino 31.0 53.3 38.0 \n",
"Udinese Udinese 29.0 42.7 38.0 \n",
"Venezia Venezia 39.0 42.3 38.0 \n",
"\n",
" team_games_starts team_minutes team_goals team_assists \\\n",
"team_idx \n",
"Atalanta 418.0 3420.0 62.0 48.0 \n",
"Bologna 418.0 3420.0 43.0 34.0 \n",
"Cagliari 418.0 3420.0 34.0 26.0 \n",
"Empoli 418.0 3420.0 47.0 27.0 \n",
"Fiorentina 418.0 3420.0 59.0 33.0 \n",
"Genoa 418.0 3420.0 26.0 19.0 \n",
"Verona 418.0 3420.0 63.0 44.0 \n",
"Inter 418.0 3420.0 83.0 57.0 \n",
"Juventus 418.0 3420.0 56.0 37.0 \n",
"Lazio 418.0 3420.0 74.0 48.0 \n",
"Milan 418.0 3420.0 66.0 39.0 \n",
"Napoli 418.0 3420.0 74.0 46.0 \n",
"Roma 418.0 3420.0 58.0 31.0 \n",
"Salernitana 418.0 3420.0 32.0 19.0 \n",
"Sampdoria 418.0 3420.0 42.0 29.0 \n",
"Sassuolo 418.0 3420.0 60.0 39.0 \n",
"Spezia 418.0 3420.0 38.0 25.0 \n",
"Torino 418.0 3420.0 43.0 27.0 \n",
"Udinese 418.0 3420.0 58.0 36.0 \n",
"Venezia 418.0 3420.0 34.0 23.0 \n",
"\n",
" team_pens_made team_pens_att ... vs_team_fouls \\\n",
"team_idx ... \n",
"Atalanta 5.0 6.0 ... 491.0 \n",
"Bologna 4.0 5.0 ... 527.0 \n",
"Cagliari 3.0 4.0 ... 526.0 \n",
"Empoli 7.0 7.0 ... 488.0 \n",
"Fiorentina 9.0 12.0 ... 585.0 \n",
"Genoa 6.0 7.0 ... 523.0 \n",
"Verona 7.0 8.0 ... 463.0 \n",
"Inter 7.0 11.0 ... 440.0 \n",
"Juventus 5.0 6.0 ... 525.0 \n",
"Lazio 7.0 9.0 ... 474.0 \n",
"Milan 5.0 8.0 ... 533.0 \n",
"Napoli 10.0 14.0 ... 517.0 \n",
"Roma 7.0 9.0 ... 497.0 \n",
"Salernitana 4.0 5.0 ... 546.0 \n",
"Sampdoria 2.0 4.0 ... 538.0 \n",
"Sassuolo 7.0 7.0 ... 519.0 \n",
"Spezia 3.0 5.0 ... 474.0 \n",
"Torino 6.0 6.0 ... 485.0 \n",
"Udinese 3.0 4.0 ... 494.0 \n",
"Venezia 3.0 5.0 ... 476.0 \n",
"\n",
" vs_team_fouled vs_team_offsides vs_team_pens_won \\\n",
"team_idx \n",
"Atalanta 488.0 69.0 4.0 \n",
"Bologna 416.0 88.0 8.0 \n",
"Cagliari 524.0 76.0 6.0 \n",
"Empoli 482.0 66.0 7.0 \n",
"Fiorentina 441.0 119.0 4.0 \n",
"Genoa 530.0 59.0 4.0 \n",
"Verona 534.0 32.0 3.0 \n",
"Inter 441.0 34.0 3.0 \n",
"Juventus 471.0 35.0 5.0 \n",
"Lazio 418.0 73.0 6.0 \n",
"Milan 440.0 63.0 3.0 \n",
"Napoli 415.0 60.0 0.0 \n",
"Roma 477.0 81.0 5.0 \n",
"Salernitana 463.0 63.0 6.0 \n",
"Sampdoria 471.0 64.0 1.0 \n",
"Sassuolo 434.0 142.0 6.0 \n",
"Spezia 477.0 62.0 8.0 \n",
"Torino 611.0 60.0 10.0 \n",
"Udinese 537.0 57.0 6.0 \n",
"Venezia 492.0 48.0 5.0 \n",
"\n",
" vs_team_pens_conceded vs_team_own_goals \\\n",
"team_idx \n",
"Atalanta 6.0 3.0 \n",
"Bologna 5.0 1.0 \n",
"Cagliari 4.0 0.0 \n",
"Empoli 7.0 3.0 \n",
"Fiorentina 12.0 0.0 \n",
"Genoa 7.0 1.0 \n",
"Verona 8.0 2.0 \n",
"Inter 11.0 1.0 \n",
"Juventus 6.0 1.0 \n",
"Lazio 9.0 3.0 \n",
"Milan 8.0 3.0 \n",
"Napoli 14.0 0.0 \n",
"Roma 9.0 1.0 \n",
"Salernitana 5.0 1.0 \n",
"Sampdoria 4.0 4.0 \n",
"Sassuolo 7.0 4.0 \n",
"Spezia 5.0 3.0 \n",
"Torino 6.0 3.0 \n",
"Udinese 4.0 3.0 \n",
"Venezia 5.0 0.0 \n",
"\n",
" vs_team_ball_recoveries vs_team_aerials_won \\\n",
"team_idx \n",
"Atalanta 2240.0 518.0 \n",
"Bologna 2032.0 520.0 \n",
"Cagliari 2112.0 742.0 \n",
"Empoli 2051.0 549.0 \n",
"Fiorentina 1825.0 456.0 \n",
"Genoa 2257.0 743.0 \n",
"Verona 2206.0 733.0 \n",
"Inter 1767.0 476.0 \n",
"Juventus 1894.0 440.0 \n",
"Lazio 1956.0 427.0 \n",
"Milan 2106.0 517.0 \n",
"Napoli 1963.0 403.0 \n",
"Roma 1970.0 441.0 \n",
"Salernitana 2043.0 506.0 \n",
"Sampdoria 2174.0 506.0 \n",
"Sassuolo 2041.0 404.0 \n",
"Spezia 2064.0 589.0 \n",
"Torino 1989.0 891.0 \n",
"Udinese 2010.0 534.0 \n",
"Venezia 2059.0 583.0 \n",
"\n",
" vs_team_aerials_lost vs_team_aerials_won_pct \n",
"team_idx \n",
"Atalanta 685.0 43.1 \n",
"Bologna 492.0 51.4 \n",
"Cagliari 696.0 51.6 \n",
"Empoli 427.0 56.3 \n",
"Fiorentina 469.0 49.3 \n",
"Genoa 635.0 53.9 \n",
"Verona 689.0 51.5 \n",
"Inter 549.0 46.4 \n",
"Juventus 550.0 44.4 \n",
"Lazio 411.0 51.0 \n",
"Milan 521.0 49.8 \n",
"Napoli 393.0 50.6 \n",
"Roma 524.0 45.7 \n",
"Salernitana 657.0 43.5 \n",
"Sampdoria 609.0 45.4 \n",
"Sassuolo 343.0 54.1 \n",
"Spezia 530.0 52.6 \n",
"Torino 781.0 53.3 \n",
"Udinese 453.0 54.1 \n",
"Venezia 564.0 50.8 \n",
"\n",
"[20 rows x 313 columns]"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"rcsv = pd.read_csv('fbref_data/season' + season + '/teams.csv') \n",
"team = pd.DataFrame(rcsv)\n",
"\n",
