Rename imputer classes and add deprecation aliases

feature_engine/imputation/__init__.py

@@ -2,20 +2,23 @@
 The module imputation includes classes to perform missing data imputation
 """
 
-from .arbitrary_number import ArbitraryNumberImputer
+from .arbitrary_number import ArbitraryImputer, ArbitraryNumberImputer
 from .categorical import CategoricalImputer
 from .drop_missing_data import DropMissingData
 from .end_tail import EndTailImputer
-from .mean_median import MeanMedianImputer
-from .missing_indicator import AddMissingIndicator
+from .mean_median import MeanImputer, MeanMedianImputer
+from .missing_indicator import AddMissingIndicator, MissingIndicator
 from .random_sample import RandomSampleImputer
 
 __all__ = [
+    "MeanImputer",
     "MeanMedianImputer",
+    "ArbitraryImputer",
     "ArbitraryNumberImputer",
+    "MissingIndicator",
+    "AddMissingIndicator",
     "CategoricalImputer",
     "EndTailImputer",
-    "AddMissingIndicator",
     "RandomSampleImputer",
     "DropMissingData",
 ]

feature_engine/imputation/arbitrary_number.py

@@ -2,7 +2,7 @@
 # License: BSD 3 clause
 
 from typing import List, Optional, Union
-
+import warnings
 import pandas as pd
 
 from feature_engine._check_init_parameters.check_input_dictionary import (
@@ -47,9 +47,9 @@
     transform=_transform_imputers_docstring,
     fit_transform=_fit_transform_docstring,
 )
-class ArbitraryNumberImputer(BaseImputer):
+class ArbitraryImputer(BaseImputer):
     """
-    The ArbitraryNumberImputer() replaces missing data by an arbitrary
+    The ArbitraryImputer() replaces missing data by an arbitrary
     value determined by the user. It works only with numerical variables.
 
     You can impute all variables with the same number by defining
@@ -104,12 +104,12 @@ class ArbitraryNumberImputer(BaseImputer):
 
     >>> import pandas as pd
     >>> import numpy as np
-    >>> from feature_engine.imputation import ArbitraryNumberImputer
+    >>> from feature_engine.imputation import ArbitraryImputer
     >>> X = pd.DataFrame(dict(
     >>>        x1 = [np.nan,1,1,0,np.nan],
     >>>        x2 = ["a", np.nan, "b", np.nan, "a"],
     >>>       ))
-    >>> ani = ArbitraryNumberImputer(arbitrary_number=-999)
+    >>> ani = ArbitraryImputer(arbitrary_number=-999)
     >>> ani.fit(X)
     >>> ani.transform(X)
           x1   x2
@@ -175,3 +175,35 @@ def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None):
         self._get_feature_names_in(X)
 
         return self
+
+
+# TODO remove in version 2.1.0
+
+
+class ArbitraryNumberImputer(ArbitraryImputer):
+    """Deprecated alias for ArbitraryImputer."""
+
+    def __init__(
+        self,
+        arbitrary_number: Union[int, float] = 999,
+        variables: Union[None, int, str, List[Union[str, int]]] = None,
+        return_empty: bool = False,
+        imputer_dict: Optional[dict] = None,
+    ) -> None:
+
+        warnings.warn(
+            (
+                "ArbitraryNumberImputer was deprecated in version 2.0.0 "
+                "in favour of ArbitraryImputer and will be removed in version 2.1.0. "
+                "Use ArbitraryImputer instead."
+            ),
+            FutureWarning,
+            stacklevel=2,
+        )
+
+        super().__init__(
+            arbitrary_number=arbitrary_number,
+            variables=variables,
+            return_empty=return_empty,
+            imputer_dict=imputer_dict,
+        )

feature_engine/imputation/mean_median.py

@@ -2,8 +2,8 @@
 # License: BSD 3 clause
 
 from typing import List, Optional, Union
-
 import pandas as pd
+import warnings
 
 from feature_engine._check_init_parameters.check_variables import (
     _check_variables_input_value,
@@ -43,13 +43,13 @@
     transform=_transform_imputers_docstring,
     fit_transform=_fit_transform_docstring,
 )
-class MeanMedianImputer(BaseImputer):
+class MeanImputer(BaseImputer):
     """
-    The MeanMedianImputer() replaces missing data by the mean or median value of the
+    The MeanImputer() replaces missing data by the mean or median value of the
     variable. It works only with numerical variables.
 
