{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "e621e3ae", "metadata": { "nbsphinx": "hidden" }, "outputs": [], "source": [ "import pandas as pd\n", "pd.set_option('display.max_columns', None)" ] }, { "cell_type": "code", "execution_count": 2, "id": "0f792a6b", "metadata": { "nbsphinx": "hidden" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "env: SOCCERDATA_LOGLEVEL=ERROR\n", "env: SOCCERDATA_NOCACHE=True\n", "env: SOCCERDATA_NOSTORE=True\n" ] } ], "source": [ "%env SOCCERDATA_LOGLEVEL=ERROR\n", "%env SOCCERDATA_NOCACHE=True\n", "%env SOCCERDATA_NOSTORE=True" ] }, { "cell_type": "code", "execution_count": 3, "id": "2454afe6", "metadata": {}, "outputs": [], "source": [ "import soccerdata as sd" ] }, { "cell_type": "markdown", "id": "b5784f2d", "metadata": {}, "source": [ "# Match History" ] }, { "cell_type": "code", "execution_count": 4, "id": "8dab5be9", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/cw/dtaijupiter/NoCsBack/dtai/pieterr/Projects/soccerdata/soccerdata/_common.py:466: UserWarning: Season id \"2021\" is ambiguous: interpreting as \"20-21\"\n", " warnings.warn(msg)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Provides pd.DataFrames from CSV files available at http://www.football-data.co.uk/data.php.\n", "\n", " Data will be downloaded as necessary and cached locally in\n", " ``~/soccerdata/data/MatchHistory``.\n", "\n", " Parameters\n", " ----------\n", " leagues : string or iterable\n", " IDs of leagues to include.\n", " seasons : string, int or list\n", " Seasons to include. Supports multiple formats.\n", " Examples: '16-17'; 2016; '2016-17'; [14, 15, 16]\n", " proxy : 'tor' or or dict or list(dict) or callable, optional\n", " Use a proxy to hide your IP address. Valid options are:\n", " - \"tor\": Uses the Tor network. Tor should be running in\n", " the background on port 9050.\n", " - dict: A dictionary with the proxy to use. The dict should be\n", " a mapping of supported protocols to proxy addresses. For example::\n", "\n", " {\n", " 'http': 'http://10.10.1.10:3128',\n", " 'https': 'http://10.10.1.10:1080',\n", " }\n", "\n", " - list(dict): A list of proxies to choose from. A different proxy will\n", " be selected from this list after failed requests, allowing rotating\n", " proxies.\n", " - callable: A function that returns a valid proxy. This function will\n", " be called after failed requests, allowing rotating proxies.\n", " no_cache : bool\n", " If True, will not use cached data.\n", " no_store : bool\n", " If True, will not store downloaded data.\n", " data_dir : Path, optional\n", " Path to directory where data will be cached.\n", " \n" ] } ], "source": [ "mh = sd.MatchHistory(leagues=\"ENG-Premier League\", seasons=2021)\n", "print(mh.