"rcsv = pd.read_csv('fbref_data/season' + season + '/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['team_idx'][i] = team_data['team_idx'][i].split(' ')[-1]\n",
"\n",
"team_data = team_data.set_index('team_idx')\n",
"\n",
"team_data\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "b6a3db98",
"metadata": {},
"outputs": [],
"source": [
"team_data.to_excel('mid_outputs/season' + season + '/team_data.xlsx')"
]
},
{
"cell_type": "code",
"execution_count": 47,
"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>Maignan</th>\n",
" <td>0</td>\n",
" <td>4312</td>\n",
" <td>P</td>\n",
" <td>Milan</td>\n",
" <td>Maignan</td>\n",
" <td>NaN</td>\n",
" <td>647</td>\n",
" <td>26</td>\n",
" <td>1995</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>38.9</td>\n",
" <td>36.5</td>\n",
" <td>347.0</td>\n",
" <td>25.0</td>\n",
" <td>7.2</td>\n",
" <td>45.0</td>\n",
" <td>1.41</td>\n",
" <td>16.8</td>\n",
" <td>6.265625</td>\n",
" <td>0.483871</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>675</td>\n",
" <td>31</td>\n",
" <td>1990</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>29.7</td>\n",
" <td>31.5</td>\n",
" <td>481.0</td>\n",
" <td>24.0</td>\n",
" <td>5.0</td>\n",
" <td>25.0</td>\n",
" <td>0.76</td>\n",
" <td>13.5</td>\n",
" <td>6.121212</td>\n",
" <td>0.628012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ospina</th>\n",
" <td>2</td>\n",
" <td>2468</td>\n",
" <td>P</td>\n",
" <td>Napoli</td>\n",
" <td>Ospina</td>\n",
" <td>NaN</td>\n",
" <td>653</td>\n",
" <td>32</td>\n",
" <td>1988</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>14.1</td>\n",
" <td>22.5</td>\n",
" <td>353.0</td>\n",
" <td>18.0</td>\n",
" <td>5.1</td>\n",
" <td>31.0</td>\n",
" <td>1.00</td>\n",
" <td>17.0</td>\n",
" <td>6.258065</td>\n",
" <td>0.332899</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Handanovic</th>\n",
" <td>3</td>\n",
" <td>250</td>\n",
" <td>P</td>\n",
" <td>Inter</td>\n",
" <td>Handanovic</td>\n",
" <td>NaN</td>\n",
" <td>644</td>\n",
" <td>37</td>\n",
" <td>1984</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>20.4</td>\n",
" <td>26.5</td>\n",
" <td>393.0</td>\n",
" <td>15.0</td>\n",
" <td>3.8</td>\n",
" <td>10.0</td>\n",
" <td>0.27</td>\n",
" <td>11.2</td>\n",
" <td>6.162162</td>\n",
" <td>0.533399</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Berisha</th>\n",
" <td>4</td>\n",
" <td>316</td>\n",
" <td>P</td>\n",
" <td>Torino</td>\n",
" <td>Berisha</td>\n",
" <td>NaN</td>\n",
" <td>637</td>\n",
" <td>32</td>\n",
" <td>1989</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>87.2</td>\n",
" <td>58.6</td>\n",
" <td>148.0</td>\n",
" <td>7.0</td>\n",
" <td>4.7</td>\n",
" <td>10.0</td>\n",
" <td>1.00</td>\n",
" <td>14.6</td>\n",
" <td>6.100000</td>\n",
" <td>0.700000</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>Kokorin</th>\n",
" <td>545</td>\n",
" <td>5391</td>\n",
" <td>A</td>\n",
" <td>Fiorentina</td>\n",
" <td>Kokorin</td>\n",
" <td>NaN</td>\n",
" <td>283</td>\n",
" <td>30</td>\n",
" <td>1991</td>\n",
" <td>6</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>5.901518</td>\n",
" <td>0.269227</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Munteanu</th>\n",
" <td>546</td>\n",
" <td>5458</td>\n",
" <td>A</td>\n",
" <td>Fiorentina</td>\n",
" <td>Munteanu</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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.215233</td>\n",
" <td>0.275498</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Buksa</th>\n",
" <td>547</td>\n",
" <td>5459</td>\n",
" <td>A</td>\n",
" <td>Genoa</td>\n",
" <td>Buksa</td>\n",
" <td>NaN</td>\n",
" <td>83</td>\n",
" <td>18</td>\n",
" <td>2003</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.035319</td>\n",
" <td>0.591212</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Kaio Jorge</th>\n",
" <td>548</td>\n",
" <td>5505</td>\n",
" <td>A</td>\n",
" <td>Juventus</td>\n",
" <td>Jorge</td>\n",
" <td>NaN</td>\n",
" <td>266</td>\n",
" <td>19</td>\n",
" <td>2002</td>\n",
" <td>9</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.137790</td>\n",
" <td>0.468234</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Lazetic</th>\n",
" <td>549</td>\n",
" <td>5785</td>\n",
" <td>A</td>\n",
" <td>Milan</td>\n",
" <td>Lazetic</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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>6.325366</td>\n",
