1fe319ef49168c2c7c8d10a7c426c1414521d164,cnvlib/tabio/genepred.py,,read_refflat,#Any#Any#Any#,80

Before Change

    dframe = (dframe.groupby(by=["chromosome", "strand", "gene"],
                             as_index=False, group_keys=False, sort=False)
              .apply(_merge_overlapping))
    return dframe


def _merge_overlapping(dframe):
    Merge overlapping regions within a group.

After Change

        raise ValueError("Arguments "cds" and "exons" are mutually exclusive")

    cols_shared = ["gene", "accession", "chromosome", "strand"]
    converters = None
    if exons:
        cols_rest = ["_start_tx", "_end_tx",  // Transcription
                     "_start_cds", "_end_cds",  // Coding region
                     "_exon_count", "exon_starts", "exon_ends"]
        converters = {"exon_starts": _split_commas, "exon_ends": _split_commas}
    elif cds:
        // Use CDS instead of transcription region
        cols_rest = ["_start_tx", "_end_tx",
                     "start", "end",
                     "_exon_count", "_exon_starts", "_exon_ends"]
    else:
        cols_rest = ["start", "end",
                     "_start_cds", "_end_cds",
                     "_exon_count", "_exon_starts", "_exon_ends"]
    colnames = cols_shared + cols_rest
    usecols = [c for c in colnames if not c.startswith("_")]
    // Parse the file contents
    dframe = pd.read_table(infile,  header=None, na_filter=False,
                           names=colnames, usecols=usecols,
                           dtype={c: str for c in cols_shared},
                           converters=converters)

    // Calculate values for output columns
    if exons:
        dframe = pd.DataFrame.from_records(_split_exons(dframe),
                                           columns=cols_shared + ["start", "end"])
        dframe["start"] = dframe["start"].astype("int")
        dframe["end"] = dframe["end"].astype("int")

    return (dframe.assign(start=dframe.start - 1)
            .sort_values(["chromosome", "start", "end"])
            .reset_index(drop=True))


def _split_commas(field):
    return field.rstrip(",").split(",")

Instances