diff --git a/Posicion15.csv b/Posicion15.csv new file mode 100644 index 0000000..01a951f --- /dev/null +++ b/Posicion15.csv @@ -0,0 +1,19 @@ +,Equipo,Posicion,Juegos_Jugados,Diferencia_Goles,Puntos +0,Bayern Munich ,1,34,62.0,79.0 +1,VfL Wolfsburg ,2,34,34.0,69.0 +2,Bor. M'gladbach ,3,34,27.0,66.0 +3,Bay. Leverkusen ,4,34,25.0,61.0 +4,FC Augsburg ,5,34,0.0,49.0 +5,FC Schalke 04 ,6,34,2.0,48.0 +6,Bor. Dortmund ,7,34,5.0,46.0 +7,TSG Hoffenheim ,8,34,-6.0,44.0 +8,E. Frankfurt ,9,34,-6.0,43.0 +9,Werder Bremen ,10,34,-15.0,43.0 +10,1.FSV Mainz 05 ,11,34,-2.0,40.0 +11,1. FC Köln   ,12,34,-6.0,40.0 +12,Hannover 96 ,13,34,-16.0,37.0 +13,VfB Stuttgart ,14,34,-18.0,36.0 +14,Hertha BSC ,15,34,-16.0,35.0 +15,Hamburger SV ,16,34,-25.0,35.0 +16,SC Freiburg ,17,34,-11.0,34.0 +17,SC Paderborn   ,18,34,-34.0,31.0 diff --git a/Posicion16.csv b/Posicion16.csv new file mode 100644 index 0000000..9b98d75 --- /dev/null +++ b/Posicion16.csv @@ -0,0 +1,19 @@ +,Equipo,Posicion,Juegos_Jugados,Diferencia_Goles,Puntos +0,Bayern Munich ,1,34,63.0,88.0 +1,Bor. Dortmund ,2,34,48.0,78.0 +2,Bay. Leverkusen ,3,34,16.0,60.0 +3,Bor. M'gladbach ,4,34,17.0,55.0 +4,FC Schalke 04 ,5,34,2.0,52.0 +5,1.FSV Mainz 05 ,6,34,4.0,50.0 +6,Hertha BSC ,7,34,0.0,50.0 +7,VfL Wolfsburg ,8,34,-2.0,45.0 +8,1. FC Köln ,9,34,-4.0,43.0 +9,Hamburger SV ,10,34,-6.0,41.0 +10,FC Ingolstadt   ,11,34,-9.0,40.0 +11,FC Augsburg ,12,34,-10.0,38.0 +12,Werder Bremen ,13,34,-15.0,38.0 +13,SV Darmstadt 98   ,14,34,-15.0,38.0 +14,TSG Hoffenheim ,15,34,-15.0,37.0 +15,E. Frankfurt ,16,34,-18.0,36.0 +16,VfB Stuttgart ,17,34,-25.0,33.0 +17,Hannover 96 ,18,34,-31.0,25.0 diff --git a/Posicion17.csv b/Posicion17.csv new file mode 100644 index 0000000..0f31393 --- /dev/null +++ b/Posicion17.csv @@ -0,0 +1,19 @@ +,Equipo,Posicion,Juegos_Jugados,Diferencia_Goles,Puntos +0,Bayern Munich ,1,34,67.0,82.0 +1,RB Leipzig   ,2,34,27.0,67.0 +2,Bor. Dortmund ,3,34,32.0,64.0 +3,TSG Hoffenheim ,4,34,27.0,62.0 +4,1. FC Köln ,5,34,9.0,49.0 +5,Hertha BSC ,6,34,-4.0,49.0 +6,SC Freiburg   ,7,34,-18.0,48.0 +7,Werder Bremen ,8,34,-3.0,45.0 +8,Bor. M'gladbach ,9,34,-4.0,45.0 +9,FC Schalke 04 ,10,34,5.0,43.0 +10,E. Frankfurt ,11,34,-7.0,42.0 +11,Bay. Leverkusen ,12,34,-2.0,41.0 +12,FC Augsburg ,13,34,-16.0,38.0 +13,Hamburger SV ,14,34,-28.0,38.0 +14,1.FSV Mainz 05 ,15,34,-11.0,37.0 +15,VfL Wolfsburg ,16,34,-18.0,37.0 +16,FC Ingolstadt ,17,34,-21.0,32.0 +17,SV Darmstadt 98 ,18,34,-35.0,25.0 diff --git a/Posicion18.csv b/Posicion18.csv new file mode 100644 index 0000000..5e1cdd0 --- /dev/null +++ b/Posicion18.csv @@ -0,0 +1,19 @@ +,Equipo,Posicion,Juegos_Jugados,Diferencia_Goles,Puntos +0,Bayern Munich ,1,34,64.0,84.0 +1,FC Schalke 04 ,2,34,16.0,63.0 +2,TSG Hoffenheim ,3,34,18.0,55.0 +3,Bor. Dortmund ,4,34,17.0,55.0 +4,Bay. Leverkusen ,5,34,14.0,55.0 +5,RB Leipzig ,6,34,4.0,53.0 +6,VfB Stuttgart   ,7,34,0.0,51.0 +7,E. Frankfurt ,8,34,0.0,49.0 +8,Bor. M'gladbach ,9,34,-5.0,47.0 +9,Hertha BSC ,10,34,-3.0,43.0 +10,Werder Bremen ,11,34,-3.0,42.0 +11,FC Augsburg ,12,34,-3.0,41.0 +12,Hannover 96   ,13,34,-10.0,39.0 +13,1.FSV Mainz 05 ,14,34,-14.0,36.0 +14,SC Freiburg ,15,34,-24.0,36.0 +15,VfL Wolfsburg ,16,34,-12.0,33.0 +16,Hamburger SV ,17,34,-24.0,31.0 +17,1. FC Köln ,18,34,-35.0,22.0 diff --git a/Posicion19.csv b/Posicion19.csv new file mode 100644 index 0000000..ca7118d --- /dev/null +++ b/Posicion19.csv @@ -0,0 +1,19 @@ +,Equipo,Posicion,Juegos_Jugados,Diferencia_Goles,Puntos +0,Bayern Munich ,1,34,56.0,78.0 +1,Bor. Dortmund ,2,34,37.0,76.0 +2,RB Leipzig ,3,34,34.0,66.0 +3,Bay. Leverkusen ,4,34,17.0,58.0 +4,Bor. M'gladbach ,5,34,13.0,55.0 +5,VfL Wolfsburg ,6,34,12.0,55.0 +6,E. Frankfurt ,7,34,12.0,54.0 +7,Werder Bremen ,8,34,9.0,53.0 +8,TSG Hoffenheim ,9,34,18.0,51.0 +9,F. Düsseldorf   ,10,34,-16.0,44.0 +10,Hertha BSC ,11,34,-8.0,43.0 +11,1.FSV Mainz 05 ,12,34,-11.0,43.0 +12,SC Freiburg ,13,34,-15.0,36.0 +13,FC Schalke 04 ,14,34,-18.0,33.0 +14,FC Augsburg ,15,34,-20.0,32.0 +15,VfB Stuttgart ,16,34,-38.0,28.0 +16,Hannover 96 ,17,34,-40.0,21.0 +17,1.FC Nuremberg   ,18,34,-42.0,19.0 diff --git a/Results.csv b/Results.csv new file mode 100644 index 0000000..54c2a34 --- /dev/null +++ b/Results.csv @@ -0,0 +1,24 @@ +Equipo,Diferencia de Goles,Puntos Totales,Valor Total Promedio,Valor Promedio por Jugador,Bang x Buck [Points/Value] +1. FC Koeln,-36,154,73.37,2.36,2.098950525 +1.FC Nuremberg,-42,19,42.88,1.48,0.443097015 +1.FSV Mainz 05,-34,206,78.68,2.172,2.618200305 +Bay. Leverkusen,70,275,239.326,7.74,1.149060278 +Bayern Munich ,312,411,642.776,19.042,0.639414042 +Bor. Dortmund,139,319,357.696,10.716,0.891818751 +Bor. M'gladbach,48,268,148.878,4.836,1.800131651 +E. Frankfurt,-19,224,89.876,2.424,2.492322756 +F. Duesseldorf,-16,44,47.43,1.39,0.927682901 +FC Augsburg,-49,198,65.852,1.768,3.006742392 +FC Ingolstadt,-30,72,30.53,421.075,2.358336063 +FC Schalke 04,7,239,222.116,6.384,1.076014335 +Hamburger SV,-83,145,88.5225,2.4275,1.638001638 +Hannover 96,-97,122,74.6775,2.1025,1.63369154 +Hertha BSC,-31,220,87.962,2.652,2.501080012 +RB Leipzig,65,186,194.87,6.176666667,0.954482475 +SC Freiburg,-68,154,66.04,1.9525,2.331920048 +SC Paderborn,-34,31,22.45,802,1.380846325 +SV Darmstadt 98,-50,63,26.315,751,2.394071822 +TSG Hoffenheim,42,249,119.992,3.526,2.075138343 +VfB Stuttgart,-81,148,103.4575,3.1375,1.43053911 +VfL Wolfsburg,14,239,192.648,5.46,1.240604626 +Werder Bremen,-27,221,76.488,2.146,2.889342119 diff --git a/Results.pptx b/Results.pptx new file mode 100644 index 0000000..2163d7d Binary files /dev/null and b/Results.pptx differ diff --git a/Tabla15.csv b/Tabla15.csv new file mode 100644 index 0000000..926f904 --- /dev/null +++ b/Tabla15.csv @@ -0,0 +1,19 @@ +,Equipo,No. Jugadores,Edad Promedio,No. Extranjeros,Valor Total [mil.EUR],Valor Promedio x Jugador [mil.EUR] +0,Bayern Munich ,33,24.6,17,564.18,17.1 +1,Bor. Dortmund,37,23.7,18,329.8,8.91 +2,FC Schalke 04,36,23.0,15,213.38,5.93 +3,VfL Wolfsburg,30,24.9,18,176.13,5.87 +4,Bay. Leverkusen,26,23.9,14,166.55,6.41 +5,Hamburger SV,38,24.2,21,114.95,3.03 +6,Bor. M'gladbach,27,24.9,14,107.33,3.98 +7,TSG Hoffenheim,30,23.4,13,100.03,3.33 +8,VfB Stuttgart,30,23.7,16,97.9,3.26 +9,Hannover 96,35,24.6,16,78.05,2.23 +10,1.FSV Mainz 05,36,23.9,19,76.9,2.14 +11,Hertha BSC,30,25.3,16,76.48,2.55 +12,E. Frankfurt,30,24.1,14,73.98,2.47 +13,Werder Bremen,36,22.9,17,58.58,1.63 +14,SC Freiburg,30,24.1,13,56.9,1.9 +15,1. FC Köln,27,24.4,14,43.33,1.6 +16,FC Augsburg,35,24.6,18,42.43,1.21 +17,SC Paderborn,28,25.2,8,22.45,802.0 diff --git a/Tabla16.csv b/Tabla16.csv new file mode 100644 index 0000000..9a61edb --- /dev/null +++ b/Tabla16.csv @@ -0,0 +1,19 @@ +,Equipo,No. Jugadores,Edad Promedio,No. Extranjeros,Valor Total [mil.EUR],Valor Promedio x Jugador [mil.EUR] +0,Bayern Munich ,34,24.9,19,608.5,17.9 +1,Bor. Dortmund,30,23.9,13,311.6,10.39 +2,VfL Wolfsburg,35,24.5,19,265.43,7.58 +3,FC Schalke 04,32,23.9,14,209.35,6.54 +4,Bay. Leverkusen,33,23.2,20,200.75,6.08 +5,Bor. M'gladbach,29,24.4,17,139.55,4.81 +6,TSG Hoffenheim,31,23.8,16,111.4,3.59 +7,E. Frankfurt,35,23.9,21,87.5,2.5 +8,VfB Stuttgart,34,23.8,18,82.6,2.43 +9,Hamburger SV,35,24.8,18,74.08,2.12 +10,Hannover 96,39,23.5,22,73.58,1.89 +11,Hertha BSC,34,24.3,15,72.9,2.14 +12,1.FSV Mainz 05,39,24.3,22,67.55,1.73 +13,FC Augsburg,39,24.9,20,62.5,1.6 +14,Werder Bremen,39,23.6,18,59.5,1.53 +15,1. FC Köln,25,24.0,12,52.05,2.08 +16,FC Ingolstadt,29,24.2,15,24.38,841.0 +17,SV Darmstadt 98,30,26.3,9,19.8,660.0 diff --git a/Tabla17.csv b/Tabla17.csv new file mode 100644 index 0000000..68468b3 --- /dev/null +++ b/Tabla17.csv @@ -0,0 +1,19 @@ +,Equipo,No. Jugadores,Edad Promedio,No. Extranjeros,Valor Total [mil.EUR],Valor Promedio x Jugador [mil.EUR] +0,Bayern Munich ,33,25.1,17,595.4,18.04 +1,Bor. Dortmund,31,24.2,16,321.05,10.36 +2,Bay. Leverkusen,39,22.8,21,244.58,6.27 +3,FC Schalke 04,39,23.7,22,238.75,6.12 +4,VfL Wolfsburg,43,23.5,21,225.35,5.24 +5,Bor. M'gladbach,33,23.4,15,155.8,4.72 +6,Hamburger SV,38,23.6,20,94.98,2.5 +7,1.FSV Mainz 05,39,23.3,22,85.7,2.2 +8,1. FC Köln,30,24.4,13,77.4,2.58 +9,TSG Hoffenheim,33,23.5,14,76.55,2.32 +10,Hertha BSC,33,24.0,14,75.98,2.3 +11,Werder Bremen,41,24.5,20,75.08,1.83 +12,RB Leipzig,33,22.6,17,69.18,2.1 +13,FC Augsburg,37,25.3,21,69.0,1.86 +14,E. Frankfurt,35,23.1,22,66.1,1.89 +15,SC Freiburg,36,24.0,13,40.25,1.12 +16,FC Ingolstadt,32,23.8,15,36.68,1.15 +17,SV Darmstadt 98,39,25.7,17,32.83,842.0 diff --git a/Tabla18.csv b/Tabla18.csv new file mode 100644 index 0000000..71deea0 --- /dev/null +++ b/Tabla18.csv @@ -0,0 +1,19 @@ +,Equipo,No. Jugadores,Edad Promedio,No. Extranjeros,Valor Total [mil.EUR],Valor Promedio x Jugador [mil.EUR] +0,Bayern Munich ,38,23.7,18,610.25,16.06 +1,Bor. Dortmund,35,24.0,19,449.23,12.84 +2,Bay. Leverkusen,27,24.3,14,225.4,8.35 +3,FC Schalke 04,29,24.6,18,205.2,7.08 +4,RB Leipzig,28,23.1,19,200.98,7.18 +5,VfL Wolfsburg,33,23.3,19,150.8,4.57 +6,Bor. M'gladbach,35,23.6,19,150.18,4.29 +7,TSG Hoffenheim,36,23.1,13,123.35,3.43 +8,1. FC Köln,38,23.5,18,120.7,3.18 +9,Hertha BSC,32,23.9,14,89.85,2.81 +10,E. Frankfurt,36,24.0,23,82.3,2.29 +11,Werder Bremen,33,24.6,19,78.43,2.38 +12,1.FSV Mainz 05,33,24.4,18,76.65,2.32 +13,VfB Stuttgart,34,23.8,17,73.88,2.17 +14,SC Freiburg,36,24.5,14,72.73,2.02 +15,Hamburger SV,34,23.5,16,70.08,2.06 +16,FC Augsburg,33,24.6,16,54.38,1.65 +17,Hannover 96,30,24.9,13,48.8,1.63 diff --git a/Tabla19.csv b/Tabla19.csv new file mode 100644 index 0000000..36cf62e --- /dev/null +++ b/Tabla19.csv @@ -0,0 +1,19 @@ +,Equipo,No. Jugadores,Edad Promedio,No. Extranjeros,Valor Total [mil.EUR],Valor Promedio x Jugador [mil.EUR] +0,Bayern Munich ,32,24.7,15,835.55,26.11 +1,Bor. Dortmund,34,23.4,19,376.8,11.08 +2,Bay. Leverkusen,31,23.6,16,359.35,11.59 +3,RB Leipzig,34,21.6,21,314.45,9.25 +4,FC Schalke 04,39,24.1,24,243.9,6.25 +5,Bor. M'gladbach,30,24.2,17,191.53,6.38 +6,TSG Hoffenheim,38,23.5,21,188.63,4.96 +7,VfB Stuttgart,34,23.9,17,159.45,4.69 +8,VfL Wolfsburg,36,24.1,21,145.53,4.04 +9,E. Frankfurt,47,23.8,29,139.5,2.97 +10,Hertha BSC,36,23.5,17,124.6,3.46 +11,Werder Bremen,33,24.8,18,110.85,3.36 +12,FC Augsburg,40,23.9,19,100.95,2.52 +13,Hannover 96,37,24.7,18,98.28,2.66 +14,SC Freiburg,34,24.0,9,94.28,2.77 +15,1.FSV Mainz 05,35,23.8,19,86.6,2.47 +16,F. Düsseldorf,34,25.3,16,47.43,1.39 +17,1.FC Nuremberg,29,24.2,11,42.88,1.48 diff --git a/your-code/191102_Web-scraping Transfermarkt_CORRECT.ipynb b/your-code/191102_Web-scraping Transfermarkt_CORRECT.ipynb new file mode 100644 index 0000000..a70483a --- /dev/null +++ b/your-code/191102_Web-scraping Transfermarkt_CORRECT.ipynb @@ -0,0 +1,498 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "#Import the needed packages\n", + "import pandas as pd\n", + "import numpy as np\n", + "import requests\n", + "from bs4 import BeautifulSoup" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#------------URL SEASON 2018-2019\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2018'\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "\n", + "#-----------------TABLA DE VALOR ECONOMICO--------------------------\n", + "equipo = []\n", + "jugadores = []\n", + "edad = []\n", + "extranjeros = []\n", + "valor_mercado = []\n", + "valor_mercado_promedio = []\n", + "for row in table.find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo.append(col[2].text)\n", + " jugadores.append(col[3].text)\n", + " edad.append(col[4].text)\n", + " extranjeros.append(col[5].text)\n", + " valor_mercado.append(col[6].text)\n", + " valor_mercado_promedio.append(col[7].text)\n", + " except:\n", + " pass\n", + " \n", + "bl19 = pd.DataFrame({'Equipo': equipo[1:],'No. Jugadores': jugadores[1:], 'Edad Promedio': edad[1:], 'No. Extranjeros': extranjeros[1:],\n", + " 'Valor Total [mil.EUR]': valor_mercado[1:], 'Valor Promedio x Jugador [mil.EUR]': valor_mercado_promedio[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "bl19['Edad Promedio'] = bl19['Edad Promedio'].str.replace(',', '.')\n", + "bl19['Valor Total [mil.EUR]'] = bl19['Valor Total [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "bl19['Valor Promedio x Jugador [mil.EUR]'] = bl19['Valor Promedio x Jugador [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "\n", + "#Convertir a float algunas columnas\n", + "bl19[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]] = bl19[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]].apply(pd.to_numeric)\n", + "bl19[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]] = bl19[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]].apply(pd.to_numeric)\n", + "\n", + "#------------------TABLA DE POSICIONES------------------------------\n", + "tabla2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "\n", + "equipo2 = []\n", + "posicion = []\n", + "juegos_jugados = []\n", + "diferencia = []\n", + "puntos = []\n", + "\n", + "for row in tabla2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo2.append(col[2].text)\n", + " posicion.append(col[0].text)\n", + " juegos_jugados.append(col[3].text)\n", + " diferencia.append(col[4].text)\n", + " puntos.append(col[5].text)\n", + " except:\n", + " pass\n", + "\n", + "blpts19 = pd.DataFrame({'Equipo': equipo2[0:],'Posicion': posicion[0:], 'Juegos_Jugados': juegos_jugados[0:], 'Diferencia_Goles': diferencia[0:],\n", + " 'Puntos': puntos[0:]})\n", + "#Limpiar la tabla\n", + "blpts19['Equipo'] = blpts19['Equipo'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "blpts19['Posicion'] = blpts19.Posicion.astype(int)\n", + "blpts19['Juegos_Jugados'] = blpts19.Juegos_Jugados.astype(int)\n", + "blpts19['Diferencia_Goles'] = blpts19.Diferencia_Goles.astype(float)\n", + "blpts19['Puntos'] = blpts19.Puntos.astype(float)\n", + "\n", + "#-----------CONVERT TO CSV--------------------\n", + "csv_bl19=bl19.to_csv('Tabla19.csv')\n", + "csv_blpts19=blpts19.to_csv('Posicion19.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#------------URL SEASON 2017-2018\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2017'\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "\n", + "#-----------------TABLA DE VALOR ECONOMICO--------------------------\n", + "equipo = []\n", + "jugadores = []\n", + "edad = []\n", + "extranjeros = []\n", + "valor_mercado = []\n", + "valor_mercado_promedio = []\n", + "for row in table.find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo.append(col[2].text)\n", + " jugadores.append(col[3].text)\n", + " edad.append(col[4].text)\n", + " extranjeros.append(col[5].text)\n", + " valor_mercado.append(col[6].text)\n", + " valor_mercado_promedio.append(col[7].text)\n", + " except:\n", + " pass\n", + " \n", + "bl18 = pd.DataFrame({'Equipo': equipo[1:],'No. Jugadores': jugadores[1:], 'Edad Promedio': edad[1:], 'No. Extranjeros': extranjeros[1:],\n", + " 'Valor Total [mil.EUR]': valor_mercado[1:], 'Valor Promedio x Jugador [mil.EUR]': valor_mercado_promedio[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "bl18['Edad Promedio'] = bl18['Edad Promedio'].str.replace(',', '.')