" <td>0.472207</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>550 rows × 165 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 id r team surname initial fb_ID age \\\n",
"name \n",
"Maignan 0 4312 P Milan Maignan NaN 647 26 \n",
"Szczesny 1 453 P Juventus Szczesny NaN 675 31 \n",
"Ospina 2 2468 P Napoli Ospina NaN 653 32 \n",
"Handanovic 3 250 P Inter Handanovic NaN 644 37 \n",
"Berisha 4 316 P Torino Berisha NaN 637 32 \n",
"... ... ... .. ... ... ... ... ... \n",
"Kokorin 545 5391 A Fiorentina Kokorin NaN 283 30 \n",
"Munteanu 546 5458 A Fiorentina Munteanu NaN -1 0 \n",
"Buksa 547 5459 A Genoa Buksa NaN 83 18 \n",
"Kaio Jorge 548 5505 A Juventus Jorge NaN 266 19 \n",
"Lazetic 549 5785 A Milan Lazetic NaN -1 0 \n",
"\n",
" birth_year games ... gk_pct_goal_kicks_launched \\\n",
"name ... \n",
"Maignan 1995 0 ... 38.9 \n",
"Szczesny 1990 0 ... 29.7 \n",
"Ospina 1988 0 ... 14.1 \n",
"Handanovic 1984 0 ... 20.4 \n",
"Berisha 1989 0 ... 87.2 \n",
"... ... ... ... ... \n",
"Kokorin 1991 6 ... 0.0 \n",
"Munteanu 0 0 ... 0.0 \n",
"Buksa 2003 4 ... 0.0 \n",
"Kaio Jorge 2002 9 ... 0.0 \n",
"Lazetic 0 0 ... 0.0 \n",
"\n",
" gk_goal_kick_length_avg gk_crosses gk_crosses_stopped \\\n",
"name \n",
"Maignan 36.5 347.0 25.0 \n",
"Szczesny 31.5 481.0 24.0 \n",
"Ospina 22.5 353.0 18.0 \n",
"Handanovic 26.5 393.0 15.0 \n",
"Berisha 58.6 148.0 7.0 \n",
"... ... ... ... \n",
"Kokorin 0.0 0.0 0.0 \n",
"Munteanu 0.0 0.0 0.0 \n",
"Buksa 0.0 0.0 0.0 \n",
"Kaio Jorge 0.0 0.0 0.0 \n",
"Lazetic 0.0 0.0 0.0 \n",
"\n",
" gk_crosses_stopped_pct gk_def_actions_outside_pen_area \\\n",
"name \n",
"Maignan 7.2 45.0 \n",
"Szczesny 5.0 25.0 \n",
"Ospina 5.1 31.0 \n",
"Handanovic 3.8 10.0 \n",
"Berisha 4.7 10.0 \n",
"... ... ... \n",
"Kokorin 0.0 0.0 \n",
"Munteanu 0.0 0.0 \n",
"Buksa 0.0 0.0 \n",
"Kaio Jorge 0.0 0.0 \n",
"Lazetic 0.0 0.0 \n",
"\n",
" gk_def_actions_outside_pen_area_per90 \\\n",
"name \n",
"Maignan 1.41 \n",
"Szczesny 0.76 \n",
"Ospina 1.00 \n",
"Handanovic 0.27 \n",
"Berisha 1.00 \n",
"... ... \n",
"Kokorin 0.00 \n",
"Munteanu 0.00 \n",
"Buksa 0.00 \n",
"Kaio Jorge 0.00 \n",
"Lazetic 0.00 \n",
"\n",
" gk_avg_distance_def_actions vote_avg vote_std \n",
"name \n",
"Maignan 16.8 6.265625 0.483871 \n",
"Szczesny 13.5 6.121212 0.628012 \n",
"Ospina 17.0 6.258065 0.332899 \n",
"Handanovic 11.2 6.162162 0.533399 \n",
"Berisha 14.6 6.100000 0.700000 \n",
"... ... ... ... \n",
"Kokorin 0.0 5.901518 0.269227 \n",
"Munteanu 0.0 6.215233 0.275498 \n",
"Buksa 0.0 6.035319 0.591212 \n",
"Kaio Jorge 0.0 6.137790 0.468234 \n",
"Lazetic 0.0 6.325366 0.472207 \n",
"\n",
"[550 rows x 165 columns]"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rx = pd.read_excel('mid_outputs/season' + season + '/players_stats.xlsx', index_col = 3) \n",
"players = pd.DataFrame(rx)\n",
"\n",
"players\n"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "f9f7f88c",
"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": "code",
"execution_count": 49,
"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>Immobile</th>\n",
" <td>438</td>\n",
" <td>785</td>\n",
" <td>A</td>\n",
" <td>Lazio</td>\n",
" <td>Immobile</td>\n",
" <td>NaN</td>\n",
" <td>258</td>\n",
" <td>31</td>\n",
" <td>1990</td>\n",
" <td>31</td>\n",
" <td>...</td>\n",
" <td>491.0</td>\n",
" <td>488.0</td>\n",
" <td>69.0</td>\n",
" <td>4.0</td>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>2240.0</td>\n",
" <td>518.0</td>\n",
" <td>685.0</td>\n",
" <td>43.1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 791 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 id r team surname initial fb_ID age birth_year \\\n",
"Immobile 438 785 A Lazio Immobile NaN 258 31 1990 \n",
"\n",
" games ... opp_vs_team_fouls opp_vs_team_fouled \\\n",
"Immobile 31 ... 491.0 488.0 \n",
"\n",
" opp_vs_team_offsides opp_vs_team_pens_won \\\n",
"Immobile 69.0 4.0 \n",
"\n",
" opp_vs_team_pens_conceded opp_vs_team_own_goals \\\n",
"Immobile 6.0 3.0 \n",
"\n",
" opp_vs_team_ball_recoveries opp_vs_team_aerials_won \\\n",
"Immobile 2240.0 518.0 \n",
"\n",
" opp_vs_team_aerials_lost opp_vs_team_aerials_won_pct \n",
"Immobile 685.0 43.1 \n",
"\n",
"[1 rows x 791 columns]"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test = player_match_data('Immobile', 'Lazio', 'Atalanta')\n",
