{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df=pd.read_csv('/kaggle/input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MDataFiles_Stage1/MRegularSeasonCompactResults.csv')\ndf_tournaments=pd.read_csv('/kaggle/input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MDataFiles_Stage1/MNCAATourneyCompactResults.csv')\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df=df[(df['Season']>=2013)&(df['Season']<=2015)]\ndf_2015=df_tournaments[df_tournaments['Season']==2015]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"points_pos_team=(df.groupby('WTeamID')['WScore'].sum()-df.groupby('WTeamID')['LScore'].sum())\npoints_neg_team=(df.groupby('LTeamID')['LScore'].sum()-df.groupby('LTeamID')['WScore'].sum())\ndiff_per_game=(points_pos_team+points_neg_team)/(df.groupby('LTeamID')['LScore'].count()+df.groupby('WTeamID')['LScore'].count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"diff_per_game","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"team_in_tournaments=np.unique(list(df_2015['WTeamID'].unique())+list(df_2015['LTeamID'].unique()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dico_proba={'team1_team2':[],'diff_avg_points':[]}\nfor team1 in team_in_tournaments:\n    for team2 in team_in_tournaments:\n        if team1!=team2:\n            dico_proba['team1_team2'].append(str(team1)+'_'+str(team2))\n            dico_proba['diff_avg_points'].append(diff_per_game[team1]-diff_per_game[team2])\ndf_proba=pd.DataFrame(dico_proba)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_proba['proba']=df_proba['diff_avg_points'].rank(pct=True)\ndf_proba['proba2']=(df_proba['diff_avg_points']-df_proba['diff_avg_points'].min())/(df_proba['diff_avg_points'].max()-df_proba['diff_avg_points'].min())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"table_proba=df_proba.set_index('team1_team2')['proba']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_2015['probaWteam']=(df_2015['WTeamID'].apply(lambda x:str(x))+'_'+df_2015['LTeamID'].apply(lambda x:str(x))).apply(lambda x:table_proba[x])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"-df_2015['probaWteam'].apply(lambda x:np.log(x)).mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_2015","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}