Fix _is_single from Phrases for case when corpus is numpy array (#…

…1987)

* fix _is_single element-wise comparison error

* fix mode

* add test for corpus as numpy array

gensim/models/phrases.py

@@ -118,7 +118,7 @@ def _is_single(obj):
     if isinstance(peek, string_types):
         # It's a document, return the iterator
         return True, obj_iter
-    if temp_iter == obj:
+    if temp_iter is obj:
         # Checking for iterator to the object
         return False, obj_iter
     else:

gensim/test/test_phrases.py

@@ -13,6 +13,8 @@
 
 import six
 
+import numpy as np
+
 from gensim.utils import to_unicode
 from gensim.models.phrases import SentenceAnalyzer, Phrases, Phraser
 from gensim.models.phrases import pseudocorpus, original_scorer
@@ -148,7 +150,7 @@ def gen_sentences(self):
 
 
 class PhrasesCommon:
-    """ Tests that need to be run for both Prases and Phraser classes."""
+    """ Tests that need to be run for both Phrases and Phraser classes."""
 
     def setUp(self):
         self.bigram = Phrases(
@@ -230,6 +232,20 @@ def testBigramConstructionFromGenerator(self):
                 break
         self.assertTrue(bigram1_seen and bigram2_seen)
 
+    def testBigramConstructionFromArray(self):
+        """Test Phrases bigram construction building when corpus is a numpy array"""
+        bigram1_seen = False
+        bigram2_seen = False
+
+        for s in self.bigram[np.array(self.sentences)]:
+            if not bigram1_seen and self.bigram1 in s:
+                bigram1_seen = True
+            if not bigram2_seen and self.bigram2 in s:
+                bigram2_seen = True
+            if bigram1_seen and bigram2_seen:
+                break
+        self.assertTrue(bigram1_seen and bigram2_seen)
+
     def testEncoding(self):
         """Test that both utf8 and unicode input work; output must be unicode."""
         expected = [u'survey', u'user', u'computer', u'system', u'response_time']