Fix for when checkm is not run for some bins

dialvarezs · dialvarezs · commit 61c23fe89145 · 2024-12-13T13:23:34.000-03:00
diff --git a/bin/combine_tables.py b/bin/combine_tables.py
@@ -138,7 +138,7 @@ def main(args=None):
         ]
         checkm_results = pd.read_csv(args.binqc_summary, usecols=use_columns, sep="\t")
         checkm_results["Bin Id"] = checkm_results["Bin Id"] + ".fa"
-        if not bins.equals(checkm_results["Bin Id"].sort_values().reset_index(drop=True)):
+        if not set(checkm_results["Bin Id"]).issubset(set(bins)):
             sys.exit("Bins in CheckM summary do not match bins in bin depths summary!")
         results = pd.merge(
             results, checkm_results, left_on="bin", right_on="Bin Id", how="outer"

Original file line number	Diff line number	Diff line change
`@@ -138,7 +138,7 @@ def main(args=None):`
`138`	`138`	`]`
`139`	`139`	`checkm_results = pd.read_csv(args.binqc_summary, usecols=use_columns, sep="\t")`
`140`	`140`	`checkm_results["Bin Id"] = checkm_results["Bin Id"] + ".fa"`
`141`		`- if not bins.equals(checkm_results["Bin Id"].sort_values().reset_index(drop=True)):`
	`141`	`+ if not set(checkm_results["Bin Id"]).issubset(set(bins)):`
`142`	`142`	`sys.exit("Bins in CheckM summary do not match bins in bin depths summary!")`
`143`	`143`	`results = pd.merge(`
`144`	`144`	`results, checkm_results, left_on="bin", right_on="Bin Id", how="outer"`