🚧 output group size table when using weighted sampling

This makes it easier to inspect the effect of a prefilter rule.
nextstrain · Nov 16, 2024 · ce86db2 · ce86db2
1 parent 90874b3
commit ce86db2
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/workflow/snakemake_rules/main_workflow.smk b/workflow/snakemake_rules/main_workflow.smk
@@ -297,6 +297,8 @@ rule subsample:
     params:
         group_by = _get_specific_subsampling_setting("group_by", optional=True),
         group_by_weights = _get_specific_subsampling_setting("group_by_weights", optional=True),
+        # only set this if using group_by_weights
+        output_group_by_weights = lambda wildcards: f"--output-group-by-sizes results/{wildcards.build_name}/sizes-{wildcards.subsample}.tsv" if _get_subsampling_settings(wildcards).get("group_by_weights", False) else "",
         sequences_per_group = _get_specific_subsampling_setting("seq_per_group", optional=True),
         subsample_max_sequences = _get_specific_subsampling_setting("max_sequences", optional=True),
         sampling_scheme = _get_specific_subsampling_setting("sampling_scheme", optional=True),
@@ -330,6 +332,7 @@ rule subsample:
             {params.sequences_per_group} \
             {params.subsample_max_sequences} \
             {params.sampling_scheme} \
+            {params.output_group_by_weights} \
             --output-strains {output.strains} 2>&1 | tee {log}
         """