scikit-learn-intelex 2024.0.1__py311-none-manylinux1_x86_64.whl → 2024.4.0__py311-none-manylinux1_x86_64.whl

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/__init__.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ==============================================================================
 # Copyright 2021 Intel Corporation
 #

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)

sklearnex/svm/nusvc.py

@@ -14,11 +14,15 @@
 # limitations under the License.
 # ==============================================================================
 
+import numpy as np
 from sklearn.exceptions import NotFittedError
+from sklearn.metrics import accuracy_score
 from sklearn.svm import NuSVC as sklearn_NuSVC
 from sklearn.utils.validation import _deprecate_positional_args
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
+from sklearnex.utils import get_namespace
 
 from .._device_offload import dispatch, wrap_output_data
 from ._common import BaseSVC
@@ -29,6 +33,9 @@ if sklearn_check_version("1.0"):
 from onedal.svm import NuSVC as onedal_NuSVC
 
 
+@control_n_jobs(
+    decorated_methods=["fit", "predict", "_predict_proba", "decision_function", "score"]
+)
 class NuSVC(sklearn_NuSVC, BaseSVC):
     __doc__ = sklearn_NuSVC.__doc__
 
@@ -74,39 +81,6 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
         )
 
     def fit(self, X, y, sample_weight=None):
-        """
-        Fit the SVM model according to the given training data.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features) \
-                or (n_samples, n_samples)
-            Training vectors, where `n_samples` is the number of samples
-            and `n_features` is the number of features.
-            For kernel="precomputed", the expected shape of X is
-            (n_samples, n_samples).
-
-        y : array-like of shape (n_samples,)
-            Target values (class labels in classification, real numbers in
-            regression).
-
-        sample_weight : array-like of shape (n_samples,), default=None
-            Per-sample weights. Rescale C per sample. Higher weights
-            force the classifier to put more emphasis on these points.
-
-        Returns
-        -------
-        self : object
-            Fitted estimator.
-
-        Notes
-        -----
-        If X and y are not C-ordered and contiguous arrays of np.float64 and
-        X is not a scipy.sparse.csr_matrix, X and/or y may be copied.
-
-        If X is a dense array, then the other methods will not support sparse
-        matrices as input.
-        """
         if sklearn_check_version("1.2"):
             self._validate_params()
         if sklearn_check_version("1.0"):
@@ -127,22 +101,6 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
 
     @wrap_output_data
     def predict(self, X):
-        """
-        Perform regression on samples in X.
-
-        For an one-class model, +1 (inlier) or -1 (outlier) is returned.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-            For kernel="precomputed", the expected shape of X is
-            (n_samples_test, n_samples_train).
-
-        Returns
-        -------
-        y_pred : ndarray of shape (n_samples,)
-            The predicted values.
-        """
         if sklearn_check_version("1.0"):
             self._check_feature_names(X, reset=False)
         return dispatch(
@@ -155,6 +113,22 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        if sklearn_check_version("1.0"):
+            self._check_feature_names(X, reset=False)
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_NuSVC.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     if sklearn_check_version("1.0"):
 
         @available_if(sklearn_NuSVC._check_proba)
@@ -187,6 +161,38 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
             """
             return self._predict_proba(X)
 
+        @available_if(sklearn_NuSVC._check_proba)
+        def predict_log_proba(self, X):
+            """Compute log probabilities of possible outcomes for samples in X.
+
+            The model need to have probability information computed at training
+            time: fit with attribute `probability` set to True.
+
+            Parameters
+            ----------
+            X : array-like of shape (n_samples, n_features) or \
+                    (n_samples_test, n_samples_train)
+                For kernel="precomputed", the expected shape of X is
+                (n_samples_test, n_samples_train).
+
+            Returns
+            -------
+            T : ndarray of shape (n_samples, n_classes)
+                Returns the log-probabilities of the sample for each class in
+                the model. The columns correspond to the classes in sorted
+                order, as they appear in the attribute :term:`classes_`.
+
+            Notes
+            -----
+            The probability model is created using cross validation, so
+            the results can be slightly different than those obtained by
+            predict. Also, it will produce meaningless results on very small
+            datasets.
+            """
+            xp, _ = get_namespace(X)
+
+            return xp.log(self.predict_proba(X))
+
     else:
 
         @property
@@ -194,6 +200,12 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
             self._check_proba()
             return self._predict_proba
 
