scikit-learn-intelex 2024.4.0__py312-none-win_amd64.whl → 2025.10.0__py312-none-win_amd64.whl

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2025.10.0.data}/data/Lib/site-packages/sklearnex/neighbors/_lof.py

@@ -15,9 +15,10 @@
 # ===============================================================================
 
 import warnings
+from functools import wraps
 
 import numpy as np
-from sklearn.neighbors import LocalOutlierFactor as sklearn_LocalOutlierFactor
+from sklearn.neighbors import LocalOutlierFactor as _sklearn_LocalOutlierFactor
 from sklearn.utils.metaestimators import available_if
 from sklearn.utils.validation import check_is_fitted
 
@@ -26,20 +27,22 @@ from daal4py.sklearn._utils import sklearn_check_version
 from sklearnex._device_offload import dispatch, wrap_output_data
 from sklearnex.neighbors.common import KNeighborsDispatchingBase
 from sklearnex.neighbors.knn_unsupervised import NearestNeighbors
-from sklearnex.utils import get_namespace
 
+from ..utils._array_api import get_namespace
+from ..utils.validation import check_feature_names
 
-@control_n_jobs(decorated_methods=["fit", "_kneighbors"])
-class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
+
+@control_n_jobs(decorated_methods=["fit", "kneighbors", "_kneighbors"])
+class LocalOutlierFactor(KNeighborsDispatchingBase, _sklearn_LocalOutlierFactor):
     __doc__ = (
-        sklearn_LocalOutlierFactor.__doc__
+        _sklearn_LocalOutlierFactor.__doc__
         + "\n NOTE: When X=None, methods kneighbors, kneighbors_graph, and predict will"
         + "\n only output numpy arrays. In that case, the only way to offload to gpu"
         + "\n is to use a global queue (e.g. using config_context)"
     )
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {
-            **sklearn_LocalOutlierFactor._parameter_constraints
+            **_sklearn_LocalOutlierFactor._parameter_constraints
         }
 
     # Only certain methods should be taken from knn to prevent code
@@ -53,7 +56,7 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
         if sklearn_check_version("1.2"):
             self._validate_params()
 
-        self._onedal_knn_fit(X, y, queue)
+        self._onedal_knn_fit(X, y, queue=queue)
 
         if self.contamination != "auto":
             if not (0.0 < self.contamination <= 0.5):
@@ -97,6 +100,15 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
                 self.negative_outlier_factor_, 100.0 * self.contamination
             )
 
+        # adoption of warning for data with duplicated samples from
+        # https://github.com/scikit-learn/scikit-learn/pull/28773
+        if sklearn_check_version("1.6"):
+            if np.min(self.negative_outlier_factor_) < -1e7 and not self.novelty:
+                warnings.warn(
+                    "Duplicate values are leading to incorrect results. "
+                    "Increase the number of neighbors for more accurate results."
+                )
+
         return self
 
     def fit(self, X, y=None):
@@ -105,7 +117,7 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
             "fit",
             {
                 "onedal": self.__class__._onedal_fit,
-                "sklearn": sklearn_LocalOutlierFactor.fit,
+                "sklearn": _sklearn_LocalOutlierFactor.fit,
             },
             X,
             None,
@@ -129,42 +141,23 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
     # This had to be done because predict loses the queue when no
     # argument is given and it is a dpctl tensor or dpnp array.
     # This would cause issues in fit_predict. Also, available_if
-    # is hard to unwrap, and this is the most straighforward way.
-    @available_if(sklearn_LocalOutlierFactor._check_novelty_fit_predict)
+    # is hard to unwrap, and this is the most straightforward way.
+    @available_if(_sklearn_LocalOutlierFactor._check_novelty_fit_predict)
+    @wraps(_sklearn_LocalOutlierFactor.fit_predict, assigned=["__doc__"])
     @wrap_output_data
     def fit_predict(self, X, y=None):
-        """Fit the model to the training set X and return the labels.
-
-        **Not available for novelty detection (when novelty is set to True).**
-        Label is 1 for an inlier and -1 for an outlier according to the LOF
-        score and the contamination parameter.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None
-            The query sample or samples to compute the Local Outlier Factor
-            w.r.t. the training samples.
-
-        y : Ignored
-            Not used, present for API consistency by convention.
-
-        Returns
-        -------
-        is_inlier : ndarray of shape (n_samples,)
-            Returns -1 for anomalies/outliers and 1 for inliers.
-        """
         return self.fit(X)._predict()
 
