Fix ValueError when instantiating SparseTermSimilarityMatrix (#2689)

* force python int before calling islice. islice don't accept numpy int

* add test to check islice error

* it makes test to fail

* make sure that islice receives a python int

* fix typo

gensim/similarities/levenshtein.py

@@ -8,7 +8,7 @@
 This module provides a namespace for functions that use the Levenshtein distance.
 """
 
-from itertools import islice
+import itertools
 import logging
 from math import floor
 
@@ -150,4 +150,4 @@ def most_similar(self, t1, topn=10):
             for (similarity, t2) in sorted(similarities, reverse=True)
             if similarity > 0
         )
-        return islice(most_similar, topn)
+        return itertools.islice(most_similar, int(topn))

gensim/test/test_similarities.py

@@ -1231,6 +1231,11 @@ def test_most_similar(self):
         second_similarities = numpy.array([similarity for term, similarity in index.most_similar(u"holiday", topn=10)])
         self.assertTrue(numpy.allclose(first_similarities ** 2.0, second_similarities))
 
+        # check proper integration with SparseTermSimilarityMatrix
+        index = LevenshteinSimilarityIndex(self.dictionary, alpha=1.0, beta=1.0)
+        similarity_matrix = SparseTermSimilarityMatrix(index, dictionary)
+        self.assertTrue(scipy.sparse.issparse(similarity_matrix.matrix))
+
 
 if __name__ == '__main__':
     logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)