preparedata.py 文件源码

def __do_label_encoding(self):
        df_train, _ = self.res_data_dict[g_singletonDataFilePath.getTrainDir()]
        df_testset1 = self.res_data_dict[g_singletonDataFilePath.getTest1Dir()]
        df_testset2 = self.res_data_dict[g_singletonDataFilePath.getTest2Dir()]
        le = LabelEncoder()
        cross_feature_dict = self.__get_label_encode_dict()
        for _, new_feature_name in cross_feature_dict.iteritems():
            to_be_stacked = [df_train[new_feature_name], df_testset1[new_feature_name], df_testset2[new_feature_name]]
            le.fit(pd.concat(to_be_stacked, axis=0))
            df_train[new_feature_name] = le.transform(df_train[new_feature_name])
            df_testset1[new_feature_name] = le.transform(df_testset1[new_feature_name])
            df_testset2[new_feature_name] = le.transform(df_testset2[new_feature_name])

        return