parse_gct.py 文件源码

def assemble_col_metadata(full_df, num_col_metadata, num_row_metadata, num_data_cols):

    # Extract values
    col_metadata_row_inds = range(1, num_col_metadata + 1)
    col_metadata_col_inds = range(num_row_metadata + 1, num_row_metadata + num_data_cols + 1)
    col_metadata = full_df.iloc[col_metadata_row_inds, col_metadata_col_inds]

    # Transpose so that samples are the rows and headers are the columns
    col_metadata = col_metadata.T

    # Create index from the top row of full_df (after the filler block)
    col_metadata.index = full_df.iloc[0, col_metadata_col_inds]

    # Create columns from the first column of full_df (before rids start)
    col_metadata.columns = full_df.iloc[col_metadata_row_inds, 0]

    # Rename the index name and columns name
    col_metadata.index.name = column_index_name
    col_metadata.columns.name = column_header_name

    # Convert metadata to numeric if possible
    col_metadata = col_metadata.apply(lambda x: pd.to_numeric(x, errors="ignore"))

    return col_metadata