Fix for Github issue #979 : (#986)

Issue: WMD Earth mover Distance for sentences that contain a single word return inf Fix: Return float 0.0 when the dictionary size is 1 (both sentences are composed with the same token)
piskvorky · Oct 31, 2016 · 4ee0078 · 4ee0078
1 parent f9a0eab
commit 4ee0078
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
@@ -1399,6 +1399,10 @@ def wmdistance(self, document1, document2):
         dictionary = Dictionary(documents=[document1, document2])
         vocab_len = len(dictionary)
 
+        if vocab_len == 1:
+            # Both documents are composed by a single unique token
+            return 0.0
+
         # Sets for faster look-up.
         docset1 = set(document1)
         docset2 = set(document2)