__doc__)" ] }, { "cell_type": "markdown", "id": "3a4c2916", "metadata": {}, "source": [ "## Historic match results and betting odds" ] }, { "cell_type": "code", "execution_count": 5, "id": "745be31a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | \n", " | \n", " | date | \n", "home_team | \n", "away_team | \n", "FTHG | \n", "FTAG | \n", "FTR | \n", "HTHG | \n", "HTAG | \n", "HTR | \n", "referee | \n", "HS | \n", "AS | \n", "HST | \n", "AST | \n", "HF | \n", "AF | \n", "HC | \n", "AC | \n", "HY | \n", "AY | \n", "HR | \n", "AR | \n", "B365H | \n", "B365D | \n", "B365A | \n", "BWH | \n", "BWD | \n", "BWA | \n", "IWH | \n", "IWD | \n", "IWA | \n", "PSH | \n", "PSD | \n", "PSA | \n", "WHH | \n", "WHD | \n", "WHA | \n", "VCH | \n", "VCD | \n", "VCA | \n", "MaxH | \n", "MaxD | \n", "MaxA | \n", "AvgH | \n", "AvgD | \n", "AvgA | \n", "B365>2.5 | \n", "B365<2.5 | \n", "P>2.5 | \n", "P<2.5 | \n", "Max>2.5 | \n", "Max<2.5 | \n", "Avg>2.5 | \n", "Avg<2.5 | \n", "AHh | \n", "B365AHH | \n", "B365AHA | \n", "PAHH | \n", "PAHA | \n", "MaxAHH | \n", "MaxAHA | \n", "AvgAHH | \n", "AvgAHA | \n", "B365CH | \n", "B365CD | \n", "B365CA | \n", "BWCH | \n", "BWCD | \n", "BWCA | \n", "IWCH | \n", "IWCD | \n", "IWCA | \n", "PSCH | \n", "PSCD | \n", "PSCA | \n", "WHCH | \n", "WHCD | \n", "WHCA | \n", "VCCH | \n", "VCCD | \n", "VCCA | \n", "MaxCH | \n", "MaxCD | \n", "MaxCA | \n", "AvgCH | \n", "AvgCD | \n", "AvgCA | \n", "B365C>2.5 | \n", "B365C<2.5 | \n", "PC>2.5 | \n", "PC<2.5 | \n", "MaxC>2.5 | \n", "MaxC<2.5 | \n", "AvgC>2.5 | \n", "AvgC<2.5 | \n", "AHCh | \n", "B365CAHH | \n", "B365CAHA | \n", "PCAHH | \n", "PCAHA | \n", "MaxCAHH | \n", "MaxCAHA | \n", "AvgCAHH | \n", "AvgCAHA | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
league | \n", "season | \n", "game | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
ENG-Premier League | \n", "2021 | \n", "2020-01-11 Aston Villa-Southampton | \n", "2020-01-11 12:00:00 | \n", "Aston Villa | \n", "Southampton | \n", "3 | \n", "4 | \n", "A | \n", "0 | \n", "3 | \n", "A | \n", "D England | \n", "19 | \n", "9 | \n", "10 | \n", "4 | \n", "12 | \n", "17 | \n", "11 | \n", "1 | \n", "1 | \n", "2 | \n", "0 | \n", "0 | \n", "2.45 | \n", "3.5 | \n", "2.80 | \n", "2.35 | \n", "3.60 | \n", "2.85 | \n", "2.50 | \n", "3.35 | \n", "2.75 | \n", "2.53 | \n", "3.72 | \n", "2.81 | \n", "2.50 | \n", "3.5 | \n", "2.75 | \n", "2.40 | \n", "3.60 | \n", "2.80 | \n", "2.60 | \n", "3.84 | \n", "2.85 | \n", "2.46 | \n", "3.60 | \n", "2.78 | \n", "1.66 | \n", "2.2 | \n", "1.66 | \n", "2.37 | \n", "1.69 | \n", "2.38 | \n", "1.65 | \n", "2.27 | \n", "0.00 | \n", "1.83 | \n", "2.07 | \n", "1.87 | \n", "2.07 | \n", "1.87 | \n", "2.09 | \n", "1.83 | \n", "2.05 | \n", "2.60 | \n", "3.50 | \n", "2.62 | \n", "2.50 | \n", "3.60 | \n", "2.70 | \n", "2.55 | \n", "3.50 | \n", "2.70 | \n", "2.69 | \n", "3.56 | \n", "2.73 | \n", "2.60 | \n", "3.50 | \n", "2.62 | \n", "2.50 | \n", "3.60 | \n", "2.70 | \n", "2.70 | \n", "3.70 | \n", "2.80 | \n", "2.57 | \n", "3.55 | \n", "2.69 | \n", "1.66 | \n", "2.20 | \n", "1.70 | \n", "2.29 | \n", "1.71 | \n", "2.37 | \n", "1.66 | \n", "2.24 | \n", "0.00 | \n", "1.93 | \n", "1.97 | \n", "1.95 | \n", "1.98 | \n", "1.97 | \n", "2.04 | \n", "1.89 | \n", "1.98 | \n", "
