805 lines
24 KiB
Plaintext
805 lines
24 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fd8a6cb9",
|
||
"metadata": {},
|
||
"source": [
|
||
"Scraping for playing probability for the current Serie A matchday.\n",
|
||
"\n",
|
||
"Data from http://fantacalcio.it"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "4c7b7d26",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import requests\n",
|
||
"from bs4 import BeautifulSoup\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"import re\n",
|
||
"import sys, getopt\n",
|
||
"import csv\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "91897dbb",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"res = requests.get('https://www.fantacalcio.it/probabili-formazioni-serie-a')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "7ba89027",
|
||
"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>player</th>\n",
|
||
" <th>starter</th>\n",
|
||
" <th>percentage</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>Falcone</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>Gendrey</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Baschirotto</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>Umtiti</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>Gallo</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>469</th>\n",
|
||
" <td>Barrenechea</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>470</th>\n",
|
||
" <td>Pogba</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>50.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>471</th>\n",
|
||
" <td>Chiesa</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>472</th>\n",
|
||
" <td>Soule'</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>473</th>\n",
|
||
" <td>Milik</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>474 rows × 3 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" player starter percentage\n",
|
||
"0 Falcone 1 90.0\n",
|
||
"1 Gendrey 1 90.0\n",
|
||
"2 Baschirotto 1 90.0\n",
|
||
"3 Umtiti 1 90.0\n",
|
||
"4 Gallo 1 65.0\n",
|
||
".. ... ... ...\n",
|
||
"469 Barrenechea 0 20.0\n",
|
||
"470 Pogba 0 50.0\n",
|
||
"471 Chiesa 0 55.0\n",
|
||
"472 Soule' 0 20.0\n",
|
||
"473 Milik 0 60.0\n",
|
||
"\n",
|
||
"[474 rows x 3 columns]"
|
||
]
|
||
},
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"soup = BeautifulSoup(res.text)\n",
|
||
"\n",
|
||
"groups = soup.findAll('ul', attrs = {'class' : 'player-list'})\n",
|
||
"\n",
|
||
"probables = pd.DataFrame(columns = ['player', 'starter', 'percentage'])\n",
|
||
"\n",
|
||
"for i in range (len(groups)):\n",
|
||
" players = groups[i].findAll('a', attrs = {'class' : 'player-name'})\n",
|
||
" bars = groups[i].findAll('div', attrs = {'class' : 'progress-bar'})\n",
|
||
" \n",
|
||
" starter_string = groups[i]['class'][1]\n",
|
||
" if(starter_string == 'starters'):\n",
|
||
" starter = 1\n",
|
||
" else:\n",
|
||
" starter = 0\n",
|
||
" \n",
|
||
" for j in range(len(players)):\n",
|
||
" player = players[j].contents[1].contents[0]\n",
|
||
" perc = float(bars[j]['aria-valuenow'])\n",
|
||
" \n",
|
||
" row_df = pd.DataFrame([[player, starter, perc]], columns = probables.columns)\n",
|
||
" \n",
|
||
" probables = pd.concat([probables, row_df], ignore_index = True)\n",
|
||
" \n",
|
||
"probables "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "29e5b389",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"probables = probables.set_index('player')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "d711726e",
|
||
"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>player1</th>\n",
|
||
" <th>player2</th>\n",
|
||
" <th>percentage</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>Gallo</td>\n",
|
||
" <td>Pezzella Giu.</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>Ceesay</td>\n",
|
||
" <td>Colombo</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>Gonzalez J.</td>\n",
|
||
" <td>Oudin</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>Samardzic</td>\n",
|
||
" <td>Success</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>Esposito Sa.</td>\n",
|
||
" <td>Agudelo</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>5</th>\n",
|
||
" <td>Bastoni S.</td>\n",
|
||
" <td>Reca</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>6</th>\n",
|
||
" <td>Verde</td>\n",
|
||
" <td>Shomurodov</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>7</th>\n",
|
||
" <td>Caldirola</td>\n",
|
||
" <td>Marlon</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>8</th>\n",
|
||
" <td>Colpani</td>\n",
|
||
" <td>Machin</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>9</th>\n",
|
||
" <td>Petagna</td>\n",
|
||
" <td>Mota</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>10</th>\n",
|
||
" <td>Lozano</td>\n",
|
||
" <td>Politano</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>11</th>\n",
|
||
