scikit-learn-intelex 2024.1.0__py310-none-win_amd64.whl → 2025.1.0__py310-none-win_amd64.whl

scikit_learn_intelex-2024.1.0.data/data/Lib/site-packages/sklearnex/preview/decomposition/pca.py

@@ -1,376 +0,0 @@
-# ===============================================================================
-# Copyright 2023 Intel Corporation
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-# ===============================================================================
-
-import numbers
-from math import sqrt
-
-import numpy as np
-from scipy.sparse import issparse
-from sklearn.base import BaseEstimator
-from sklearn.utils.extmath import stable_cumsum
-from sklearn.utils.validation import check_array, check_is_fitted
-
-from daal4py.sklearn._utils import control_n_jobs, run_with_n_jobs, sklearn_check_version
-from onedal.utils import _check_array
-
-from ..._device_offload import dispatch
-from ..._utils import PatchingConditionsChain, register_hyperparameters
-
-if sklearn_check_version("1.1") and not sklearn_check_version("1.2"):
-    from sklearn.utils import check_scalar
-if sklearn_check_version("0.23"):
-    from sklearn.decomposition._pca import _infer_dimension
-else:
-    from sklearn.decomposition._pca import _infer_dimension_
-
-from sklearn.decomposition import PCA as sklearn_PCA
-
-from onedal.common.hyperparameters import get_hyperparameters
-from onedal.decomposition import PCA as onedal_PCA
-
-
-@register_hyperparameters({"fit": get_hyperparameters("covariance", "compute")})
-@control_n_jobs
-class PCA(sklearn_PCA):
-    __doc__ = sklearn_PCA.__doc__
-
-    if sklearn_check_version("1.2"):
-        _parameter_constraints: dict = {**sklearn_PCA._parameter_constraints}
-
-    def __init__(
-        self,
-        n_components=None,
-        *,
-        copy=True,
-        whiten=False,
-        svd_solver="auto",
-        tol=0.0,
-        iterated_power="auto",
-        n_oversamples=10,
-        power_iteration_normalizer="auto",
-        random_state=None,
-    ):
-        self.n_components = n_components
-        self.copy = copy
-        self.whiten = whiten
-        self.svd_solver = svd_solver
-        self.tol = tol
-        self.iterated_power = iterated_power
-        self.n_oversamples = n_oversamples
-        self.power_iteration_normalizer = power_iteration_normalizer
-        self.random_state = random_state
-
-    def _validate_n_components(self, n_components, n_samples, n_features, n_sf_min):
-        if n_components == "mle":
-            if n_samples < n_features:
-                raise ValueError(
-                    "n_components='mle' is only supported if" " n_samples >= n_features"
-                )
-        elif not 0 <= n_components <= n_sf_min:
-            raise ValueError(
-                "n_components=%r must be between 0 and "
-                "min(n_samples, n_features)=%r with "
-                "svd_solver='full'" % (n_components, min(n_samples, n_features))
-            )
-        elif n_components >= 1:
-            if not isinstance(n_components, numbers.Integral):
-                raise ValueError(
-                    "n_components=%r must be of type int "
-                    "when greater than or equal to 1, "
-                    "was of type=%r" % (n_components, type(n_components))
-                )
-
-    def fit(self, X, y=None):
-        if sklearn_check_version("1.2"):
-            self._validate_params()
-        elif sklearn_check_version("1.1"):
-            check_scalar(
-                self.n_oversamples,
-                "n_oversamples",
-                min_val=1,
-                target_type=numbers.Integral,
-            )
-
-        if sklearn_check_version("0.23"):
-            X = self._validate_data(
-                X,
-                dtype=[np.float64, np.float32],
-                ensure_2d=True,
-                copy=False,
-                accept_sparse=True,
-            )
-        else:
-            X = _check_array(
-                X,
-                dtype=[np.float64, np.float32],
-                ensure_2d=True,
-                copy=False,
-                accept_sparse=True,
-            )
-
-        n_samples, n_features = X.shape
-        n_sf_min = min(n_samples, n_features)
-
-        if self.n_components is None:
-            if self.svd_solver == "arpack":
-                n_components = n_sf_min - 1
-            else:
-                n_components = n_sf_min
-        else:
-            n_components = self.n_components
-
-        self._validate_n_components(n_components, n_samples, n_features, n_sf_min)
-
-        self._fit_svd_solver = self.svd_solver
-
-        if self._fit_svd_solver == "auto":
-            if sklearn_check_version("1.1"):
-                if max(X.shape) <= 500 or n_components == "mle":
-                    self._fit_svd_solver = "full"
-                elif 1 <= n_components < 0.8 * n_sf_min:
-                    self._fit_svd_solver = "randomized"
-                else:
-                    self._fit_svd_solver = "full"
-            else:
-                if n_components == "mle":
-                    self._fit_svd_solver = "full"
-                else:
-                    n, p, k = X.shape[0], X.shape[1], n_components
