INNER CODE UNIT · Python

part_data

BigDataBiology/SemiBin · SemiBin/main.py:1074

            part_data = (part_data_split_values[::2] + part_data_split_values[1::2]) / 2
            columns = [f'{abun}' for abun in args.abundances]
            part_data = pd.DataFrame(part_data, index=data_index_name, columns=columns)
            part_data.to_csv(os.path.join(
                output_path, 'data_cov.csv'))

            sample_contig_fasta = os.path.join(
                args.output, f'samples/{sample}.fa')
            kmer_whole = generate_kmer_features_from_fasta(
                sample_contig_fasta, binning_threshold[sample], 4)
            kmer_split = generate_kmer_features_from_fasta(
                sample_contig_fasta, 1000, 4, split=True, split_threshold=must_link_threshold)
            data = pd.merge(kmer_whole, part_data, how='inner', on=None,
                            left_index=True, right_index=True, sort=False)
            data_split = pd.merge(kmer_split, part_data_split, how='inner', on=None,
                                  left_index=True, right_index=True, sort=False)

            with atomic_write(os.path.join(output_path, 'data.csv'), overwrite=True) as ofile:

View source record →