scikit-learn-intelex 2024.5.0__py312-none-win_amd64.whl → 2024.7.0__py312-none-win_amd64.whl

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/metrics/pairwise.py

@@ -15,3 +15,8 @@
 # ===============================================================================
 
 from daal4py.sklearn.metrics import pairwise_distances
+from onedal._device_offload import support_usm_ndarray
+
+pairwise_distances = support_usm_ndarray(freefunc=True, queue_param=False)(
+    pairwise_distances
+)

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/metrics/ranking.py

@@ -15,3 +15,6 @@
 # ===============================================================================
 
 from daal4py.sklearn.metrics import roc_auc_score
+from onedal._device_offload import support_usm_ndarray
+
+roc_auc_score = support_usm_ndarray(freefunc=True, queue_param=False)(roc_auc_score)

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/model_selection/split.py

@@ -15,3 +15,6 @@
 # ===============================================================================
 
 from daal4py.sklearn.model_selection import train_test_split
+from onedal._device_offload import support_usm_ndarray
+
+train_test_split = support_usm_ndarray(freefunc=True, queue_param=False)(train_test_split)

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/neighbors/_lof.py

@@ -97,6 +97,15 @@ 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):

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/neighbors/common.py

@@ -19,14 +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 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 import get_namespace
 
 
 class KNeighborsDispatchingBase:
@@ -147,6 +149,10 @@ 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)),
@@ -264,3 +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-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_classification.py

@@ -32,7 +32,7 @@ from .common import KNeighborsDispatchingBase
 @control_n_jobs(
     decorated_methods=["fit", "predict", "predict_proba", "kneighbors", "score"]
 )
-class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBase):
+class KNeighborsClassifier(KNeighborsDispatchingBase, sklearn_KNeighborsClassifier):
     __doc__ = sklearn_KNeighborsClassifier.__doc__
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {
@@ -169,24 +169,6 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
             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,
@@ -242,4 +224,3 @@ class KNeighborsClassifier(sklearn_KNeighborsClassifier, KNeighborsDispatchingBa
     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__

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_regression.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 # ==============================================================================
 
+from sklearn.metrics import r2_score
 from sklearn.neighbors._regression import (
     KNeighborsRegressor as sklearn_KNeighborsRegressor,
 )
@@ -29,7 +30,7 @@ from .common import KNeighborsDispatchingBase
 
 
 @control_n_jobs(decorated_methods=["fit", "predict", "kneighbors"])
-class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase):
+class KNeighborsRegressor(KNeighborsDispatchingBase, sklearn_KNeighborsRegressor):
     __doc__ = sklearn_KNeighborsRegressor.__doc__
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {
@@ -117,6 +118,23 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
             X,
         )
 
+    @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)
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_KNeighborsRegressor.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     @wrap_output_data
     def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
@@ -134,24 +152,6 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
             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,
@@ -184,6 +184,11 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
             X, n_neighbors, return_distance, queue=queue
         )
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return r2_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
     def _save_attributes(self):
         self.n_features_in_ = self._onedal_estimator.n_features_in_
         self.n_samples_fit_ = self._onedal_estimator.n_samples_fit_
@@ -195,4 +200,4 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
     fit.__doc__ = sklearn_KNeighborsRegressor.__doc__
     predict.__doc__ = sklearn_KNeighborsRegressor.predict.__doc__
     kneighbors.__doc__ = sklearn_KNeighborsRegressor.kneighbors.__doc__
-    radius_neighbors.__doc__ = sklearn_NearestNeighbors.radius_neighbors.__doc__
+    score.__doc__ = sklearn_KNeighborsRegressor.score.__doc__

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_unsupervised.py

@@ -26,7 +26,7 @@ from .common import KNeighborsDispatchingBase
 
 
 @control_n_jobs(decorated_methods=["fit", "kneighbors"])
-class NearestNeighbors(sklearn_NearestNeighbors, KNeighborsDispatchingBase):
+class NearestNeighbors(KNeighborsDispatchingBase, sklearn_NearestNeighbors):
     __doc__ = sklearn_NearestNeighbors.__doc__
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {**sklearn_NearestNeighbors._parameter_constraints}
@@ -88,19 +88,40 @@ class NearestNeighbors(sklearn_NearestNeighbors, KNeighborsDispatchingBase):
     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
+            hasattr(self, "_onedal_estimator")
             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 dispatch(
+            self,
+            "radius_neighbors",
+            {
+                "onedal": None,
+                "sklearn": sklearn_NearestNeighbors.radius_neighbors,
+            },
+            X,
+            radius=radius,
+            return_distance=return_distance,
+            sort_results=sort_results,
         )
 
