cast to str, then fill with 'NA'

tedil · Oliver Stolpe · commit f8509f454ff3 · 2025-03-11T15:03:38.000+01:00
diff --git a/rules/work/genes/scripts/gnomad_constraints_v4_to_tsv.py b/rules/work/genes/scripts/gnomad_constraints_v4_to_tsv.py
@@ -57,6 +57,8 @@ def main(
         .with_columns(pl.lit(None).alias(col) for col in additional_columns)
         .join(ensembl_xlink, on=["ensembl_transcript_id"])
         .select(columns_dst)
+        .with_columns(pl.exclude(pl.String).cast(str))
+        .fill_null("NA")
     )
     df.write_csv(output_tsv_path, separator="\t")
     shell(f"md5sum {output_tsv_path} > {output_tsv_md5_path}")

Original file line number	Diff line number	Diff line change
`@@ -57,6 +57,8 @@ def main(`
`57`	`57`	`.with_columns(pl.lit(None).alias(col) for col in additional_columns)`
`58`	`58`	`.join(ensembl_xlink, on=["ensembl_transcript_id"])`
`59`	`59`	`.select(columns_dst)`
	`60`	`+ .with_columns(pl.exclude(pl.String).cast(str))`
	`61`	`+ .fill_null("NA")`
`60`	`62`	`)`
`61`	`63`	`df.write_csv(output_tsv_path, separator="\t")`
`62`	`64`	`shell(f"md5sum {output_tsv_path} > {output_tsv_md5_path}")`