-                    # check if sklearnex is faster than randomized sklearn
-                    # Refer to daal4py
-                    regression_coefs = np.array(
-                        [
-                            [9.779873e-11, n * p * k],
-                            [-1.122062e-11, n * p * p],
-                            [1.127905e-09, n**2],
-                        ]
-                    )
-
-                    if (
-                        n_components >= 1
-                        and np.dot(regression_coefs[:, 0], regression_coefs[:, 1]) <= 0
-                    ):
-                        self._fit_svd_solver = "randomized"
-                    else:
-                        self._fit_svd_solver = "full"
-
-        dispatch(
-            self,
-            "fit",
-            {
-                "onedal": self.__class__._onedal_fit,
-                "sklearn": sklearn_PCA.fit,
-            },
-            X,
-        )
-        return self
-
-    def _onedal_supported(self, method_name, *data):
-        class_name = self.__class__.__name__
-        X = data[0]
-
-        if method_name == "fit":
-            patching_status = PatchingConditionsChain(
-                f"sklearn.decomposition.{class_name}.{method_name}"
-            )
-            patching_status.and_conditions(
-                [
-                    (
-                        self._fit_svd_solver == "full",
-                        f"'{self._fit_svd_solver}' SVD solver is not supported. "
-                        "Only 'full' solver is supported.",
-                    ),
-                    (not issparse(X), "oneDAL PCA does not support sparse inputs"),
-                    (
-                        X.shape[1] / X.shape[0] < 2,
-                        "The shape of X does not satisfy oneDAL requirements: "
-                        "number of features / number of samples >= 2",
-                    ),
-                ]
-            )
-            return patching_status
-        elif method_name == "transform":
-            patching_status = PatchingConditionsChain(
-                f"sklearn.decomposition.{class_name}.{method_name}"
-            )
-            patching_status.and_conditions(
-                [
-                    (hasattr(self, "_onedal_estimator"), "oneDAL model was not trained"),
-                ]
-            )
-            return patching_status
-        raise RuntimeError(f"Unknown method {method_name} in {self.__class__.__name__}")
-
-    def _onedal_cpu_supported(self, method_name, *data):
-        return self._onedal_supported(method_name, *data)
-
-    def _onedal_gpu_supported(self, method_name, *data):
-        return self._onedal_supported(method_name, *data)
-
-    @run_with_n_jobs
-    def _onedal_fit(self, X, y=None, queue=None):
-        if self.n_components == "mle" or self.n_components is None:
-            onedal_n_components = min(X.shape)
-        elif 0 < self.n_components < 1:
-            onedal_n_components = min(X.shape)
-        else:
-            onedal_n_components = self.n_components
-
-        onedal_params = {
-            "n_components": onedal_n_components,
-            "is_deterministic": True,
-            "method": "precomputed",
-        }
-        self._onedal_estimator = onedal_PCA(**onedal_params)
-        self._onedal_estimator.fit(X, queue=queue)
-        self._save_attributes()
-
-        U = None
-        S = self.singular_values_
-        V = self.components_
-
-        return U, S, V
-
-    @run_with_n_jobs
-    def _onedal_predict(self, X, queue=None):
-        return self._onedal_estimator.predict(X, queue)
-
-    @run_with_n_jobs
-    def _onedal_transform(self, X):
-        X = _check_array(X, dtype=[np.float64, np.float32], ensure_2d=True, copy=False)
-
-        if hasattr(self, "n_features_in_"):
-            if self.n_features_in_ != X.shape[1]:
-                raise ValueError(
-                    f"X has {X.shape[1]} features, "
-                    f"but {self.__class__.__name__} is expecting "
-                    f"{self.n_features_in_} features as input"
-                )
-        elif hasattr(self, "n_features_"):
-            if self.n_features_ != X.shape[1]:
-                raise ValueError(
-                    f"X has {X.shape[1]} features, "
-                    f"but {self.__class__.__name__} is expecting "
-                    f"{self.n_features_} features as input"
-                )
-
-        # Mean center
-        X_centered = X - self.mean_
-        return dispatch(
-            self,
-            "transform",
-            {
-                "onedal": self.__class__._onedal_predict,
-                "sklearn": sklearn_PCA.transform,
-            },
-            X_centered,
-        )
-
-    def transform(self, X):
-        check_is_fitted(self)
-        if hasattr(self, "_onedal_estimator"):
-            X_new = self._onedal_transform(X)[:, : self.n_components_]
-            if self.whiten:
-                X_new /= np.sqrt(self.explained_variance_)
-        else:
-            return super().transform(X)
-        return X_new
-
-    def fit_transform(self, X, y=None):
-        """Fit the model with X and apply the dimensionality reduction on X.
