Fix return dtype for matutils.unitvec according to input dtype. Fix #1722

gensim/matutils.py

@@ -667,45 +667,51 @@ def ret_log_normalize_vec(vec, axis=1):
 
 def unitvec(vec, norm='l2'):
     """Scale a vector to unit length.
-
     Parameters
     ----------
     vec : {numpy.ndarray, scipy.sparse, list of (int, float)}
         Input vector in any format
     norm : {'l1', 'l2'}, optional
         Normalization that will be used.
-
     Returns
     -------
     {numpy.ndarray, scipy.sparse, list of (int, float)}
         Normalized vector in same format as `vec`.
-
     Notes
     -----
     Zero-vector will be unchanged.
-
     """
     if norm not in ('l1', 'l2'):
         raise ValueError("'%s' is not a supported norm. Currently supported norms are 'l1' and 'l2'." % norm)
+
     if scipy.sparse.issparse(vec):
         vec = vec.tocsr()
         if norm == 'l1':
             veclen = np.sum(np.abs(vec.data))
         if norm == 'l2':
             veclen = np.sqrt(np.sum(vec.data ** 2))
         if veclen > 0.0:
-            return vec / veclen
+            if np.issubdtype(vec.dtype, np.int) == True:
+                vec = vec.astype(np.float)
+                return vec / veclen
+            else:
+                vec /= veclen
+                return vec.astype(vec.dtype)
         else:
             return vec
 
     if isinstance(vec, np.ndarray):
-        vec = np.asarray(vec, dtype=float)
+        vec = np.asarray(vec, dtype=vec.dtype)
         if norm == 'l1':
             veclen = np.sum(np.abs(vec))
         if norm == 'l2':
             veclen = blas_nrm2(vec)
         if veclen > 0.0:
-            return blas_scal(1.0 / veclen, vec)
+            if np.issubdtype(vec.dtype, np.int) == True:
+                vec = vec.astype(np.float)
+                return blas_scal(1.0 / veclen, vec).astype(vec.dtype)
+            else:
+                return blas_scal(1.0 / veclen, vec).astype(vec.dtype)
         else:
             return vec
 

gensim/test_unitvec.py

@@ -0,0 +1,27 @@
+import numpy as np
+from scipy import sparse
+import unittest
+import matutils
+
+class UnitvecTestCase(unittest.TestCase):
+
+	def manual_unitvec(self, vec):
+		self.vec = vec
+		if sparse.issparse(self.vec):
+			vec_sum_of_squares = self.vec.multiply(self.vec)
+			unit = 1. / np.sqrt(vec_sum_of_squares.sum())
+			return self.vec.multiply(unit)
+		elif not sparse.issparse(self.vec):
+			sum_vec_squared = np.sum(self.vec ** 2)
+			self.vec /= np.sqrt(sum_vec_squared)
+			return self.vec
+
+	def test_unitvec(self):
+		input_vector = np.random.uniform(size=(5,)).astype(np.float32)
+		unit_vector = matutils.unitvec(input_vector)
+		self.assertEqual(input_vector.dtype, unit_vector.dtype)
+		self.assertTrue(np.allclose(unit_vector, self.manual_unitvec(input_vector)))
+
+if __name__ == '__main__':
+
+	unittest.main()