+        def _predict_log_proba(self, X):
+            xp, _ = get_namespace(X)
+            return xp.log(self.predict_proba(X))
+
+        predict_proba.__doc__ = sklearn_NuSVC.predict_proba.__doc__
+
     @wrap_output_data
     def _predict_proba(self, X):
         if sklearn_check_version("1.0"):
@@ -228,6 +240,8 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
             X,
         )
 
+    decision_function.__doc__ = sklearn_NuSVC.decision_function.__doc__
+
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
         onedal_params = {
             "nu": self.nu,
@@ -270,3 +284,13 @@ class NuSVC(sklearn_NuSVC, BaseSVC):
 
     def _onedal_decision_function(self, X, queue=None):
         return self._onedal_estimator.decision_function(X, queue=queue)
+
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return accuracy_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
+    fit.__doc__ = sklearn_NuSVC.fit.__doc__
+    predict.__doc__ = sklearn_NuSVC.predict.__doc__
+    decision_function.__doc__ = sklearn_NuSVC.decision_function.__doc__
+    score.__doc__ = sklearn_NuSVC.score.__doc__

sklearnex/svm/nusvr.py

@@ -17,6 +17,7 @@
 from sklearn.svm import NuSVR as sklearn_NuSVR
 from sklearn.utils.validation import _deprecate_positional_args
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
 from onedal.svm import NuSVR as onedal_NuSVR
 
@@ -24,6 +25,7 @@ from .._device_offload import dispatch, wrap_output_data
 from ._common import BaseSVR
 
 
+@control_n_jobs(decorated_methods=["fit", "predict"])
 class NuSVR(sklearn_NuSVR, BaseSVR):
     __doc__ = sklearn_NuSVR.__doc__
 
@@ -34,14 +36,14 @@ class NuSVR(sklearn_NuSVR, BaseSVR):
     def __init__(
         self,
         *,
+        nu=0.5,
+        C=1.0,
         kernel="rbf",
         degree=3,
         gamma="scale",
         coef0=0.0,
-        tol=1e-3,
-        C=1.0,
-        nu=0.5,
         shrinking=True,
+        tol=1e-3,
         cache_size=200,
         verbose=False,
         max_iter=-1,
@@ -61,39 +63,6 @@ class NuSVR(sklearn_NuSVR, BaseSVR):
         )
 
     def fit(self, X, y, sample_weight=None):
-        """
-        Fit the SVM model according to the given training data.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features) \
-                or (n_samples, n_samples)
-            Training vectors, where `n_samples` is the number of samples
-            and `n_features` is the number of features.
-            For kernel="precomputed", the expected shape of X is
-            (n_samples, n_samples).
-
-        y : array-like of shape (n_samples,)
-            Target values (class labels in classification, real numbers in
-            regression).
-
-        sample_weight : array-like of shape (n_samples,), default=None
-            Per-sample weights. Rescale C per sample. Higher weights
-            force the classifier to put more emphasis on these points.
-
-        Returns
-        -------
-        self : object
-            Fitted estimator.
-
-        Notes
-        -----
-        If X and y are not C-ordered and contiguous arrays of np.float64 and
-        X is not a scipy.sparse.csr_matrix, X and/or y may be copied.
-
-        If X is a dense array, then the other methods will not support sparse
-        matrices as input.
-        """
         if sklearn_check_version("1.2"):
             self._validate_params()
         if sklearn_check_version("1.0"):
@@ -113,22 +82,6 @@ class NuSVR(sklearn_NuSVR, BaseSVR):
 
     @wrap_output_data
     def predict(self, X):
-        """
-        Perform regression on samples in X.
-
-        For an one-class model, +1 (inlier) or -1 (outlier) is returned.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-            For kernel="precomputed", the expected shape of X is
-            (n_samples_test, n_samples_train).
-
-        Returns
-        -------
-        y_pred : ndarray of shape (n_samples,)
-            The predicted values.
-        """
         if sklearn_check_version("1.0"):
             self._check_feature_names(X, reset=False)
         return dispatch(
@@ -161,3 +114,6 @@ class NuSVR(sklearn_NuSVR, BaseSVR):
 
     def _onedal_predict(self, X, queue=None):
         return self._onedal_estimator.predict(X, queue=queue)
+
+    fit.__doc__ = sklearn_NuSVR.fit.__doc__
+    predict.__doc__ = sklearn_NuSVR.predict.__doc__

sklearnex/svm/svc.py

@@ -17,10 +17,13 @@
 import numpy as np
 from scipy import sparse as sp
 from sklearn.exceptions import NotFittedError
+from sklearn.metrics import accuracy_score
 from sklearn.svm import SVC as sklearn_SVC
 from sklearn.utils.validation import _deprecate_positional_args
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
+from sklearnex.utils import get_namespace
 
 from .._device_offload import dispatch, wrap_output_data
 from .._utils import PatchingConditionsChain
@@ -32,6 +35,9 @@ if sklearn_check_version("1.0"):
 from onedal.svm import SVC as onedal_SVC
 
