{ "cells": [ { "cell_type": "markdown", "id": "81215b75-f5f8-4c17-9cd4-08b1b0ed4234", "metadata": {}, "source": [ "# Applying Weighting to the Goals Models" ] }, { "cell_type": "code", "execution_count": 1, "id": "1f931497-c1f9-4cb4-969a-058676e42a24", "metadata": { "tags": [] }, "outputs": [], "source": [ "import sys\n", "\n", "sys.path.append(\"../../\")\n", "\n", "import penaltyblog as pb" ] }, { "cell_type": "markdown", "id": "4a1b5c76-8f47-4f59-8351-d5add2f69309", "metadata": {}, "source": [ "## Get data from football-data.co.uk" ] }, { "cell_type": "code", "execution_count": 2, "id": "949b129d-e4e5-4975-8318-dd601d918e90", "metadata": { "tags": [] }, "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", "
datedatetimeseasoncompetitiondivtimeteam_hometeam_awayfthgftag...b365_cahhb365_cahapcahhpcahamax_cahhmax_cahaavg_cahhavg_cahagoals_homegoals_away
id
1565308800---liverpool---norwich2019-08-092019-08-09 20:00:002019-2020ENG Premier LeagueE020:00LiverpoolNorwich41...1.911.991.941.981.992.071.901.9941
1565395200---bournemouth---sheffield_united2019-08-102019-08-10 15:00:002019-2020ENG Premier LeagueE015:00BournemouthSheffield United11...1.951.951.981.952.001.961.961.9211
1565395200---burnley---southampton2019-08-102019-08-10 15:00:002019-2020ENG Premier LeagueE015:00BurnleySouthampton30...1.872.031.892.031.902.071.862.0230
1565395200---crystal_palace---everton2019-08-102019-08-10 15:00:002019-2020ENG Premier LeagueE015:00Crystal PalaceEverton00...1.822.081.971.962.032.081.961.9300
1565395200---tottenham---aston_villa2019-08-102019-08-10 17:30:002019-2020ENG Premier LeagueE017:30TottenhamAston Villa31...2.101.702.181.772.211.872.081.8031
\n", "

5 rows × 111 columns

\n", "
" ], "text/plain": [ " date datetime \\\n", "id \n", "1565308800---liverpool---norwich 2019-08-09 2019-08-09 20:00:00 \n", "1565395200---bournemouth---sheffield_united 2019-08-10 2019-08-10 15:00:00 \n", "1565395200---burnley---southampton 2019-08-10 2019-08-10 15:00:00 \n", "1565395200---crystal_palace---everton 2019-08-10 2019-08-10 15:00:00 \n", "1565395200---tottenham---aston_villa 2019-08-10 2019-08-10 17:30:00 \n", "\n", " season competition \\\n", "id \n", "1565308800---liverpool---norwich 2019-2020 ENG Premier League \n", "1565395200---bournemouth---sheffield_united 2019-2020 ENG Premier League \n", "1565395200---burnley---southampton 2019-2020 ENG Premier League \n", "1565395200---crystal_palace---everton 2019-2020 ENG Premier League \n", "1565395200---tottenham---aston_villa 2019-2020 ENG Premier League \n", "\n", " div time team_home \\\n", "id \n", "1565308800---liverpool---norwich E0 20:00 Liverpool \n", "1565395200---bournemouth---sheffield_united E0 15:00 Bournemouth \n", "1565395200---burnley---southampton E0 15:00 Burnley \n", "1565395200---crystal_palace---everton E0 15:00 Crystal Palace \n", "1565395200---tottenham---aston_villa E0 17:30 Tottenham \n", "\n", " team_away fthg ftag \\\n", "id \n", "1565308800---liverpool---norwich Norwich 4 1 \n", "1565395200---bournemouth---sheffield_united Sheffield United 1 1 \n", "1565395200---burnley---southampton Southampton 3 0 \n", "1565395200---crystal_palace---everton Everton 0 0 \n", "1565395200---tottenham---aston_villa Aston Villa 3 1 \n", "\n", " ... b365_cahh b365_caha pcahh \\\n", "id ... \n", "1565308800---liverpool---norwich ... 1.91 1.99 1.94 \n", "1565395200---bournemouth---sheffield_united ... 1.95 1.95 1.98 \n", "1565395200---burnley---southampton ... 1.87 2.03 1.89 \n", "1565395200---crystal_palace---everton ... 1.82 2.08 1.97 \n", "1565395200---tottenham---aston_villa ... 