write_gctx.py 文件源码

def write_metadata(hdf5_out, dim, metadata_df, convert_back_to_neg_666):
    """
    Writes either column or row metadata to proper node of gctx out (hdf5) file.

    Input:
        - hdf5_out (h5py): open hdf5 file to write to
        - dim (str; must be "row" or "col"): dimension of metadata to write to 
        - metadata_df (pandas DataFrame): metadata DataFrame to write to file 
        - convert_back_to_neg_666 (bool): Whether to convert numpy.nans back to "-666",
                as per CMap metadata null convention 
    """
    if dim == "col":
        hdf5_out.create_group(col_meta_group_node)
        metadata_node_name = col_meta_group_node
    elif dim == "row":
        hdf5_out.create_group(row_meta_group_node)
        metadata_node_name = row_meta_group_node
    else:
        logger.error("'dim' argument must be either 'row' or 'col'!")

    # write id field to expected node
    hdf5_out.create_dataset(metadata_node_name + "/id", data=[str(x) for x in metadata_df.index])

    metadata_fields = list(metadata_df.columns.copy())

    # if specified, convert numpy.nans in metadata back to -666
    if convert_back_to_neg_666:
        for c in metadata_fields:
            metadata_df[[c]] = metadata_df[[c]].replace([numpy.nan], ["-666"])

    # write metadata columns to their own arrays
    for field in [entry for entry in metadata_fields if entry != "ind"]:
        hdf5_out.create_dataset(metadata_node_name + "/" + field,
                                data=numpy.array(list(metadata_df.loc[:, field])))