"test.to_excel('tmp/playermatchdata.xlsx')\n",
"\n",
"test"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "6b4c1b00",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Lazio'"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pteam = 'Lazio'\n",
"pteam_stats = team_data.loc[[pteam]]\n",
"pteam_stats.index[0]"
]
},
{
"cell_type": "code",
"execution_count": 51,
"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",
" '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": 51,
"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": "code",
"execution_count": 52,
"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",
"\n",
"features_rel_gamecorr = [\n",
" 'goals',\n",
" 'assists',\n",
" 'xg',\n",
" 'npxg',\n",
" 'cards_yellow',\n",
" 'cards_red'\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 53,
"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": "code",
"execution_count": 54,
"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>dribble_tackles_pct</th>\n",
" <th>dribbles_completed_pct</th>\n",
" <th>...</th>\n",
" <th>touches_live_ball</th>\n",
" <th>dribbles_completed</th>\n",
" <th>dribbles</th>\n",
" <th>passes_received</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Immobile</th>\n",
" <td>A</td>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" <td>2711</td>\n",
" <td>45.9</td>\n",
" <td>0.18</td>\n",
" <td>0.4</td>\n",
" <td>77.0</td>\n",
" <td>6.7</td>\n",
" <td>47.5</td>\n",
" <td>...</td>\n",
" <td>0.430468</td>\n",
" <td>0.007008</td>\n",
" <td>0.014755</td>\n",
" <td>0.362966</td>\n",
" <td>0.028403</td>\n",
" <td>0.01623</td>\n",
" <td>0.013279</td>\n",
" <td>0.014386</td>\n",
" <td>0.008115</td>\n",
" <td>0.016968</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 121 columns</p>\n",
"</div>"
],
"text/plain": [
" r games games_starts minutes shots_on_target_pct \\\n",
"Immobile A 31 31 2711 45.9 \n",
"\n",
" goals_per_shot goals_per_shot_on_target passes_pct \\\n",
"Immobile 0.18 0.4 77.0 \n",
"\n",
" dribble_tackles_pct dribbles_completed_pct ... touches_live_ball \\\n",
"Immobile 6.7 47.5 ... 0.430468 \n",
"\n",
" dribbles_completed dribbles passes_received miscontrols \\\n",
"Immobile 0.007008 0.014755 0.362966 0.028403 \n",
"\n",
" dispossessed fouls fouled aerials_won aerials_lost \n",
"Immobile 0.01623 0.013279 0.014386 0.008115 0.016968 \n",
"\n",
"[1 rows x 121 columns]"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test = player_match_data_ext('Immobile', 'Lazio', 'Atalanta')\n",
"\n",
"add_columns = test.columns\n",
"\n",
"test"
]
},
{
"cell_type": "code",
"execution_count": 55,
"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>Torino</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>4.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Pezzella Giu.</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>Gosens</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Palomino</td>\n",
" <td>Atalanta</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",
" </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>10649</th>\n",
" <td>38</td>\n",
" <td>Tameze</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10650</th>\n",
" <td>38</td>\n",
" <td>Hongla</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10651</th>\n",
" <td>38</td>\n",
" <td>Lasagna</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10652</th>\n",
" <td>38</td>\n",
" <td>Caprari</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10653</th>\n",
" <td>38</td>\n",
" <td>Simeone</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10654 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"0 1 Musso Atalanta Torino 0 6.0 -1 0 \n",
"1 1 Pezzella Giu. Atalanta Torino 0 6.0 0 0 \n",
"2 1 Djimsiti Atalanta Torino 0 6.0 0 0 \n",
"3 1 Gosens Atalanta Torino 0 5.5 0 0 \n",
"4 1 Palomino Atalanta Torino 0 6.5 0 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"10649 38 Tameze Verona Lazio 0 5.5 0 0 \n",
"10650 38 Hongla Verona Lazio 0 7.0 1 0 \n",
"10651 38 Lasagna Verona Lazio 0 7.0 1 0 \n",
"10652 38 Caprari Verona Lazio 0 6.0 0 0 \n",
"10653 38 Simeone Verona Lazio 0 7.0 1 0 \n",
"\n",
" cards_malus fantavote \n",
"0 0.5 4.5 \n",
"1 0.0 6.0 \n",
"2 0.0 6.0 \n",
"3 0.0 5.5 \n",
"4 0.0 6.5 \n",
"... ... ... \n",
