scikit-learn-intelex 2024.0.1__py38-none-win_amd64.whl → 2024.2.0__py38-none-win_amd64.whl

scikit_learn_intelex-2024.2.0.data/data/Lib/site-packages/sklearnex/neighbors/_lof.py

@@ -0,0 +1,167 @@
+# ===============================================================================
+# 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 .._device_offload import dispatch, wrap_output_data
+from .common import KNeighborsDispatchingBase
+from .knn_unsupervised import NearestNeighbors
+
+
+@control_n_jobs(decorated_methods=["fit", "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
+            )
+
+        return self
+
+    def fit(self, X, y=None):
+        self._fit_validation(X, y)
+        result = dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_LocalOutlierFactor.fit,
+            },
+            X,
+            None,
+        )
+        return result
+
+    # Subtle order change to remove check_array and preserve dpnp and
+    # dpctl conformance. decision_function will return a dpnp or dpctl
+    # instance via kneighbors and an equivalent check_array exists in
+    # that call already in sklearn so no loss of functionality occurs
+    def _predict(self, X=None):
+        check_is_fitted(self)
+
+        if X is not None:
+            output = self.decision_function(X) < 0
+            is_inlier = np.ones(output.shape[0], 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):
+        return self.fit(X)._predict()
+
+    @available_if(sklearn_LocalOutlierFactor._check_novelty_predict)
+    @wrap_output_data
+    def predict(self, X=None):
+        return self._predict(X)
+
+    @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)
+        return dispatch(
+            self,
+            "kneighbors",
+            {
+                "onedal": self.__class__._onedal_kneighbors,
+                "sklearn": sklearn_LocalOutlierFactor.kneighbors,
+            },
+            X,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
+        )
+
+    fit.__doc__ = sklearn_LocalOutlierFactor.fit.__doc__
+    fit_predict.__doc__ = sklearn_LocalOutlierFactor.fit_predict.__doc__
+    predict.__doc__ = sklearn_LocalOutlierFactor.predict.__doc__
+    kneighbors.__doc__ = sklearn_LocalOutlierFactor.kneighbors.__doc__

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/neighbors/common.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2023 Intel Corporation
 #
@@ -177,7 +176,7 @@ 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
 

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_classification.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2021 Intel Corporation
 #
@@ -21,6 +20,7 @@ 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._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
 
 if not sklearn_check_version("1.2"):
@@ -141,6 +141,7 @@ else:
             self.weights = _check_weights(weights)
 
 
+@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba", "kneighbors"])
 class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {**KNeighborsClassifier_._parameter_constraints}
@@ -245,7 +246,7 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
     @wrap_output_data
     def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
-        if sklearn_check_version("1.0"):
+        if sklearn_check_version("1.0") and X is not None:
             self._check_feature_names(X, reset=False)
         return dispatch(
             self,
@@ -255,8 +256,8 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
                 "sklearn": sklearn_KNeighborsClassifier.kneighbors,
             },
             X,
-            n_neighbors,
-            return_distance,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
         )
 
     @wrap_output_data

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_regression.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2021 Intel Corporation
 #
@@ -21,6 +20,7 @@ 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._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
 
 if not sklearn_check_version("1.2"):
@@ -137,6 +137,7 @@ else:
             self.weights = _check_weights(weights)
 
 
+@control_n_jobs(decorated_methods=["fit", "predict", "kneighbors"])
 class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {**KNeighborsRegressor_._parameter_constraints}
@@ -226,7 +227,7 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
     @wrap_output_data
     def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
-        if sklearn_check_version("1.0"):
+        if sklearn_check_version("1.0") and X is not None:
             self._check_feature_names(X, reset=False)
         return dispatch(
             self,
@@ -236,8 +237,8 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
                 "sklearn": sklearn_KNeighborsRegressor.kneighbors,
             },
             X,
-            n_neighbors,
-            return_distance,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
         )
 
     @wrap_output_data

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/neighbors/knn_unsupervised.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2021 Intel Corporation
 #
@@ -31,6 +30,7 @@ from sklearn.neighbors._kd_tree import KDTree
 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 NearestNeighbors as onedal_NearestNeighbors
 from onedal.utils import _check_array, _num_features, _num_samples
@@ -96,6 +96,7 @@ else:
             )
 
 
+@control_n_jobs(decorated_methods=["fit", "kneighbors"])
 class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {**NearestNeighbors_._parameter_constraints}
@@ -150,8 +151,8 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
                 "sklearn": sklearn_NearestNeighbors.kneighbors,
             },
             X,
-            n_neighbors,
-            return_distance,
+            n_neighbors=n_neighbors,
+            return_distance=return_distance,
         )
 