     You can pass a list of variables to impute. Alternatively, the
-    MeanMedianImputer() will automatically select all variables of type numeric in the
+    MeanImputer() will automatically select all variables of type numeric in the
     training set.
 
     More details in the :ref:`User Guide <mean_median_imputer>`.
@@ -87,12 +87,12 @@ class MeanMedianImputer(BaseImputer):
 
     >>> import pandas as pd
     >>> import numpy as np
-    >>> from feature_engine.imputation import MeanMedianImputer
+    >>> from feature_engine.imputation import MeanImputer
     >>> X = pd.DataFrame(dict(
     >>>        x1 = [np.nan,1,1,0,np.nan],
     >>>        x2 = ["a", np.nan, "b", np.nan, "a"],
     >>>        ))
-    >>> mmi = MeanMedianImputer(imputation_method='median')
+    >>> mmi = MeanImputer(imputation_method='median')
     >>> mmi.fit(X)
     >>> mmi.transform(X)
         x1   x2
@@ -151,3 +151,31 @@ def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None):
         self._get_feature_names_in(X)
 
         return self
+
+
+# TODO remove in version 2.1.0
+
+
+class MeanMedianImputer(MeanImputer):
+    def __init__(
+        self,
+        imputation_method: str = "median",
+        variables: Union[None, int, str, List[Union[str, int]]] = None,
+        return_empty: bool = False,
+    ) -> None:
+
+        warnings.warn(
+            (
+                "MeanMedianImputer was deprecated in version 2.0.0 "
+                "and will be removed in version 2.1.0. "
+                "Use MeanImputer instead."
+            ),
+            FutureWarning,
+            stacklevel=2,
+        )
+
+        super().__init__(
+            imputation_method=imputation_method,
+            variables=variables,
+            return_empty=return_empty,
+        )

feature_engine/imputation/missing_indicator.py

@@ -2,7 +2,7 @@
 # License: BSD 3 clause
 
 from typing import List, Optional, Union
-
+import warnings
 import pandas as pd
 
 from feature_engine._check_init_parameters.check_variables import (
@@ -32,13 +32,13 @@
     n_features_in_=_n_features_in_docstring,
     fit_transform=_fit_transform_docstring,
 )
-class AddMissingIndicator(BaseImputer):
+class MissingIndicator(BaseImputer):
     """
-    The AddMissingIndicator() adds binary variables that indicate if data is
+    The MissingIndicator() adds binary variables that indicate if data is
     missing (one indicator per variable). The added variables (missing indicators) are
     named with the original variable name plus '_na'.
 
-    The AddMissingIndicator() works for both numerical and categorical variables. You
+    The MissingIndicator() works for both numerical and categorical variables. You
     can pass a list with the variables for which the missing indicators should be
     added. Alternatively, the imputer will select and add missing indicators to all
     variables in the training set.
@@ -91,12 +91,12 @@ class AddMissingIndicator(BaseImputer):
 
     >>> import pandas as pd
     >>> import numpy as np
-    >>> from feature_engine.imputation import AddMissingIndicator
+    >>> from feature_engine.imputation import MissingIndicator
     >>> X = pd.DataFrame(dict(
     >>>        x1 = [np.nan,1,1,0,np.nan],
     >>>        x2 = ["a", np.nan, "b", np.nan, "a"],
     >>>        ))
-    >>> ami = AddMissingIndicator()
+    >>> ami = MissingIndicator()
     >>> ami.fit(X)
     >>> ami.transform(X)
         x1   x2  x1_na  x2_na
@@ -200,3 +200,36 @@ def __sklearn_tags__(self):
         tags = super().__sklearn_tags__()
         tags.input_tags.allow_nan = True
         return tags
+
+
+# TODO remove in version 2.1.0
+
+class AddMissingIndicator(MissingIndicator):
+    """
+    Deprecated alias for MissingIndicator.
+
+    Use MissingIndicator instead.
+    """
+
+    def __init__(
+        self,
+        missing_only: bool = True,
+        variables: Union[None, int, str, List[Union[str, int]]] = None,
+        return_empty: bool = False,
+    ) -> None:
+
+        warnings.warn(
+            (
+                "AddMissingIndicator was deprecated in version 2.0.0 "
+                "in favour of MissingIndicator and will be removed in "
+                "version 2.1.0. Use MissingIndicator instead."
+            ),
+            FutureWarning,
+            stacklevel=2,
+        )
+
+        super().__init__(
+            missing_only=missing_only,
+            variables=variables,
+            return_empty=return_empty,
+        )

tests/test_imputation/test_arbitrary_number_imputer.py

@@ -1,12 +1,19 @@
 import pandas as pd
 import pytest
 
-from feature_engine.imputation import ArbitraryNumberImputer
+from feature_engine.imputation import (
+    ArbitraryImputer,
+    ArbitraryNumberImputer,
+)
 
