{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Exporting event data to a dataframe"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup\n",
"Start by loading some event data using the Kloppy module. For the sake of this demonstration, we will use Statsbomb Open Event Data."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/cw/dtaijupiter/NoCsBack/dtai/pieterr/Projects/kloppy/kloppy/_providers/statsbomb.py:83: UserWarning: \n",
"\n",
"You are about to use StatsBomb public data.\n",
"By using this data, you are agreeing to the user agreement. \n",
"The user agreement can be found here: https://github.com/statsbomb/open-data/blob/master/LICENSE.pdf\n",
"\n",
" warnings.warn(\n"
]
}
],
"source": [
"from kloppy import statsbomb\n",
"\n",
"# Load Statsbomb open dataset\n",
"dataset = statsbomb.load_open_data(\n",
" match_id=15946,\n",
" # Optional arguments\n",
" coordinates=\"statsbomb\",\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Test if the loading worked by printing the home and away teams."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Barcelona vs Deportivo Alavés'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Get teams\n",
"home_team, away_team = dataset.metadata.teams\n",
"f\"{home_team} vs {away_team}\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Filter the `shot` events from the dataset. "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Only keep shots\n",
"shots = dataset.filter(\"shot\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Convert to Polars DataFrame\n",
"Parameters:\n",
"\n",
"- `player_id`: Includes the player’s unique identifier.\n",
"\n",
"- Lambda function: Extracts `player_name` and `is_goal` status from each shot event.\n",
" - `player_name`: Converts the player object to a string.\n",
" - `is_goal`: Retrieves whether the shot resulted in a goal (True or False).\n",
"\n",
"- `coordinates_*`: Includes all coordinate-related fields in the dataset.\n",
"\n",
"- `prev_pass_player`: Captures the player who made the pass before the shot.\n",
"\n",
"- `engine=\"polars\"`: Specifies the use of the Polars library for DataFrame processing. Alternatively, using `engine=\"pandas\"` would convert the dataset into a Pandas DataFrame. "
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><style>\n",
".dataframe > thead > tr,\n",
".dataframe > tbody > tr {\n",
" text-align: right;\n",
" white-space: pre-wrap;\n",
"}\n",
"</style>\n",
"<small>shape: (28, 6)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>player_id</th><th>player_name</th><th>is_goal</th><th>coordinates_x</th><th>coordinates_y</th><th>prev_pass_player</th></tr><tr><td>str</td><td>str</td><td>bool</td><td>f64</td><td>f64</td><td>str</td></tr></thead><tbody><tr><td>"5503"</td><td>"Lionel Andrés Messi Cuccittini"</td><td>false</td><td>111.45</td><td>52.85</td><td>"Ivan Rakitić"</td></tr><tr><td>"5211"</td><td>"Jordi Alba Ramos"</td><td>false</td><td>113.85</td><td>26.35</td><td>"Lionel Andrés Messi Cuccittini"</td></tr><tr><td>"5503"</td><td>"Lionel Andrés Messi Cuccittini"</td><td>false</td><td>93.65</td><td>34.65</td><td>"Rubén Duarte Sánchez"</td></tr><tr><td>"6613"</td><td>"Rubén Sobrino Pozuelo"</td><td>false</td><td>109.15</td><td>39.05</td><td>"Manuel Alejandro García Sánche…</td></tr><tr><td>"5246"</td><td>"Luis Alberto Suárez