     @wrap_output_data

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/neighbors/tests/test_neighbors.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2021 Intel Corporation
 #
@@ -24,11 +23,16 @@ from onedal.tests.utils._dataframes_support import (
     _convert_to_dataframe,
     get_dataframes_and_queues,
 )
+from sklearnex.neighbors import (
+    KNeighborsClassifier,
+    KNeighborsRegressor,
+    LocalOutlierFactor,
+    NearestNeighbors,
+)
 
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_knn_classifier(dataframe, queue):
-    from sklearnex.neighbors import KNeighborsClassifier
 
     X = _convert_to_dataframe([[0], [1], [2], [3]], sycl_queue=queue, target_df=dataframe)
     y = _convert_to_dataframe([0, 0, 1, 1], sycl_queue=queue, target_df=dataframe)
@@ -41,7 +45,6 @@ def test_sklearnex_import_knn_classifier(dataframe, queue):
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_knn_regression(dataframe, queue):
-    from sklearnex.neighbors import KNeighborsRegressor
 
     X = _convert_to_dataframe([[0], [1], [2], [3]], sycl_queue=queue, target_df=dataframe)
     y = _convert_to_dataframe([0, 0, 1, 1], sycl_queue=queue, target_df=dataframe)
@@ -52,18 +55,17 @@ def test_sklearnex_import_knn_regression(dataframe, queue):
     assert_allclose(pred, [0.5])
 
 
-# TODO:
-# investigate failure for `dpnp.ndarrays` and `dpctl.tensors`.
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 @pytest.mark.parametrize(
-    "dataframe,queue", get_dataframes_and_queues(dataframe_filter_="numpy")
+    "estimator",
+    [LocalOutlierFactor, NearestNeighbors],
 )
-def test_sklearnex_import_nn(dataframe, queue):
-    from sklearnex.neighbors import NearestNeighbors
+def test_sklearnex_kneighbors(estimator, dataframe, queue):
 
     X = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
     X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
     test = _convert_to_dataframe([[0, 0, 1.3]], sycl_queue=queue, target_df=dataframe)
-    neigh = NearestNeighbors(n_neighbors=2).fit(X)
+    neigh = estimator(n_neighbors=2).fit(X)
     result = neigh.kneighbors(test, 2, return_distance=False)
     result = _as_numpy(result)
     assert "sklearnex" in neigh.__module__
@@ -72,14 +74,12 @@ def test_sklearnex_import_nn(dataframe, queue):
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_lof(dataframe, queue):
-    from sklearnex.neighbors import LocalOutlierFactor
 
     X = [[7, 7, 7], [1, 0, 0], [0, 0, 1], [0, 0, 1]]
     X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
     lof = LocalOutlierFactor(n_neighbors=2)
     result = lof.fit_predict(X)
     result = _as_numpy(result)
-    assert hasattr(lof, "_knn")
+    assert hasattr(lof, "_onedal_estimator")
     assert "sklearnex" in lof.__module__
-    assert "sklearnex" in lof._knn.__module__
     assert_allclose(result, [-1, 1, 1, 1])

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/preview/__init__.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2023 Intel Corporation
 #
@@ -15,4 +14,4 @@
 # limitations under the License.
 # ==============================================================================
 
-__all__ = ["cluster", "decomposition"]
+__all__ = ["cluster", "covariance", "decomposition"]

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/preview/cluster/__init__.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2023 Intel Corporation
 #

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/preview/cluster/k_means.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2023 Intel Corporation
 #
@@ -30,6 +29,7 @@ if daal_check_version((2023, "P", 200)):
         check_is_fitted,
     )
 
+    from daal4py.sklearn._n_jobs_support import control_n_jobs
     from daal4py.sklearn._utils import sklearn_check_version
     from onedal.cluster import KMeans as onedal_KMeans
 
@@ -37,6 +37,7 @@ if daal_check_version((2023, "P", 200)):
     from ..._utils import PatchingConditionsChain
     from ._common import BaseKMeans
 
+    @control_n_jobs(decorated_methods=["fit", "predict"])
     class KMeans(sklearn_KMeans, BaseKMeans):
         __doc__ = sklearn_KMeans.__doc__
         n_iter_, inertia_ = None, None

scikit_learn_intelex-2024.2.0.data/data/Lib/site-packages/sklearnex/preview/covariance/__init__.py

@@ -0,0 +1,19 @@
+# ===============================================================================
+# Copyright 2023 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 .covariance import EmpiricalCovariance
+
+__all__ = ["EmpiricalCovariance"]

scikit_learn_intelex-2024.2.0.data/data/Lib/site-packages/sklearnex/preview/covariance/covariance.py