"10649 0.0 5.5 \n",
"10650 0.5 9.5 \n",
"10651 0.5 9.5 \n",
"10652 0.0 6.0 \n",
"10653 0.0 10.0 \n",
"\n",
"[10654 rows x 10 columns]"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"votes = pd.read_excel('mid_outputs/season' + season + '/players_votes.xlsx', index_col = 0)\n",
"votes"
]
},
{
"cell_type": "code",
"execution_count": 69,
"id": "ec0bc56b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0\n",
"200\n",
"300\n",
"400\n",
"500\n",
"600\n",
"700\n",
"800\n",
"900\n",
"1000\n",
"1100\n",
"1200\n",
"1300\n",
"1400\n",
"1500\n",
"1600\n",
"1700\n",
"1800\n",
"2000\n",
"2100\n",
"2200\n",
"2300\n",
"2400\n",
"2500\n",
"2600\n",
"2700\n",
"2800\n",
"2900\n",
"3000\n",
"3100\n",
"3200\n",
"3300\n",
"3400\n",
"3500\n",
"3600\n",
"3700\n",
"3800\n",
"3900\n",
"4000\n",
"4100\n",
"4200\n",
"4300\n",
"4400\n",
"4500\n",
"4600\n",
"4700\n",
"4800\n",
"4900\n",
"5000\n",
"5100\n",
"5200\n",
"5300\n",
"5400\n",
"5500\n",
"5600\n",
"5700\n",
"5800\n",
"5900\n",
"6100\n",
"6200\n",
"6300\n",
"6400\n",
"6500\n",
"6600\n",
"6700\n",
"6800\n",
"6900\n",
"7000\n",
"7100\n",
"7200\n",
"7300\n",
"7400\n",
"7500\n",
"7600\n",
"7700\n",
"7800\n",
"7900\n",
"8000\n",
"8100\n",
"8200\n",
"8300\n",
"8400\n",
"8500\n",
"8600\n",
"8700\n",
"8800\n",
"8900\n",
"9000\n",
"9100\n",
"9200\n",
"9300\n",
"9400\n",
"9500\n",
"9600\n",
"9700\n",
"9800\n",
"9900\n",
"10000\n",
"10100\n",
"10200\n",
"10300\n",
"10400\n",
"10500\n",
"10600\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": 70,
"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>touches_live_ball</th>\n",
" <th>dribbles_completed</th>\n",
" <th>dribbles</th>\n",
" <th>passes_received</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",
" </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>Torino</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0.5</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>Pezzella Giu.</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>0.728545</td>\n",
" <td>0.007463</td>\n",
" <td>0.017724</td>\n",
" <td>0.458022</td>\n",
" <td>0.016791</td>\n",
" <td>0.011194</td>\n",
" <td>0.017724</td>\n",
" <td>0.027985</td>\n",
" <td>0.013060</td>\n",
" <td>0.013060</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>0.731826</td>\n",
" <td>0.001773</td>\n",
" <td>0.002660</td>\n",
" <td>0.460550</td>\n",
" <td>0.007979</td>\n",
" <td>0.001330</td>\n",
" <td>0.009309</td>\n",
" <td>0.006206</td>\n",
" <td>0.025266</td>\n",
" <td>0.011968</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Gosens</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.745562</td>\n",
" <td>0.000000</td>\n",
" <td>0.005917</td>\n",
" <td>0.473373</td>\n",
" <td>0.017751</td>\n",
" <td>0.000000</td>\n",
" <td>0.005917</td>\n",
" <td>0.011834</td>\n",
" <td>0.023669</td>\n",
" <td>0.005917</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Palomino</td>\n",
" <td>Atalanta</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>0.752620</td>\n",
" <td>0.002246</td>\n",
" <td>0.002994</td>\n",
" <td>0.399326</td>\n",
" <td>0.005614</td>\n",
" <td>0.002620</td>\n",
" <td>0.014596</td>\n",
" <td>0.006362</td>\n",
" <td>0.039296</td>\n",
" <td>0.017964</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>10649</th>\n",
" <td>38</td>\n",
" <td>Tameze</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.629371</td>\n",
" <td>0.013209</td>\n",
" <td>0.023310</td>\n",
" <td>0.358197</td>\n",
" <td>0.019814</td>\n",
" <td>0.010101</td>\n",
" <td>0.012821</td>\n",
" <td>0.013209</td>\n",
" <td>0.023699</td>\n",
" <td>0.021368</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10650</th>\n",
" <td>38</td>\n",
" <td>Hongla</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.582181</td>\n",
" <td>0.001536</td>\n",
" <td>0.007680</td>\n",
" <td>0.341014</td>\n",
" <td>0.018433</td>\n",
" <td>0.012289</td>\n",
" <td>0.023041</td>\n",
" <td>0.007680</td>\n",
" <td>0.023041</td>\n",
" <td>0.026114</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10651</th>\n",
" <td>38</td>\n",
" <td>Lasagna</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.369932</td>\n",
" <td>0.008446</td>\n",
" <td>0.016047</td>\n",
" <td>0.262669</td>\n",
" <td>0.046453</td>\n",
" <td>0.022804</td>\n",
" <td>0.016047</td>\n",
