data_node_frame.py 文件源码

def make_drop_duplicate(self, _df_csv_read_ori, _drop_duplicate , _label):
        """ Label? ??? ??? ??? ??? ??? Row ??? ????.
        Args:
          params:
            * _preprocessing_type: ['scale', 'minmax_scale', 'robust_scale', 'normalize', 'maxabs_scale']
            * _df_csv_read_ori : pandas dataframe
            * _label
        Returns:
          Preprocessing Dataframe
        """
        if _drop_duplicate == None or _drop_duplicate == 'null' or _drop_duplicate == False:
            logging.info("No Duplicate")
            result_df =  _df_csv_read_ori
        else :
            cell_features = _df_csv_read_ori.columns.tolist()
            cell_features.remove(_label)
            result_df = _df_csv_read_ori.drop_duplicates(cell_features, keep="first")
            logging.info("duplicated row delete {0}".format(len(_df_csv_read_ori.index)-len(result_df.index)))
            temp_duplicate_filename = strftime("%Y-%m-%d-%H:%M:%S", gmtime()) + "_dup.csvbk"
            result_df.to_csv(self.data_src_path + "/backup/" + temp_duplicate_filename)
        return result_df