 
-def test_impute_with_99_and_automatically_select_variables(df_na):
+@pytest.mark.parametrize(
+    "imputer_cls",
+    [ArbitraryImputer, ArbitraryNumberImputer],
+)
+def test_impute_with_99_and_automatically_select_variables(df_na, imputer_cls):
     # set up the transformer
-    imputer = ArbitraryNumberImputer(arbitrary_number=99, variables=None)
+    imputer = imputer_cls(arbitrary_number=99, variables=None)
     X_transformed = imputer.fit_transform(df_na)
 
     # set up output reference
@@ -24,16 +31,18 @@ def test_impute_with_99_and_automatically_select_variables(df_na):
     assert imputer.imputer_dict_ == {"Age": 99, "Marks": 99}
 
     # test transform output
-    # selected variables should not contain NA
-    # non selected variables should still contain NA
     assert X_transformed[["Age", "Marks"]].isnull().sum().sum() == 0
     assert X_transformed[["Name", "City"]].isnull().sum().sum() > 0
     pd.testing.assert_frame_equal(X_transformed, X_reference)
 
 
-def test_impute_with_1_and_single_variable_entered_by_user(df_na):
+@pytest.mark.parametrize(
+    "imputer_cls",
+    [ArbitraryImputer, ArbitraryNumberImputer],
+)
+def test_impute_with_1_and_single_variable_entered_by_user(df_na, imputer_cls):
     # set up transformer
-    imputer = ArbitraryNumberImputer(arbitrary_number=-1, variables=["Age"])
+    imputer = imputer_cls(arbitrary_number=-1, variables=["Age"])
     X_transformed = imputer.fit_transform(df_na)
 
     # set up output reference
@@ -54,14 +63,25 @@ def test_impute_with_1_and_single_variable_entered_by_user(df_na):
     pd.testing.assert_frame_equal(X_transformed, X_reference)
 
 
-def test_error_when_arbitrary_number_is_string():
+@pytest.mark.parametrize(
+    "imputer_cls",
+    [ArbitraryImputer, ArbitraryNumberImputer],
+)
+def test_error_when_arbitrary_number_is_string(imputer_cls):
     with pytest.raises(ValueError):
-        ArbitraryNumberImputer(arbitrary_number="arbitrary")
+        imputer_cls(arbitrary_number="arbitrary")
 
 
-def test_dictionary_of_imputation_values(df_na):
+@pytest.mark.parametrize(
+    "imputer_cls",
+    [ArbitraryImputer, ArbitraryNumberImputer],
+)
+def test_dictionary_of_imputation_values(df_na, imputer_cls):
     # set up transformer
-    imputer = ArbitraryNumberImputer(imputer_dict={"Age": -42, "Marks": -999})
+    imputer = imputer_cls(
+        imputer_dict={"Age": -42, "Marks": -999}
+    )
+
     X_transformed = imputer.fit_transform(df_na)
 
     # set up expected output
@@ -71,14 +91,29 @@ def test_dictionary_of_imputation_values(df_na):
 
     # test fit params
     assert imputer.n_features_in_ == 6
-    assert imputer.imputer_dict_ == {"Age": -42, "Marks": -999}
+    assert imputer.imputer_dict_ == {
+        "Age": -42,
+        "Marks": -999,
+    }
 
     # test transform params
     assert X_transformed[["Age", "Marks"]].isnull().sum().sum() == 0
     assert X_transformed[["Name", "City"]].isnull().sum().sum() > 0
     pd.testing.assert_frame_equal(X_transformed, X_reference)
 
 
-def imputer_error_when_dictionary_value_is_string():
+@pytest.mark.parametrize(
+    "imputer_cls",
+    [ArbitraryImputer, ArbitraryNumberImputer],
+)
+def test_error_when_dictionary_value_is_string(imputer_cls):
     with pytest.raises(ValueError):
-        ArbitraryNumberImputer(imputer_dict={"Age": "arbitrary_number"})
+        imputer_cls(imputer_dict={"Age": "arbitrary_number"})
+
+
+def test_arbitrary_number_imputer_deprecation_warning():
+    with pytest.warns(
+        FutureWarning,
+        match="Use ArbitraryImputer instead",
+    ):
+        ArbitraryNumberImputer()