f1_data.py 文件源码

def clean_data(self):
        # load qualif and race data
        df_qual = self.load_qualif_data()
        df_races = self.load_results_data()
        # remove Japan as no data for 2015 race
        df_qual = self.del_japan15(df_qual)
        df_races = self.del_japan15(df_races)
        # create unique id
        df_qual = self.unique_id(df_qual)
        df_races = self.unique_id(df_races)
        # merge the results
        df_out = df_races.merge(
            df_qual, on='id_', how='inner', suffixes=('', '_qual'))
        df_out = df_out[pd.isnull(df_out.q_min) == False]
        print df_out.shape
        return df_out.reset_index(drop=1), df_races.reset_index(drop=1), df_qual.reset_index(drop=1)

    # load the data