 
+@control_n_jobs(
+    decorated_methods=["fit", "predict", "_predict_proba", "decision_function", "score"]
+)
 class SVC(sklearn_SVC, BaseSVC):
     __doc__ = sklearn_SVC.__doc__
 
@@ -77,39 +83,6 @@ class SVC(sklearn_SVC, BaseSVC):
         )
 
     def fit(self, X, y, sample_weight=None):
-        """
-        Fit the SVM model according to the given training data.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features) \
-                or (n_samples, n_samples)
-            Training vectors, where `n_samples` is the number of samples
-            and `n_features` is the number of features.
-            For kernel="precomputed", the expected shape of X is
-            (n_samples, n_samples).
-
-        y : array-like of shape (n_samples,)
-            Target values (class labels in classification, real numbers in
-            regression).
-
-        sample_weight : array-like of shape (n_samples,), default=None
-            Per-sample weights. Rescale C per sample. Higher weights
-            force the classifier to put more emphasis on these points.
-
-        Returns
-        -------
-        self : object
-            Fitted estimator.
-
-        Notes
-        -----
-        If X and y are not C-ordered and contiguous arrays of np.float64 and
-        X is not a scipy.sparse.csr_matrix, X and/or y may be copied.
-
-        If X is a dense array, then the other methods will not support sparse
-        matrices as input.
-        """
         if sklearn_check_version("1.2"):
             self._validate_params()
         if sklearn_check_version("1.0"):
@@ -129,22 +102,6 @@ class SVC(sklearn_SVC, BaseSVC):
 
     @wrap_output_data
     def predict(self, X):
-        """
-        Perform regression on samples in X.
-
-        For an one-class model, +1 (inlier) or -1 (outlier) is returned.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-            For kernel="precomputed", the expected shape of X is
-            (n_samples_test, n_samples_train).
-
-        Returns
-        -------
-        y_pred : ndarray of shape (n_samples,)
-            The predicted values.
-        """
         if sklearn_check_version("1.0"):
             self._check_feature_names(X, reset=False)
         return dispatch(
@@ -157,6 +114,22 @@ class SVC(sklearn_SVC, BaseSVC):
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        if sklearn_check_version("1.0"):
+            self._check_feature_names(X, reset=False)
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_SVC.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     if sklearn_check_version("1.0"):
 
         @available_if(sklearn_SVC._check_proba)
@@ -189,6 +162,38 @@ class SVC(sklearn_SVC, BaseSVC):
             """
             return self._predict_proba(X)
 
+        @available_if(sklearn_SVC._check_proba)
+        def predict_log_proba(self, X):
+            """Compute log probabilities of possible outcomes for samples in X.
+
+            The model need to have probability information computed at training
+            time: fit with attribute `probability` set to True.
+
+            Parameters
+            ----------
+            X : array-like of shape (n_samples, n_features) or \
+                    (n_samples_test, n_samples_train)
+                For kernel="precomputed", the expected shape of X is
+                (n_samples_test, n_samples_train).
+
+            Returns
+            -------
+            T : ndarray of shape (n_samples, n_classes)
+                Returns the log-probabilities of the sample for each class in
+                the model. The columns correspond to the classes in sorted
+                order, as they appear in the attribute :term:`classes_`.
+
+            Notes
+            -----
+            The probability model is created using cross validation, so
+            the results can be slightly different than those obtained by
+            predict. Also, it will produce meaningless results on very small
+            datasets.
+            """
+            xp, _ = get_namespace(X)
+
+            return xp.log(self.predict_proba(X))
+
     else:
 
         @property
@@ -196,6 +201,12 @@ class SVC(sklearn_SVC, BaseSVC):
             self._check_proba()
             return self._predict_proba
 
+        def _predict_log_proba(self, X):
+            xp, _ = get_namespace(X)
+            return xp.log(self.predict_proba(X))
+
+        predict_proba.__doc__ = sklearn_SVC.predict_proba.__doc__
+
     @wrap_output_data
     def _predict_proba(self, X):
         sklearn_pred_proba = (
@@ -228,6 +239,8 @@ class SVC(sklearn_SVC, BaseSVC):
             X,
         )
 
