fix doc2vec compatibility for word2vec batching

piskvorky · Nov 21, 2015 · d8b4134 · d8b4134
1 parent da0b269
commit d8b4134
Show file tree

Hide file tree

Showing 4 changed files with 2,132 additions and 843 deletions.
diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
@@ -673,8 +673,9 @@ def _do_train_job(self, job, alpha, inits):
             self.docvecs.trained_item(indexed_doctags)
         return tally, self._raw_word_count(job)
 
-    def _raw_word_count(self, items):
-        return sum(len(item.words) for item in items)
+    def _raw_word_count(self, job):
+        """Return the number of words in a given job."""
+        return sum(len(sentence.words) for sentence in job)
 
     def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5):
         """