{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#change this cell to change season and player name\n",
"season = '2009/2010'\n",
"ssn = '0506'\n",
"length = int(20)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done\n"
]
}
],
"source": [
"import os\n",
"import json\n",
"import codecs\n",
"import pandas as pd\n",
"import codecs\n",
"import StatsbombPitch as sb\n",
"main_df = pd.DataFrame(data=None)\n",
"path_match = \"/home/kirugulige/Documents/Football-Analytics/open-data-master/data/events/\" #location for play by play events\n",
"for root, dirs, files in os.walk('/home/kirugulige/Documents/Football-Analytics/open-data-master/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 = pd.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 = pd.json_normalize(df_match,sep=\"_\") \n",
" \n",
" main_df = main_df.append(df_match2,ignore_index=True,sort=False) \n",
"print('Done')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"#change player_id to get different player 5503 = Messi\n",
"Player = main_df.query('player_id == 5503 & type_id ==43 & play_pattern_id ==1 & duration >= 1.50')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"player_name = Player.player_name.iloc[0]\n",
"#df[['a','b']]\n",
"Player = Player [['location','carry_end_location']]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from math import sqrt\n",
"distance= []\n",
"for i in range(len(Player)):\n",
" distance.append(sqrt((Player.iloc[i]['carry_end_location'][0] - Player.iloc[i]['location'][0])**2 + ((Player.iloc[i]['carry_end_location'][1] - Player.iloc[i]['location'][1])**2)))\n",
" #using distance formula above (sqrt((x2-x1)^2 + (y2-y1)^2))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"Player['dribble_distance'] = distance"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" location | \n",
" carry_end_location | \n",
" dribble_distance | \n",
"
\n",
" \n",
" \n",
" \n",
" | 109 | \n",
" [64.4, 78.2] | \n",
" [64.4, 73.7] | \n",
" 4.500000 | \n",
"
\n",
" \n",
" | 800 | \n",
" [53.3, 25.5] | \n",
" [54.4, 27.9] | \n",
" 2.640076 | \n",
"
\n",
" \n",
" | 1000 | \n",
" [75.5, 58.8] | \n",
" [71.0, 69.7] | \n",
" 11.792370 | \n",
"
\n",
" \n",
" | 1015 | \n",
" [94.6, 65.1] | \n",
" [89.9, 58.0] | \n",
" 8.514693 | \n",
"
\n",
" \n",
" | 1417 | \n",
" [67.0, 37.0] | \n",
" [85.8, 21.6] | \n",
" 24.302263 | \n",
"
\n",
" \n",
"
\n",
"