Ensures FastText returns consistent dtypes

piskvorky · Oct 24, 2017 · b648db7 · b648db7
1 parent e92b45d
commit b648db7
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/gensim/models/wrappers/fasttext.py b/gensim/models/wrappers/fasttext.py
@@ -90,7 +90,7 @@ def word_vec(self, word, use_norm=False):
         if word in self.vocab:
             return super(FastTextKeyedVectors, self).word_vec(word, use_norm)
         else:
-            word_vec = np.zeros(self.syn0_ngrams.shape[1])
+            word_vec = np.zeros(self.syn0_ngrams.shape[1], dtype=np.float32)
             ngrams = compute_ngrams(word, self.min_n, self.max_n)
             ngrams = [ng for ng in ngrams if ng in self.ngrams]
             if use_norm:

diff --git a/gensim/test/test_fasttext_wrapper.py b/gensim/test/test_fasttext_wrapper.py
@@ -337,6 +337,12 @@ def testHash(self):
         ft_hash = fasttext.ft_hash('word')
         self.assertEqual(ft_hash, 1788406269)
 
+    def testConsistentDtype(self):
+        """Test that the same dtype is returned for "imputed" words as for words in the vocabulary"""
+        present_word = self.test_model['night']
+        missing_word = self.test_model['wordnotpresentinvocabulary']
+        self.assertEqual(present_word.dtype, missing_word.dtype)
+
 
 if __name__ == '__main__':
     logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)