699cb4d8ab7365b3a20ddd3de56a2a0ecc8b0046,skgenome/tabio/gff.py,,read_gff,#,26

Before Change

                "str", "str", "str", "str"]
    dframe = pd.read_table(infile, comment="//", header=None, na_filter=False,
                           names=colnames, dtype=dict(zip(colnames, coltypes)))
    return (dframe
            .assign(start=dframe.start - 1,
                    score=dframe.score.replace(".", "nan").astype("float"),
                    gene=dframe.attribute.apply(_parse_name))
            .sort_values(["chromosome", "start", "end"])
            .reset_index(drop=True))


def _parse_name(text, default="-"):
    Extract name from the "attributes" field, if present.

After Change

        else:
            // Default to a set of likely relevant tags
            rx = re.compile(r"(Name|gene_id|gene_name|gene)[= ]"?(\S+?)"?(;|$)")
            matches = dframe["attribute"].str.extractall(rx)
            if len(matches):
                dframe["gene"] = matches.xs(0, level=1)[1]
    if "gene" in dframe.columns:
        dframe["gene"] = dframe["gene"].fillna("-").astype("str")
    else:
        dframe["gene"] = ["-"] * len(dframe)
    return dframe

Instances