scikit-learn-intelex 2024.1.0__py311-none-manylinux1_x86_64.whl → 2024.2.0__py311-none-manylinux1_x86_64.whl

sklearnex/linear_model/linear.py

@@ -65,13 +65,8 @@ if daal_check_version((2023, "P", 100)):
     import numpy as np
     from sklearn.linear_model import LinearRegression as sklearn_LinearRegression
 
-    from daal4py.sklearn._utils import (
-        control_n_jobs,
-        get_dtype,
-        make2d,
-        run_with_n_jobs,
-        sklearn_check_version,
-    )
+    from daal4py.sklearn._n_jobs_support import control_n_jobs
+    from daal4py.sklearn._utils import get_dtype, make2d, sklearn_check_version
 
     from .._device_offload import dispatch, wrap_output_data
     from .._utils import (
@@ -93,7 +88,7 @@ if daal_check_version((2023, "P", 100)):
     from onedal.utils import _num_features, _num_samples
 
     @register_hyperparameters({"fit": get_hyperparameters("linear_regression", "train")})
-    @control_n_jobs
+    @control_n_jobs(decorated_methods=["fit", "predict"])
     class LinearRegression(sklearn_LinearRegression, BaseLinearRegression):
         __doc__ = sklearn_LinearRegression.__doc__
         intercept_, coef_ = None, None
@@ -330,7 +325,6 @@ if daal_check_version((2023, "P", 100)):
             onedal_params = {"fit_intercept": self.fit_intercept, "copy_X": self.copy_X}
             self._onedal_estimator = onedal_LinearRegression(**onedal_params)
 
-        @run_with_n_jobs
         def _onedal_fit(self, X, y, sample_weight, queue=None):
             assert sample_weight is None
 
@@ -369,7 +363,6 @@ if daal_check_version((2023, "P", 100)):
                 del self._onedal_estimator
                 super().fit(X, y)
 
-        @run_with_n_jobs
         def _onedal_predict(self, X, queue=None):
             X = self._validate_data(X, accept_sparse=False, reset=False)
             if not hasattr(self, "_onedal_estimator"):

sklearnex/{preview/linear_model → linear_model}/logistic_regression.py

@@ -1,5 +1,5 @@
 # ===============================================================================
-# Copyright 2023 Intel Corporation
+# 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.
@@ -17,14 +17,11 @@
 import logging
 from abc import ABC
 
-import sklearn.linear_model._logistic as logistic_module
-
 from daal4py.sklearn._utils import daal_check_version
 from daal4py.sklearn.linear_model.logistic_path import (
-    LogisticRegression,
-    daal4py_predict,
-    logistic_regression_path,
+    LogisticRegression as LogisticRegression_daal4py,
 )
+from daal4py.sklearn.linear_model.logistic_path import daal4py_fit, daal4py_predict
 
 
 class BaseLogisticRegression(ABC):
@@ -43,14 +40,18 @@ if daal_check_version((2024, "P", 1)):
     from sklearn.linear_model import LogisticRegression as sklearn_LogisticRegression
     from sklearn.utils.validation import check_X_y
 
+    from daal4py.sklearn._n_jobs_support import control_n_jobs
     from daal4py.sklearn._utils import sklearn_check_version
     from onedal.linear_model import LogisticRegression as onedal_LogisticRegression
     from onedal.utils import _num_features, _num_samples
 
-    from ..._device_offload import dispatch, wrap_output_data
-    from ..._utils import PatchingConditionsChain, get_patch_message
-    from ...utils.validation import _assert_all_finite
+    from .._device_offload import dispatch, wrap_output_data
+    from .._utils import PatchingConditionsChain, get_patch_message
+    from ..utils.validation import _assert_all_finite
 
+    @control_n_jobs(
+        decorated_methods=["fit", "predict", "predict_proba", "predict_log_proba"]
+    )
     class LogisticRegression(sklearn_LogisticRegression, BaseLogisticRegression):
         __doc__ = sklearn_LogisticRegression.__doc__
         intercept_, coef_, n_iter_ = None, None, None
@@ -97,6 +98,8 @@ if daal_check_version((2024, "P", 1)):
                 l1_ratio=l1_ratio,
             )
 
+        _onedal_cpu_fit = daal4py_fit
+
         def fit(self, X, y, sample_weight=None):
             if sklearn_check_version("1.0"):
                 self._check_feature_names(X, reset=True)
@@ -160,10 +163,8 @@ if daal_check_version((2024, "P", 1)):
         def _test_type_and_finiteness(self, X_in):
             X = np.asarray(X_in)
 
-            dtype = X.dtype
-            if "complex" in str(type(dtype)):
+            if np.iscomplexobj(X):
                 return False
-
             try:
                 _assert_all_finite(X)
             except BaseException:
@@ -268,15 +269,6 @@ if daal_check_version((2024, "P", 1)):
             }
             self._onedal_estimator = onedal_LogisticRegression(**onedal_params)
 
