scikit-learn-intelex 2024.2.0__py38-none-manylinux1_x86_64.whl → 2024.4.0__py38-none-manylinux1_x86_64.whl

sklearnex/neighbors/knn_regression.py

@@ -14,133 +14,27 @@
 # 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._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
-
-import numpy as np
-from sklearn.neighbors._base import VALID_METRICS
 from sklearn.neighbors._regression import (
     KNeighborsRegressor as sklearn_KNeighborsRegressor,
 )
 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 KNeighborsRegressor as onedal_KNeighborsRegressor
-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 KNeighborsRegressor_(sklearn_KNeighborsRegressor):
-        if sklearn_check_version("1.2"):
-            _parameter_constraints: dict = {
-                **sklearn_KNeighborsRegressor._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 SupervisedFloatMixin as BaseSupervisedFloatMixin
-
-    class KNeighborsRegressor_(sklearn_KNeighborsRegressor, BaseSupervisedFloatMixin):
-        @_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)
-
-else:
-    from sklearn.neighbors.base import SupervisedFloatMixin as BaseSupervisedFloatMixin
-
-    class KNeighborsRegressor_(sklearn_KNeighborsRegressor, BaseSupervisedFloatMixin):
-        @_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)
-
 
 @control_n_jobs(decorated_methods=["fit", "predict", "kneighbors"])
-class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
+class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase):
+    __doc__ = sklearn_KNeighborsRegressor.__doc__
     if sklearn_check_version("1.2"):
-        _parameter_constraints: dict = {**KNeighborsRegressor_._parameter_constraints}
+        _parameter_constraints: dict = {
+            **sklearn_KNeighborsRegressor._parameter_constraints
+        }
 
     if sklearn_check_version("1.0"):
 
@@ -196,7 +90,6 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
             )
 
     def fit(self, X, y):
-        self._fit_validation(X, y)
         dispatch(
             self,
             "fit",
@@ -252,18 +145,10 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
             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
-            )
+            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
 
@@ -306,3 +191,8 @@ class KNeighborsRegressor(KNeighborsRegressor_, KNeighborsDispatchingBase):
         self._y = self._onedal_estimator._y
         self._fit_method = self._onedal_estimator._fit_method
         self._tree = self._onedal_estimator._tree
+
+    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__

sklearnex/neighbors/knn_unsupervised.py

@@ -14,92 +14,22 @@
 # limitations under the License.
 # ===============================================================================
 
-try:
-    from packaging.version import Version
-except ImportError:
-    from distutils.version import LooseVersion as Version
-
-import warnings
-
-import numpy as np
-from sklearn import __version__ as sklearn_version
-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._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
 
 from .._device_offload import dispatch, wrap_output_data
 from .common import KNeighborsDispatchingBase
 
-if sklearn_check_version("0.22") and Version(sklearn_version) < Version("0.23"):
-
-    class NearestNeighbors_(sklearn_NearestNeighbors):
-        def __init__(
-            self,
-            n_neighbors=5,
-            radius=1.0,
-            algorithm="auto",
-            leaf_size=30,
-            metric="minkowski",
-            p=2,
-            metric_params=None,
-            n_jobs=None,
-        ):
-            super().__init__(
-                n_neighbors=n_neighbors,
-                radius=radius,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-            )
-
-else:
-
-    class NearestNeighbors_(sklearn_NearestNeighbors):
-        if sklearn_check_version("1.2"):
-            _parameter_constraints: dict = {
-                **sklearn_NearestNeighbors._parameter_constraints
-            }
-
-        @_deprecate_positional_args
-        def __init__(
-            self,
-            *,
-            n_neighbors=5,
-            radius=1.0,
-            algorithm="auto",
-            leaf_size=30,
-            metric="minkowski",
-            p=2,
-            metric_params=None,
-            n_jobs=None,
-        ):
-            super().__init__(
-                n_neighbors=n_neighbors,
-                radius=radius,
-                algorithm=algorithm,
-                leaf_size=leaf_size,
-                metric=metric,
-                p=p,
-                metric_params=metric_params,
-                n_jobs=n_jobs,
-            )
-
 
 @control_n_jobs(decorated_methods=["fit", "kneighbors"])
-class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
+class NearestNeighbors(sklearn_NearestNeighbors, KNeighborsDispatchingBase):
+    __doc__ = sklearn_NearestNeighbors.__doc__
     if sklearn_check_version("1.2"):
-        _parameter_constraints: dict = {**NearestNeighbors_._parameter_constraints}
+        _parameter_constraints: dict = {**sklearn_NearestNeighbors._parameter_constraints}
 
     @_deprecate_positional_args
     def __init__(
@@ -125,7 +55,6 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
         )
 
     def fit(self, X, y=None):
-        self._fit_validation(X, y)
         dispatch(
             self,
             "fit",
@@ -166,18 +95,10 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
             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
-            )
+            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
 
