scikit-learn-intelex 2024.1.0__py311-none-manylinux1_x86_64.whl → 2024.4.0__py311-none-manylinux1_x86_64.whl

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
 
@@ -23,12 +22,16 @@ 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)
     neigh = KNeighborsClassifier(n_neighbors=3).fit(X, y)
@@ -40,8 +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):
-    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)
     neigh = KNeighborsRegressor(n_neighbors=2).fit(X, y)
@@ -51,18 +52,16 @@ 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 +70,11 @@ 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"]

sklearnex/preview/cluster/k_means.py

@@ -29,18 +29,15 @@ if daal_check_version((2023, "P", 200)):
         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.cluster import KMeans as onedal_KMeans
 
     from ..._device_offload import dispatch, wrap_output_data
     from ..._utils import PatchingConditionsChain
     from ._common import BaseKMeans
 
-    @control_n_jobs
+    @control_n_jobs(decorated_methods=["fit", "predict"])
     class KMeans(sklearn_KMeans, BaseKMeans):
         __doc__ = sklearn_KMeans.__doc__
         n_iter_, inertia_ = None, None
@@ -175,24 +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"):
@@ -212,7 +191,6 @@ if daal_check_version((2023, "P", 200)):
 
             return self
 
-        @run_with_n_jobs
         def _onedal_fit(self, X, _, sample_weight, queue=None):
             assert sample_weight is None
 
@@ -261,24 +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"):
@@ -294,7 +254,6 @@ if daal_check_version((2023, "P", 200)):
                 X,
             )
 
-        @run_with_n_jobs
         def _onedal_predict(self, X, queue=None):
             X = self._validate_data(
                 X, accept_sparse=False, reset=False, dtype=[np.float64, np.float32]
@@ -322,52 +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

@@ -14,35 +14,55 @@
 # 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._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 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
+from sklearnex.metrics import pairwise_distances
 
-from ..._device_offload import dispatch
+from ..._device_offload import dispatch, wrap_output_data
 from ..._utils import PatchingConditionsChain, register_hyperparameters
 
 
 @register_hyperparameters({"fit": get_hyperparameters("covariance", "compute")})
-@control_n_jobs
+@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.covariance_ = self._onedal_estimator.covariance_
+        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_
 
     _onedal_covariance = staticmethod(onedal_EmpiricalCovariance)
 
-    @run_with_n_jobs
     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,
+            "assume_centered": self.assume_centered,
         }
 
         self._onedal_estimator = self._onedal_covariance(**onedal_params)
@@ -54,18 +74,10 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
         patching_status = PatchingConditionsChain(
             f"sklearn.covariance.{class_name}.{method_name}"
         )
-        if method_name == "fit":
+        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",
-                    ),
-                    (
-                        self.store_precision == False,
-                        "precision matrix calculation is not supported on oneDAL side",
-                    ),
                     (not sp.issparse(X), "X is sparse. Sparse input is not supported."),
                 ]
             )
@@ -79,9 +91,9 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
         if sklearn_check_version("1.2"):
             self._validate_params()
         if sklearn_check_version("0.23"):
-            self._validate_data(X)
+            X = self._validate_data(X, force_all_finite=False)
         else:
-            check_array(X)
+            X = check_array(X, force_all_finite=False)
 
         dispatch(
             self,
@@ -95,4 +107,27 @@ class EmpiricalCovariance(sklearn_EmpiricalCovariance):
 
         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__

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/__init__.py

@@ -17,6 +17,7 @@
 __all__ = [
     "basic_statistics",
     "cluster",
+    "covariance",
     "decomposition",
     "ensemble",
     "linear_model",

sklearnex/{preview/linear_model → spmd/covariance}/__init__.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.
@@ -12,8 +12,8 @@
 # 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 .logistic_regression import LogisticRegression
+from .covariance import EmpiricalCovariance
 
-__all__ = ["LogisticRegression"]
+__all__ = ["EmpiricalCovariance"]

sklearnex/spmd/covariance/covariance.py

@@ -0,0 +1,21 @@
+# ==============================================================================
+# 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 onedal.spmd.covariance import EmpiricalCovariance
+
+# TODO:
+# Currently it uses `onedal` module interface.
+# Add sklearnex dispatching.

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/spmd/linear_model/__init__.py

@@ -15,5 +15,6 @@
 # ==============================================================================
 
 from .linear_model import LinearRegression
+from .logistic_regression import LogisticRegression
 
-__all__ = ["LinearRegression"]
+__all__ = ["LinearRegression", "LogisticRegression"]

sklearnex/spmd/linear_model/logistic_regression.py

@@ -0,0 +1,21 @@
+# ==============================================================================
+# 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 onedal.spmd.linear_model import LogisticRegression
+
+# TODO:
+# Currently it uses `onedal` module interface.
+# Add sklearnex dispatching.

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)