+    decision_function.__doc__ = sklearn_SVC.decision_function.__doc__
+
     def _onedal_gpu_supported(self, method_name, *data):
         class_name = self.__class__.__name__
         patching_status = PatchingConditionsChain(
@@ -235,7 +248,7 @@ class SVC(sklearn_SVC, BaseSVC):
         )
         if len(data) > 1:
             self._class_count = len(np.unique(data[1]))
-        self._is_sparse = sp.isspmatrix(data[0])
+        self._is_sparse = sp.issparse(data[0])
         conditions = [
             (
                 self.kernel in ["linear", "rbf"],
@@ -249,7 +262,7 @@ class SVC(sklearn_SVC, BaseSVC):
         if method_name == "fit":
             patching_status.and_conditions(conditions)
             return patching_status
-        if method_name in ["predict", "predict_proba", "decision_function"]:
+        if method_name in ["predict", "predict_proba", "decision_function", "score"]:
             conditions.append(
                 (hasattr(self, "_onedal_estimator"), "oneDAL model was not trained")
             )
@@ -299,3 +312,13 @@ class SVC(sklearn_SVC, BaseSVC):
 
     def _onedal_decision_function(self, X, queue=None):
         return self._onedal_estimator.decision_function(X, queue=queue)
+
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return accuracy_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
+    fit.__doc__ = sklearn_SVC.fit.__doc__
+    predict.__doc__ = sklearn_SVC.predict.__doc__
+    decision_function.__doc__ = sklearn_SVC.decision_function.__doc__
+    score.__doc__ = sklearn_SVC.score.__doc__

sklearnex/svm/svr.py

@@ -17,6 +17,7 @@
 from sklearn.svm import SVR as sklearn_SVR
 from sklearn.utils.validation import _deprecate_positional_args
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
 from onedal.svm import SVR as onedal_SVR
 
@@ -24,6 +25,7 @@ from .._device_offload import dispatch, wrap_output_data
 from ._common import BaseSVR
 
 
+@control_n_jobs(decorated_methods=["fit", "predict"])
 class SVR(sklearn_SVR, BaseSVR):
     __doc__ = sklearn_SVR.__doc__
 
@@ -61,39 +63,6 @@ class SVR(sklearn_SVR, BaseSVR):
         )
 
     def fit(self, X, y, sample_weight=None):
-        """
-        Fit the SVM model according to the given training data.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features) \
-                or (n_samples, n_samples)
-            Training vectors, where `n_samples` is the number of samples
-            and `n_features` is the number of features.
-            For kernel="precomputed", the expected shape of X is
-            (n_samples, n_samples).
-
-        y : array-like of shape (n_samples,)
-            Target values (class labels in classification, real numbers in
-            regression).
-
-        sample_weight : array-like of shape (n_samples,), default=None
-            Per-sample weights. Rescale C per sample. Higher weights
-            force the classifier to put more emphasis on these points.
-
-        Returns
-        -------
-        self : object
-            Fitted estimator.
-
-        Notes
-        -----
-        If X and y are not C-ordered and contiguous arrays of np.float64 and
-        X is not a scipy.sparse.csr_matrix, X and/or y may be copied.
-
-        If X is a dense array, then the other methods will not support sparse
-        matrices as input.
-        """
         if sklearn_check_version("1.2"):
             self._validate_params()
         if sklearn_check_version("1.0"):
@@ -114,22 +83,6 @@ class SVR(sklearn_SVR, BaseSVR):
 
     @wrap_output_data
     def predict(self, X):
-        """
-        Perform regression on samples in X.
-
-        For an one-class model, +1 (inlier) or -1 (outlier) is returned.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-            For kernel="precomputed", the expected shape of X is
-            (n_samples_test, n_samples_train).
-
-        Returns
-        -------
-        y_pred : ndarray of shape (n_samples,)
-            The predicted values.
-        """
         if sklearn_check_version("1.0"):
             self._check_feature_names(X, reset=False)
         return dispatch(
@@ -162,3 +115,6 @@ class SVR(sklearn_SVR, BaseSVR):
 
     def _onedal_predict(self, X, queue=None):
         return self._onedal_estimator.predict(X, queue=queue)
+
+    fit.__doc__ = sklearn_SVR.fit.__doc__
+    predict.__doc__ = sklearn_SVR.predict.__doc__

sklearnex/svm/tests/test_svm.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # ===============================================================================
 # Copyright 2021 Intel Corporation
 #