Preprocess.py 文件源码

def __SplitData(cls, InputDir, OutputDir, mode):
        """"""
        if(mode == 'train'):
            InputFileData = '%s/train.pkl' % InputDir
        else:
            InputFileData = '%s/test.pkl' % InputDir

        InputFileFeatMap = '%s/featmap.pkl' % InputDir

        ## load
        with open(InputFileData, 'rb') as i_file:
            df_data = pickle.load(i_file)
        i_file.close()
        with open(InputFileFeatMap, 'rb') as i_file:
            d_feat = pickle.load(i_file)
        i_file.close()

        if (os.path.exists(OutputDir) == False):
            os.makedirs(OutputDir)
        with open('%s/featmap.pkl' % OutputDir, 'wb') as o_file:
            pickle.dump(d_feat, o_file, -1)
        o_file.close()

        ## output into individual pkl files
        for i in range(12):
            month = i + 1
            df_MonthData = df_data[(df_data['transactiondate'].dt.month == month)]
            with open('%s/%s.pkl'% (OutputDir, month), 'wb') as o_file:
                pickle.dump(df_MonthData, o_file, -1)
            o_file.close()

        return

    ## launch single task