     def _kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
-        if sklearn_check_version("1.0") and X is not None:
-            self._check_feature_names(X, reset=False)
+        if X is not None:
+            check_feature_names(self, X, reset=False)
         return dispatch(
             self,
             "kneighbors",
             {
                 "onedal": self.__class__._onedal_kneighbors,
-                "sklearn": sklearn_LocalOutlierFactor.kneighbors,
+                "sklearn": _sklearn_LocalOutlierFactor.kneighbors,
             },
             X,
             n_neighbors=n_neighbors,
@@ -173,35 +166,10 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
 
     kneighbors = wrap_output_data(_kneighbors)
 
-    @available_if(sklearn_LocalOutlierFactor._check_novelty_score_samples)
+    @available_if(_sklearn_LocalOutlierFactor._check_novelty_score_samples)
+    @wraps(_sklearn_LocalOutlierFactor.score_samples, assigned=["__doc__"])
     @wrap_output_data
     def score_samples(self, X):
-        """Opposite of the Local Outlier Factor of X.
-
-        It is the opposite as bigger is better, i.e. large values correspond
-        to inliers.
-
-        **Only available for novelty detection (when novelty is set to True).**
-        The argument X is supposed to contain *new data*: if X contains a
-        point from training, it considers the later in its own neighborhood.
-        Also, the samples in X are not considered in the neighborhood of any
-        point. Because of this, the scores obtained via ``score_samples`` may
-        differ from the standard LOF scores.
-        The standard LOF scores for the training data is available via the
-        ``negative_outlier_factor_`` attribute.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-            The query sample or samples to compute the Local Outlier Factor
-            w.r.t. the training samples.
-
-        Returns
-        -------
-        opposite_lof_scores : ndarray of shape (n_samples,)
-            The opposite of the Local Outlier Factor of each input samples.
-            The lower, the more abnormal.
-        """
         check_is_fitted(self)
 
         distances_X, neighbors_indices_X = self._kneighbors(
@@ -217,5 +185,5 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
 
         return -np.mean(lrd_ratios_array, axis=1)
 
-    fit.__doc__ = sklearn_LocalOutlierFactor.fit.__doc__
-    kneighbors.__doc__ = sklearn_LocalOutlierFactor.kneighbors.__doc__
+    fit.__doc__ = _sklearn_LocalOutlierFactor.fit.__doc__
+    kneighbors.__doc__ = _sklearn_LocalOutlierFactor.kneighbors.__doc__

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2025.10.0.data}/data/Lib/site-packages/sklearnex/neighbors/common.py

@@ -19,22 +19,26 @@ import warnings
 import numpy as np
 from scipy import sparse as sp
 from sklearn.neighbors._ball_tree import BallTree
-from sklearn.neighbors._base import VALID_METRICS
-from sklearn.neighbors._base import NeighborsBase as sklearn_NeighborsBase
+from sklearn.neighbors._base import VALID_METRICS, KNeighborsMixin
+from sklearn.neighbors._base import NeighborsBase as _sklearn_NeighborsBase
 from sklearn.neighbors._kd_tree import KDTree
+from sklearn.utils.validation import check_is_fitted
 
 from daal4py.sklearn._utils import sklearn_check_version
-from onedal.utils import _check_array, _num_features, _num_samples
+from onedal._device_offload import _transfer_to_host
+from onedal.utils.validation import _check_array, _num_features, _num_samples
 
 from .._utils import PatchingConditionsChain
+from ..base import oneDALEstimator
+from ..utils._array_api import get_namespace
+from ..utils.validation import check_feature_names
 
