Add TargetEncoder for scikit-learn (#384)

Author: x99b

stubs/sklearn/preprocessing/__init__.pyi

@@ -28,6 +28,7 @@ from ._label import (
     label_binarize as label_binarize,
 )
 from ._polynomial import PolynomialFeatures as PolynomialFeatures, SplineTransformer as SplineTransformer
+from ._target_encoder import TargetEncoder as TargetEncoder
 
 __all__ = [
     "Binarizer",
@@ -36,26 +37,27 @@ __all__ = [
     "KernelCenterer",
     "LabelBinarizer",
     "LabelEncoder",
-    "MultiLabelBinarizer",
-    "MinMaxScaler",
     "MaxAbsScaler",
-    "QuantileTransformer",
+    "MinMaxScaler",
+    "MultiLabelBinarizer",
     "Normalizer",
     "OneHotEncoder",
     "OrdinalEncoder",
+    "PolynomialFeatures",
     "PowerTransformer",
+    "QuantileTransformer",
     "RobustScaler",
     "SplineTransformer",
     "StandardScaler",
+    "TargetEncoder",
     "add_dummy_feature",
-    "PolynomialFeatures",
     "binarize",
-    "normalize",
-    "scale",
-    "robust_scale",
+    "label_binarize",
     "maxabs_scale",
     "minmax_scale",
-    "label_binarize",
-    "quantile_transform",
+    "normalize",
     "power_transform",
+    "quantile_transform",
+    "robust_scale",
+    "scale",
 ]

stubs/sklearn/preprocessing/_target_encoder.pyi

@@ -0,0 +1,34 @@
+from typing import ClassVar, Literal
+from typing_extensions import Self
+
+from numpy import ndarray
+
+from .._typing import ArrayLike, Int, MatrixLike
+from ..base import OneToOneFeatureMixin
+from ._encoders import _BaseEncoder
+
+class TargetEncoder(OneToOneFeatureMixin, _BaseEncoder):
+    encodings_: list[ndarray]
+    categories_: list[ndarray]
+    target_type_: str
+    target_mean_: float
+    n_features_in_: int
+    feature_names_in_: ndarray
+    classes_: ndarray | None
+
+    _parameter_constraints: ClassVar[dict] = ...
+
+    def __init__(
+        self,
+        categories: list[ArrayLike] | Literal["auto"] = "auto",
+        target_type: Literal["auto", "continuous", "binary", "multiclass"] = "auto",
+        smooth: Literal["auto"] | float = "auto",
+        cv: int = 5,
+        shuffle: bool = True,
+        random_state: Int | None = None,
+    ) -> None: ...
+    def fit(self, X: MatrixLike, y: ArrayLike) -> Self: ...
+    def fit_transform(self, X: MatrixLike, y: ArrayLike) -> ndarray: ...
+    def transform(self, X: MatrixLike) -> ndarray: ...
+    def get_feature_names_out(self, input_features: ArrayLike | None = None) -> ndarray: ...
+    def __sklearn_tags__(self) -> dict: ...

stubs/sklearn/stubtest_allowlist.txt

@@ -1103,8 +1103,6 @@ sklearn.preprocessing.StandardScaler.set_fit_request
 sklearn.preprocessing.StandardScaler.set_inverse_transform_request
 sklearn.preprocessing.StandardScaler.set_partial_fit_request
 sklearn.preprocessing.StandardScaler.set_transform_request
-sklearn.preprocessing.TargetEncoder
-sklearn.preprocessing.__all__
 sklearn.preprocessing._data.Binarizer.__sklearn_tags__
 sklearn.preprocessing._data.Binarizer.set_transform_request
 sklearn.preprocessing._data.KernelCenterer.__sklearn_tags__