preparedata.py 文件源码

def __do_one_hot_encodings(self):
        df_train, cv = 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()]
        enc = OneHotEncoder(sparse=False)
        cross_feature_dict = self.__get_label_encode_dict()
        to_be_encoded = []
        for _, new_feature_name in cross_feature_dict.iteritems():
            to_be_encoded.append(new_feature_name)
        #fix all data source
        to_be_stacked_df = pd.concat([df_train[to_be_encoded], df_testset1[to_be_encoded], df_testset2[to_be_encoded]], axis = 0)
        enc.fit(to_be_stacked_df)

        enc, to_be_encoded = self.__filter_too_big_onehot_encoding(enc, to_be_encoded, df_train, df_testset1, df_testset2)
        # transform on seprate data source
        self.res_data_dict[g_singletonDataFilePath.getTrainDir()] = self.__do_one_hot_encoding(df_train, enc, to_be_encoded),cv
        self.res_data_dict[g_singletonDataFilePath.getTest1Dir()] = self.__do_one_hot_encoding(df_testset1,enc, to_be_encoded)
        self.res_data_dict[g_singletonDataFilePath.getTest2Dir()] = self.__do_one_hot_encoding(df_testset2, enc, to_be_encoded)
        return