rams/fantabeto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
14923289583410043a6671d9b622ae2f19f6b029
fantabeto/2_votes_dataset_creation.ipynb
T
Giuseppe Musicco 1492328958 Code updated for Serie A 2023/2024 
- Reorganization of data folders
- Code adapted for the new Serie A season, also considering only a small number of league games has been played
- Stats from other leagues are considered for players at their first Serie A season (rookies), for now without any adaptation based on league difficulty
- Minor fixes
2023-09-09 19:31:52 +02:00

770 lines
23 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": "5c9991b1",
"metadata": {},
"source": [
"Generate player votes database, containing votes for Serie A matchday and player.\n",
"\n",
"Votes data is manually downloaded from https://www.fantacalcio.it/voti-fantacalcio-serie-a\n",
"\n",
"Serie A calendar is loaded from another file, to add information not containing in votes files: home/away, team opponent."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "b63beb69",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c39376",
"metadata": {},
"outputs": [],
"source": [
"cal = np.array(pd.read_excel('fantacalcio/seriea_calendar.xlsx', header = None))\n",
"\n",
"cal_df = pd.DataFrame(columns = ['matchday', 'team1', 'team2'])\n",
"\n",
"matchday = 0\n",
"\n",
"for i in range(cal.shape[0]):\n",
" if(cal[i, 0][0].isnumeric()):\n",
" matchday = matchday + 1\n",
" continue\n",
" \n",
" teams = cal[i, 0].split('-')\n",
" \n",
" frame = pd.DataFrame([[matchday, teams[0], teams[1]]], columns = cal_df.columns)\n",
"\n",
" cal_df = pd.concat([cal_df, frame], ignore_index = True)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "92d3c6fb",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>team1</th>\n",
" <th>team2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Bologna</td>\n",
" <td>Milan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Empoli</td>\n",
" <td>Verona</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Frosinone</td>\n",
" <td>Napoli</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Genoa</td>\n",
" <td>Fiorentina</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Inter</td>\n",
" <td>Monza</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>375</th>\n",
" <td>38</td>\n",
" <td>Verona</td>\n",
" <td>Inter</td>\n",
" </tr>\n",
" <tr>\n",
" <th>376</th>\n",
" <td>38</td>\n",
" <td>Juventus</td>\n",
" <td>Monza</td>\n",
" </tr>\n",
" <tr>\n",
" <th>377</th>\n",
" <td>38</td>\n",
" <td>Lazio</td>\n",
" <td>Sassuolo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>378</th>\n",
" <td>38</td>\n",
" <td>Milan</td>\n",
" <td>Salernitana</td>\n",
" </tr>\n",
" <tr>\n",
" <th>379</th>\n",
" <td>38</td>\n",
" <td>Napoli</td>\n",
" <td>Lecce</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>380 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday team1 team2\n",
"0 1 Bologna Milan\n",
"1 1 Empoli Verona\n",
"2 1 Frosinone Napoli\n",
"3 1 Genoa Fiorentina\n",
"4 1 Inter Monza\n",
".. ... ... ...\n",
"375 38 Verona Inter\n",
"376 38 Juventus Monza\n",
"377 38 Lazio Sassuolo\n",
"378 38 Milan Salernitana\n",
"379 38 Napoli Lecce\n",
"\n",
"[380 rows x 3 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cal_df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "0d4a330d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loaded votes for matchday 1\n",
"loaded votes for matchday 2\n",
"loaded votes for matchday 3\n"
]
}
],
"source": [
"df = pd.DataFrame(columns = ['matchday', 'player', 'team', 'oppteam', 'home', 'vote', 'goals', 'assists', 'cards_malus', 'fantavote'])\n",
"\n",
"LAST_MATCH = 38\n",
"\n",
"for matchday in range(1, LAST_MATCH + 1):\n",
" \n",
" votes_file = 'fantacalcio/voti/Voti_Fantacalcio_Stagione_2023_24_Giornata_' + str(matchday) + '.xlsx'\n",
"\n",
