helper_functions.py 文件源码

def merge_same_files(sample1_dfs, sample2_dfs, nb_cpu):
    # type: (List[pd.DataFrame], List[pd.DataFrame], int) -> List[pd.DataFrame]

    # if one list is missing a chromosome, we might pair up the wrong dataframes
    # therefore creating dicts beforehand to ensure they are paired up properly
    d1, d2 = ensure_same_chromosomes_in_list(sample1_dfs,
                                             sample2_dfs)

    assert len(d1) == len(d2)

    logging.info("Merging same class data.")
    merged_chromosome_dfs = Parallel(n_jobs=nb_cpu)(delayed(_merge_same_files)(
        d1[chromosome],
        d2[chromosome]) for chromosome in d1.keys())

    return merged_chromosome_dfs