07d2442c2bfe4521b6e88bb63dc484efac9a53e4,cnvlib/tabio/genepred.py,,read_refflat,#Any#Any#Any#,80

Before Change

            dframe["start"] = dframe["start"].astype("int") - 1
            dframe["end"] = dframe["end"].astype("int")

    for key in ("start_cds", "end_cds", "exon_starts", "exon_ends"):
        del dframe[key]
    // NB: same gene name can appear on alt. contigs
    dframe = (dframe.groupby(by=["chromosome", "strand", "gene"],
                             as_index=False, group_keys=False, sort=False)
              .apply(_merge_overlapping))
    return dframe.reindex()

After Change

    try:
        dframe = pd.read_table(infile,  header=None,
                               names=colnames, usecols=usecols,
                               dtype={c: str for c in cols_shared})
    except (pd.parser.CParserError, csv.Error) as err:
        raise ValueError("Unexpected dataframe contents:\n%s\n%s" %
                            (line, next(infile)))

    // Calculate values for output columns
    if exons:
        // TODO -- pandas trickery; then _merge_overlapping
        // es = dframe["exon_starts"].str.rstrip(",").str.split(",")
        // ee = dframe["exon_ends"].str.rstrip(",").str.split(",")
        // exons = list(zip(es, ee))
        // dframe.apply,applymap,...
        raise NotImplementedError
    else:
        dframe = dframe.sort_values(["chromosome", "start", "end"])
        dframe["start"] -= 1

    // NB: same gene name can appear on alt. contigs
    dframe = (dframe.groupby(by=["chromosome", "strand", "gene"],
                             as_index=False, group_keys=False, sort=False)

Instances