" <td>0.008446</td>\n",
" <td>0.026182</td>\n",
" <td>0.041385</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10652</th>\n",
" <td>38</td>\n",
" <td>Caprari</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.602410</td>\n",
" <td>0.023731</td>\n",
" <td>0.043447</td>\n",
" <td>0.453815</td>\n",
" <td>0.033954</td>\n",
" <td>0.019715</td>\n",
" <td>0.015334</td>\n",
" <td>0.027017</td>\n",
" <td>0.002921</td>\n",
" <td>0.009858</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10653</th>\n",
" <td>38</td>\n",
" <td>Simeone</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.407086</td>\n",
" <td>0.008669</td>\n",
" <td>0.022993</td>\n",
" <td>0.320392</td>\n",
" <td>0.051263</td>\n",
" <td>0.030155</td>\n",
" <td>0.021108</td>\n",
" <td>0.021862</td>\n",
" <td>0.022616</td>\n",
" <td>0.040709</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10654 rows × 131 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"0 1 Musso Atalanta Torino 0 6.0 -1 0 \n",
"1 1 Pezzella Giu. Atalanta Torino 0 6.0 0 0 \n",
"2 1 Djimsiti Atalanta Torino 0 6.0 0 0 \n",
"3 1 Gosens Atalanta Torino 0 5.5 0 0 \n",
"4 1 Palomino Atalanta Torino 0 6.5 0 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"10649 38 Tameze Verona Lazio 0 5.5 0 0 \n",
"10650 38 Hongla Verona Lazio 0 7.0 1 0 \n",
"10651 38 Lasagna Verona Lazio 0 7.0 1 0 \n",
"10652 38 Caprari Verona Lazio 0 6.0 0 0 \n",
"10653 38 Simeone Verona Lazio 0 7.0 1 0 \n",
"\n",
" cards_malus fantavote ... touches_live_ball dribbles_completed \\\n",
"0 0.5 6.5 ... 0.000000 0.000000 \n",
"1 0.0 6.0 ... 0.728545 0.007463 \n",
"2 0.0 6.0 ... 0.731826 0.001773 \n",
"3 0.0 5.5 ... 0.745562 0.000000 \n",
"4 0.0 6.5 ... 0.752620 0.002246 \n",
"... ... ... ... ... ... \n",
"10649 0.0 5.5 ... 0.629371 0.013209 \n",
"10650 0.5 9.5 ... 0.582181 0.001536 \n",
"10651 0.5 9.5 ... 0.369932 0.008446 \n",
"10652 0.0 6.0 ... 0.602410 0.023731 \n",
"10653 0.0 10.0 ... 0.407086 0.008669 \n",
"\n",
" dribbles passes_received miscontrols dispossessed fouls \\\n",
"0 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"1 0.017724 0.458022 0.016791 0.011194 0.017724 \n",
"2 0.002660 0.460550 0.007979 0.001330 0.009309 \n",
"3 0.005917 0.473373 0.017751 0.000000 0.005917 \n",
"4 0.002994 0.399326 0.005614 0.002620 0.014596 \n",
"... ... ... ... ... ... \n",
"10649 0.023310 0.358197 0.019814 0.010101 0.012821 \n",
"10650 0.007680 0.341014 0.018433 0.012289 0.023041 \n",
"10651 0.016047 0.262669 0.046453 0.022804 0.016047 \n",
"10652 0.043447 0.453815 0.033954 0.019715 0.015334 \n",
"10653 0.022993 0.320392 0.051263 0.030155 0.021108 \n",
"\n",
" fouled aerials_won aerials_lost \n",
"0 0.000000 0.000000 0.000000 \n",
"1 0.027985 0.013060 0.013060 \n",
"2 0.006206 0.025266 0.011968 \n",
"3 0.011834 0.023669 0.005917 \n",
"4 0.006362 0.039296 0.017964 \n",
"... ... ... ... \n",
"10649 0.013209 0.023699 0.021368 \n",
"10650 0.007680 0.023041 0.026114 \n",
"10651 0.008446 0.026182 0.041385 \n",
"10652 0.027017 0.002921 0.009858 \n",
"10653 0.021862 0.022616 0.040709 \n",
"\n",
"[10654 rows x 131 columns]"
]
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db"
]
},
{
"cell_type": "code",
"execution_count": 71,
"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 extisting players\n",
"db = db.drop(db[db.r != db.r].index) # remove non extisting players\n",
"db = db.drop(db[db.xg != db.xg].index) \n"
]
},
{
"cell_type": "code",
"execution_count": 72,
"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>touches_live_ball</th>\n",
" <th>dribbles_completed</th>\n",
" <th>dribbles</th>\n",
" <th>passes_received</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Pezzella Giu.</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>0.728545</td>\n",
" <td>0.007463</td>\n",
" <td>0.017724</td>\n",
" <td>0.458022</td>\n",
" <td>0.016791</td>\n",
" <td>0.011194</td>\n",
" <td>0.017724</td>\n",
" <td>0.027985</td>\n",
" <td>0.013060</td>\n",
" <td>0.013060</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Djimsiti</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</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>0.731826</td>\n",
" <td>0.001773</td>\n",
" <td>0.002660</td>\n",
" <td>0.460550</td>\n",
" <td>0.007979</td>\n",
" <td>0.001330</td>\n",