\n", + "bl18['Valor Total [mil.EUR]'] = bl18['Valor Total [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "bl18['Valor Promedio x Jugador [mil.EUR]'] = bl18['Valor Promedio x Jugador [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "\n", + "#Convertir a float algunas columnas\n", + "bl18[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]] = bl18[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]].apply(pd.to_numeric)\n", + "bl18[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]] = bl18[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]].apply(pd.to_numeric)\n", + "\n", + "#------------------TABLA DE POSICIONES------------------------------\n", + "tabla2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "\n", + "equipo2 = []\n", + "posicion = []\n", + "juegos_jugados = []\n", + "diferencia = []\n", + "puntos = []\n", + "\n", + "for row in tabla2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo2.append(col[2].text)\n", + " posicion.append(col[0].text)\n", + " juegos_jugados.append(col[3].text)\n", + " diferencia.append(col[4].text)\n", + " puntos.append(col[5].text)\n", + " except:\n", + " pass\n", + "\n", + "blpts18 = pd.DataFrame({'Equipo': equipo2[0:],'Posicion': posicion[0:], 'Juegos_Jugados': juegos_jugados[0:], 'Diferencia_Goles': diferencia[0:],\n", + " 'Puntos': puntos[0:]})\n", + "#Limpiar la tabla\n", + "blpts18['Equipo'] = blpts18['Equipo'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "blpts18['Posicion'] = blpts18.Posicion.astype(int)\n", + "blpts18['Juegos_Jugados'] = blpts18.Juegos_Jugados.astype(int)\n", + "blpts18['Diferencia_Goles'] = blpts18.Diferencia_Goles.astype(float)\n", + "blpts18['Puntos'] = blpts18.Puntos.astype(float)\n", + "\n", + "#-----------CONVERT TO CSV--------------------\n", + "csv_bl18=bl18.to_csv('Tabla18.csv')\n", + "csv_blpts18=blpts18.to_csv('Posicion18.csv')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#------------URL SEASON 2016-2017\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2016'\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "\n", + "#-----------------TABLA DE VALOR ECONOMICO--------------------------\n", + "equipo = []\n", + "jugadores = []\n", + "edad = []\n", + "extranjeros = []\n", + "valor_mercado = []\n", + "valor_mercado_promedio = []\n", + "for row in table.find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo.append(col[2].text)\n", + " jugadores.append(col[3].text)\n", + " edad.append(col[4].text)\n", + " extranjeros.append(col[5].text)\n", + " valor_mercado.append(col[6].text)\n", + " valor_mercado_promedio.append(col[7].text)\n", + " except:\n", + " pass\n", + " \n", + "bl17 = pd.DataFrame({'Equipo': equipo[1:],'No. Jugadores': jugadores[1:], 'Edad Promedio': edad[1:], 'No. Extranjeros': extranjeros[1:],\n", + " 'Valor Total [mil.EUR]': valor_mercado[1:], 'Valor Promedio x Jugador [mil.EUR]': valor_mercado_promedio[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "bl17['Edad Promedio'] = bl17['Edad Promedio'].str.replace(',', '.')\n", + "bl17['Valor Total [mil.EUR]'] = bl17['Valor Total [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "bl17['Valor Promedio x Jugador [mil.EUR]'] = bl17['Valor Promedio x Jugador [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','').str.replace('K €','')\n", + "\n", + "#Convertir a float algunas columnas\n", + "bl17[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]] = bl17[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]].apply(pd.to_numeric)\n", + "bl17[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]] = bl17[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]].apply(pd.to_numeric)\n", + "\n", + "#------------------TABLA DE POSICIONES------------------------------\n", + "tabla2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "\n", + "equipo2 = []\n", + "posicion = []\n", + "juegos_jugados = []\n", + "diferencia = []\n", + "puntos = []\n", + "\n", + "for row in tabla2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo2.append(col[2].text)\n", + " posicion.append(col[0].text)\n", + " juegos_jugados.append(col[3].text)\n", + " diferencia.append(col[4].text)\n", + " puntos.append(col[5].text)\n", + " except:\n", + " pass\n", + "\n", + "blpts17 = pd.DataFrame({'Equipo': equipo2[0:],'Posicion': posicion[0:], 'Juegos_Jugados': juegos_jugados[0:], 'Diferencia_Goles': diferencia[0:],\n", + " 'Puntos': puntos[0:]})\n", + "#Limpiar la tabla\n", + "blpts17['Equipo'] = blpts17['Equipo'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "blpts17['Posicion'] = blpts17.Posicion.astype(int)\n", + "blpts17['Juegos_Jugados'] = blpts17.Juegos_Jugados.astype(int)\n", + "blpts17['Diferencia_Goles'] = blpts17.Diferencia_Goles.astype(float)\n", + "blpts17['Puntos'] = blpts17.Puntos.astype(float)\n", + "\n", + "#-----------CONVERT TO CSV--------------------\n", + "csv_bl17=bl17.to_csv('Tabla17.csv')\n", + "csv_blpts17=blpts17.to_csv('Posicion17.csv')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#------------URL SEASON 2015-2016\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2015'\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "\n", + "#-----------------TABLA DE VALOR ECONOMICO--------------------------\n", + "equipo = []\n", + "jugadores = []\n", + "edad = []\n", + "extranjeros = []\n", + "valor_mercado = []\n", + "valor_mercado_promedio = []\n", + "for row in table.find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo.append(col[2].text)\n", + " jugadores.append(col[3].text)\n", + " edad.append(col[4].text)\n", + " extranjeros.append(col[5].text)\n", + " valor_mercado.append(col[6].text)\n", + " valor_mercado_promedio.append(col[7].text)\n", + " except:\n", + " pass\n", + " \n", + "bl16 = pd.DataFrame({'Equipo': equipo[1:],'No. Jugadores': jugadores[1:], 'Edad Promedio': edad[1:], 'No. Extranjeros': extranjeros[1:],\n", + " 'Valor Total [mil.EUR]': valor_mercado[1:], 'Valor Promedio x Jugador [mil.EUR]': valor_mercado_promedio[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "bl16['Edad Promedio'] = bl16['Edad Promedio'].str.replace(',', '.')