ENH Avoid calling _encode_check_unknown() twice in BaseEncoder.transform (scikit-learn#13810)

Author: NicolasHug

sklearn/preprocessing/_encoders.py

@@ -134,7 +134,10 @@ def _transform(self, X, handle_unknown='error'):
  Xi = Xi.copy()
 
  Xi[~valid_mask] = self.categories_[i][0]
- _, encoded = _encode(Xi, self.categories_[i], encode=True)
+ # We use check_unknown=False, since _encode_check_unknown was
+ # already called above.
+ _, encoded = _encode(Xi, self.categories_[i], encode=True,
+ check_unknown=False)
  X_int[:, i] = encoded
 
  return X_int, X_mask

sklearn/preprocessing/label.py

@@ -33,7 +33,7 @@
 ]
 
 
-def _encode_numpy(values, uniques=None, encode=False):
+def _encode_numpy(values, uniques=None, encode=False, check_unknown=True):
  # only used in _encode below, see docstring there for details
  if uniques is None:
  if encode:
@@ -43,10 +43,11 @@ def _encode_numpy(values, uniques=None, encode=False):
  # unique sorts
  return np.unique(values)
  if encode:
- diff = _encode_check_unknown(values, uniques)
- if diff:
- raise ValueError("y contains previously unseen labels: %s"
- % str(diff))
+ if check_unknown:
+ diff = _encode_check_unknown(values, uniques)
+ if diff:
+ raise ValueError("y contains previously unseen labels: %s"
+ % str(diff))
  encoded = np.searchsorted(uniques, values)
  return uniques, encoded
  else:
@@ -70,7 +71,7 @@ def _encode_python(values, uniques=None, encode=False):
  return uniques
 
 
-def _encode(values, uniques=None, encode=False):
+def _encode(values, uniques=None, encode=False, check_unknown=True):
  """Helper function to factorize (find uniques) and encode values.
 
  Uses pure python method for object dtype, and numpy method for
@@ -90,6 +91,12 @@ def _encode(values, uniques=None, encode=False):
  already have been determined in fit).
  encode : bool, default False
  If True, also encode the values into integer codes based on `uniques`.
+ check_unknown : bool, default True
+ If True, check for values in ``values`` that are not in ``unique``
+ and raise an error. This is ignored for object dtype, and treated as
+ True in this case. This parameter is useful for
+ _BaseEncoder._transform() to avoid calling _encode_check_unknown()
+ twice.
 
  Returns
  -------
@@ -107,7 +114,8 @@ def _encode(values, uniques=None, encode=False):
  raise TypeError("argument must be a string or number")
  return res
  else:
- return _encode_numpy(values, uniques, encode)
+ return _encode_numpy(values, uniques, encode,
+ check_unknown=check_unknown)
 
 
 def _encode_check_unknown(values, uniques, return_mask=False):

sklearn/preprocessing/tests/test_label.py

@@ -605,3 +605,24 @@ def test_encode_util(values, expected):
  assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
  _, encoded = _encode(values, uniques, encode=True)
  assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
+
+
+def test_encode_check_unknown():
+ # test for the check_unknown parameter of _encode()
+ uniques = np.array([1, 2, 3])
+ values = np.array([1, 2, 3, 4])
+
+ # Default is True, raise error
+ with pytest.raises(ValueError,
+ match='y contains previously unseen labels'):
+ _encode(values, uniques, encode=True, check_unknown=True)
+
+ # dont raise error if False
+ _encode(values, uniques, encode=True, check_unknown=False)
+
+ # parameter is ignored for object dtype
+ uniques = np.array(['a', 'b', 'c'], dtype=object)
+ values = np.array(['a', 'b', 'c', 'd'], dtype=object)
+ with pytest.raises(ValueError,
+ match='y contains previously unseen labels'):
+ _encode(values, uniques, encode=True, check_unknown=False)