Díaz"</td><td>false</td><td>107.75</td><td>24.65</td><td>"Ousmane Dembélé"</td></tr><tr><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td></tr><tr><td>"6935"</td><td>"Adrián Marín Gómez"</td><td>false</td><td>114.45</td><td>32.75</td><td>"Ibai Gómez Pérez"</td></tr><tr><td>"3501"</td><td>"Philippe Coutinho Correia"</td><td>false</td><td>113.15</td><td>31.35</td><td>"Lionel Andrés Messi Cuccittini"</td></tr><tr><td>"3501"</td><td>"Philippe Coutinho Correia"</td><td>true</td><td>105.25</td><td>33.35</td><td>"Arthur Henrique Ramos de Olive…</td></tr><tr><td>"5503"</td><td>"Lionel Andrés Messi Cuccittini"</td><td>false</td><td>106.55</td><td>46.75</td><td>"Sergi Roberto Carnicer"</td></tr><tr><td>"5503"</td><td>"Lionel Andrés Messi Cuccittini"</td><td>true</td><td>111.45</td><td>36.15</td><td>"Luis Alberto Suárez Díaz"</td></tr></tbody></table></div>"
],
"text/plain": [
"shape: (28, 6)\n",
"┌───────────┬──────────────────────┬─────────┬───────────────┬───────────────┬─────────────────────┐\n",
"│ player_id ┆ player_name ┆ is_goal ┆ coordinates_x ┆ coordinates_y ┆ prev_pass_player │\n",
"│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ bool ┆ f64 ┆ f64 ┆ str │\n",
"╞═══════════╪══════════════════════╪═════════╪═══════════════╪═══════════════╪═════════════════════╡\n",
"│ 5503 ┆ Lionel Andrés Messi ┆ false ┆ 111.45 ┆ 52.85 ┆ Ivan Rakitić │\n",
"│ ┆ Cuccittini ┆ ┆ ┆ ┆ │\n",
"│ 5211 ┆ Jordi Alba Ramos ┆ false ┆ 113.85 ┆ 26.35 ┆ Lionel Andrés Messi │\n",
"│ ┆ ┆ ┆ ┆ ┆ Cuccittini │\n",
"│ 5503 ┆ Lionel Andrés Messi ┆ false ┆ 93.65 ┆ 34.65 ┆ Rubén Duarte │\n",
"│ ┆ Cuccittini ┆ ┆ ┆ ┆ Sánchez │\n",
"│ 6613 ┆ Rubén Sobrino ┆ false ┆ 109.15 ┆ 39.05 ┆ Manuel Alejandro │\n",
"│ ┆ Pozuelo ┆ ┆ ┆ ┆ García Sánche… │\n",
"│ 5246 ┆ Luis Alberto Suárez ┆ false ┆ 107.75 ┆ 24.65 ┆ Ousmane Dembélé │\n",
"│ ┆ Díaz ┆ ┆ ┆ ┆ │\n",
"│ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n",
"│ 6935 ┆ Adrián Marín Gómez ┆ false ┆ 114.45 ┆ 32.75 ┆ Ibai Gómez Pérez │\n",
"│ 3501 ┆ Philippe Coutinho ┆ false ┆ 113.15 ┆ 31.35 ┆ Lionel Andrés Messi │\n",
"│ ┆ Correia ┆ ┆ ┆ ┆ Cuccittini │\n",
"│ 3501 ┆ Philippe Coutinho ┆ true ┆ 105.25 ┆ 33.35 ┆ Arthur Henrique │\n",
"│ ┆ Correia ┆ ┆ ┆ ┆ Ramos de Olive… │\n",
"│ 5503 ┆ Lionel Andrés Messi ┆ false ┆ 106.55 ┆ 46.75 ┆ Sergi Roberto │\n",
"│ ┆ Cuccittini ┆ ┆ ┆ ┆ Carnicer │\n",
"│ 5503 ┆ Lionel Andrés Messi ┆ true ┆ 111.45 ┆ 36.15 ┆ Luis Alberto Suárez │\n",
"│ ┆ Cuccittini ┆ ┆ ┆ ┆ Díaz │\n",
"└───────────┴──────────────────────┴─────────┴───────────────┴───────────────┴─────────────────────┘"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Convert Kloppy dataset to Polars DataFrame\n",
"shots.to_df(\n",
" \"player_id\",\n",
" lambda event: {\n",
" \"player_name\": str(event.player),\n",
" \"is_goal\": event.result.is_success,\n",
" },\n",
" \"coordinates_*\",\n",
" prev_pass_player=lambda event: str(event.prev(\"pass\").player),\n",
" engine=\"polars\",\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Filter using lambda functions\n",
"You can also use lambda functions to apply filtering. For eg. this snippet demonstrates how to filter events using a lambda function to extract actions performed by left center-backs (LCBs) and convert them into a Polars DataFrame."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><style>\n",
".dataframe > thead > tr,\n",