 
-class KNeighborsDispatchingBase:
+class KNeighborsDispatchingBase(oneDALEstimator):
     def _fit_validation(self, X, y=None):
         if sklearn_check_version("1.2"):
             self._validate_params()
-        if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=True)
+        check_feature_names(self, X, reset=True)
         if self.metric_params is not None and "p" in self.metric_params:
             if self.p is not None:
                 warnings.warn(
@@ -62,7 +66,7 @@ class KNeighborsDispatchingBase:
             elif p == np.inf:
                 self.effective_metric_ = "chebyshev"
 
-        if not isinstance(X, (KDTree, BallTree, sklearn_NeighborsBase)):
+        if not isinstance(X, (KDTree, BallTree, _sklearn_NeighborsBase)):
             self._fit_X = _check_array(
                 X, dtype=[np.float64, np.float32], accept_sparse=True
             )
@@ -95,7 +99,7 @@ class KNeighborsDispatchingBase:
             delattr(self, "_onedal_estimator")
         # To cover test case when we pass patched
         # estimator as an input for other estimator
-        if isinstance(X, sklearn_NeighborsBase):
+        if isinstance(X, _sklearn_NeighborsBase):
             self._fit_X = X._fit_X
             self._tree = X._tree
             self._fit_method = X._fit_method
@@ -147,9 +151,13 @@ class KNeighborsDispatchingBase:
         patching_status = PatchingConditionsChain(
             f"sklearn.neighbors.{class_name}.{method_name}"
         )
+        if not patching_status.and_condition(
+            "radius" not in method_name, "RadiusNeighbors not implemented in sklearnex"
+        ):
+            return patching_status
 
         if not patching_status.and_condition(
-            not isinstance(data[0], (KDTree, BallTree, sklearn_NeighborsBase)),
+            not isinstance(data[0], (KDTree, BallTree, _sklearn_NeighborsBase)),
             f"Input type {type(data[0])} is not supported.",
         ):
             return patching_status
@@ -264,3 +272,42 @@ class KNeighborsDispatchingBase:
 
     def _onedal_cpu_supported(self, method_name, *data):
         return self._onedal_supported("cpu", method_name, *data)
+
+    def kneighbors_graph(self, X=None, n_neighbors=None, mode="connectivity"):
+        check_is_fitted(self)
+        if n_neighbors is None:
+            n_neighbors = self.n_neighbors
+
+        # check the input only in self.kneighbors
+
+        # construct CSR matrix representation of the k-NN graph
+        # requires moving data to host to construct the csr_matrix
+        if mode == "connectivity":
+            A_ind = self.kneighbors(X, n_neighbors, return_distance=False)
+            _, (A_ind,) = _transfer_to_host(A_ind)
+            n_queries = A_ind.shape[0]
+            A_data = np.ones(n_queries * n_neighbors)
+
+        elif mode == "distance":
+            A_data, A_ind = self.kneighbors(X, n_neighbors, return_distance=True)
+            _, (A_data, A_ind) = _transfer_to_host(A_data, A_ind)
+            A_data = np.reshape(A_data, (-1,))
+
+        else:
+            raise ValueError(
+                'Unsupported mode, must be one of "connectivity", '
+                f'or "distance" but got "{mode}" instead'
+            )
+
+        n_queries = A_ind.shape[0]
+        n_samples_fit = self.n_samples_fit_
+        n_nonzero = n_queries * n_neighbors
+        A_indptr = np.arange(0, n_nonzero + 1, n_neighbors)
+
+        kneighbors_graph = sp.csr_matrix(
+            (A_data, np.reshape(A_ind, (-1,)), A_indptr), shape=(n_queries, n_samples_fit)
+        )
+
+        return kneighbors_graph
+
+    kneighbors_graph.__doc__ = KNeighborsMixin.kneighbors_graph.__doc__

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2025.10.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_classification.py

@@ -16,81 +16,52 @@
 
 from sklearn.metrics import accuracy_score
 from sklearn.neighbors._classification import (
-    KNeighborsClassifier as sklearn_KNeighborsClassifier,
+    KNeighborsClassifier as _sklearn_KNeighborsClassifier,
 )
-from sklearn.neighbors._unsupervised import NearestNeighbors as sklearn_NearestNeighbors
-from sklearn.utils.validation import _deprecate_positional_args, check_is_fitted
+from sklearn.utils.validation import check_is_fitted
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
+from daal4py.sklearn.utils.validation import get_requires_y_tag
 from onedal.neighbors import KNeighborsClassifier as onedal_KNeighborsClassifier
 
 from .._device_offload import dispatch, wrap_output_data
+from ..utils.validation import check_feature_names
 from .common import KNeighborsDispatchingBase
 
 
 @control_n_jobs(
     decorated_methods=["fit", "predict", "predict_proba", "kneighbors", "score"]
 )
-class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBase):
-    __doc__ = sklearn_KNeighborsClassifier.__doc__
+class KNeighborsClassifier(KNeighborsDispatchingBase, _sklearn_KNeighborsClassifier):
+    __doc__ = _sklearn_KNeighborsClassifier.__doc__
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {
-            **sklearn_KNeighborsClassifier._parameter_constraints
+            **_sklearn_KNeighborsClassifier._parameter_constraints
         }
 
-    if sklearn_check_version("1.0"):
-
-        def __init__(
-            self,
-            n_neighbors=5,
-            *,
-            weights="uniform",
-            algorithm="auto",
-            leaf_size=30,
-            p=2,
-            metric="minkowski",
-            metric_params=None,
-            n_jobs=None,
-        ):
-            super().__init__(
-                n_neighbors=n_neighbors,
-                weights=weights,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-            )
-
-    else:
-
-        @_deprecate_positional_args
-        def __init__(
-            self,
-            n_neighbors=5,
-            *,
-            weights="uniform",
-            algorithm="auto",
-            leaf_size=30,
-            p=2,
-            metric="minkowski",
-            metric_params=None,
-            n_jobs=None,
-            **kwargs,
-        ):
-            super().__init__(
-                n_neighbors=n_neighbors,
-                weights=weights,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-                **kwargs,
-            )
+    def __init__(
+        self,
+        n_neighbors=5,
+        *,
+        weights="uniform",
+        algorithm="auto",
+        leaf_size=30,
+        p=2,
+        metric="minkowski",
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            weights=weights,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
 
     def fit(self, X, y):
         dispatch(
@@ -98,7 +69,7 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
             "fit",
             {
                 "onedal": self.__class__._onedal_fit,
-                "sklearn": sklearn_KNeighborsClassifier.fit,
+                "sklearn": _sklearn_KNeighborsClassifier.fit,
             },
             X,
             y,
@@ -108,14 +79,13 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
     @wrap_output_data
     def predict(self, X):
         check_is_fitted(self)
-        if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+        check_feature_names(self, X, reset=False)
         return dispatch(
             self,
             "predict",
             {
                 "onedal": self.__class__._onedal_predict,
-                "sklearn": sklearn_KNeighborsClassifier.predict,
+                "sklearn": _sklearn_KNeighborsClassifier.predict,
             },
             X,
         )
@@ -123,14 +93,13 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
     @wrap_output_data
     def predict_proba(self, X):
         check_is_fitted(self)
-        if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+        check_feature_names(self, X, reset=False)
         return dispatch(
             self,
             "predict_proba",
             {
                 "onedal": self.__class__._onedal_predict_proba,
-                "sklearn": sklearn_KNeighborsClassifier.predict_proba,
+                "sklearn": _sklearn_KNeighborsClassifier.predict_proba,
             },
             X,
         )
@@ -138,14 +107,13 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
     @wrap_output_data
     def score(self, X, y, sample_weight=None):
         check_is_fitted(self)
-        if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+        check_feature_names(self, X, reset=False)
         return dispatch(
             self,
             "score",
             {
                 "onedal": self.__class__._onedal_score,
-                "sklearn": sklearn_KNeighborsClassifier.score,
+                "sklearn": _sklearn_KNeighborsClassifier.score,
             },
             X,
             y,
@@ -155,38 +123,20 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
     @wrap_output_data
     def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
-        if sklearn_check_version("1.0") and X is not None:
-            self._check_feature_names(X, reset=False)
+        if X is not None:
+            check_feature_names(self, X, reset=False)
         return dispatch(
             self,
             "kneighbors",
             {
                 "onedal": self.__class__._onedal_kneighbors,
-                "sklearn": sklearn_KNeighborsClassifier.kneighbors,
+                "sklearn": _sklearn_KNeighborsClassifier.kneighbors,
             },
             X,
             n_neighbors=n_neighbors,
             return_distance=return_distance,
         )
 
-    @wrap_output_data
-    def radius_neighbors(
-        self, X=None, radius=None, return_distance=True, sort_results=False
-    ):
-        _onedal_estimator = getattr(self, "_onedal_estimator", None)
-
-        if (
-            _onedal_estimator is not None
-            or getattr(self, "_tree", 0) is None
-            and self._fit_method == "kd_tree"
-        ):
-            sklearn_NearestNeighbors.fit(self, self._fit_X, getattr(self, "_y", None))
-        result = sklearn_NearestNeighbors.radius_neighbors(
-            self, X, radius, return_distance, sort_results
-        )
-
-        return result
-
     def _onedal_fit(self, X, y, queue=None):
         onedal_params = {
             "n_neighbors": self.n_neighbors,
@@ -196,13 +146,8 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
             "p": self.effective_metric_params_["p"],
         }
 
-        try:
-            requires_y = self._get_tags()["requires_y"]
-        except KeyError:
-            requires_y = False
-
         self._onedal_estimator = onedal_KNeighborsClassifier(**onedal_params)
-        self._onedal_estimator.requires_y = requires_y
+        self._onedal_estimator.requires_y = get_requires_y_tag(self)
         self._onedal_estimator.effective_metric_ = self.effective_metric_
         self._onedal_estimator.effective_metric_params_ = self.effective_metric_params_
         self._onedal_estimator.fit(X, y, queue=queue)
@@ -237,9 +182,8 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
         self.outputs_2d_ = self._onedal_estimator.outputs_2d_
         self._tree = self._onedal_estimator._tree
 
-    fit.__doc__ = sklearn_KNeighborsClassifier.fit.__doc__
-    predict.__doc__ = sklearn_KNeighborsClassifier.predict.__doc__
-    predict_proba.__doc__ = sklearn_KNeighborsClassifier.predict_proba.__doc__
-    score.__doc__ = sklearn_KNeighborsClassifier.score.__doc__
-    kneighbors.__doc__ = sklearn_KNeighborsClassifier.kneighbors.__doc__
-    radius_neighbors.__doc__ = sklearn_NearestNeighbors.radius_neighbors.__doc__
+    fit.__doc__ = _sklearn_KNeighborsClassifier.fit.__doc__
+    predict.__doc__ = _sklearn_KNeighborsClassifier.predict.__doc__
+    predict_proba.__doc__ = _sklearn_KNeighborsClassifier.predict_proba.__doc__
+    score.__doc__ = _sklearn_KNeighborsClassifier.score.__doc__
+    kneighbors.__doc__ = _sklearn_KNeighborsClassifier.kneighbors.__doc__