" <td>0.009309</td>\n",
" <td>0.006206</td>\n",
" <td>0.025266</td>\n",
" <td>0.011968</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Gosens</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.745562</td>\n",
" <td>0.000000</td>\n",
" <td>0.005917</td>\n",
" <td>0.473373</td>\n",
" <td>0.017751</td>\n",
" <td>0.000000</td>\n",
" <td>0.005917</td>\n",
" <td>0.011834</td>\n",
" <td>0.023669</td>\n",
" <td>0.005917</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Palomino</td>\n",
" <td>Atalanta</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>0.752620</td>\n",
" <td>0.002246</td>\n",
" <td>0.002994</td>\n",
" <td>0.399326</td>\n",
" <td>0.005614</td>\n",
" <td>0.002620</td>\n",
" <td>0.014596</td>\n",
" <td>0.006362</td>\n",
" <td>0.039296</td>\n",
" <td>0.017964</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1</td>\n",
" <td>Demiral</td>\n",
" <td>Atalanta</td>\n",
" <td>Torino</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>0.553469</td>\n",
" <td>0.001043</td>\n",
" <td>0.002087</td>\n",
" <td>0.283255</td>\n",
" <td>0.007825</td>\n",
" <td>0.002608</td>\n",
" <td>0.015128</td>\n",
" <td>0.008346</td>\n",
" <td>0.044340</td>\n",
" <td>0.019301</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>10649</th>\n",
" <td>38</td>\n",
" <td>Tameze</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>5.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.5</td>\n",
" <td>...</td>\n",
" <td>0.629371</td>\n",
" <td>0.013209</td>\n",
" <td>0.023310</td>\n",
" <td>0.358197</td>\n",
" <td>0.019814</td>\n",
" <td>0.010101</td>\n",
" <td>0.012821</td>\n",
" <td>0.013209</td>\n",
" <td>0.023699</td>\n",
" <td>0.021368</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10650</th>\n",
" <td>38</td>\n",
" <td>Hongla</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.582181</td>\n",
" <td>0.001536</td>\n",
" <td>0.007680</td>\n",
" <td>0.341014</td>\n",
" <td>0.018433</td>\n",
" <td>0.012289</td>\n",
" <td>0.023041</td>\n",
" <td>0.007680</td>\n",
" <td>0.023041</td>\n",
" <td>0.026114</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10651</th>\n",
" <td>38</td>\n",
" <td>Lasagna</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>9.5</td>\n",
" <td>...</td>\n",
" <td>0.369932</td>\n",
" <td>0.008446</td>\n",
" <td>0.016047</td>\n",
" <td>0.262669</td>\n",
" <td>0.046453</td>\n",
" <td>0.022804</td>\n",
" <td>0.016047</td>\n",
" <td>0.008446</td>\n",
" <td>0.026182</td>\n",
" <td>0.041385</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10652</th>\n",
" <td>38</td>\n",
" <td>Caprari</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>...</td>\n",
" <td>0.602410</td>\n",
" <td>0.023731</td>\n",
" <td>0.043447</td>\n",
" <td>0.453815</td>\n",
" <td>0.033954</td>\n",
" <td>0.019715</td>\n",
" <td>0.015334</td>\n",
" <td>0.027017</td>\n",
" <td>0.002921</td>\n",
" <td>0.009858</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10653</th>\n",
" <td>38</td>\n",
" <td>Simeone</td>\n",
" <td>Verona</td>\n",
" <td>Lazio</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>10.0</td>\n",
" <td>...</td>\n",
" <td>0.407086</td>\n",
" <td>0.008669</td>\n",
" <td>0.022993</td>\n",
" <td>0.320392</td>\n",
" <td>0.051263</td>\n",
" <td>0.030155</td>\n",
" <td>0.021108</td>\n",
" <td>0.021862</td>\n",
" <td>0.022616</td>\n",
" <td>0.040709</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9567 rows × 131 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday player team oppteam home vote goals assists \\\n",
"1 1 Pezzella Giu. Atalanta Torino 0 6.0 0 0 \n",
"2 1 Djimsiti Atalanta Torino 0 6.0 0 0 \n",
"3 1 Gosens Atalanta Torino 0 5.5 0 0 \n",
"4 1 Palomino Atalanta Torino 0 6.5 0 0 \n",
"5 1 Demiral Atalanta Torino 0 5.5 0 0 \n",
"... ... ... ... ... ... ... ... ... \n",
"10649 38 Tameze Verona Lazio 0 5.5 0 0 \n",
"10650 38 Hongla Verona Lazio 0 7.0 1 0 \n",
"10651 38 Lasagna Verona Lazio 0 7.0 1 0 \n",
"10652 38 Caprari Verona Lazio 0 6.0 0 0 \n",
"10653 38 Simeone Verona Lazio 0 7.0 1 0 \n",
"\n",
" cards_malus fantavote ... touches_live_ball dribbles_completed \\\n",
"1 0.0 6.0 ... 0.728545 0.007463 \n",
"2 0.0 6.0 ... 0.731826 0.001773 \n",
"3 0.0 5.5 ... 0.745562 0.000000 \n",
"4 0.0 6.5 ... 0.752620 0.002246 \n",
"5 0.5 5.0 ... 0.553469 0.001043 \n",