\n", + "bl16['Valor Total [mil.EUR]'] = bl16['Valor Total [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "bl16['Valor Promedio x Jugador [mil.EUR]'] = bl16['Valor Promedio x Jugador [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','').str.replace('K €','')\n", + "\n", + "#Convertir a float algunas columnas\n", + "bl16[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]] = bl16[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]].apply(pd.to_numeric)\n", + "bl16[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]] = bl16[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]].apply(pd.to_numeric)\n", + "\n", + "#------------------TABLA DE POSICIONES------------------------------\n", + "tabla2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "\n", + "equipo2 = []\n", + "posicion = []\n", + "juegos_jugados = []\n", + "diferencia = []\n", + "puntos = []\n", + "\n", + "for row in tabla2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo2.append(col[2].text)\n", + " posicion.append(col[0].text)\n", + " juegos_jugados.append(col[3].text)\n", + " diferencia.append(col[4].text)\n", + " puntos.append(col[5].text)\n", + " except:\n", + " pass\n", + "\n", + "blpts16 = pd.DataFrame({'Equipo': equipo2[0:],'Posicion': posicion[0:], 'Juegos_Jugados': juegos_jugados[0:], 'Diferencia_Goles': diferencia[0:],\n", + " 'Puntos': puntos[0:]})\n", + "#Limpiar la tabla\n", + "blpts16['Equipo'] = blpts16['Equipo'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "blpts16['Posicion'] = blpts16.Posicion.astype(int)\n", + "blpts16['Juegos_Jugados'] = blpts16.Juegos_Jugados.astype(int)\n", + "blpts16['Diferencia_Goles'] = blpts16.Diferencia_Goles.astype(float)\n", + "blpts16['Puntos'] = blpts16.Puntos.astype(float)\n", + "\n", + "#-----------CONVERT TO CSV--------------------\n", + "csv_bl16=bl16.to_csv('Tabla16.csv')\n", + "csv_blpts16=blpts16.to_csv('Posicion16.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#------------URL SEASON 2014-2015\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2014'\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "table = soup.find(\"table\", {\"class\" : \"items\"})\n", + "row = table.find_all('tr')\n", + "\n", + "#-----------------TABLA DE VALOR ECONOMICO--------------------------\n", + "equipo = []\n", + "jugadores = []\n", + "edad = []\n", + "extranjeros = []\n", + "valor_mercado = []\n", + "valor_mercado_promedio = []\n", + "for row in table.find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo.append(col[2].text)\n", + " jugadores.append(col[3].text)\n", + " edad.append(col[4].text)\n", + " extranjeros.append(col[5].text)\n", + " valor_mercado.append(col[6].text)\n", + " valor_mercado_promedio.append(col[7].text)\n", + " except:\n", + " pass\n", + " \n", + "bl15 = pd.DataFrame({'Equipo': equipo[1:],'No. Jugadores': jugadores[1:], 'Edad Promedio': edad[1:], 'No. Extranjeros': extranjeros[1:],\n", + " 'Valor Total [mil.EUR]': valor_mercado[1:], 'Valor Promedio x Jugador [mil.EUR]': valor_mercado_promedio[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "bl15['Edad Promedio'] = bl15['Edad Promedio'].str.replace(',', '.')\n", + "bl15['Valor Total [mil.EUR]'] = bl15['Valor Total [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','')\n", + "bl15['Valor Promedio x Jugador [mil.EUR]'] = bl15['Valor Promedio x Jugador [mil.EUR]'].str.replace(',', '.').str.replace('mil. €','').str.replace('K €','')\n", + "\n", + "#Convertir a float algunas columnas\n", + "bl15[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]] = bl15[[\"No. Jugadores\", \"Edad Promedio\", \"No. Extranjeros\"]].apply(pd.to_numeric)\n", + "bl15[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]] = bl15[[\"Valor Total [mil.EUR]\",\"Valor Promedio x Jugador [mil.EUR]\"]].apply(pd.to_numeric)\n", + "\n", + "#------------------TABLA DE POSICIONES------------------------------\n", + "tabla2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "\n", + "equipo2 = []\n", + "posicion = []\n", + "juegos_jugados = []\n", + "diferencia = []\n", + "puntos = []\n", + "\n", + "for row in tabla2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " equipo2.append(col[2].text)\n", + " posicion.append(col[0].text)\n", + " juegos_jugados.append(col[3].text)\n", + " diferencia.append(col[4].text)\n", + " puntos.append(col[5].text)\n", + " except:\n", + " pass\n", + "\n", + "blpts15 = pd.DataFrame({'Equipo': equipo2[0:],'Posicion': posicion[0:], 'Juegos_Jugados': juegos_jugados[0:], 'Diferencia_Goles': diferencia[0:],\n", + " 'Puntos': puntos[0:]})\n", + "#Limpiar la tabla\n", + "blpts15['Equipo'] = blpts15['Equipo'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "blpts15['Posicion'] = blpts15.Posicion.astype(int)\n", + "blpts15['Juegos_Jugados'] = blpts15.Juegos_Jugados.astype(int)\n", + "blpts15['Diferencia_Goles'] = blpts15.Diferencia_Goles.astype(float)\n", + "blpts15['Puntos'] = blpts15.Puntos.astype(float)\n", + "\n", + "#-----------CONVERT TO CSV--------------------\n", + "csv_bl15=bl15.to_csv('Tabla15.csv')\n", + "csv_blpts15=blpts15.to_csv('Posicion15.