" <td>Zielinski</td>\n",
|
||
" <td>Elmas</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>12</th>\n",
|
||
" <td>Piatek</td>\n",
|
||
" <td>Botheim</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>13</th>\n",
|
||
" <td>Kastanos</td>\n",
|
||
" <td>Mazzocchi</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>14</th>\n",
|
||
" <td>Lovato</td>\n",
|
||
" <td>Troost-Ekong</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>15</th>\n",
|
||
" <td>El Shaarawy</td>\n",
|
||
" <td>Dybala</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>16</th>\n",
|
||
" <td>Belotti</td>\n",
|
||
" <td>Abraham</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>17</th>\n",
|
||
" <td>Kalulu</td>\n",
|
||
" <td>Kjaer</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>18</th>\n",
|
||
" <td>Diaz B.</td>\n",
|
||
" <td>Saelemaekers</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>19</th>\n",
|
||
" <td>Giroud</td>\n",
|
||
" <td>Origi</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>20</th>\n",
|
||
" <td>Miranchuk</td>\n",
|
||
" <td>Vlasic</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>21</th>\n",
|
||
" <td>Gravillon</td>\n",
|
||
" <td>Djidji</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>22</th>\n",
|
||
" <td>Ricci S.</td>\n",
|
||
" <td>Linetty</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>23</th>\n",
|
||
" <td>Palomino</td>\n",
|
||
" <td>Djimsiti</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>24</th>\n",
|
||
" <td>Pasalic</td>\n",
|
||
" <td>Ederson D.s.</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25</th>\n",
|
||
" <td>Hojlund</td>\n",
|
||
" <td>Boga</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>26</th>\n",
|
||
" <td>Lukaku</td>\n",
|
||
" <td>Dzeko</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>27</th>\n",
|
||
" <td>Dimarco</td>\n",
|
||
" <td>Gosens</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>28</th>\n",
|
||
" <td>Immobile</td>\n",
|
||
" <td>Pedro</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>29</th>\n",
|
||
" <td>Hysaj</td>\n",
|
||
" <td>Lazzari</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>30</th>\n",
|
||
" <td>Castagnetti</td>\n",
|
||
" <td>Galdames</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>31</th>\n",
|
||
" <td>Vasquez</td>\n",
|
||
" <td>Lochoshvili</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>32</th>\n",
|
||
" <td>Buonaiuto</td>\n",
|
||
" <td>Ghiglione</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>33</th>\n",
|
||
" <td>Duda</td>\n",
|
||
" <td>Abildgaard</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>34</th>\n",
|
||
" <td>Gaich</td>\n",
|
||
" <td>Djuric</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>35</th>\n",
|
||
" <td>Lazovic</td>\n",
|
||
" <td>Doig</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>36</th>\n",
|
||
" <td>Erlic</td>\n",
|
||
" <td>Ferrari G.</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>37</th>\n",
|
||
" <td>Bajrami</td>\n",
|
||
" <td>Defrel</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>38</th>\n",
|
||
" <td>Matheus Henrique</td>\n",
|
||
" <td>Harroui</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>39</th>\n",
|
||
" <td>Vicario</td>\n",
|
||
" <td>Perisan</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>40</th>\n",
|
||
" <td>Marin</td>\n",
|
||
" <td>Grassi</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>41</th>\n",
|
||
" <td>Cambiaghi</td>\n",
|
||
" <td>Satriano</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>42</th>\n",
|
||
" <td>Gonzalez N.</td>\n",
|
||
" <td>Ikone'</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>43</th>\n",
|
||
" <td>Saponara</td>\n",
|
||
" <td>Sottil</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>44</th>\n",
|
||
" <td>Martinez Quarta</td>\n",
|
||
" <td>Igor</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>45</th>\n",
|
||
" <td>Djuricic</td>\n",
|
||
" <td>Cuisance</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>46</th>\n",
|
||
" <td>Lammers</td>\n",
|
||
" <td>Jese'</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>47</th>\n",
|
||
" <td>Aebischer</td>\n",
|
||
" <td>Orsolini</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48</th>\n",
|
||
" <td>Zirkzee</td>\n",
|
||
" <td>Sansone</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>49</th>\n",
|
||
" <td>Dominguez</td>\n",
|
||
" <td>Moro N.</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50</th>\n",
|
||
" <td>Di Maria</td>\n",
|
||
" <td>Chiesa</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>51</th>\n",
|
||
" <td>Cuadrado</td>\n",
|
||
" <td>De Sciglio</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>52</th>\n",
|
||
" <td>Vlahovic</td>\n",
|
||
" <td>Milik</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" player1 player2 percentage\n",
|
||
"0 Gallo Pezzella Giu. 65.0\n",
