Added vwmodel2ldamodel function

gensim/models/wrappers/ldavowpalwabbit.py

@@ -66,6 +66,7 @@
 import numpy
 
 from gensim import utils, matutils
+from gensim.models.ldamodel import LdaModel
 
 LOG = logging.getLogger(__name__)
 
@@ -559,3 +560,25 @@ def _run_vw_command(cmd):
 def _bit_length(num):
     """Return number of bits needed to encode given number."""
     return len(bin(num).lstrip('-0b'))
+
+def vwmodel2ldamodel(vw_model, iterations=50):
+    """
+    Function to convert vowpal wabbit model to gensim LdaModel. This works by
+    simply copying the training model weights (alpha, beta...) from a trained
+    vwmodel into the gensim model.
+
+    Args:
+    ----
+    vw_model : Trained vowpal wabbit model.
+    iterations : Number of iterations to be used for inference of the new LdaModel.
+
+    Returns:
+    -------
+    model_gensim : LdaModel instance; copied gensim LdaModel.
+    """
+    model_gensim = LdaModel(
+        num_topics=vw_model.num_topics, id2word=vw_model.id2word, chunksize=vw_model.chunksize,
+        passes=vw_model.passes, alpha=vw_model.alpha, eta=vw_model.eta, decay=vw_model.decay,
+        offset=vw_model.offset, iterations=iterations, gamma_threshold=vw_model.gamma_threshold)
+    model_gensim.expElogbeta[:] = vw_model._get_topics()
+    return model_gensim

gensim/test/test_ldavowpalwabbit_wrapper.py

@@ -213,6 +213,18 @@ def test_corpus_to_vw(self):
         result = '\n'.join(ldavowpalwabbit.corpus_to_vw(corpus))
         self.assertEqual(result, expected)
 
+    def testvwmodel2ldamodel(self):
+        """Test copying of VWModel to LdaModel"""
+        if not self.vw_path:
+            return
+        tm1 = LdaVowpalWabbit(vw_path=self.vw_path, corpus=self.corpus, num_topics=2, id2word=self.dictionary)
+        tm2 = ldavowpalwabbit.vwmodel2ldamodel(tm1)
+        for document in self.corpus:
+            self.assertEqual(tm1[document][0], tm2[document][0])
+            self.assertEqual(tm1[document][1], tm2[document][1])
+            logging.debug('%d %d', tm1[document][0], tm2[document][0])
+            logging.debug('%d %d', tm1[document][1], tm2[document][1])
+
 
 if __name__ == '__main__':
     logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)