-        return result
+    def radius_neighbors_graph(
+        self, X=None, radius=None, mode="connectivity", sort_results=False
+    ):
+        return dispatch(
+            self,
+            "radius_neighbors_graph",
+            {
+                "onedal": None,
+                "sklearn": sklearn_NearestNeighbors.radius_neighbors_graph,
+            },
+            X,
+            radius=radius,
+            mode=mode,
+            sort_results=sort_results,
+        )
 
     def _onedal_fit(self, X, y=None, queue=None):
         onedal_params = {
@@ -144,3 +165,6 @@ class NearestNeighbors(sklearn_NearestNeighbors, KNeighborsDispatchingBase):
     fit.__doc__ = sklearn_NearestNeighbors.__doc__
     kneighbors.__doc__ = sklearn_NearestNeighbors.kneighbors.__doc__
     radius_neighbors.__doc__ = sklearn_NearestNeighbors.radius_neighbors.__doc__
+    radius_neighbors_graph.__doc__ = (
+        sklearn_NearestNeighbors.radius_neighbors_graph.__doc__
+    )

{scikit_learn_intelex-2024.5.0.data → scikit_learn_intelex-2024.7.0.data}/data/Lib/site-packages/sklearnex/preview/__init__.py

@@ -14,4 +14,4 @@
 # limitations under the License.
 # ==============================================================================
 
-__all__ = ["cluster", "covariance"]
+__all__ = ["cluster", "covariance", "decomposition", "linear_model"]

scikit_learn_intelex-2024.7.0.data/data/Lib/site-packages/sklearnex/preview/decomposition/__init__.py

@@ -0,0 +1,19 @@
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+from .incremental_pca import IncrementalPCA
+
+__all__ = ["IncrementalPCA"]

scikit_learn_intelex-2024.7.0.data/data/Lib/site-packages/sklearnex/preview/decomposition/incremental_pca.py

