INNER CODE UNIT · Python

df

BortonWrightonLabs/DRAM · bin/distill.py:95

    df = df.group_by(fasta_column).agg(pl.exclude(fasta_column).sum())

    df = df.select(pl.exclude(fasta_column)).transpose(
        include_header=True, header_name="gene_id", column_names=df[fasta_column]
    )

    df = genome_summary_frame.collect().join(df, on="gene_id", how="left")

    df = df.drop(OPTIONAL_COLUMNS, strict=False)

    return df


# TODO: add assembly stats like N50, longest contig, total assembled length etc
def make_genome_stats(
    annotations: pl.DataFrame,
    rrna_frame: pl.DataFrame = None,
    trna_frame: pl.DataFrame = None,

View source record →