"... ... ... ... ... ... \n",
"10649 0.0 5.5 ... 0.629371 0.013209 \n",
"10650 0.5 9.5 ... 0.582181 0.001536 \n",
"10651 0.5 9.5 ... 0.369932 0.008446 \n",
"10652 0.0 6.0 ... 0.602410 0.023731 \n",
"10653 0.0 10.0 ... 0.407086 0.008669 \n",
"\n",
" dribbles passes_received miscontrols dispossessed fouls \\\n",
"1 0.017724 0.458022 0.016791 0.011194 0.017724 \n",
"2 0.002660 0.460550 0.007979 0.001330 0.009309 \n",
"3 0.005917 0.473373 0.017751 0.000000 0.005917 \n",
"4 0.002994 0.399326 0.005614 0.002620 0.014596 \n",
"5 0.002087 0.283255 0.007825 0.002608 0.015128 \n",
"... ... ... ... ... ... \n",
"10649 0.023310 0.358197 0.019814 0.010101 0.012821 \n",
"10650 0.007680 0.341014 0.018433 0.012289 0.023041 \n",
"10651 0.016047 0.262669 0.046453 0.022804 0.016047 \n",
"10652 0.043447 0.453815 0.033954 0.019715 0.015334 \n",
"10653 0.022993 0.320392 0.051263 0.030155 0.021108 \n",
"\n",
" fouled aerials_won aerials_lost \n",
"1 0.027985 0.013060 0.013060 \n",
"2 0.006206 0.025266 0.011968 \n",
"3 0.011834 0.023669 0.005917 \n",
"4 0.006362 0.039296 0.017964 \n",
"5 0.008346 0.044340 0.019301 \n",
"... ... ... ... \n",
"10649 0.013209 0.023699 0.021368 \n",
"10650 0.007680 0.023041 0.026114 \n",
"10651 0.008446 0.026182 0.041385 \n",
"10652 0.027017 0.002921 0.009858 \n",
"10653 0.021862 0.022616 0.040709 \n",
"\n",
"[9567 rows x 131 columns]"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db"
]
},
{
"cell_type": "code",
"execution_count": 73,
"id": "df26c8e0",
"metadata": {},
"outputs": [],
"source": [
"db.to_excel('mid_outputs/season' + season + '/database_entries.xlsx')"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "ba7b838c",
"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": 57,
"id": "1d2682b9",
"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": 58,
"id": "bc6e9d52",
"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>37.0</td>\n",
" <td>37.0</td>\n",
" <td>3322.0</td>\n",
" <td>1.71</td>\n",
" <td>67.8</td>\n",
" <td>8.1</td>\n",
" <td>-0.16</td>\n",
" <td>43.2</td>\n",
" <td>29.0</td>\n",
" <td>30.9</td>\n",
" <td>...</td>\n",
" <td>56.0</td>\n",
" <td>0.28</td>\n",
" <td>-6.0</td>\n",
" <td>186.0</td>\n",
" <td>431.0</td>\n",
" <td>1219.0</td>\n",
" <td>174.0</td>\n",
" <td>246.0</td>\n",
" <td>491.0</td>\n",
" <td>21.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 98 columns</p>\n",
"</div>"
],
"text/plain": [
" gk_games gk_games_starts gk_minutes gk_goals_against_per90 \\\n",
"Consigli 37.0 37.0 3322.0 1.71 \n",
"\n",
" gk_save_pct gk_clean_sheets_pct gk_psxg_net_per90 \\\n",
"Consigli 67.8 8.1 -0.16 \n",
"\n",
" gk_passes_pct_launched gk_pct_passes_launched \\\n",
"Consigli 43.2 29.0 \n",
"\n",
" gk_passes_length_avg ... gk_psxg \\\n",
"Consigli 30.9 ... 56.0 \n",
"\n",
" gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n",
"Consigli 0.28 -6.0 \n",
"\n",
" gk_passes_completed_launched gk_passes_launched gk_passes \\\n",
"Consigli 186.0 431.0 1219.0 \n",
"\n",
" gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n",
"Consigli 174.0 246.0 491.0 21.0 \n",
"\n",
"[1 rows x 98 columns]"
]
},
"execution_count": 58,
"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": null,
"id": "6f08e718",
"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",
"1200\n",
"1300\n",
"1400\n",
"1500\n",
"1600\n",
"1700\n",
"1800\n",
"1900\n",
"2000\n",
"2100\n",
"2200\n",
"2300\n",
"2400\n",
"2500\n",
"2600\n",
"2700\n",
"2800\n",
"2900\n",
"3000\n",
"3100\n",
"3200\n",
"3300\n",
"3400\n",
"3500\n",
"3600\n",
"3700\n",
"3800\n",
"3900\n",
"4000\n",
"4100\n",
"4200\n",
"4300\n",
"4400\n",
"4500\n",
"4600\n",
"4700\n",
"4800\n",
"4900\n",
"5000\n",
"5100\n",
"5200\n",
"5300\n",
"5400\n",
"5500\n",
"5600\n",
"5700\n",
"5800\n",
"5900\n",
"6000\n",
"6100\n",
"6200\n",
"6300\n",
"6400\n",
"6500\n",
"6600\n",
"6700\n",
"6800\n",
"6900\n",
"7000\n",
"7100\n",
"7200\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": null,
"id": "2b540670",
"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": null,
"id": "35495581",
"metadata": {},
"outputs": [],
"source": [
"db_gk.to_excel('mid_outputs/season' + season + '/database_entries_gk.xlsx')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "43b85925",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}