".dataframe > tbody > tr {\n",
" text-align: right;\n",
" white-space: pre-wrap;\n",
"}\n",
"</style>\n",
"<small>shape: (252, 5)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>player_id</th><th>player_name</th><th>event_name</th><th>coordinates_x</th><th>coordinates_y</th></tr><tr><td>str</td><td>str</td><td>str</td><td>f64</td><td>f64</td></tr></thead><tbody><tr><td>"6855"</td><td>"Guillermo Alfonso Maripán Loay…</td><td>"Ball Receipt*"</td><td>33.75</td><td>27.95</td></tr><tr><td>"6855"</td><td>"Guillermo Alfonso Maripán Loay…</td><td>"carry"</td><td>33.75</td><td>27.95</td></tr><tr><td>"6855"</td><td>"Guillermo Alfonso Maripán Loay…</td><td>"pass"</td><td>36.75</td><td>27.25</td></tr><tr><td>"5492"</td><td>"Samuel Yves Umtiti"</td><td>"Ball Receipt*"</td><td>36.55</td><td>33.25</td></tr><tr><td>"5492"</td><td>"Samuel Yves Umtiti"</td><td>"carry"</td><td>36.55</td><td>33.25</td></tr><tr><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td></tr><tr><td>"5492"</td><td>"Samuel Yves Umtiti"</td><td>"pass"</td><td>57.95</td><td>21.55</td></tr><tr><td>"6855"</td><td>"Guillermo Alfonso Maripán Loay…</td><td>"pass"</td><td>12.25</td><td>42.05</td></tr><tr><td>"5492"</td><td>"Samuel Yves Umtiti"</td><td>"interception"</td><td>15.65</td><td>39.65</td></tr><tr><td>"5492"</td><td>"Samuel Yves Umtiti"</td><td>"pass"</td><td>15.65</td><td>39.65</td></tr><tr><td>"6855"</td><td>"Guillermo Alfonso Maripán Loay…</td><td>"pressure"</td><td>15.45</td><td>41.35</td></tr></tbody></table></div>"
],
"text/plain": [
"shape: (252, 5)\n",
"┌───────────┬─────────────────────────────────┬───────────────┬───────────────┬───────────────┐\n",
"│ player_id ┆ player_name ┆ event_name ┆ coordinates_x ┆ coordinates_y │\n",
"│ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str ┆ f64 ┆ f64 │\n",
"╞═══════════╪═════════════════════════════════╪═══════════════╪═══════════════╪═══════════════╡\n",
"│ 6855 ┆ Guillermo Alfonso Maripán Loay… ┆ Ball Receipt* ┆ 33.75 ┆ 27.95 │\n",
"│ 6855 ┆ Guillermo Alfonso Maripán Loay… ┆ carry ┆ 33.75 ┆ 27.95 │\n",
"│ 6855 ┆ Guillermo Alfonso Maripán Loay… ┆ pass ┆ 36.75 ┆ 27.25 │\n",
"│ 5492 ┆ Samuel Yves Umtiti ┆ Ball Receipt* ┆ 36.55 ┆ 33.25 │\n",
"│ 5492 ┆ Samuel Yves Umtiti ┆ carry ┆ 36.55 ┆ 33.25 │\n",
"│ … ┆ … ┆ … ┆ … ┆ … │\n",
"│ 5492 ┆ Samuel Yves Umtiti ┆ pass ┆ 57.95 ┆ 21.55 │\n",
"│ 6855 ┆ Guillermo Alfonso Maripán Loay… ┆ pass ┆ 12.25 ┆ 42.05 │\n",
"│ 5492 ┆ Samuel Yves Umtiti ┆ interception ┆ 15.65 ┆ 39.65 │\n",
"│ 5492 ┆ Samuel Yves Umtiti ┆ pass ┆ 15.65 ┆ 39.65 │\n",
"│ 6855 ┆ Guillermo Alfonso Maripán Loay… ┆ pressure ┆ 15.45 ┆ 41.35 │\n",
"└───────────┴─────────────────────────────────┴───────────────┴───────────────┴───────────────┘"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"left_centerbacks_actions = dataset.filter(\n",
" lambda event: event.player\n",
" and event.player.starting_position\n",
" and str(event.player.starting_position.code) == \"LCB\"\n",
").to_df(\n",
" \"player_id\",\n",
" lambda event: {\"player_name\": str(event.player), \"event_name\": event.event_name},\n",
" \"coordinates_*\",\n",
" engine=\"polars\",\n",
")\n",
"\n",
"left_centerbacks_actions"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "/home/pieterr/Jupiter/Projects/kloppy",
"language": "python",
"name": "kloppy"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}