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/your-code/191102_Web-scrapping-Transfermarkt_OLD NOT VALID.ipynb b/your-code/191102_Web-scrapping-Transfermarkt_OLD NOT VALID.ipynb new file mode 100644 index 0000000..0bbc41a --- /dev/null +++ b/your-code/191102_Web-scrapping-Transfermarkt_OLD NOT VALID.ipynb @@ -0,0 +1,809 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import requests\n", + "from bs4 import BeautifulSoup" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\urllib3\\connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n", + " InsecureRequestWarning)\n" + ] + } + ], + "source": [ + "#URL con la tabla del valor de los equipos en LaLiga para la temporada 2019-2020\n", + "url = 'https://www.transfermarkt.com/bundesliga/startseite/wettbewerb/L1/plus/?saison_id=2018'\n", + "#Para accesar la página\n", + "headers = {\"User-Agent\":\"Mozilla/5.0\"}\n", + "\n", + "#Parsear el contenido \n", + "response = requests.get(url, headers=headers, verify=False)\n", + "soup = BeautifulSoup(response.text, 'html.parser')" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "
ClubnamenameSquadø agePlayers playing abroadTotal market valueø market valueTotal MVø MV
   000----
\"BayernBayern Munich \"GermanBayern Munich 3224,715835,55 mil. €26,11 mil. €835,55 mil. €26,11 mil. €
\"BorussiaBorussia Dortmund Bor. Dortmund3423,419376,80 mil. €11,08 mil. €376,80 mil. €11,08 mil. €
\"BayerBayer 04 Leverkusen Bay. Leverkusen3123,616359,35 mil. €11,59 mil. €359,35 mil. €11,59 mil. €
\"RBRB Leipzig RB Leipzig3421,621314,45 mil. €9,25 mil. €314,45 mil. €9,25 mil. €
\"FCFC Schalke 04 FC Schalke 043924,124243,90 mil. €6,25 mil. €243,90 mil. €6,25 mil. €
\"BorussiaBorussia Mönchengladbach Bor. M'gladbach3024,217191,53 mil. €6,38 mil. €191,53 mil. €6,38 mil. €
\"TSGTSG 1899 Hoffenheim TSG Hoffenheim3823,521188,63 mil. €4,96 mil. €188,63 mil. €4,96 mil. €
\"VfBVfB Stuttgart VfB Stuttgart3423,917159,45 mil. €4,69 mil. €159,45 mil. €4,69 mil. €
\"VfLVfL Wolfsburg VfL Wolfsburg3624,121145,53 mil. €4,04 mil. €145,53 mil. €4,04 mil. €
\"EintrachtEintracht Frankfurt \"GermanE. Frankfurt4723,829139,50 mil. €2,97 mil. €139,50 mil. €2,97 mil. €
\"HerthaHertha BSC Hertha BSC3623,517124,60 mil. €3,46 mil. €124,60 mil. €3,46 mil. €
\"SVSV Werder Bremen Werder Bremen3324,818110,85 mil. €3,36 mil. €110,85 mil. €3,36 mil. €
\"FCFC Augsburg FC Augsburg4023,919100,95 mil. €2,52 mil. €100,95 mil. €2,52 mil. €
\"HannoverHannover 96 Hannover 963724,71898,28 mil. €2,66 mil. €98,28 mil. €2,66 mil. €
\"SCSC Freiburg SC Freiburg3424,0994,28 mil. €2,77 mil. €94,28 mil. €2,77 mil. €
\"1.FSV1.FSV Mainz 05 1.FSV Mainz 053523,81986,60 mil. €2,47 mil. €86,60 mil. €2,47 mil. €
\"FortunaFortuna Düsseldorf \"German F. Düsseldorf3425,31647,43 mil. €1,39 mil. €47,43 mil. €1,39 mil. €
\"1.FC1.FC Nuremberg  1.FC Nuremberg2924,21142,88 mil. €1,48 mil. €42,88 mil. €1,48 mil. €
" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Instrucciones para obtener todos los elementos de la tabla\n", + "table = soup.find('table', {'class' : 'items'})\n", + "table" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "20" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Encuentra todas las filas(tr) de la tabla.\n", + "row = table.find_all('tr')\n", + "#Para conocer el número de filas en la tabla\n", + "len(row)" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [], + "source": [ + "team = []\n", + "squad = []\n", + "age = []\n", + "foreigners = []\n", + "total_market_value = []\n", + "average_market_value = []\n", + "for x in row:\n", + " try:\n", + " col = x.find_all('td')\n", + " team.append(col[2].text)\n", + " squad.append(col[3].text)\n", + " age.append(col[4].text)\n", + " foreigners.append(col[5].text)\n", + " total_market_value.append(col[6].text)\n", + " average_market_value.append(col[7].text)\n", + " except:\n", + " pass" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TeamNo. PlayersAvg. AgeNo. ForeignersTotal ValueAverage value
0Bayern Munich3224.715835.55 mil. €26.11 mil. €
1Bor. Dortmund3423.419376.80 mil. €11.08 mil. €
2Bay. Leverkusen3123.616359.35 mil. €11.59 mil. €
3RB Leipzig3421.621314.45 mil. €9.25 mil. €
4FC Schalke 043924.124243.90 mil. €6.25 mil. €
5Bor. M'gladbach3024.217191.53 mil. €6.38 mil. €
6TSG Hoffenheim3823.521188.63 mil. €4.96 mil. €
7VfB Stuttgart3423.917159.45 mil. €4.69 mil. €
8VfL Wolfsburg3624.121145.53 mil. €4.04 mil. €
9E. Frankfurt4723.829139.50 mil. €2.97 mil. €
10Hertha BSC3623.517124.60 mil. €3.46 mil. €
11Werder Bremen3324.818110.85 mil. €3.36 mil. €
12FC Augsburg4023.919100.95 mil. €2.52 mil. €
13Hannover 963724.71898.28 mil. €2.66 mil. €