@@ -0,0 +1,228 @@
+# ===============================================================================
+# 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 numpy as np
+from sklearn.decomposition import IncrementalPCA as sklearn_IncrementalPCA
+from sklearn.utils import check_array, gen_batches
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+from onedal.decomposition import IncrementalPCA as onedal_IncrementalPCA
+
+from ..._device_offload import dispatch, wrap_output_data
+from ..._utils import PatchingConditionsChain
+
+
+@control_n_jobs(
+    decorated_methods=["fit", "partial_fit", "transform", "_onedal_finalize_fit"]
+)
+class IncrementalPCA(sklearn_IncrementalPCA):
+
+    def __init__(self, n_components=None, *, whiten=False, copy=True, batch_size=None):
+        super().__init__(
+            n_components=n_components, whiten=whiten, copy=copy, batch_size=batch_size
+        )
+        self._need_to_finalize = False
+        self._need_to_finalize_attrs = {
+            "mean_",
+            "explained_variance_",
+            "explained_variance_ratio_",
+            "n_components_",
+            "components_",
+            "noise_variance_",
+            "singular_values_",
+            "var_",
+        }
+
+    _onedal_incremental_pca = staticmethod(onedal_IncrementalPCA)
+
+    def _onedal_transform(self, X, queue=None):
+        assert hasattr(self, "_onedal_estimator")
+        if self._need_to_finalize:
+            self._onedal_finalize_fit()
+        X = check_array(X, dtype=[np.float64, np.float32])
+        return self._onedal_estimator.predict(X, queue)
+
+    def _onedal_fit_transform(self, X, queue=None):
+        self._onedal_fit(X, queue)
+        return self._onedal_transform(X, queue)
+
+    def _onedal_partial_fit(self, X, check_input=True, queue=None):
+        first_pass = not hasattr(self, "components_")
+
+        if check_input:
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X, dtype=[np.float64, np.float32], reset=first_pass
+                )
+            else:
+                X = check_array(
+                    X,
+                    dtype=[np.float64, np.float32],
+                    copy=self.copy,
+                )
+
+        n_samples, n_features = X.shape
+
+        if self.n_components is None:
+            if not hasattr(self, "components_"):
+                self.n_components_ = min(n_samples, n_features)
+            else:
+                self.n_components_ = self.components_.shape[0]
+        elif not self.n_components <= n_features:
+            raise ValueError(
+                "n_components=%r invalid for n_features=%d, need "
+                "more rows than columns for IncrementalPCA "
+                "processing" % (self.n_components, n_features)
+            )
+        elif not self.n_components <= n_samples:
+            raise ValueError(
+                "n_components=%r must be less or equal to "
+                "the batch number of samples "
+                "%d." % (self.n_components, n_samples)
+            )
+        else:
+            self.n_components_ = self.n_components
+
+        if not hasattr(self, "n_samples_seen_"):
+            self.n_samples_seen_ = n_samples
+        else:
+            self.n_samples_seen_ += n_samples
+
+        onedal_params = {"n_components": self.n_components_, "whiten": self.whiten}
+
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_incremental_pca(**onedal_params)
+        self._onedal_estimator.partial_fit(X, queue)
+        self._need_to_finalize = True
+
+    def _onedal_finalize_fit(self):
+        assert hasattr(self, "_onedal_estimator")
+        self._onedal_estimator.finalize_fit()
+        self._need_to_finalize = False
+
+    def _onedal_fit(self, X, queue=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, dtype=[np.float64, np.float32], copy=self.copy)
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                copy=self.copy,
+            )
+
+        n_samples, n_features = X.shape
+
+        if self.batch_size is None:
+            self.batch_size_ = 5 * n_features
+        else:
+            self.batch_size_ = self.batch_size
+
+        self.n_samples_seen_ = 0
+        if hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator._reset()
+
+        for batch in gen_batches(n_samples, self.batch_size_):
+            X_batch = X[batch]
+            self._onedal_partial_fit(X_batch, queue=queue)
+
+        self._onedal_finalize_fit()
+
+        return self
+
+    def _onedal_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearn.decomposition.{self.__class__.__name__}.{method_name}"
+        )
+        return patching_status
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def __getattr__(self, attr):
+        if attr in self._need_to_finalize_attrs:
+            if hasattr(self, "_onedal_estimator"):
+                if self._need_to_finalize:
+                    self._onedal_finalize_fit()
+                return getattr(self._onedal_estimator, attr)
+            else:
+                raise AttributeError(
+                    f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+                )
+        if attr in self.__dict__:
+            return self.__dict__[attr]
+
+        raise AttributeError(
+            f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+        )
+
+    def partial_fit(self, X, y=None, check_input=True):
+        dispatch(
+            self,
+            "partial_fit",
+            {
+                "onedal": self.__class__._onedal_partial_fit,
+                "sklearn": sklearn_IncrementalPCA.partial_fit,
+            },
+            X,
+            check_input=check_input,
+        )
+        return self
+
+    def fit(self, X, y=None):
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_IncrementalPCA.fit,
+            },
+            X,
+        )
+        return self
+
+    @wrap_output_data
+    def transform(self, X):
+        return dispatch(
+            self,
+            "transform",
+            {
+                "onedal": self.__class__._onedal_transform,
+                "sklearn": sklearn_IncrementalPCA.transform,
+            },
+            X,
+        )
+
+    @wrap_output_data
+    def fit_transform(self, X, y=None, **fit_params):
+        return dispatch(
+            self,
+            "fit_transform",
+            {
+                "onedal": self.__class__._onedal_fit_transform,
+                "sklearn": sklearn_IncrementalPCA.fit_transform,
+            },
+            X,
+        )
+
+    __doc__ = sklearn_IncrementalPCA.__doc__
+    fit.__doc__ = sklearn_IncrementalPCA.fit.__doc__
+    fit_transform.__doc__ = sklearn_IncrementalPCA.fit_transform.__doc__
+    transform.__doc__ = sklearn_IncrementalPCA.transform.__doc__
+    partial_fit.__doc__ = sklearn_IncrementalPCA.partial_fit.__doc__