Merge branch 'main' of https://github.com/microsoft/python-type-stubs into remove-networkx

Author: Avasam

pyproject.toml

@@ -26,7 +26,7 @@ tests = [
     # The libraries we're stubbing.
     # Needed for stubtest and downloads their dependencies to get known import symbols
     "scikit-image",
-    "scikit-learn",
+    "scikit-learn <1.7.0", # TODO: Update stubs for sklearn
     "sympy",
     "vispy",
 ]

stubs/sklearn/_config.pyi

@@ -16,6 +16,8 @@ def set_config(
     enable_cython_pairwise_dist: None | bool = None,
     array_api_dispatch: None | bool = None,
     transform_output: None | str = None,
+    enable_metadata_routing: None | bool = None,
+    skip_parameter_validation: None | bool = None,
 ) -> None: ...
 def config_context(
     *,
@@ -27,4 +29,6 @@ def config_context(
     enable_cython_pairwise_dist: None | bool = None,
     array_api_dispatch: None | bool = None,
     transform_output: None | str = None,
+    enable_metadata_routing: None | bool = None,
+    skip_parameter_validation: None | bool = None,
 ) -> Iterator[None]: ...

stubs/sklearn/base.pyi

@@ -15,6 +15,7 @@ from ._config import get_config as get_config
 from ._typing import ArrayLike, Float, Int, MatrixLike
 from .metrics import accuracy_score as accuracy_score, r2_score as r2_score
 from .utils._estimator_html_repr import estimator_html_repr as estimator_html_repr
+from .utils._metadata_requests import _MetadataRequester
 from .utils._param_validation import validate_parameter_constraints as validate_parameter_constraints
 from .utils._set_output import _SetOutputMixin
 from .utils.validation import check_array as check_array, check_is_fitted as check_is_fitted, check_X_y as check_X_y
@@ -24,7 +25,7 @@ from .utils.validation import check_array as check_array, check_is_fitted as che
 
 def clone(estimator: BaseEstimator | Iterable[BaseEstimator], *, safe: bool = True) -> Any: ...
 
-class BaseEstimator:
+class BaseEstimator(_MetadataRequester):
     def get_params(self, deep: bool = True) -> dict: ...
     def set_params(self, **params) -> Self: ...
     def __repr__(self, N_CHAR_MAX: int = 700) -> str: ...

stubs/sklearn/cluster/_agglomerative.pyi

@@ -49,8 +49,7 @@ class AgglomerativeClustering(ClusterMixin, BaseEstimator):
         self,
         n_clusters: None | int = 2,
         *,
-        affinity: str | Callable = "deprecated",  # TODO(1.4): Remove
-        metric: None | str | Callable = None,  # TODO(1.4): Set to "euclidean"
+        metric: str | Callable = "euclidean",
         memory: None | Memory | str = None,
         connectivity: None | ArrayLike | Callable = None,
         compute_full_tree: Literal["auto"] | bool = "auto",
@@ -77,8 +76,7 @@ class FeatureAgglomeration(ClassNamePrefixFeaturesOutMixin, AgglomerativeCluster
         self,
         n_clusters: None | int = 2,
         *,
-        affinity: str | Callable = "deprecated",  # TODO(1.4): Remove
-        metric: None | str | Callable = None,  # TODO(1.4): Set to "euclidean"
+        metric: str | Callable = "euclidean",
         memory: None | Memory | str = None,
         connectivity: None | ArrayLike | Callable = None,
         compute_full_tree: Literal["auto"] | bool = "auto",

stubs/sklearn/covariance/_robust_covariance.pyi

@@ -7,17 +7,6 @@ from numpy.random import RandomState
 from .._typing import Float, Int, MatrixLike
 from . import EmpiricalCovariance
 
-# Author: Virgile Fritsch <[email protected]>
-#
-# License: BSD 3 clause
-
-# Minimum Covariance Determinant
-#   Implementing of an algorithm by Rousseeuw & Van Driessen described in
-#   (A Fast Algorithm for the Minimum Covariance Determinant Estimator,
-#   1999, American Statistical Association and the American Society
-#   for Quality, TECHNOMETRICS)
-# XXX Is this really a public function? It's not listed in the docs or
-# exported by sklearn.covariance. Deprecate?
 def c_step(
     X: MatrixLike,
     n_support: Int,

stubs/sklearn/datasets/_samples_generator.pyi

@@ -110,9 +110,6 @@ def make_low_rank_matrix(
     tail_strength: Float = 0.5,
     random_state: RandomState | None | Int = None,
 ) -> ndarray: ...
-
-# TODO(1.3): Change argument `data_transposed` default from True to False.
-# TODO(1.3): Deprecate data_transposed, always return data not transposed.
 def make_sparse_coded_signal(
     n_samples: Int,
     *,

stubs/sklearn/ensemble/_gb.pyi

@@ -70,7 +70,6 @@ class GradientBoostingClassifier(ClassifierMixin, BaseGradientBoosting):
     feature_importances_: ndarray = ...
     n_estimators_: int = ...
 
-    # TODO(1.3): remove "deviance"
     _parameter_constraints: ClassVar[dict] = ...
 
     def __init__(

stubs/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.pyi

@@ -96,7 +96,6 @@ class HistGradientBoostingClassifier(ClassifierMixin, BaseHistGradientBoosting):
     do_early_stopping_: bool = ...
     classes_: ndarray = ...
 
-    # TODO(1.3): Remove "binary_crossentropy", "categorical_crossentropy", "auto"
     _parameter_constraints: ClassVar[dict] = ...
 
     def __init__(

stubs/sklearn/feature_selection/_univariate_selection.pyi

@@ -92,8 +92,6 @@ class SelectFwe(_BaseFilter):
 # Generic filter
 ######################################################################
 
-# TODO this class should fit on either p-values or scores,
-# depending on the mode.
 class GenericUnivariateSelect(_BaseFilter):
     feature_names_in_: ndarray = ...
     n_features_in_: int = ...

stubs/sklearn/linear_model/_stochastic_gradient.pyi

@@ -86,7 +86,6 @@ def fit_binary(
 ) -> tuple[ndarray, float, int]: ...
 
 class BaseSGDClassifier(LinearClassifierMixin, BaseSGD, metaclass=ABCMeta):
-    # TODO(1.3): Remove "log""
     loss_functions: ClassVar[dict] = ...
 
     _parameter_constraints: ClassVar[dict] = ...