add assert to catch bad vocab. See #27

exabiome · Mar 1, 2021 · 343f419 · 343f419
1 parent 0ff57db
commit 343f419
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/src/exabiome/gtdb/prepare_data.py b/src/exabiome/gtdb/prepare_data.py
@@ -304,6 +304,8 @@ def func(row):
                 skbio_cls = DNA
 
             vocab = np.array(list(vocab_it.characters()))
+            if not args.protein:
+                np.assert_array_equal(vocab, list('ACYWSKDVNTGRWSMHBN'))
 
             sequence = list()
             names = list()