validate constant and invert params

Author: rwedge

rdt/transformers/numerical.py

@@ -668,12 +668,19 @@ def __init__(
         self,
         missing_value_replacement='mean',
         missing_value_generation='random',
-        constant: float = 0,
+        constant: float = 0.0,
         invert: bool = False,
         learn_rounding_scheme: bool = False,
     ):
-        self.constant = constant
-        self.invert = invert
+        if isinstance(constant, float):
+            self.constant = constant
+        else:
+            raise ValueError('The constant parameter must be a float.')
+        if isinstance(invert, bool):
+            self.invert = invert
+        else:
+            raise ValueError('The invert parameter must be a bool.')
+
         super().__init__(
             missing_value_replacement=missing_value_replacement,
             missing_value_generation=missing_value_generation,

tests/integration/test_transformers.py

@@ -26,7 +26,7 @@
     'FloatFormatter': {'missing_value_generation': 'from_column'},
     'GaussianNormalizer': {'missing_value_generation': 'from_column'},
     'ClusterBasedNormalizer': {'missing_value_generation': 'from_column'},
-    'LogScaler': {'constant': INT64_MIN, 'missing_value_generation': 'from_column'},
+    'LogScaler': {'constant': float(INT64_MIN), 'missing_value_generation': 'from_column'},
 }
 
 # Mapping of rdt sdtype to dtype

tests/integration/transformers/test_numerical.py

@@ -608,7 +608,7 @@ def test_missing_value_generation_random(self):
             missing_value_generation='random',
             missing_value_replacement='mode',
             invert=True,
-            constant=3,
+            constant=3.0,
         )
         expected = pd.DataFrame({'test': [np.nan, 1.5, 1.5, 1.5]})
 

tests/unit/transformers/test_numerical.py

@@ -1888,6 +1888,14 @@ def test___init__constant(self):
         assert ls_set.constant == 2.5
         assert ls_default.constant == 0.0
 
+    def test__init__validates_constant(self):
+        """Test __init__ validates constat parameter."""
+        # Setup
+        message = 'The constant parameter must be a float.'
+        # Run and Assert
+        with pytest.raises(ValueError, match=message):
+            LogScaler(constant=2)
+
     def test___init__invert(self):
         """Test invert parameter is set as an attribute."""
         # Setup
@@ -1898,6 +1906,14 @@ def test___init__invert(self):
         assert ls_set.invert
         assert not ls_default.invert
 
+    def test__init__validates_invert(self):
+        """Test __init__ validates constat parameter."""
+        # Setup
+        message = 'The invert parameter must be a bool.'
+        # Run and Assert
+        with pytest.raises(ValueError, match=message):
+            LogScaler(invert=2)
+
     def test__validate_data(self):
         """Test the ``_validate_data`` method"""
         # Setup
@@ -1987,7 +2003,7 @@ def test__transform(self):
     def test__transform_invert(self):
         """Test the ``_transform`` method with ``invert=True``"""
         # Setup
-        ls = LogScaler(constant=3, invert=True, missing_value_replacement='from_column')
+        ls = LogScaler(constant=3.0, invert=True, missing_value_replacement='from_column')
         ls._validate_data = Mock()
         ls.null_transformer = NullTransformer(
             missing_value_replacement='mean', missing_value_generation='from_column'
@@ -2027,7 +2043,7 @@ def test__transform_null_values(self):
     def test__transform_null_values_invert(self):
         """Test the ``_transform`` method with ``invert=True``"""
         # Setup
-        ls = LogScaler(constant=3, invert=True, missing_value_replacement='from_column')
+        ls = LogScaler(constant=3.0, invert=True, missing_value_replacement='from_column')
         ls._validate_data = Mock()
         ls.null_transformer = NullTransformer(
             missing_value_replacement='mean', missing_value_generation='from_column'
@@ -2117,7 +2133,7 @@ def test__reverse_transform_invert(self):
             [0, 0, 1.0],
         ]).T
         expected = pd.Series([0.1, 1.0, np.nan])
-        ls = LogScaler(constant=3, invert=True)
+        ls = LogScaler(constant=3.0, invert=True)
         ls.null_transformer = NullTransformer(
             missing_value_replacement='mean',
             missing_value_generation='from_column',
@@ -2158,7 +2174,7 @@ def test__reverse_transform_invert_missing_value_generation(self):
         # Setup
         data = np.array([1.06471, 0.69315, 0])
         expected = pd.Series([0.1, 1.0, 2.0])
-        ls = LogScaler(constant=3, invert=True)
+        ls = LogScaler(constant=3.0, invert=True)
         ls.null_transformer = NullTransformer(None, missing_value_generation='random')
 
         # Run