2.10 1.70 2.18 \n", "\n", " pcaha max_cahh max_caha \\\n", "id \n", "1565308800---liverpool---norwich 1.98 1.99 2.07 \n", "1565395200---bournemouth---sheffield_united 1.95 2.00 1.96 \n", "1565395200---burnley---southampton 2.03 1.90 2.07 \n", "1565395200---crystal_palace---everton 1.96 2.03 2.08 \n", "1565395200---tottenham---aston_villa 1.77 2.21 1.87 \n", "\n", " avg_cahh avg_caha goals_home \\\n", "id \n", "1565308800---liverpool---norwich 1.90 1.99 4 \n", "1565395200---bournemouth---sheffield_united 1.96 1.92 1 \n", "1565395200---burnley---southampton 1.86 2.02 3 \n", "1565395200---crystal_palace---everton 1.96 1.93 0 \n", "1565395200---tottenham---aston_villa 2.08 1.80 3 \n", "\n", " goals_away \n", "id \n", "1565308800---liverpool---norwich 1 \n", "1565395200---bournemouth---sheffield_united 1 \n", "1565395200---burnley---southampton 0 \n", "1565395200---crystal_palace---everton 0 \n", "1565395200---tottenham---aston_villa 1 \n", "\n", "[5 rows x 111 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fb = pb.scrapers.FootballData(\"ENG Premier League\", \"2019-2020\")\n", "df = fb.get_fixtures()\n", "\n", "df.head()" ] }, { "cell_type": "markdown", "id": "f8f22180", "metadata": {}, "source": [ "# Create the Weights" ] }, { "cell_type": "code", "execution_count": 4, "id": "39f8efb0", "metadata": {}, "outputs": [], "source": [ "xi = 0.001\n", "weights = pb.models.dixon_coles_weights(df[\"date\"], xi)" ] }, { "cell_type": "markdown", "id": "9257f0fc-5f2b-402f-9209-d005d14880be", "metadata": {}, "source": [ "## Train the model" ] }, { "cell_type": "code", "execution_count": 5, "id": "7d39d92f-6fa0-4a2a-8a48-22d214e38efc", "metadata": { "tags": [] }, "outputs": [], "source": [ "clf = pb.models.DixonColesGoalModel(\n", " df[\"goals_home\"], df[\"goals_away\"], df[\"team_home\"], df[\"team_away\"], weights\n", ")\n", "clf.fit()" ] }, { "cell_type": "markdown", "id": "63a12589-0066-431f-8444-92e2944b55a4", "metadata": {}, "source": [ "## The model's parameters" ] }, { "cell_type": "code", "execution_count": 6, "id": "1831867d-c26e-4970-9586-a9e23e75cfed", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "Module: Penaltyblog\n", "\n", "Model: Dixon and Coles\n", "\n", "Number of parameters: 42\n", "Log Likelihood: -879.671\n", "AIC: 1843.343\n", "\n", "Team Attack Defence \n", "------------------------------------------------------------\n", "Arsenal 1.145 -0.96 \n", "Aston Villa 0.821 -0.642 \n", "Bournemouth 0.824 -0.649 \n", "Brighton 0.773 -0.836 \n", "Burnley 0.869 -0.941 \n", "Chelsea 1.348 -0.812 \n", "Crystal Palace 0.531 -0.912 \n", "Everton 0.898 -0.813 \n", "Leicester 1.283 -1.055 \n", "Liverpool 1.537 -1.264 \n", "Man City 1.727 -1.255 \n", "Man United 1.31 -1.242 \n", "Newcastle 0.781 -0.768 \n", "Norwich 0.32 -0.527 \n", "Sheffield United 0.756 -1.158 \n", "Southampton 1.069 -0.761 \n", "Tottenham 1.218 -0.972 \n", "Watford 0.733 -0.666 \n", "West Ham 1.026 -0.708 \n", "Wolves 1.031 -1.148 \n", "------------------------------------------------------------\n", "Home Advantage: 0.239\n", "Rho: -0.078" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf" ] }, { "cell_type": "code", "execution_count": 7, "id": "fc93ec32-d113-4155-a516-abfe58dc8469", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "{'attack_Arsenal': np.float64(1.144949905929318),\n", " 'attack_Aston Villa': np.float64(0.8211833050535601),\n", " 'attack_Bournemouth': np.float64(0.8238000396326658),\n", " 'attack_Brighton': np.float64(0.7730705244669612),\n", " 'attack_Burnley': np.float64(0.8689343441725552),\n", " 'attack_Chelsea': np.float64(1.3475855486891566),\n", " 'attack_Crystal Palace': np.float64(0.5309831147050881),\n", " 'attack_Everton': np.float64(0.898409705429681),\n", " 'attack_Leicester': np.float64(1.282663505849936),\n", " 'attack_Liverpool': np.float64(1.5372296425830276),\n", " 'attack_Man City': np.float64(1.7267149046878532),\n", " 'attack_Man United': np.float64(1.310318077147705),\n", " 'attack_Newcastle': np.float64(0.7810821985130814),\n", " 'attack_Norwich': np.float64(0.32031537569664587),\n", " 'attack_Sheffield United': np.float64(0.756397077539036),\n", " 'attack_Southampton': np.float64(1.068666804409662),\n", " 'attack_Tottenham': np.float64(1.2184558429326078),\n", " 'attack_Watford': np.float64(0.7325661771016169),\n", " 'attack_West Ham': np.float64(1.0260467035815914),\n", " 'attack_Wolves': np.float64(1.0306272018767515),\n", " 'defence_Arsenal': np.float64(-0.9597520519607475),\n", " 'defence_Aston Villa': np.float64(-0.6424612731039607),\n", " 'defence_Bournemouth': np.float64(-0.6485814937773848),\n", " 'defence_Brighton': np.float64(-0.8360247260429235),\n", " 'defence_Burnley': np.float64(-0.9412626602561426),\n", " 'defence_Chelsea': np.float64(-0.8121173879097644),\n", " 