2020-01-11 Man United-Arsenal | \n", "2020-01-11 16:30:00 | \n", "Man United | \n", "Arsenal | \n", "0 | \n", "1 | \n", "A | \n", "0 | \n", "0 | \n", "D | \n", "M Dean | \n", "8 | \n", "7 | \n", "2 | \n", "2 | \n", "12 | \n", "12 | \n", "6 | \n", "3 | \n", "3 | \n", "3 | \n", "0 | \n", "0 | \n", "2.00 | \n", "3.6 | \n", "3.60 | \n", "2.00 | \n", "3.70 | \n", "3.60 | \n", "2.05 | \n", "3.45 | \n", "3.55 | \n", "2.05 | \n", "3.78 | \n", "3.73 | \n", "2.05 | \n", "3.6 | \n", "3.60 | \n", "2.05 | \n", "3.60 | \n", "3.50 | \n", "2.10 | \n", "3.85 | \n", "3.76 | \n", "2.04 | \n", "3.66 | \n", "3.58 | \n", "1.72 | \n", "2.1 | \n", "1.76 | \n", "2.19 | \n", "1.81 | \n", "2.22 | \n", "1.74 | \n", "2.12 | \n", "-0.50 | \n", "2.05 | \n", "1.85 | \n", "2.05 | \n", "1.88 | \n", "2.09 | \n", "1.90 | \n", "2.04 | \n", "1.84 | \n", "1.95 | \n", "3.60 | \n", "3.80 | \n", "1.95 | \n", "3.60 | \n", "3.90 | \n", "2.00 | \n", "3.50 | \n", "3.80 | \n", "2.02 | \n", "3.65 | \n", "3.97 | \n", "2.00 | \n", "3.50 | \n", "3.80 | \n", "1.95 | \n", "3.50 | \n", "4.00 | \n", "2.06 | \n", "3.75 | \n", "4.00 | \n", "1.99 | \n", "3.59 | \n", "3.87 | \n", "1.90 | \n", "1.90 | \n", "1.96 | \n", "1.96 | \n", "1.99 | \n", "2.10 | \n", "1.88 | \n", "1.95 | \n", "-0.50 | \n", "2.00 | \n", "1.90 | \n", "2.03 | \n", "1.90 | \n", "2.05 | \n", "1.92 | \n", "2.00 | \n", "1.88 | \n", "||
2020-01-11 Newcastle-Everton | \n", "2020-01-11 14:00:00 | \n", "Newcastle | \n", "Everton | \n", "2 | \n", "1 | \n", "H | \n", "0 | \n", "0 | \n", "D | \n", "S Attwell | \n", "11 | \n", "15 | \n", "4 | \n", "4 | \n", "9 | \n", "10 | \n", "5 | \n", "4 | \n", "2 | \n", "4 | \n", "0 | \n", "0 | \n", "3.70 | \n", "3.4 | \n", "2.05 | \n", "3.75 | \n", "3.40 | \n", "2.05 | \n", "3.55 | \n", "3.30 | \n", "2.10 | \n", "3.82 | \n", "3.56 | \n", "2.09 | \n", "3.70 | \n", "3.4 | \n", "2.05 | \n", "3.50 | \n", "3.50 | \n", "2.05 | \n", "4.00 | \n", "3.59 | \n", "2.15 | \n", "3.71 | \n", "3.47 | \n", "2.06 | \n", "1.80 | \n", "2.0 | \n", "1.86 | \n", "2.07 | \n", "1.88 | \n", "2.08 | \n", "1.82 | \n", "2.01 | \n", "0.25 | \n", "2.05 | \n", "1.75 | \n", "2.15 | \n", "1.80 | \n", "2.17 | \n", "1.83 | \n", "2.12 | \n", "1.77 | \n", "3.30 | \n", "3.30 | \n", "2.25 | \n", "3.30 | \n", "3.30 | \n", "2.25 | \n", "3.15 | \n", "3.35 | \n", "2.30 | \n", "3.34 | \n", "3.43 | \n", "2.33 | \n", "3.40 | \n", "3.25 | \n", "2.25 | \n", "3.30 | \n", "3.30 | \n", "2.25 | \n", "3.62 | \n", "3.50 | \n", "2.34 | \n", "3.34 | \n", "3.33 | \n", "2.27 | \n", "2.00 | \n", "1.80 | \n", "2.12 | \n", "1.81 | \n", "2.14 | \n", "1.92 | \n", "2.04 | \n", "1.80 | \n", "0.25 | \n", "1.95 | \n", "1.95 | \n", "1.93 | \n", "2.00 | \n", "1.99 | \n", "2.03 | \n", "1.93 | \n", "1.95 | \n", "||
