n_similarity() in word2vec and doc2vec raises ValueError if an empty list is passed

CHANGELOG.md

@@ -6,6 +6,7 @@ Changes
   - In hdpmodel and dtmmodel
   - NOT BACKWARDS COMPATIBLE!
 * Added random_state parameter to LdaState initializer and check_random_state() (@droudy, #113)
+* `n_similarity()` raises `ValueError` if an empty list is passed to it in word2vec, doc2vec (@droudy, #761)
 
 0.13.1, 2016-06-22
 

gensim/models/doc2vec.py

@@ -492,6 +492,8 @@ def n_similarity(self, ds1, ds2):
         index or string tag. (TODO: Accept vectors of out-of-training-set docs, as if from inference.)
 
         """
+        if not ds1 or not ds2:
+            raise ValueError("Can't compute similarity with an empty list")
         v1 = [self[doc] for doc in ds1]
         v2 = [self[doc] for doc in ds2]
         return dot(matutils.unitvec(array(v1).mean(axis=0)), matutils.unitvec(array(v2).mean(axis=0)))

gensim/models/word2vec.py

@@ -1511,6 +1511,8 @@ def n_similarity(self, ws1, ws2):
           True
 
         """
+        if not ws1 or not ws2:
+            raise ValueError("Can't compute similarity with an empty list")
         v1 = [self[word] for word in ws1]
         v2 = [self[word] for word in ws2]
         return dot(matutils.unitvec(array(v1).mean(axis=0)), matutils.unitvec(array(v2).mean(axis=0)))

gensim/test/test_doc2vec.py

@@ -124,6 +124,13 @@ def test_empty_errors(self):
         # input not empty, but rather completely filtered out
         self.assertRaises(RuntimeError, doc2vec.Doc2Vec, list_corpus, min_count=10000)
 
+    def test_n_similarity(self):
+        corpus = DocsLeeCorpus()
+        model = doc2vec.Doc2Vec(size=100, min_count=2, iter=20)
+        model.build_vocab(corpus)
+        model.train(corpus)
+        self.assertRaises(ValueError, model.n_similarity, ['graph', 'trees'], [])
+
     def test_similarity_unseen_docs(self):
         """Test similarity of out of training sentences"""
         rome_str = ['rome', 'italy']

gensim/test/test_word2vec.py

@@ -349,6 +349,7 @@ def testSimilarities(self):
 
         self.assertTrue(model.n_similarity(['graph', 'trees'], ['trees', 'graph']))
         self.assertTrue(model.n_similarity(['graph'], ['trees']) == model.similarity('graph', 'trees'))
+        self.assertRaises(ValueError, model.n_similarity, ['graph', 'trees'], [])
 
     def testSimilarBy(self):
         """Test word2vec similar_by_word and similar_by_vector."""