{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "PassClusters.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyPfMQt+YGiFxDzZsdceN8ls",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "code",
"metadata": {
"id": "8HJxpCQF07Lo",
"colab_type": "code",
"outputId": "71b81ca6-8e11-41ae-bf43-fece6a8d4244",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 153
}
},
"source": [
"!git clone https://github.com/statsbomb/open-data.git"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"Cloning into 'open-data'...\n",
"remote: Enumerating objects: 760, done.\u001b[K\n",
"remote: Counting objects: 100% (760/760), done.\u001b[K\n",
"remote: Compressing objects: 100% (367/367), done.\u001b[K\n",
"remote: Total 9482 (delta 640), reused 504 (delta 384), pack-reused 8722\u001b[K\n",
"Receiving objects: 100% (9482/9482), 991.55 MiB | 26.66 MiB/s, done.\n",
"Resolving deltas: 100% (8387/8387), done.\n",
"Checking out files: 100% (1648/1648), done.\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "j4gtYmw71qLx",
"colab_type": "code",
"colab": {}
},
"source": [
"#5503\n",
"\n",
"#change this cell to change season and player name\n",
"season = '2009/2010'\n",
"ssn = '5503'\n",
"length = int(20)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "A2aofsrG1VvE",
"colab_type": "code",
"outputId": "e142d619-15ae-4a10-f68e-3bbc45dc567e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"import os\n",
"import json\n",
"from pandas.io.json import json_normalize\n",
"import codecs\n",
"import pandas as pd\n",
"import codecs\n",
"main_df = pd.DataFrame(data=None)\n",
"path_match = \"/content/open-data/data/events/\" #location for play by play events\n",
"for root, dirs, files in os.walk(r'/content/open-data/data/matches'):\n",
" for file in files:\n",
" with open(os.path.join(root, file), \"r\") as auto:\n",
" with codecs.open(root + str('/') + file,encoding='utf-8') as data_file:\n",
" data = json.load(data_file)\n",
" df = pd.DataFrame(data=None)\n",
" df = json_normalize(data, sep = \"_\")\n",
" #for x in df.competition_country_name:\n",
" # if x == 'Spain':\n",
" # print(df.match_id)\n",
" for i in range(len(df)):\n",
" if df.iloc[i]['competition_country_name'] == 'Spain' and df.iloc[i]['season_season_name'] == season :\n",
" match_no = df.iloc[i]['match_id'] #gets match with Spain as country\n",
" match_no = str(match_no) # from int to str \n",
" with codecs.open(path_match + match_no + str(r'.json'),encoding=\"utf8\") as event_file: #open the respective file\n",
" df_match = json.load(event_file)\n",
" df_match2 = pd.DataFrame(data=None)\n",
" df_match2 = json_normalize(df_match,sep=\"_\") \n",
" \n",
" main_df = main_df.append(df_match2,ignore_index=True,sort=False) \n",
"print('Done')"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"Done\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "VDmUsMN74fmX",
"colab_type": "code",
"colab": {}
},
"source": [
"messi_df = main_df.query('type_id == 30 & player_id == 5503')"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "MwcFd8lx5dza",
"colab_type": "code",
"colab": {}
},
"source": [
"messi_df = messi_df[['location','pass_end_location','pass_height_name','pass_type_name','pass_body_part_name']]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "z_jbQy5Q5uvW",
"colab_type": "code",
"outputId": "b6361e15-f95a-4b2a-fffc-fc35f3d83549",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
}
},
"source": [
"messi_df.head()"
],
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" location | \n",
" pass_end_location | \n",
" pass_height_name | \n",
" pass_type_name | \n",
" pass_body_part_name | \n",
"
\n",
" \n",
" \n",
" \n",
" | 29 | \n",
" [29.5, 55.8] | \n",
" [33.1, 48.1] | \n",
" Low Pass | \n",
" NaN | \n",
" Left Foot | \n",
"
\n",
" \n",
" | 99 | \n",
" [64.7, 72.8] | \n",