14SC Freiburg3424.0994.28 mil. €2.77 mil. €
151.FSV Mainz 053523.81986.60 mil. €2.47 mil. €
16F. Düsseldorf3425.31647.43 mil. €1.39 mil. €
171.FC Nuremberg2924.21142.88 mil. €1.48 mil. €
\n", + "
" + ], + "text/plain": [ + " Team No. Players Avg. Age No. Foreigners Total Value \\\n", + "0 Bayern Munich 32 24.7 15 835.55 mil. € \n", + "1 Bor. Dortmund 34 23.4 19 376.80 mil. € \n", + "2 Bay. Leverkusen 31 23.6 16 359.35 mil. € \n", + "3 RB Leipzig 34 21.6 21 314.45 mil. € \n", + "4 FC Schalke 04 39 24.1 24 243.90 mil. € \n", + "5 Bor. M'gladbach 30 24.2 17 191.53 mil. € \n", + "6 TSG Hoffenheim 38 23.5 21 188.63 mil. € \n", + "7 VfB Stuttgart 34 23.9 17 159.45 mil. € \n", + "8 VfL Wolfsburg 36 24.1 21 145.53 mil. € \n", + "9 E. Frankfurt 47 23.8 29 139.50 mil. € \n", + "10 Hertha BSC 36 23.5 17 124.60 mil. € \n", + "11 Werder Bremen 33 24.8 18 110.85 mil. € \n", + "12 FC Augsburg 40 23.9 19 100.95 mil. € \n", + "13 Hannover 96 37 24.7 18 98.28 mil. € \n", + "14 SC Freiburg 34 24.0 9 94.28 mil. € \n", + "15 1.FSV Mainz 05 35 23.8 19 86.60 mil. € \n", + "16 F. Düsseldorf 34 25.3 16 47.43 mil. € \n", + "17 1.FC Nuremberg 29 24.2 11 42.88 mil. € \n", + "\n", + " Average value \n", + "0 26.11 mil. € \n", + "1 11.08 mil. € \n", + "2 11.59 mil. € \n", + "3 9.25 mil. € \n", + "4 6.25 mil. € \n", + "5 6.38 mil. € \n", + "6 4.96 mil. € \n", + "7 4.69 mil. € \n", + "8 4.04 mil. € \n", + "9 2.97 mil. € \n", + "10 3.46 mil. € \n", + "11 3.36 mil. € \n", + "12 2.52 mil. € \n", + "13 2.66 mil. € \n", + "14 2.77 mil. € \n", + "15 2.47 mil. € \n", + "16 1.39 mil. € \n", + "17 1.48 mil. € " + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "df_bundesliga = pd.DataFrame({'Team': team[1:],'No. Players': squad[1:], \n", + " 'Avg. Age': age[1:], 'No. Foreigners': foreigners[1:],\n", + " 'Total Value': total_market_value[1:], \n", + " 'Average value': average_market_value[1:]})\n", + "#Limpiar y cambiar nomenclatura\n", + "df_bundesliga['Avg. Age'] = df_bundesliga['Avg. Age'].str.replace(',', '.')\n", + "df_bundesliga['Total Value'] = df_bundesliga['Total Value'].str.replace(',', '.')\n", + "df_bundesliga['Average value'] = df_bundesliga['Average value'].str.replace(',', '.')\n", + "df_bundesliga" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "#Limpiar y cambiar nomenclatura\n", + "df_bundesliga['Avg. Age'] = df_bundesliga['Avg. Age'].str.replace(',', '.')\n", + "df_bundesliga['Total Value'] = df_bundesliga['Total Value'].str.replace(',', '.')\n", + "df_bundesliga['Average value'] = df_bundesliga['Average value'].str.replace(',', '.')\n", + "df_bundesliga\n", + "\n", + "#Perteneciente a temporada 2019-2020\n", + "df_bl20 = df_bundesliga\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Team object\n", + "No. Players int64\n", + "Avg. Age float64\n", + "No. Foreigners int64\n", + "Total Value object\n", + "Average value object\n", + "dtype: object" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Convertir a float algunas columnas\n", + "df_bl20[[\"No. Players\", \"Avg. Age\", \"No. Foreigners\"]] = df_bl20[[\"No. Players\", \"Avg. Age\", \"No. Foreigners\"]].apply(pd.to_numeric)\n", + "df_bl20.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [], + "source": [ + "#Tabla de posiciones\n", + "table2 = soup.find_all(\"div\", {\"class\" : \"responsive-table\"})\n", + "team2 = []\n", + "place = []\n", + "matches = []\n", + "difference = []\n", + "pts = []\n", + "for row in table2[2].find_all('tr'):\n", + " try:\n", + " col = row.find_all('td')\n", + " team2.append(col[2].text)\n", + " place.append(col[0].text)\n", + " matches.append(col[3].text)\n", + " difference.append(col[4].text)\n", + " pts.append(col[5].text)\n", + " except:\n", + " pass\n" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "('Unable to parse string \"1\\xa0\" at position 0', 'occurred at index Rank')", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32mpandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mValueError\u001b[0m: Unable to parse string \"1 \"", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;31m#Convertir a float algunas columnas\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m \u001b[0mdf_blpts20\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"Rank\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"Matches\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"Difference\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf_blpts20\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"Rank\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"Matches\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"Difference\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_numeric\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 9\u001b[0m \u001b[0mdf_bl20\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtypes\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36mapply\u001b[1;34m(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)\u001b[0m\n\u001b[0;32m 6485\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6486\u001b[0m kwds=kwds)\n\u001b[1;32m-> 6487\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 