fix: Tanhscaler nan output for constant feature (#153)

Signed-off-by: Avik Basu <[email protected]>

numalogic/preprocess/transformer.py

@@ -54,7 +54,7 @@ def inverse_transform(self, X) -> ArrayLike:
 
 class TanhScaler(OneToOneFeatureMixin, TransformerMixin):
  r"""
- Tanh Estimator applies tanh normalization to the Z-score,
+ Tanh Estimator applies column-wise tanh normalization to the Z-score,
  and scales the values between 0 and 1.
 
  After scaling, the data has a mean of 0.5.
@@ -63,21 +63,29 @@ class TanhScaler(OneToOneFeatureMixin, TransformerMixin):
  Higher the value, the linear portion of the curve will have a higher slope
  but will reach the asymptote (flatten out) earlier.
 
+ Args:
+ coeff: float value determining the spread of the scores
+ eps: minimum value below which the feature will be treated as constant.
+ In order to avoid division by zero or a very small number,
+ standard deviation will be set as 1 for that feature.
+
  References:
  Nandakumar, Jain, Ross. 2005. Score Normalization in
  Multimodal Biometric Systems, Pattern Recognition 38, 2270-2285.
  https://web.cse.msu.edu/~rossarun/pubs/RossScoreNormalization_PR05.pdf
  """
- __slots__ = ("_coeff", "_std", "_mean")
+ __slots__ = ("_coeff", "_std", "_mean", "_eps")
 
- def __init__(self, coeff: float = 0.2):
+ def __init__(self, coeff: float = 0.2, eps: float = 1e-10):
  self._coeff = coeff
  self._std = None
  self._mean = None
+ self._eps = eps
 
  def fit(self, x: npt.NDArray[float]) -> Self:
  self._mean = np.mean(x, axis=0)
  self._std = np.std(x, axis=0)
+ self._check_if_constant(x)
  return self
 
  def transform(self, x: npt.NDArray[float]) -> npt.NDArray[float]:
@@ -86,3 +94,7 @@ def transform(self, x: npt.NDArray[float]) -> npt.NDArray[float]:
 
  def fit_transform(self, x: npt.NDArray[float], y=None, **_) -> npt.NDArray[float]:
  return self.fit(x).transform(x)
+
+ def _check_if_constant(self, x: npt.NDArray[float]) -> None:
+ delta = np.max(x, axis=0) - np.min(x, axis=0)
+ self._std[delta < self._eps] = 1.0

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "numalogic"
-version = "0.3.6"
+version = "0.3.7"
 description = "Collection of operational Machine Learning models and tools."
 authors = ["Numalogic Developers"]
 packages = [{ include = "numalogic" }]

tests/preprocess/test_transformer.py

@@ -42,6 +42,26 @@ def test_tanh_scaler_2(self):
  assert_array_less(x_scaled, np.ones_like(x_scaled))
  assert_array_less(np.zeros_like(x_scaled), x_scaled)
 
+ def test_tanh_scaler_3(self):
+ x = np.random.randn(5, 3)
+ x[:, 1] = np.zeros(5)
+
+ scaler = TanhScaler()
+
+ x_scaled = scaler.fit_transform(x)
+ self.assertFalse(np.isnan(x_scaled[:, 1]).all())
+ assert_array_less(x_scaled, np.ones_like(x_scaled))
+ assert_array_less(np.zeros_like(x_scaled), x_scaled)
+
+ def test_tanh_scaler_nan(self):
+ x = np.random.randn(5, 3)
+ x[:, 1] = np.zeros(5)
+
+ scaler = TanhScaler(eps=0.0)
+
+ x_scaled = scaler.fit_transform(x)
+ self.assertTrue(np.isnan(x_scaled[:, 1]).all())
+
 
 if __name__ == "__main__":
  unittest.main()