-        def _onedal_cpu_fit(self, X, y, sample_weight):
-            which, what = logistic_module, "_logistic_regression_path"
-            replacer = logistic_regression_path
-            descriptor = getattr(which, what, None)
-            setattr(which, what, replacer)
-            clf = super().fit(X, y, sample_weight)
-            setattr(which, what, descriptor)
-            return clf
-
         def _onedal_fit(self, X, y, sample_weight, queue=None):
             if queue is None or queue.sycl_device.is_cpu:
                 return self._onedal_cpu_fit(X, y, sample_weight)
@@ -313,38 +305,27 @@ if daal_check_version((2024, "P", 1)):
                 return daal4py_predict(self, X, "computeClassLabels")
 
             X = self._validate_data(X, accept_sparse=False, reset=False)
-            if not hasattr(self, "_onedal_estimator"):
-                self._initialize_onedal_estimator()
-                self._onedal_estimator.coef_ = self.coef_
-                self._onedal_estimator.intercept_ = self.intercept_
-                self._onedal_estimator.classes_ = self.classes_
-
+            assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict(X, queue=queue)
 
         def _onedal_predict_proba(self, X, queue=None):
             if queue is None or queue.sycl_device.is_cpu:
                 return daal4py_predict(self, X, "computeClassProbabilities")
-            X = self._validate_data(X, accept_sparse=False, reset=False)
-            if not hasattr(self, "_onedal_estimator"):
-                self._initialize_onedal_estimator()
-                self._onedal_estimator.coef_ = self.coef_
-                self._onedal_estimator.intercept_ = self.intercept_
 
+            X = self._validate_data(X, accept_sparse=False, reset=False)
+            assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict_proba(X, queue=queue)
 
         def _onedal_predict_log_proba(self, X, queue=None):
             if queue is None or queue.sycl_device.is_cpu:
                 return daal4py_predict(self, X, "computeClassLogProbabilities")
-            X = self._validate_data(X, accept_sparse=False, reset=False)
-            if not hasattr(self, "_onedal_estimator"):
-                self._initialize_onedal_estimator()
-                self._onedal_estimator.coef_ = self.coef_
-                self._onedal_estimator.intercept_ = self.intercept_
 
+            X = self._validate_data(X, accept_sparse=False, reset=False)
+            assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict_log_proba(X, queue=queue)
 
 else:
-    from daal4py.sklearn.linear_model import LogisticRegression
+    LogisticRegression = LogisticRegression_daal4py
 
     logging.warning(
         "Sklearnex LogisticRegression requires oneDAL version >= 2024.0.1 "

sklearnex/linear_model/tests/test_logreg.py

@@ -15,14 +15,79 @@
 # ===============================================================================
 
 import numpy as np
+import pytest
 from numpy.testing import assert_allclose
-from sklearn.datasets import load_iris
+from sklearn.datasets import load_breast_cancer, load_iris
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
 
+from daal4py.sklearn._utils import daal_check_version
+from onedal.tests.utils._dataframes_support import (
+    _as_numpy,
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
 
-def test_sklearnex_import():
+
+def prepare_input(X, y, dataframe, queue):
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, train_size=0.8, random_state=42
+    )
+    X_train = _convert_to_dataframe(X_train, sycl_queue=queue, target_df=dataframe)
+    y_train = _convert_to_dataframe(y_train, sycl_queue=queue, target_df=dataframe)
+    X_test = _convert_to_dataframe(X_test, sycl_queue=queue, target_df=dataframe)
+    return X_train, X_test, y_train, y_test
+
+
+@pytest.mark.parametrize(
+    "dataframe,queue",
+    get_dataframes_and_queues(device_filter_="cpu"),
+)
+def test_sklearnex_multiclass_classification(dataframe, queue):
     from sklearnex.linear_model import LogisticRegression
 
