In similarity_matrix, process rows in index order when IDFs are the same

piskvorky · Mar 17, 2018 · 6dcb687 · 6dcb687
1 parent db303b2
commit 6dcb687
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/gensim/models/keyedvectors.py b/gensim/models/keyedvectors.py
@@ -497,7 +497,8 @@ def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0,
         else:
             assert max(tfidf.idfs) < matrix_order
             word_indices = [
-                index for index, _ in sorted(tfidf.idfs.items(), key=lambda x: x[1], reverse=True)
+                index for index, _
+                in sorted(tfidf.idfs.items(), key=lambda x: (x[1], -x[0]), reverse=True)
             ]
 
         # Traverse rows.