@@ -219,3 +140,7 @@ class NearestNeighbors(NearestNeighbors_, KNeighborsDispatchingBase):
         self._fit_X = self._onedal_estimator._fit_X
         self._fit_method = self._onedal_estimator._fit_method
         self._tree = self._onedal_estimator._tree
+
+    fit.__doc__ = sklearn_NearestNeighbors.__doc__
+    kneighbors.__doc__ = sklearn_NearestNeighbors.kneighbors.__doc__
+    radius_neighbors.__doc__ = sklearn_NearestNeighbors.radius_neighbors.__doc__

sklearnex/neighbors/tests/test_neighbors.py

@@ -14,7 +14,6 @@
 # limitations under the License.
 # ===============================================================================
 
-import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 
@@ -33,7 +32,6 @@ from sklearnex.neighbors import (
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_knn_classifier(dataframe, queue):
-
     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)
     neigh = KNeighborsClassifier(n_neighbors=3).fit(X, y)
@@ -45,7 +43,6 @@ 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):
-
     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)
     neigh = KNeighborsRegressor(n_neighbors=2).fit(X, y)
@@ -61,7 +58,6 @@ def test_sklearnex_import_knn_regression(dataframe, queue):
     [LocalOutlierFactor, 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)
@@ -74,7 +70,6 @@ def test_sklearnex_kneighbors(estimator, dataframe, queue):
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_lof(dataframe, queue):
-
     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)

sklearnex/preview/__init__.py

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

sklearnex/preview/cluster/k_means.py

@@ -172,24 +172,6 @@ if daal_check_version((2023, "P", 200)):
             return patching_status
 
         def fit(self, X, y=None, sample_weight=None):
-            """Compute k-means clustering.
-
-            Parameters
-            ----------
-            X : array-like or sparse matrix, shape=(n_samples, n_features)
-                Training instances to cluster. It must be noted that the data
-                will be converted to C ordering, which will cause a memory
-                copy if the given data is not C-contiguous.
-
-            y : Ignored
-                not used, present here for API consistency by convention.
-
-            sample_weight : array-like, shape (n_samples,), optional
-                The weights for each observation in X. If None, all observations
-                are assigned equal weight (default: None)
-
-            """
-
             if sklearn_check_version("1.0"):
                 self._check_feature_names(X, reset=True)
             if sklearn_check_version("1.2"):
@@ -257,24 +239,6 @@ if daal_check_version((2023, "P", 200)):
 
         @wrap_output_data
         def predict(self, X):
-            """Compute k-means clustering.
-
-            Parameters
-            ----------
-            X : array-like or sparse matrix, shape=(n_samples, n_features)
-                Training instances to cluster. It must be noted that the data
-                will be converted to C ordering, which will cause a memory
-                copy if the given data is not C-contiguous.
-
-            y : Ignored
-                not used, present here for API consistency by convention.
-
-            sample_weight : array-like, shape (n_samples,), optional
-                The weights for each observation in X. If None, all observations
-                are assigned equal weight (default: None)
-
-            """
-
             if sklearn_check_version("1.0"):
                 self._check_feature_names(X, reset=True)
             if sklearn_check_version("1.2"):
@@ -317,52 +281,20 @@ if daal_check_version((2023, "P", 200)):
 
         @wrap_output_data
         def fit_transform(self, X, y=None, sample_weight=None):
-            """Compute clustering and transform X to cluster-distance space.
-
-            Equivalent to fit(X).transform(X), but more efficiently implemented.
-
-            Parameters
-            ----------
-            X : {array-like, sparse matrix} of shape (n_samples, n_features)
-                New data to transform.
-
-            y : Ignored
-                Not used, present here for API consistency by convention.
-
-            sample_weight : array-like of shape (n_samples,), default=None
-                The weights for each observation in X. If None, all observations
-                are assigned equal weight.
-
-            Returns
-            -------
-            X_new : ndarray of shape (n_samples, n_clusters)
-                X transformed in the new space.
-            """
             return self.fit(X, sample_weight=sample_weight)._transform(X)
 
         @wrap_output_data
         def transform(self, X):
-            """Transform X to a cluster-distance space.
-
-            In the new space, each dimension is the distance to the cluster
-            centers. Note that even if X is sparse, the array returned by
-            `transform` will typically be dense.
-
-            Parameters
-            ----------
-            X : {array-like, sparse matrix} of shape (n_samples, n_features)
-                New data to transform.
-
-            Returns
-            -------
-            X_new : ndarray of shape (n_samples, n_clusters)
-                X transformed in the new space.
-            """
             check_is_fitted(self)
 
             X = self._check_test_data(X)
             return self._transform(X)
 