     X, y = load_iris(return_X_y=True)
-    logreg = LogisticRegression(random_state=0, max_iter=200).fit(X, y)
-    assert "daal4py" in logreg.__module__
-    assert_allclose(logreg.score(X, y), 0.9733, atol=1e-3)
+    X_train, X_test, y_train, y_test = prepare_input(X, y, dataframe, queue)
+
+    logreg = LogisticRegression(fit_intercept=True, solver="lbfgs", max_iter=200).fit(
+        X_train, y_train
+    )
+
+    if daal_check_version((2024, "P", 1)):
+        assert "sklearnex" in logreg.__module__
+    else:
+        assert "daal4py" in logreg.__module__
+
+    y_pred = _as_numpy(logreg.predict(X_test))
+    assert accuracy_score(y_test, y_pred) > 0.99
+
+
+@pytest.mark.parametrize(
+    "dataframe,queue",
+    get_dataframes_and_queues(),
+)
+def test_sklearnex_binary_classification(dataframe, queue):
+    from sklearnex.linear_model import LogisticRegression
+
+    X, y = load_breast_cancer(return_X_y=True)
+    X_train, X_test, y_train, y_test = prepare_input(X, y, dataframe, queue)
+
+    logreg = LogisticRegression(fit_intercept=True, solver="newton-cg", max_iter=100).fit(
+        X_train, y_train
+    )
+
+    if daal_check_version((2024, "P", 1)):
+        assert "sklearnex" in logreg.__module__
+    else:
+        assert "daal4py" in logreg.__module__
+    if (
+        dataframe != "numpy"
+        and queue is not None
+        and queue.sycl_device.is_gpu
+        and daal_check_version((2024, "P", 1))
+    ):
+        # fit was done on gpu
+        assert hasattr(logreg, "_onedal_estimator")
+
+    y_pred = _as_numpy(logreg.predict(X_test))
+    assert accuracy_score(y_test, y_pred) > 0.95

sklearnex/neighbors/__init__.py

@@ -14,10 +14,10 @@
 # limitations under the License.
 # ===============================================================================
 
+from ._lof import LocalOutlierFactor
 from .knn_classification import KNeighborsClassifier
 from .knn_regression import KNeighborsRegressor
 from .knn_unsupervised import NearestNeighbors
-from .lof import LocalOutlierFactor
 
 __all__ = [
     "KNeighborsClassifier",

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__

sklearnex/neighbors/knn_classification.py

@@ -20,7 +20,8 @@ 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 control_n_jobs, run_with_n_jobs, sklearn_check_version
+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"):
     from sklearn.neighbors._base import _check_weights
@@ -140,7 +141,7 @@ else:
             self.weights = _check_weights(weights)
 
 
-@control_n_jobs
+@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
@@ -285,7 +286,6 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
 
         return result
 
-    @run_with_n_jobs
     def _onedal_fit(self, X, y, queue=None):
         onedal_params = {
             "n_neighbors": self.n_neighbors,
@@ -308,15 +308,12 @@ class KNeighborsClassifier(KNeighborsClassifier_, KNeighborsDispatchingBase):
 
         self._save_attributes()
 
-    @run_with_n_jobs
     def _onedal_predict(self, X, queue=None):
         return self._onedal_estimator.predict(X, queue=queue)
 
-    @run_with_n_jobs
     def _onedal_predict_proba(self, X, queue=None):
         return self._onedal_estimator.predict_proba(X, queue=queue)
 
-    @run_with_n_jobs
     def _onedal_kneighbors(
         self, X=None, n_neighbors=None, return_distance=True, queue=None
     ):

sklearnex/neighbors/knn_regression.py

@@ -20,7 +20,8 @@ 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 control_n_jobs, run_with_n_jobs, sklearn_check_version
+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"):
     from sklearn.neighbors._base import _check_weights
@@ -136,7 +137,7 @@ else:
             self.weights = _check_weights(weights)
 
 
-@control_n_jobs
+@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
@@ -266,7 +267,6 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
 
         return result
 
-    @run_with_n_jobs
     def _onedal_fit(self, X, y, queue=None):
         onedal_params = {
             "n_neighbors": self.n_neighbors,
@@ -289,11 +289,9 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
 
         self._save_attributes()
 
-    @run_with_n_jobs
     def _onedal_predict(self, X, queue=None):
         return self._onedal_estimator.predict(X, queue=queue)
 
-    @run_with_n_jobs
     def _onedal_kneighbors(
         self, X=None, n_neighbors=None, return_distance=True, queue=None
     ):

sklearnex/neighbors/knn_unsupervised.py

@@ -30,7 +30,8 @@ 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._utils import control_n_jobs, run_with_n_jobs, sklearn_check_version
+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
 
@@ -95,7 +96,7 @@ else:
             )
 
 
-@control_n_jobs
+@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
@@ -180,7 +181,6 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
 
         return result
 
-    @run_with_n_jobs
     def _onedal_fit(self, X, y=None, queue=None):
         onedal_params = {
             "n_neighbors": self.n_neighbors,
@@ -202,11 +202,9 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
 
         self._save_attributes()
 
-    @run_with_n_jobs
     def _onedal_predict(self, X, queue=None):
         return self._onedal_estimator.predict(X, queue=queue)
 
-    @run_with_n_jobs
     def _onedal_kneighbors(
         self, X=None, n_neighbors=None, return_distance=True, queue=None
     ):

sklearnex/neighbors/tests/test_neighbors.py

@@ -23,11 +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)
@@ -40,7 +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)
@@ -51,18 +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__
@@ -71,14 +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])

sklearnex/preview/__init__.py

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