abstract_data_project.py 文件源码

def to_xls(self, module_name, file_name):
        '''
        Takes the file specified by module and file names and writes an xls in 
        the same directory with the same name (changing the file extension).

        Columns of the original file will be written in the first sheet.
        Columns containing "__" will be written the second sheet

        Use for download only!

        INPUT:
            - module_name:
            - file_name:
        '''
        raise DeprecationWarning('Excel download currently not supported due'\
                                 'to potential memory issues with large files')

        file_path = self.path_to(module_name, file_name)

        assert file_name[-4:] == '.csv'
        new_file_name = file_name[:-4] + '.xlsx'
        new_file_path = self.path_to(module_name, new_file_name)

        tab = pd.read_csv(file_path, encoding='utf-8', dtype=str)


        columns_og = [x for x in tab.columns if '__' not in x]
        columns_new = [x for x in tab.columns if '__' in x]

        writer = pd.ExcelWriter(new_file_path)
        tab[columns_og].to_excel(writer, 'original_file', index=False)
        tab[columns_new].to_excel(writer, 'normalization', index=False)
        writer.save()        
        return new_file_name