Reduce memory usage of filter-fasta through usecols

nextstrain · Dec 9, 2022 · 5b2e288 · 5b2e288
1 parent c7dfca1
commit 5b2e288
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/bin/filter-fasta b/bin/filter-fasta
@@ -30,7 +30,7 @@ but missing the input TSV file. This is useful in order to find which sequences
 def main():
     args = parse_args()
 
-    tsv = pd.read_csv(args.input_tsv, sep="\t", low_memory=False)
+    tsv = pd.read_csv(args.input_tsv, sep="\t", usecols=["seqName"], dtype=str)
     tsv_ids = set(tsv['seqName'])
 
     with open(args.input_fasta) as f_input: