scikit-learn-intelex 2024.0.1__py310-none-win_amd64.whl → 2025.1.0__py310-none-win_amd64.whl

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/neighbors/_lof.py

@@ -0,0 +1,236 @@
+# ===============================================================================
+# Copyright 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ===============================================================================
+
+import warnings
+
+import numpy as np
+from sklearn.neighbors import LocalOutlierFactor as _sklearn_LocalOutlierFactor
+from sklearn.utils.metaestimators import available_if
+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 sklearnex._device_offload import dispatch, wrap_output_data
+from sklearnex.neighbors.common import KNeighborsDispatchingBase
+from sklearnex.neighbors.knn_unsupervised import NearestNeighbors
+
+from ..utils._array_api import get_namespace
+
+if sklearn_check_version("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+    validate_data = _sklearn_LocalOutlierFactor._validate_data
+
+
+@control_n_jobs(decorated_methods=["fit", "kneighbors", "_kneighbors"])
+class LocalOutlierFactor(KNeighborsDispatchingBase, _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
+        }
+
+    # Only certain methods should be taken from knn to prevent code
+    # duplication. Inheriting would yield a complicated inheritance
+    # structure and violate the sklearn inheritance path.
+    _save_attributes = NearestNeighbors._save_attributes
+    _onedal_knn_fit = NearestNeighbors._onedal_fit
+    _onedal_kneighbors = NearestNeighbors._onedal_kneighbors
+
+    def _onedal_fit(self, X, y, queue=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        self._onedal_knn_fit(X, y, queue)
+
+        if self.contamination != "auto":
+            if not (0.0 < self.contamination <= 0.5):
+                raise ValueError(
+                    "contamination must be in (0, 0.5], " "got: %f" % self.contamination
+                )
+
+        n_samples = self.n_samples_fit_
+
+        if self.n_neighbors > n_samples:
+            warnings.warn(
+                "n_neighbors (%s) is greater than the "
+                "total number of samples (%s). n_neighbors "
+                "will be set to (n_samples - 1) for estimation."
+                % (self.n_neighbors, n_samples)
+            )
+        self.n_neighbors_ = max(1, min(self.n_neighbors, n_samples - 1))
+
+        (
+            self._distances_fit_X_,
+            _neighbors_indices_fit_X_,
+        ) = self._onedal_kneighbors(n_neighbors=self.n_neighbors_, queue=queue)
+
+        # Sklearn includes a check for float32 at this point which may not be
+        # necessary for onedal
+
+        self._lrd = self._local_reachability_density(
+            self._distances_fit_X_, _neighbors_indices_fit_X_
+        )
+
+        # Compute lof score over training samples to define offset_:
+        lrd_ratios_array = self._lrd[_neighbors_indices_fit_X_] / self._lrd[:, np.newaxis]
+
+        self.negative_outlier_factor_ = -np.mean(lrd_ratios_array, axis=1)
+
+        if self.contamination == "auto":
+            # inliers score around -1 (the higher, the less abnormal).
+            self.offset_ = -1.5
+        else:
+            self.offset_ = np.percentile(
+                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):
+        result = dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": _sklearn_LocalOutlierFactor.fit,
+            },
+            X,
+            None,
+        )
+        return result
+
+    def _predict(self, X=None):
+        check_is_fitted(self)
+
+        if X is not None:
+            xp, _ = get_namespace(X)
+            output = self.decision_function(X) < 0
+            is_inlier = xp.ones_like(output, dtype=int)
+            is_inlier[output] = -1
+        else:
+            is_inlier = np.ones(self.n_samples_fit_, dtype=int)
+            is_inlier[self.negative_outlier_factor_ < self.offset_] = -1
+
+        return is_inlier
+
+    # 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)
+    @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)
+        return dispatch(
+            self,
+            "kneighbors",
+            {
+                "onedal": self.__class__._onedal_kneighbors,
+                "sklearn": _sklearn_LocalOutlierFactor.kneighbors,
+            },
+            X,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
+        )
+
+    kneighbors = wrap_output_data(_kneighbors)
+
+    @available_if(_sklearn_LocalOutlierFactor._check_novelty_score_samples)
+    @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(
+            X, n_neighbors=self.n_neighbors_
+        )
+
+        X_lrd = self._local_reachability_density(
+            distances_X,
+            neighbors_indices_X,
+        )
+
+        lrd_ratios_array = self._lrd[neighbors_indices_X] / X_lrd[:, np.newaxis]
+
+        return -np.mean(lrd_ratios_array, axis=1)
+
+    fit.__doc__ = _sklearn_LocalOutlierFactor.fit.__doc__
+    kneighbors.__doc__ = _sklearn_LocalOutlierFactor.kneighbors.__doc__

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/neighbors/common.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2023 Intel Corporation
 #
@@ -20,14 +19,16 @@ 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 .._utils import PatchingConditionsChain
+from ..utils._array_api import get_namespace
 
 
 class KNeighborsDispatchingBase:
@@ -63,7 +64,7 @@ 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
             )
@@ -96,7 +97,7 @@ 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
@@ -138,6 +139,9 @@ class KNeighborsDispatchingBase:
             self.n_features_in_ = X.data.shape[1]
 
     def _onedal_supported(self, device, method_name, *data):
+        if method_name == "fit":
+            self._fit_validation(data[0], data[1])
+
         class_name = self.__class__.__name__
         is_classifier = "Classifier" in class_name
         is_regressor = "Regressor" in class_name
@@ -145,9 +149,13 @@ 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
@@ -177,7 +185,7 @@ class KNeighborsDispatchingBase:
             return patching_status
 
         if not patching_status.and_condition(
-            not sp.isspmatrix(data[0]), "Sparse input is not supported."
+            not sp.issparse(data[0]), "Sparse input is not supported."
         ):
             return patching_status
 
@@ -250,7 +258,7 @@ class KNeighborsDispatchingBase:
                     class_count >= 2, "One-class case is not supported."
                 )
             return patching_status
-        if method_name in ["predict", "predict_proba", "kneighbors"]:
+        if method_name in ["predict", "predict_proba", "kneighbors", "score"]:
             patching_status.and_condition(
                 hasattr(self, "_onedal_estimator"), "oneDAL model was not trained."
             )
@@ -262,3 +270,41 @@ 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
+        if mode == "connectivity":
+            A_ind = self.kneighbors(X, n_neighbors, return_distance=False)
+            xp, _ = get_namespace(A_ind)
+            n_queries = A_ind.shape[0]
+            A_data = xp.ones(n_queries * n_neighbors)
+
+        elif mode == "distance":
+            A_data, A_ind = self.kneighbors(X, n_neighbors, return_distance=True)
+            xp, _ = get_namespace(A_ind)
+            A_data = xp.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 = xp.arange(0, n_nonzero + 1, n_neighbors)
+
+        kneighbors_graph = sp.csr_matrix(
+            (A_data, xp.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-2024.0.1.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_classification.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2021 Intel Corporation
 #
@@ -15,135 +14,35 @@
 # limitations under the License.
 # ===============================================================================
 
-import warnings
-
-from sklearn.neighbors._ball_tree import BallTree
-from sklearn.neighbors._base import NeighborsBase as sklearn_NeighborsBase
-from sklearn.neighbors._kd_tree import KDTree
-
-from daal4py.sklearn._utils import sklearn_check_version
-
-if not sklearn_check_version("1.2"):
-    from sklearn.neighbors._base import _check_weights
-
-import numpy as np
-from sklearn.neighbors._base import VALID_METRICS
+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.neighbors._unsupervised import NearestNeighbors as _sklearn_NearestNeighbors
 from sklearn.utils.validation import _deprecate_positional_args, check_is_fitted
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
 from onedal.neighbors import KNeighborsClassifier as onedal_KNeighborsClassifier
-from onedal.utils import _check_array, _num_features, _num_samples
 
 from .._device_offload import dispatch, wrap_output_data
 from .common import KNeighborsDispatchingBase
 
-if sklearn_check_version("0.24"):
-
-    class KNeighborsClassifier_(sklearn_KNeighborsClassifier):
-        if sklearn_check_version("1.2"):
-            _parameter_constraints: dict = {
-                **sklearn_KNeighborsClassifier._parameter_constraints
-            }
-
-        @_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,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-                **kwargs,
-            )
-            self.weights = (
-                weights if sklearn_check_version("1.0") else _check_weights(weights)
-            )
-
-elif sklearn_check_version("0.22"):
-    from sklearn.neighbors._base import (
-        SupervisedIntegerMixin as BaseSupervisedIntegerMixin,
-    )
-
-    class KNeighborsClassifier_(sklearn_KNeighborsClassifier, BaseSupervisedIntegerMixin):
-        @_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,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-                **kwargs,
-            )
-            self.weights = _check_weights(weights)
-
+if sklearn_check_version("1.6"):
+    from sklearn.utils.validation import validate_data
 else:
-    from sklearn.neighbors.base import (
-        SupervisedIntegerMixin as BaseSupervisedIntegerMixin,
-    )
+    validate_data = _sklearn_KNeighborsClassifier._validate_data
 
-    class KNeighborsClassifier_(sklearn_KNeighborsClassifier, BaseSupervisedIntegerMixin):
-        @_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,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-                **kwargs,
-            )
-            self.weights = _check_weights(weights)
 
-
-class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
+@control_n_jobs(
+    decorated_methods=["fit", "predict", "predict_proba", "kneighbors", "score"]
+)
+class KNeighborsClassifier(KNeighborsDispatchingBase, _sklearn_KNeighborsClassifier):
+    __doc__ = _sklearn_KNeighborsClassifier.__doc__
     if sklearn_check_version("1.2"):
-        _parameter_constraints: dict = {**KNeighborsClassifier_._parameter_constraints}
+        _parameter_constraints: dict = {
+            **_sklearn_KNeighborsClassifier._parameter_constraints
+        }
 
     if sklearn_check_version("1.0"):
 
@@ -199,13 +98,12 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
             )
 
     def fit(self, X, y):
-        self._fit_validation(X, y)
         dispatch(
             self,
             "fit",
             {
                 "onedal": self.__class__._onedal_fit,
-                "sklearn": sklearn_KNeighborsClassifier.fit,
+                "sklearn": _sklearn_KNeighborsClassifier.fit,
             },
             X,
             y,
@@ -222,7 +120,7 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
             "predict",
             {
                 "onedal": self.__class__._onedal_predict,
-                "sklearn": sklearn_KNeighborsClassifier.predict,
+                "sklearn": _sklearn_KNeighborsClassifier.predict,
             },
             X,
         )
@@ -237,53 +135,44 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
             "predict_proba",
             {
                 "onedal": self.__class__._onedal_predict_proba,
-                "sklearn": sklearn_KNeighborsClassifier.predict_proba,
+                "sklearn": _sklearn_KNeighborsClassifier.predict_proba,
             },
             X,
         )
 
     @wrap_output_data
-    def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
+    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)
         return dispatch(
             self,
-            "kneighbors",
+            "score",
             {
-                "onedal": self.__class__._onedal_kneighbors,
-                "sklearn": sklearn_KNeighborsClassifier.kneighbors,
+                "onedal": self.__class__._onedal_score,
+                "sklearn": _sklearn_KNeighborsClassifier.score,
             },
             X,
-            n_neighbors,
-            return_distance,
+            y,
+            sample_weight=sample_weight,
         )
 
     @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"
-        ):
-            if sklearn_check_version("0.24"):
-                sklearn_NearestNeighbors.fit(self, self._fit_X, getattr(self, "_y", None))
-            else:
-                sklearn_NearestNeighbors.fit(self, self._fit_X)
-        if sklearn_check_version("0.22"):
-            result = sklearn_NearestNeighbors.radius_neighbors(
-                self, X, radius, return_distance, sort_results
-            )
-        else:
-            result = sklearn_NearestNeighbors.radius_neighbors(
-                self, X, radius, return_distance
-            )
-
-        return result
+    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)
+        return dispatch(
+            self,
+            "kneighbors",
+            {
+                "onedal": self.__class__._onedal_kneighbors,
+                "sklearn": _sklearn_KNeighborsClassifier.kneighbors,
+            },
+            X,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
+        )
 
     def _onedal_fit(self, X, y, queue=None):
         onedal_params = {
@@ -320,6 +209,11 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
             X, n_neighbors, return_distance, queue=queue
         )
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return accuracy_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
     def _save_attributes(self):
         self.classes_ = self._onedal_estimator.classes_
         self.n_features_in_ = self._onedal_estimator.n_features_in_
@@ -329,3 +223,9 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
         self._fit_method = self._onedal_estimator._fit_method
         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__