" try:\n",
" rx = np.array(pd.read_excel(votes_file, header = None))\n",
" except:\n",
" break\n",
"\n",
" read = 0\n",
" for i in range(rx.shape[0]):\n",
" if(rx[i, 0] == \"Cod.\"):\n",
" read = 1\n",
" team = rx[i-1, 0];\n",
" continue\n",
"\n",
" if(read):\n",
" if(isinstance(rx[i, 0], int)):\n",
" if((isinstance(rx[i, 3], float) or isinstance(rx[i, 3], int)) and rx[i, 1] != \"ALL\") :\n",
" player = rx[i, 2];\n",
" vote = float(rx[i, 3])\n",
" goals = rx[i, 4] + rx[i, 8] - rx[i, 5]\n",
" assists = rx[i, 12]\n",
" cards_malus = rx[i, 10] * 0.5 + rx[i, 11]\n",
" \n",
" oppteam = ''\n",
" home = 0\n",
" for j in range(cal_df.shape[0]):\n",
" if(cal_df['matchday'][j] == matchday):\n",
" if(cal_df['team1'][j] == team):\n",
" oppteam = cal_df['team2'][j] \n",
" home = 1\n",
" elif(cal_df['team2'][j] == team):\n",
" oppteam = cal_df['team1'][j] \n",
" home = 0\n",
"\n",
" goals_gen = goals * 3;\n",
" if(goals < 0):\n",
" goals_gen = goals\n",
" \n",
" fantavote = vote + goals_gen + assists - cards_malus \n",
" \n",
" frame = pd.DataFrame([[matchday, player, team, oppteam, home, vote, goals, assists, cards_malus, fantavote]], columns = df.columns)\n",
"\n",
" df = pd.concat([df, frame], axis = 0, ignore_index = True)\n",
" else:\n",
" read = 0\n",
" continue\n",
" \n",
" print('loaded votes for matchday ' + str(matchday))\n",
"\n",
" df"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "6ade957d",
"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>859</th>\n",
" <td>3</td>\n",
" <td>Folorunsho</td>\n",
" <td>Verona</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>860</th>\n",
" <td>3</td>\n",
" <td>Serdar</td>\n",
" <td>Verona</td>\n",
" <td>Sassuolo</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>861</th>\n",
" <td>3</td>\n",
" <td>Bonazzoli</td>\n",
" <td>Verona</td>\n",
" <td>Sassuolo</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>862</th>\n",
" <td>3</td>\n",
" <td>Djuric</td>\n",
" <td>Verona</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>863</th>\n",
" <td>3</td>\n",
" <td>Ngonge</td>\n",
" <td>Verona</td>\n",
" <td>Sassuolo</td>\n",
" <td>0</td>\n",
" <td>6.5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>9.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>864 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",
"859 3 Folorunsho Verona Sassuolo 0 5.0 0 0 \n",
"860 3 Serdar Verona Sassuolo 0 5.5 0 0 \n",
"861 3 Bonazzoli Verona Sassuolo 0 5.5 0 0 \n",
"862 3 Djuric Verona Sassuolo 0 6.0 0 0 \n",
"863 3 Ngonge Verona Sassuolo 0 6.5 1 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",
"859 0.0 5.0 \n",
"860 0.0 5.5 \n",
"861 0.0 5.5 \n",
"862 0.0 6.0 \n",
"863 0.0 9.5 \n",
"\n",
"[864 rows x 10 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "230213fe",
"metadata": {},
"outputs": [],
"source": [
"df.to_excel('mid_outputs/players_votes.xlsx')"
]
},
{
"cell_type": "markdown",
"id": "ef91ece3",
"metadata": {},
"source": [
"Elaborate data for past seasons.\n",
"\n",
"Do not repeat if data is already present."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "da35bdf9",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>matchday</th>\n",
" <th>team1</th>\n",
" <th>team2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Verona</td>\n",
" <td>Sassuolo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Inter</td>\n",
" <td>Genoa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Empoli</td>\n",
" <td>Lazio</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Torino</td>\n",
" <td>Atalanta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Bologna</td>\n",
" <td>Salernitana</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>375</th>\n",
" <td>38</td>\n",
" <td>Spezia</td>\n",
" <td>Napoli</td>\n",
" </tr>\n",
" <tr>\n",
" <th>376</th>\n",
" <td>38</td>\n",
" <td>Sassuolo</td>\n",