6488\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6489\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mapplymap\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mget_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 149\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_raw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 150\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 151\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_standard\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 152\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 153\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mapply_empty_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mapply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 255\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 256\u001b[0m \u001b[1;31m# compute the result using the series generator\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 257\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_series_generator\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 258\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 259\u001b[0m \u001b[1;31m# wrap results\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mapply_series_generator\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 284\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 285\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mv\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mseries_gen\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 286\u001b[1;33m \u001b[0mresults\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mv\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 287\u001b[0m \u001b[0mkeys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mv\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 288\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\tools\\numeric.py\u001b[0m in \u001b[0;36mto_numeric\u001b[1;34m(arg, errors, downcast)\u001b[0m\n\u001b[0;32m 133\u001b[0m \u001b[0mcoerce_numeric\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mFalse\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0merrors\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;34m'ignore'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'raise'\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32melse\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 134\u001b[0m values = lib.maybe_convert_numeric(values, set(),\n\u001b[1;32m--> 135\u001b[1;33m coerce_numeric=coerce_numeric)\n\u001b[0m\u001b[0;32m 136\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 137\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mpandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mValueError\u001b[0m: ('Unable to parse string \"1\\xa0\" at position 0', 'occurred at index Rank')" + ] + } + ], + "source": [ + "df_blpts20 = pd.DataFrame({'Team': team2[0:],'Rank': place[0:], \n", + " 'Matches': matches[0:], 'Difference': difference[0:],\n", + " 'Points': pts[0:]})\n", + "#Limpiar la tabla\n", + "df_blpts20['Team'] = df_blpts20['Team'].str.replace('\\n', '')\n", + "\n", + "#Convertir a float algunas columnas\n", + "df_blpts20[[\"Rank\", \"Matches\", \"Difference\"]] = df_blpts20[[\"Rank\", \"Matches\", \"Difference\"]].apply(pd.to_numeric)\n", + "df_bl20.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 171, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TeamRankMatchesDifferencePoints
0Real Madrid2101221
1Atlético Madrid311520
2Sevilla FC411220
3Granada CF511520
4Real Sociedad611619
5Valencia712-117
6Levante812117
7Villarreal911917
8Athletic1011416
9Getafe1111216
10CA Osasuna1211115
11Real Valladolid1311-314
12Alavés1411-512
13SD Eibar1511-412
14Real Betis1611-712
15RCD Mallorca1711-611
16Celta de Vigo1811-89
17Espanyol1912-148
18CD Leganés2011-145
\n", + "
" + ], + "text/plain": [ + " Team Rank Matches Difference Points\n", + "0 Real Madrid 2  10 12 21\n", + "1 Atlético Madrid 3  11 5 20\n", + "2 Sevilla FC 4  11 2 20\n", + "3 Granada CF   5  11 5 20\n", + "4 Real Sociedad 6  11 6 19\n", + "5 Valencia 7  12 -1 17\n", + "6 Levante 8  12 1 17\n", + "7 Villarreal 9  11 9 17\n", + "8 Athletic 10  11 4 16\n", + "9 Getafe 11  11 2 16\n", + "10 CA Osasuna   12  11 1 15\n", + "11 Real Valladolid 13  11 -3 14\n", + "12 Alavés 14  11 -5 12\n", + "13 SD Eibar 15  11 -4 12\n", + "14 Real Betis 16  11 -7 12\n", + "15 RCD Mallorca   17  11 -6 11\n", + "16 Celta de Vigo 18  11 -8 9\n", + "17 Espanyol 19  12 -14 8\n", + "18 CD Leganés 20  11 -14 5" + ] + }, + "execution_count": 171, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Clean Table\n", + "dfliga['Team'] = dfliga['Team'].str.replace('\\n', '')\n", + "\n", + "\n", + "dfliga" + ] + }, + { + "cell_type": "code", + "execution_count": 174, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Team object\n", + "Rank object\n", + "Matches object\n", + "Difference object\n", + "Points object\n", + "dtype: object" + ] + }, + "execution_count": 174, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dfliga = " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}