" [57.2, 74.5] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
"
\n",
" \n",
" | 111 | \n",
" [64.4, 73.7] | \n",
" [54.1, 42.1] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
"
\n",
" \n",
" | 140 | \n",
" [80.6, 33.0] | \n",
" [73.3, 43.8] | \n",
" Ground Pass | \n",
" NaN | \n",
" Right Foot | \n",
"
\n",
" \n",
" | 155 | \n",
" [97.9, 46.4] | \n",
" [115.5, 53.8] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "UQsuobid9gd5",
"colab_type": "code",
"colab": {}
},
"source": [
"messi_df[['X','Y']] = pd.DataFrame(messi_df.location.values.tolist(), index= messi_df.index)\n",
"messi_df[['endX','endY']] = pd.DataFrame(messi_df.pass_end_location.values.tolist(), index= messi_df.index)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "OxiCT0hn-W4b",
"colab_type": "code",
"outputId": "376ac331-3689-437c-af90-d553c4086510",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 419
}
},
"source": [
"messi_df"
],
"execution_count": 10,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" location | \n",
" pass_end_location | \n",
" pass_height_name | \n",
" pass_type_name | \n",
" pass_body_part_name | \n",
" X | \n",
" Y | \n",
" endX | \n",
" endY | \n",
"
\n",
" \n",
" \n",
" \n",
" | 29 | \n",
" [29.5, 55.8] | \n",
" [33.1, 48.1] | \n",
" Low Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 29.5 | \n",
" 55.8 | \n",
" 33.1 | \n",
" 48.1 | \n",
"
\n",
" \n",
" | 99 | \n",
" [64.7, 72.8] | \n",
" [57.2, 74.5] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 64.7 | \n",
" 72.8 | \n",
" 57.2 | \n",
" 74.5 | \n",
"
\n",
" \n",
" | 111 | \n",
" [64.4, 73.7] | \n",
" [54.1, 42.1] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 64.4 | \n",
" 73.7 | \n",
" 54.1 | \n",
" 42.1 | \n",
"
\n",
" \n",
" | 140 | \n",
" [80.6, 33.0] | \n",
" [73.3, 43.8] | \n",
" Ground Pass | \n",
" NaN | \n",
" Right Foot | \n",
" 80.6 | \n",
" 33.0 | \n",
" 73.3 | \n",
" 43.8 | \n",
"
\n",
" \n",
" | 155 | \n",
" [97.9, 46.4] | \n",
" [115.5, 53.8] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 97.9 | \n",
" 46.4 | \n",
" 115.5 | \n",
" 53.8 | \n",
"
\n",
" \n",
" | ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
" ... | \n",
"
\n",
" \n",
" | 127962 | \n",
" [69.9, 56.5] | \n",
" [75.1, 73.7] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 69.9 | \n",
" 56.5 | \n",
" 75.1 | \n",
" 73.7 | \n",
"
\n",
" \n",
" | 127969 | \n",
" [85.4, 60.7] | \n",
" [90.3, 62.4] | \n",
" Ground Pass | \n",
" NaN | \n",
" Right Foot | \n",
" 85.4 | \n",
" 60.7 | \n",
" 90.3 | \n",
" 62.4 | \n",
"
\n",
" \n",
" | 128096 | \n",
" [75.3, 47.8] | \n",
" [93.0, 45.7] | \n",
" Ground Pass | \n",
" NaN | \n",
" Right Foot | \n",
" 75.3 | \n",
" 47.8 | \n",
" 93.0 | \n",
" 45.7 | \n",
"
\n",
" \n",
" | 128221 | \n",
" [87.9, 26.6] | \n",
" [81.4, 37.8] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 87.9 | \n",
" 26.6 | \n",
" 81.4 | \n",
" 37.8 | \n",
"
\n",
" \n",
" | 128301 | \n",
" [83.7, 43.2] | \n",
" [91.3, 64.7] | \n",
" Ground Pass | \n",
" NaN | \n",
" Left Foot | \n",
" 83.7 | \n",
" 43.2 | \n",
" 91.3 | \n",
" 64.7 | \n",
"
\n",
" \n",
"
\n",
"
1642 rows × 9 columns
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" X | \n",
" Y | \n",
" endX | \n",
" endY | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 69.526437 | \n",
" 73.794253 | \n",
" 61.916092 | \n",
" 70.040230 | \n",
"
\n",
" \n",
" | 1 | \n",
" 91.892045 | \n",
" 33.001136 | \n",
" 104.770455 | \n",
" 24.712500 | \n",
"
\n",
" \n",
" | 2 | \n",
" 56.681333 | \n",
" 40.832000 | \n",
" 50.676000 | \n",
" 40.288000 | \n",
"
\n",
" \n",
" | 3 | \n",
" 86.620000 | \n",
" 48.557778 | \n",
" 96.874444 | \n",
" 34.186667 | \n",
"
\n",
" \n",
" | 4 | \n",
" 78.813235 | \n",
" 36.172059 | \n",
" 83.302941 | \n",
" 49.801471 | \n",
"
\n",
" \n",
"
\n",
"