LsiModel: Only log top words that actually exist in the dictionary

CHANGELOG.md

@@ -1,6 +1,10 @@
 Changes
 =======
 
+## Unreleased
+
+- LsiModel: Only log top words that actually exist in the dictionary (PR [#3091](https://github.com/RaRe-Technologies/gensim/pull/3091), [@kmurphy4](https://github.com/kmurphy4))
+
 ## 4.0.1, 2021-04-01
 
 Bugfix release to address issues with Wheels on Windows:

gensim/models/lsimodel.py

@@ -670,7 +670,9 @@ def show_topic(self, topicno, topn=10):
         c = np.asarray(self.projection.u.T[topicno, :]).flatten()
         norm = np.sqrt(np.sum(np.dot(c, c)))
         most = matutils.argsort(np.abs(c), topn, reverse=True)
-        return [(self.id2word[val], 1.0 * c[val] / norm) for val in most]
+
+        # Output only (word, score) pairs for `val`s that are within `self.id2word`.  See #3090 for details.
+        return [(self.id2word[val], 1.0 * c[val] / norm) for val in most if val in self.id2word]
 
     def show_topics(self, num_topics=-1, num_words=10, log=False, formatted=True):
         """Get the most significant topics.

gensim/utils.py

@@ -835,6 +835,9 @@ def __getitem__(self, val):
             return str(val)
         raise ValueError("internal id out of bounds (%s, expected <0..%s))" % (val, self.num_terms))
 
+    def __contains__(self, val):
+        return 0 <= val < self.num_terms
+
     def iteritems(self):
         """Iterate over all keys and values.