|
||
"1 Ceesay Colombo 60.0\n",
|
||
"2 Gonzalez J. Oudin 55.0\n",
|
||
"3 Samardzic Success 55.0\n",
|
||
"4 Esposito Sa. Agudelo 55.0\n",
|
||
"5 Bastoni S. Reca 60.0\n",
|
||
"6 Verde Shomurodov 60.0\n",
|
||
"7 Caldirola Marlon 60.0\n",
|
||
"8 Colpani Machin 55.0\n",
|
||
"9 Petagna Mota 55.0\n",
|
||
"10 Lozano Politano 65.0\n",
|
||
"11 Zielinski Elmas 60.0\n",
|
||
"12 Piatek Botheim 55.0\n",
|
||
"13 Kastanos Mazzocchi 55.0\n",
|
||
"14 Lovato Troost-Ekong 55.0\n",
|
||
"15 El Shaarawy Dybala 65.0\n",
|
||
"16 Belotti Abraham 55.0\n",
|
||
"17 Kalulu Kjaer 60.0\n",
|
||
"18 Diaz B. Saelemaekers 55.0\n",
|
||
"19 Giroud Origi 60.0\n",
|
||
"20 Miranchuk Vlasic 60.0\n",
|
||
"21 Gravillon Djidji 60.0\n",
|
||
"22 Ricci S. Linetty 60.0\n",
|
||
"23 Palomino Djimsiti 60.0\n",
|
||
"24 Pasalic Ederson D.s. 60.0\n",
|
||
"25 Hojlund Boga 60.0\n",
|
||
"26 Lukaku Dzeko 60.0\n",
|
||
"27 Dimarco Gosens 60.0\n",
|
||
"28 Immobile Pedro 60.0\n",
|
||
"29 Hysaj Lazzari 65.0\n",
|
||
"30 Castagnetti Galdames 60.0\n",
|
||
"31 Vasquez Lochoshvili 60.0\n",
|
||
"32 Buonaiuto Ghiglione 55.0\n",
|
||
"33 Duda Abildgaard 55.0\n",
|
||
"34 Gaich Djuric 55.0\n",
|
||
"35 Lazovic Doig 60.0\n",
|
||
"36 Erlic Ferrari G. 60.0\n",
|
||
"37 Bajrami Defrel 60.0\n",
|
||
"38 Matheus Henrique Harroui 60.0\n",
|
||
"39 Vicario Perisan 55.0\n",
|
||
"40 Marin Grassi 65.0\n",
|
||
"41 Cambiaghi Satriano 55.0\n",
|
||
"42 Gonzalez N. Ikone' 55.0\n",
|
||
"43 Saponara Sottil 60.0\n",
|
||
"44 Martinez Quarta Igor 60.0\n",
|
||
"45 Djuricic Cuisance 55.0\n",
|
||
"46 Lammers Jese' 60.0\n",
|
||
"47 Aebischer Orsolini 60.0\n",
|
||
"48 Zirkzee Sansone 55.0\n",
|
||
"49 Dominguez Moro N. 60.0\n",
|
||
"50 Di Maria Chiesa 60.0\n",
|
||
"51 Cuadrado De Sciglio 60.0\n",
|
||
"52 Vlahovic Milik 60.0"
|
||
]
|
||
},
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"groups = soup.findAll('ul', attrs = {'class' : 'ballot-list'})\n",
|
||
"\n",
|
||
"ballots = pd.DataFrame(columns = ['player1', 'player2', 'percentage'])\n",
|
||
"for i in range (len(groups)):\n",
|
||
" players = groups[i].findAll('a', attrs = {'class' : 'player-name'})\n",
|
||
" percs = groups[i].findAll('strong', attrs = {'class' : 'percentage'})\n",
|
||
" \n",
|
||
" player1 = players[0].contents[1].contents[0]\n",
|
||
" player2 = players[1].contents[1].contents[0]\n",
|
||
" perc = float(percs[0].contents[0].replace('%', ''))\n",
|
||
" \n",
|
||
" row_df = pd.DataFrame([[player1, player2, perc]], columns = ballots.columns)\n",
|
||
" \n",
|
||
" ballots = pd.concat([ballots, row_df], ignore_index = True)\n",
|
||
" \n",
|
||
"ballots"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "0171c61d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>starter</th>\n",
|
||
" <th>percentage</th>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>player</th>\n",
|
||
" <th></th>\n",
|
||
" <th></th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>Falcone</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Gendrey</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Baschirotto</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Umtiti</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>90.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Gallo</th>\n",
|
||
" <td>0.65</td>\n",
|
||
" <td>65.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Barrenechea</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Pogba</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>50.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Chiesa</th>\n",
|
||
" <td>0.4</td>\n",
|
||
" <td>55.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Soule'</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>Milik</th>\n",
|
||
" <td>0.4</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>474 rows × 2 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" starter percentage\n",
|
||
"player \n",
|
||
"Falcone 1 90.0\n",
|
||
"Gendrey 1 90.0\n",
|
||
"Baschirotto 1 90.0\n",
|
||
"Umtiti 1 90.0\n",
|
||
"Gallo 0.65 65.0\n",
|
||
"... ... ...\n",
|
||
"Barrenechea 0 20.0\n",
|
||
"Pogba 0 50.0\n",
|
||
"Chiesa 0.4 55.0\n",
|
||
"Soule' 0 20.0\n",
|
||
"Milik 0.4 60.0\n",
|
||
"\n",
|
||
"[474 rows x 2 columns]"
|
||
]
|
||
},
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"for i in range(ballots.shape[0]):\n",
|
||
" p1 = ballots['player1'][i]\n",
|
||
" p2 = ballots['player2'][i]\n",
|
||
" \n",
|
||
" perc = float(ballots['percentage'][i])\n",
|
||
" \n",
|
||
" probables.at[p1, 'starter'] = perc/100\n",
|
||
" probables.at[p2, 'starter'] = 1 - perc/100\n",
|
||
" \n",
|
||
"probables"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "8b5468aa",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"probables.to_excel('mid_outputs/match_probable_players.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
|
||
}
|