'defence_Crystal Palace': np.float64(-0.911934038315484),\n", " 'defence_Everton': np.float64(-0.8128562445182332),\n", " 'defence_Leicester': np.float64(-1.0548116769925087),\n", " 'defence_Liverpool': np.float64(-1.2639681889819574),\n", " 'defence_Man City': np.float64(-1.2550748290155953),\n", " 'defence_Man United': np.float64(-1.2420940177658861),\n", " 'defence_Newcastle': np.float64(-0.7679483380308282),\n", " 'defence_Norwich': np.float64(-0.5269116672528777),\n", " 'defence_Sheffield United': np.float64(-1.1579048379110184),\n", " 'defence_Southampton': np.float64(-0.7609806462356308),\n", " 'defence_Tottenham': np.float64(-0.9715679787843047),\n", " 'defence_Watford': np.float64(-0.6656257049737819),\n", " 'defence_West Ham': np.float64(-0.7077751518777993),\n", " 'defence_Wolves': np.float64(-1.148290961379967),\n", " 'home_advantage': np.float64(0.23856467457373232),\n", " 'rho': np.float64(-0.07846937040455315)}" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf.get_params()" ] }, { "cell_type": "markdown", "id": "43bb1f12-7010-421b-bf93-bb8e1dba2df6", "metadata": {}, "source": [ "## Predict Match Outcomes" ] }, { "cell_type": "code", "execution_count": 8, "id": "3a047b77-707d-46b6-bcf8-57f3356efee3", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "Module: Penaltyblog\n", "\n", "Class: FootballProbabilityGrid\n", "\n", "Home Goal Expectation: [1.8729287]\n", "Away Goal Expectation: [0.79188351]\n", "\n", "Home Win: 0.6215177796020613\n", "Draw: 0.23427193067485133\n", "Away Win: 0.14421028809547223" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs = clf.predict(\"Liverpool\", \"Wolves\")\n", "probs" ] }, { "cell_type": "markdown", "id": "2a5274e7-d13e-455b-8e77-a6f51ba6f830", "metadata": {}, "source": [ "### 1x2 Probabilities" ] }, { "cell_type": "code", "execution_count": 9, "id": "cc1d6199-c35e-4ea3-bf82-a89c31a7277d", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "[np.float64(0.6215177796020613),\n", " np.float64(0.23427193067485133),\n", " np.float64(0.14421028809547223)]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.home_draw_away" ] }, { "cell_type": "code", "execution_count": 10, "id": "eef96983-d83d-4c39-bd49-47cb4a704ab4", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.6215177796020613)" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.home_win" ] }, { "cell_type": "code", "execution_count": 11, "id": "e08561b2-07ed-47b3-89d7-14c0a05cf854", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.23427193067485133)" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.draw" ] }, { "cell_type": "code", "execution_count": 12, "id": "594e21a7-9a75-49a3-b3e8-50fa4bd8ac51", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.14421028809547223)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.away_win" ] }, { "cell_type": "markdown", "id": "9996be1b-acf8-4305-9bf0-6e4832505d47", "metadata": {}, "source": [ "### Probablity of Total Goals >1.5" ] }, { "cell_type": "code", "execution_count": 13, "id": "8da5ea91-ff28-4c6d-b6bf-0d5ef417da2b", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.7529851084800863)" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.total_goals(\"over\", 1.5)" ] }, { "cell_type": "markdown", "id": "5a0876d3-9d69-4b63-ae8a-d2b3b8f40aa6", "metadata": {}, "source": [ "### Probability of Asian Handicap 1.5" ] }, { "cell_type": "code", "execution_count": 14, "id": "280e7570-5010-4b39-8104-71ca27e4005a", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.37547110035717224)" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.asian_handicap(\"home\", 1.5)" ] }, { "cell_type": "markdown", "id": "f1205e38-8afc-45fc-ba5f-59292aad9e21", "metadata": {}, "source": [ "## Probability of both teams scoring" ] }, { "cell_type": "code", "execution_count": 15, "id": "1b63af09-9383-4c5a-ae1c-dadb1a57193a", "metadata": { "tags": [] }, "outputs": [ { "data": { "text/plain": [ "np.float64(0.4710502787522432)" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probs.both_teams_to_score" ] } ], "metadata": { "kernelspec": { "display_name": "venv", "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": "3.13.1" } }, "nbformat": 4, "nbformat_minor": 5 }