2020-01-11 Tottenham-Brighton | \n", "2020-01-11 19:15:00 | \n", "Tottenham | \n", "Brighton | \n", "2 | \n", "1 | \n", "H | \n", "1 | \n", "0 | \n", "H | \n", "G Scott | \n", "9 | \n", "6 | \n", "3 | \n", "2 | \n", "14 | \n", "13 | \n", "4 | \n", "5 | \n", "2 | \n", "1 | \n", "0 | \n", "0 | \n", "1.61 | \n", "4.0 | \n", "5.50 | \n", "1.62 | \n", "4.25 | \n", "5.00 | \n", "1.65 | \n", "3.90 | \n", "5.00 | \n", "1.65 | \n", "4.26 | \n", "5.54 | \n", "1.63 | \n", "4.0 | \n", "5.25 | \n", "1.62 | \n", "4.20 | \n", "5.25 | \n", "1.67 | \n", "4.30 | \n", "5.75 | \n", "1.63 | \n", "4.17 | \n", "5.29 | \n", "1.66 | \n", "2.2 | \n", "1.68 | \n", "2.32 | \n", "1.71 | \n", "2.35 | \n", "1.65 | \n", "2.26 | \n", "-1.00 | \n", "2.02 | \n", "1.77 | \n", "2.15 | \n", "1.80 | \n", "2.16 | \n", "1.84 | \n", "2.09 | \n", "1.80 | \n", "1.55 | \n", "4.33 | \n", "6.00 | \n", "1.57 | \n", "4.25 | \n", "5.50 | \n", "1.60 | \n", "4.20 | \n", "5.75 | \n", "1.61 | \n", "4.36 | \n", "5.77 | \n", "1.57 | \n", "4.00 | \n", "6.00 | \n", "1.57 | \n", "4.20 | \n", "5.75 | \n", "1.63 | \n", "4.45 | \n", "6.39 | \n", "1.59 | \n", "4.29 | \n", "5.62 | \n", "1.66 | \n", "2.20 | \n", "1.68 | \n", "2.32 | \n", "1.72 | \n", "2.37 | \n", "1.65 | \n", "2.27 | \n", "-1.00 | \n", "2.06 | \n", "1.84 | \n", "2.11 | \n", "1.84 | \n", "2.13 | \n", "1.99 | \n", "2.02 | \n", "1.86 | \n", "||
2020-02-11 Fulham-West Brom | \n", "2020-02-11 17:30:00 | \n", "Fulham | \n", "West Brom | \n", "2 | \n", "0 | \n", "H | \n", "2 | \n", "0 | \n", "H | \n", "S Hooper | \n", "13 | \n", "10 | \n", "6 | \n", "1 | \n", "13 | \n", "11 | \n", "5 | \n", "2 | \n", "3 | \n", "2 | \n", "0 | \n", "0 | \n", "2.40 | \n", "3.3 | \n", "3.00 | \n", "2.40 | \n", "3.30 | \n", "3.00 | \n", "2.45 | \n", "3.10 | \n", "3.00 | \n", "2.47 | \n", "3.40 | \n", "3.13 | \n", "2.40 | \n", "3.3 | \n", "3.00 | \n", "2.45 | \n", "3.25 | \n", "3.00 | \n", "2.56 | \n", "3.50 | \n", "3.17 | \n", "2.44 | \n", "3.32 | \n", "3.01 | \n", "2.00 | \n", "1.8 | \n", "2.13 | \n", "1.80 | \n", "2.14 | \n", "1.85 | \n", "2.06 | \n", "1.78 | \n", "-0.25 | \n", "2.10 | \n", "1.80 | \n", "2.11 | \n", "1.84 | \n", "2.15 | \n", "1.86 | \n", "2.10 | \n", "1.80 | \n", "2.40 | \n", "3.30 | \n", "3.00 | \n", "2.45 | \n", "3.30 | \n", "2.95 | \n", "2.40 | \n", "3.05 | \n", "3.10 | \n", "2.48 | \n", "3.32 | \n", "3.19 | \n", "2.40 | \n", "3.20 | \n", "3.10 | \n", "2.40 | \n", "3.25 | \n", "3.10 | \n", "2.48 | \n", "3.45 | \n", "3.22 | \n", "2.41 | \n", "3.27 | \n", "3.09 | \n", "2.05 | \n", "1.85 | \n", "2.05 | \n", "1.88 | \n", "2.11 | \n", "1.92 | \n", "2.02 | \n", "1.81 | \n", "-0.25 | \n", "2.06 | \n", "1.84 | \n", "2.11 | \n", "1.84 | \n", "2.12 | \n", "1.87 | \n", "2.08 | \n", "1.82 | \n", "