" <td>Milan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>377</th>\n",
" <td>38</td>\n",
" <td>Inter</td>\n",
" <td>Sampdoria</td>\n",
" </tr>\n",
" <tr>\n",
" <th>378</th>\n",
" <td>38</td>\n",
" <td>Salernitana</td>\n",
" <td>Udinese</td>\n",
" </tr>\n",
" <tr>\n",
" <th>379</th>\n",
" <td>38</td>\n",
" <td>Venezia</td>\n",
" <td>Cagliari</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>380 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" matchday team1 team2\n",
"0 1 Verona Sassuolo\n",
"1 1 Inter Genoa\n",
"2 1 Empoli Lazio\n",
"3 1 Torino Atalanta\n",
"4 1 Bologna Salernitana\n",
".. ... ... ...\n",
"375 38 Spezia Napoli\n",
"376 38 Sassuolo Milan\n",
"377 38 Inter Sampdoria\n",
"378 38 Salernitana Udinese\n",
"379 38 Venezia Cagliari\n",
"\n",
"[380 rows x 3 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# BACKUP CODE FOR SEASON 2122 and 2021 (different calendar file format than 2223 and 2324)\n",
"\n",
"cal_df = pd.read_excel('fantacalcio/season2122/seriea_calendar.xlsx')\n",
"\n",
"to_drop = list()\n",
"\n",
"for i in range(cal_df.shape[0]):\n",
" if(not isinstance(cal_df['matchday'][i], int)):\n",
" to_drop.append(i)\n",
" \n",
"cal_df = cal_df.drop(to_drop)\n",
"\n",
"cal_df = cal_df.reset_index(drop = True)\n",
"\n",
"cal_df"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "a0b100da",
"metadata": {},
"outputs": [],
"source": [
"cal = np.array(pd.read_excel('fantacalcio/season2223/seriea_calendar.xlsx', header = None))\n",
"\n",
"cal_df = pd.DataFrame(columns = ['matchday', 'team1', 'team2'])\n",
"\n",
"matchday = 0\n",
"\n",
"for i in range(cal.shape[0]):\n",
" if(cal[i, 0][0].isnumeric()):\n",
" matchday = matchday + 1\n",
" continue\n",
" \n",
" teams = cal[i, 0].split('-')\n",
" \n",
" frame = pd.DataFrame([[matchday, teams[0], teams[1]]], columns = cal_df.columns)\n",
"\n",
" cal_df = pd.concat([cal_df, frame], ignore_index = True)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "0313a0f4",
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(columns = ['matchday', 'player', 'team', 'oppteam', 'home', 'vote', 'goals', 'assists', 'cards_malus', 'fantavote'])\n",
"\n",
"LAST_MATCH = 38\n",
"\n",
"for matchday in range(1, LAST_MATCH + 1):\n",
" \n",
" votes_file = 'fantacalcio/season2223/voti/Voti_Fantacalcio_Stagione_2022_23_Giornata_' + str(matchday) + '.xlsx'\n",
"\n",
"\n",
"\n",
"\n",
" rx = np.array(pd.read_excel(votes_file, header = None))\n",
"\n",
" read = 0\n",
" for i in range(rx.shape[0]):\n",
" if(rx[i, 0] == \"Cod.\"):\n",
" read = 1\n",
" team = rx[i-1, 0];\n",
" continue\n",
"\n",
" if(read):\n",
" if(isinstance(rx[i, 0], int)):\n",
" if((isinstance(rx[i, 3], float) or isinstance(rx[i, 3], int)) and rx[i, 1] != \"ALL\") :\n",
" player = rx[i, 2];\n",
" vote = float(rx[i, 3])\n",
" goals = rx[i, 4] + rx[i, 8] - rx[i, 5]\n",
" assists = rx[i, 12]\n",
" cards_malus = rx[i, 10] * 0.5 + rx[i, 11]\n",
" \n",
" oppteam = ''\n",
" home = 0\n",
" for j in range(cal_df.shape[0]):\n",
" if(cal_df['matchday'][j] == matchday):\n",
" if(cal_df['team1'][j] == team):\n",
" oppteam = cal_df['team2'][j] \n",
" home = 1\n",
" elif(cal_df['team2'][j] == team):\n",
" oppteam = cal_df['team1'][j] \n",
" home = 0\n",
"\n",
" goals_gen = goals * 3;\n",
" if(goals < 0):\n",
" goals_gen = goals\n",
" \n",
" fantavote = vote + goals_gen + assists - cards_malus \n",
" \n",
" frame = pd.DataFrame([[matchday, player, team, oppteam, home, vote, goals, assists, cards_malus, fantavote]], columns = df.columns)\n",
"\n",
" df = pd.concat([df, frame], axis = 0, ignore_index = True)\n",
" else:\n",
" read = 0\n",
" continue\n",
"\n",
" df"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "82b1cfc8",
"metadata": {},
"outputs": [],
"source": [
"df.to_excel('mid_outputs/season2223/players_votes.xlsx')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink