change unknown and missing

ktmeaton · Jun 23, 2020 · f823a84 · f823a84
1 parent 70d3f75
commit f823a84
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/scripts/format_metadata_Assembly.sh b/scripts/format_metadata_Assembly.sh
@@ -58,3 +58,10 @@ tail -n +2 $project/nextstrain/metadata_nextstrain_split.tsv  | \
 sed -i 's/GCA_000009065.1_ASM906v1_genomic/Reference/g' $project/nextstrain/metadata_nextstrain_split_strain.tsv
 # Standardize biovar nomenclature
 sed -i 's/Mediaevalis/Medievalis/g' $project/nextstrain/metadata_nextstrain_split_strain.tsv
+# Change missing and unknown
+sed 's/missing\|Missing\|unknown\|Unknown/?/g' $project/nextstrain/metadata_nextstrain.tsv
+
+# Cleanup and rename
+rm $project/nextstrain/metadata_nextstrain_split.tsv
+rm $project/nextstrain/metadata_nextstrain.tsv
+mv $project/nextstrain/metadata_nextstrain_split_strain.tsv $project/nextstrain/metadata_nextstrain.tsv