-        Parameters
-        ----------
-        X : array-like of shape (n_samples, n_features)
-            Training data, where `n_samples` is the number of samples
-            and `n_features` is the number of features.
-        y : Ignored.
-
-        Returns
-        -------
-        X_new : ndarray of shape (n_samples, n_components)
-            Transformed values of X.
-        """
-        if self.svd_solver in ["randomized", "arpack"]:
-            return super().fit_transform(X)
-        else:
-            self.fit(X)
-            if hasattr(self, "_onedal_estimator"):
-                X_new = self._onedal_transform(X)[:, : self.n_components_]
-                if self.whiten:
-                    X_new /= np.sqrt(self.explained_variance_)
-                return X_new
-            else:
-                return super().transform(X)
-
-    fit.__doc__ = sklearn_PCA.fit.__doc__
-    transform.__doc__ = sklearn_PCA.transform.__doc__
-    fit_transform.__doc__ = sklearn_PCA.fit_transform.__doc__
-
-    def _save_attributes(self):
-        self.n_samples_ = self._onedal_estimator.n_samples_
-
-        if sklearn_check_version("1.2"):
-            self.n_features_in_ = self._onedal_estimator.n_features_in_
-            n_features = self.n_features_in_
-        elif sklearn_check_version("0.24"):
-            self.n_features_ = self._onedal_estimator.n_features_
-            self.n_features_in_ = self._onedal_estimator.n_features_in_
-            n_features = self.n_features_in_
-        else:
-            self.n_features_ = self._onedal_estimator.n_features_
-            n_features = self.n_features_
-        n_sf_min = min(self.n_samples_, n_features)
-
-        self.mean_ = self._onedal_estimator.mean_
-        self.singular_values_ = self._onedal_estimator.singular_values_
-        self.explained_variance_ = self._onedal_estimator.explained_variance_
-        self.explained_variance_ratio_ = self._onedal_estimator.explained_variance_ratio_
-
-        if self.n_components is None:
-            self.n_components_ = self._onedal_estimator.n_components_
-        elif self.n_components == "mle":
-            if sklearn_check_version("0.23"):
-                self.n_components_ = _infer_dimension(
-                    self.explained_variance_, self.n_samples_
-                )
-            else:
-                self.n_components_ = _infer_dimension_(
-                    self.explained_variance_, self.n_samples_, n_features
-                )
-        elif 0 < self.n_components < 1.0:
-            ratio_cumsum = stable_cumsum(self.explained_variance_ratio_)
-            self.n_components_ = (
-                np.searchsorted(ratio_cumsum, self.n_components, side="right") + 1
-            )
-        else:
-            self.n_components_ = self._onedal_estimator.n_components_
-
-        if self.n_components_ < n_sf_min:
-            if self.explained_variance_.shape[0] == n_sf_min:
-                self.noise_variance_ = self.explained_variance_[
-                    self.n_components_ :
-                ].mean()
-            else:
-                self.noise_variance_ = self._onedal_estimator.noise_variance_
-        else:
-            self.noise_variance_ = 0.0
-
-        self.explained_variance_ = self.explained_variance_[: self.n_components_]
-        self.explained_variance_ratio_ = self.explained_variance_ratio_[
-            : self.n_components_
-        ]
-        self.components_ = self._onedal_estimator.components_[: self.n_components_]
-        self.singular_values_ = self.singular_values_[: self.n_components_]

scikit_learn_intelex-2024.1.0.data/data/Lib/site-packages/sklearnex/preview/linear_model/tests/test_preview_logistic_regression.py

@@ -1,59 +0,0 @@
-# ===============================================================================
-# Copyright 2023 Intel Corporation
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-# ===============================================================================
-
-import numpy as np
-import pytest
-from numpy.testing import assert_allclose
-from sklearn.datasets import load_breast_cancer
-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,
-)
-from sklearnex import config_context
-
-
-@pytest.mark.parametrize(
-    "dataframe,queue",
-    get_dataframes_and_queues(dataframe_filter_="dpnp,dpctl", device_filter_="gpu"),
-)
-def test_sklearnex_import(dataframe, queue):
-    from sklearnex.preview.linear_model import LogisticRegression
-
-    X, y = load_breast_cancer(return_X_y=True)
-    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)
-
-    model = LogisticRegression(fit_intercept=True, solver="newton-cg")