@@ -0,0 +1,132 @@
+# ===============================================================================
+# Copyright 2023 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 scipy import sparse as sp
+from sklearn.covariance import EmpiricalCovariance as sklearn_EmpiricalCovariance
+from sklearn.utils import check_array
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+from onedal.common.hyperparameters import get_hyperparameters
+from onedal.covariance import EmpiricalCovariance as onedal_EmpiricalCovariance
+from sklearnex import config_context
+from sklearnex.metrics import pairwise_distances
+
+from ..._device_offload import dispatch, wrap_output_data
+from ..._utils import PatchingConditionsChain, register_hyperparameters
+
+
+@register_hyperparameters({"fit": get_hyperparameters("covariance", "compute")})
+@control_n_jobs(decorated_methods=["fit", "mahalanobis"])
+class EmpiricalCovariance(sklearn_EmpiricalCovariance):
+    __doc__ = sklearn_EmpiricalCovariance.__doc__
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {
+            **sklearn_EmpiricalCovariance._parameter_constraints,
+        }
+
+    def _save_attributes(self):
+        assert hasattr(self, "_onedal_estimator")
+        self._set_covariance(self._onedal_estimator.covariance_)
+        self.location_ = self._onedal_estimator.location_
+
+    _onedal_covariance = staticmethod(onedal_EmpiricalCovariance)
+
+    def _onedal_fit(self, X, queue=None):
+        if X.shape[0] == 1:
+            warnings.warn(
+                "Only one sample available. You may want to reshape your data array"
+            )
+
+        onedal_params = {
+            "method": "dense",
+            "bias": True,
+        }
+
+        self._onedal_estimator = self._onedal_covariance(**onedal_params)
+        self._onedal_estimator.fit(X, queue=queue)
+        self._save_attributes()
+
+    def _onedal_supported(self, method_name, *data):
+        class_name = self.__class__.__name__
+        patching_status = PatchingConditionsChain(
+            f"sklearn.covariance.{class_name}.{method_name}"
+        )
+        if method_name in ["fit", "mahalanobis"]:
+            (X,) = data
+            patching_status.and_conditions(
+                [
+                    (
+                        self.assume_centered == False,
+                        "assume_centered parameter is not supported on oneDAL side",
+                    ),
+                    (not sp.issparse(X), "X is sparse. Sparse input is not supported."),
+                ]
+            )
+            return patching_status
+        raise RuntimeError(f"Unknown method {method_name} in {self.__class__.__name__}")
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def fit(self, X, y=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+        if sklearn_check_version("0.23"):
+            X = self._validate_data(X, force_all_finite=False)
+        else:
+            X = check_array(X, force_all_finite=False)
+
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_EmpiricalCovariance.fit,
+            },
+            X,
+        )
+
+        return self
+
+    # expose sklearnex pairwise_distances if mahalanobis distance eventually supported
+    @wrap_output_data
+    def mahalanobis(self, X):
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, reset=False)
+        else:
+            X = check_array(X)
+
+        precision = self.get_precision()
+        with config_context(assume_finite=True):
+            # compute mahalanobis distances
+            dist = pairwise_distances(
+                X, self.location_[np.newaxis, :], metric="mahalanobis", VI=precision
+            )
+
+        return np.reshape(dist, (len(X),)) ** 2
+
+    error_norm = wrap_output_data(sklearn_EmpiricalCovariance.error_norm)
+    score = wrap_output_data(sklearn_EmpiricalCovariance.score)
+
+    fit.__doc__ = sklearn_EmpiricalCovariance.fit.__doc__
+    mahalanobis.__doc__ = sklearn_EmpiricalCovariance.mahalanobis
+    error_norm.__doc__ = sklearn_EmpiricalCovariance.error_norm.__doc__
+    score.__doc__ = sklearn_EmpiricalCovariance.score.__doc__

scikit_learn_intelex-2024.2.0.data/data/Lib/site-packages/sklearnex/preview/covariance/tests/test_covariance.py

@@ -0,0 +1,53 @@
+# ===============================================================================
+# Copyright 2023 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
+import pytest
+from numpy.testing import assert_allclose
+
+from daal4py.sklearn._utils import daal_check_version
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("macro_block", [None, 1024])
+def test_sklearnex_import_covariance(dataframe, queue, macro_block):
+    from sklearnex.preview.covariance import EmpiricalCovariance
+
+    X = np.array([[0, 1], [0, 1]])
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    empcov = EmpiricalCovariance()
+    if daal_check_version((2024, "P", 0)) and macro_block is not None:
+        hparams = empcov.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+    result = empcov.fit(X)
+    expected_covariance = np.array([[0, 0], [0, 0]])
+    expected_means = np.array([0, 1])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)
+
+    X = np.array([[1, 2], [3, 6]])
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    result = empcov.fit(X)
+    expected_covariance = np.array([[1, 2], [2, 4]])
+    expected_means = np.array([2, 4])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)

{scikit_learn_intelex-2024.0.1.data → scikit_learn_intelex-2024.2.0.data}/data/Lib/site-packages/sklearnex/preview/decomposition/__init__.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2023 Intel Corporation
 #