+        fit.__doc__ = sklearn_KMeans.fit.__doc__
+        predict.__doc__ = sklearn_KMeans.predict.__doc__
+        transform.__doc__ = sklearn_KMeans.transform.__doc__
+        fit_transform.__doc__ = sklearn_KMeans.fit_transform.__doc__
+
 else:
     from daal4py.sklearn.cluster import KMeans
 

sklearnex/preview/covariance/covariance.py

@@ -22,7 +22,7 @@ from sklearn.covariance import EmpiricalCovariance as sklearn_EmpiricalCovarianc
 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 daal4py.sklearn._utils import daal_check_version, sklearn_check_version
 from onedal.common.hyperparameters import get_hyperparameters
 from onedal.covariance import EmpiricalCovariance as onedal_EmpiricalCovariance
 from sklearnex import config_context
@@ -44,6 +44,10 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
 
     def _save_attributes(self):
         assert hasattr(self, "_onedal_estimator")
+        if not daal_check_version((2024, "P", 400)) and self.assume_centered:
+            location = self._onedal_estimator.location_[None, :]
+            self._onedal_estimator.covariance_ += np.dot(location.T, location)
+            self._onedal_estimator.location_ = np.zeros_like(np.squeeze(location))
         self._set_covariance(self._onedal_estimator.covariance_)
         self.location_ = self._onedal_estimator.location_
 
@@ -58,6 +62,7 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
         onedal_params = {
             "method": "dense",
             "bias": True,
+            "assume_centered": self.assume_centered,
         }
 
         self._onedal_estimator = self._onedal_covariance(**onedal_params)
@@ -73,10 +78,6 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
             (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."),
                 ]
             )

sklearnex/preview/covariance/tests/test_covariance.py

@@ -27,27 +27,40 @@ from onedal.tests.utils._dataframes_support import (
 
 @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):
+@pytest.mark.parametrize("assume_centered", [True, False])
+def test_sklearnex_import_covariance(dataframe, queue, macro_block, assume_centered):
     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()
+    empcov = EmpiricalCovariance(assume_centered=assume_centered)
     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])
+    expected_means = np.array([0, 0])
+
+    if assume_centered:
+        expected_covariance = np.array([[0, 0], [0, 1]])
+    else:
+        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])
+
+    if assume_centered:
+        expected_covariance = np.array([[5, 10], [10, 20]])
+    else:
+        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_)

sklearnex/spmd/ensemble/forest.py

@@ -14,8 +14,6 @@
 # limitations under the License.
 # ==============================================================================
 
-from abc import ABC
-
 from onedal.spmd.ensemble import RandomForestClassifier as onedal_RandomForestClassifier
 from onedal.spmd.ensemble import RandomForestRegressor as onedal_RandomForestRegressor
 
@@ -23,16 +21,9 @@ from ...ensemble import RandomForestClassifier as RandomForestClassifier_Batch
 from ...ensemble import RandomForestRegressor as RandomForestRegressor_Batch
 
 
-class BaseForestSPMD(ABC):
-    def _onedal_classifier(self, **onedal_params):
-        return onedal_RandomForestClassifier(**onedal_params)
-
-    def _onedal_regressor(self, **onedal_params):
-        return onedal_RandomForestRegressor(**onedal_params)
-
-
-class RandomForestClassifier(BaseForestSPMD, RandomForestClassifier_Batch):
+class RandomForestClassifier(RandomForestClassifier_Batch):
     __doc__ = RandomForestClassifier_Batch.__doc__
+    _onedal_factory = onedal_RandomForestClassifier
 
     def _onedal_cpu_supported(self, method_name, *data):
         # TODO:
@@ -55,8 +46,9 @@ class RandomForestClassifier(BaseForestSPMD, RandomForestClassifier_Batch):
         return ready
 
 
-class RandomForestRegressor(BaseForestSPMD, RandomForestRegressor_Batch):
+class RandomForestRegressor(RandomForestRegressor_Batch):
     __doc__ = RandomForestRegressor_Batch.__doc__
+    _onedal_factory = onedal_RandomForestRegressor
 
     def _onedal_cpu_supported(self, method_name, *data):
         # TODO:

sklearnex/svm/_common.py

@@ -76,7 +76,7 @@ class BaseSVM(ABC):
         inference_methods = (
             ["predict"]
             if class_name.endswith("R")
-            else ["predict", "predict_proba", "decision_function"]
+            else ["predict", "predict_proba", "decision_function", "score"]
         )
         if method_name in inference_methods:
             patching_status.and_conditions(
@@ -111,12 +111,9 @@ class BaseSVC(BaseSVM):
             cv = StratifiedKFold(
                 n_splits=n_splits, shuffle=True, random_state=self.random_state
             )
-            if sklearn_check_version("0.24"):
-                self.clf_prob = CalibratedClassifierCV(
-                    clf_base, ensemble=False, cv=cv, method="sigmoid", n_jobs=n_jobs
-                )
-            else:
-                self.clf_prob = CalibratedClassifierCV(clf_base, cv=cv, method="sigmoid")
+            self.clf_prob = CalibratedClassifierCV(
+                clf_base, ensemble=False, cv=cv, method="sigmoid", n_jobs=n_jobs
+            )
             self.clf_prob.fit(X, y, sample_weight)
         except ValueError:
             clf_base = clf_base.fit(X, y, sample_weight)