{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#change this cell to change season and player name\n",
"season = '2005/2006'\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",
"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 = \"\"\"C:\\\\Users\\\\koushik.r\\\\Documents\\\\open-data-master\\\\\\\\data\\\\events\\\\\"\"\" #location for play by play events\n",
"for root, dirs, files in os.walk(r'C:\\Users\\koushik.r\\Documents\\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 = 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')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"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))\n"
]
},
{
"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",
" | 2791 | \n",
" [81.9, 77.4] | \n",
" [85.6, 66.6] | \n",
" 11.416217 | \n",
"
\n",
" \n",
" | 3160 | \n",
" [78.7, 7.3] | \n",
" [115.6, 22.8] | \n",
" 40.023243 | \n",
"
\n",
" \n",
" | 3765 | \n",
" [45.5, 4.5] | \n",
" [48.2, 6.4] | \n",
" 3.301515 | \n",
"
\n",
" \n",
" | 4811 | \n",
" [43.1, 40.0] | \n",
" [50.3, 28.4] | \n",
" 13.652839 | \n",
"
\n",
" \n",
" | 5012 | \n",
" [77.0, 65.6] | \n",
" [97.8, 53.3] | \n",
" 24.164644 | \n",
"
\n",
" \n",
"
\n",
"