-    model.fit(X_train, y_train)
-    y_pred = _as_numpy(model.predict(X_test))
-    if daal_check_version((2024, "P", 1)):
-        assert "sklearnex" in model.__module__
-    else:
-        assert "daal4py" in model.__module__
-    # in case dataframe='numpy' algorithm should fallback to sklearn
-    # as cpu method is not implemented in onedal
-    if dataframe != "numpy" and daal_check_version((2024, "P", 1)):
-        assert hasattr(model, "_onedal_estimator")
-    assert accuracy_score(y_test, y_pred) > 0.95

scikit_learn_intelex-2024.1.0.data/data/Lib/site-packages/sklearnex/svm/_common.py

@@ -1,188 +0,0 @@
-# ==============================================================================
-# Copyright 2021 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 abc import ABC
-
-import numpy as np
-from sklearn.calibration import CalibratedClassifierCV
-from sklearn.model_selection import StratifiedKFold
-from sklearn.preprocessing import LabelEncoder
-
-from daal4py.sklearn._utils import sklearn_check_version
-from onedal.utils import _column_or_1d
-
-from .._utils import PatchingConditionsChain
-
-
-def get_dual_coef(self):
-    return self.dual_coef_
-
-
-def set_dual_coef(self, value):
-    self.dual_coef_ = value
-    if hasattr(self, "_onedal_estimator"):
-        self._onedal_estimator.dual_coef_ = value
-        if not self._is_in_fit:
-            del self._onedal_estimator._onedal_model
-
-
-def get_intercept(self):
-    return self._intercept_
-
-
-def set_intercept(self, value):
-    self._intercept_ = value
-    if hasattr(self, "_onedal_estimator"):
-        self._onedal_estimator.intercept_ = value
-        if not self._is_in_fit:
-            del self._onedal_estimator._onedal_model
-
-
-class BaseSVM(ABC):
-    def _onedal_gpu_supported(self, method_name, *data):
-        patching_status = PatchingConditionsChain(f"sklearn.{method_name}")
-        patching_status.and_conditions([(False, "GPU offloading is not supported.")])
-        return patching_status
-
-    def _onedal_cpu_supported(self, method_name, *data):
-        class_name = self.__class__.__name__
-        patching_status = PatchingConditionsChain(
-            f"sklearn.svm.{class_name}.{method_name}"
-        )
-        if method_name == "fit":
-            patching_status.and_conditions(
-                [
-                    (
-                        self.kernel in ["linear", "rbf", "poly", "sigmoid"],
-                        f'Kernel is "{self.kernel}" while '
-                        '"linear", "rbf", "poly" and "sigmoid" are only supported.',
-                    )
-                ]
-            )
-            return patching_status
-        inference_methods = (
-            ["predict"]
-            if class_name.endswith("R")
-            else ["predict", "predict_proba", "decision_function"]
-        )
-        if method_name in inference_methods:
-            patching_status.and_conditions(
-                [(hasattr(self, "_onedal_estimator"), "oneDAL model was not trained.")]
-            )
-            return patching_status
-        raise RuntimeError(f"Unknown method {method_name} in {class_name}")
-
-
-class BaseSVC(BaseSVM):
-    def _compute_balanced_class_weight(self, y):
-        y_ = _column_or_1d(y)
-        classes, _ = np.unique(y_, return_inverse=True)
-
-        le = LabelEncoder()
-        y_ind = le.fit_transform(y_)
-        if not all(np.in1d(classes, le.classes_)):
-            raise ValueError("classes should have valid labels that are in y")
-
-        recip_freq = len(y_) / (len(le.classes_) * np.bincount(y_ind).astype(np.float64))
-        return recip_freq[le.transform(classes)]
-
-    def _fit_proba(self, X, y, sample_weight=None, queue=None):
-        params = self.get_params()
-        params["probability"] = False
-        params["decision_function_shape"] = "ovr"
-        clf_base = self.__class__(**params)
-
-        try:
-            n_splits = 5
-            n_jobs = n_splits if queue is None or queue.sycl_device.is_cpu else 1
-            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.fit(X, y, sample_weight)
-        except ValueError:
-            clf_base = clf_base.fit(X, y, sample_weight)
-            self.clf_prob = CalibratedClassifierCV(
-                clf_base, cv="prefit", method="sigmoid"
-            )
-            self.clf_prob.fit(X, y, sample_weight)
-
-    def _save_attributes(self):
-        self.support_vectors_ = self._onedal_estimator.support_vectors_
-        self.n_features_in_ = self._onedal_estimator.n_features_in_
-        self.fit_status_ = 0
-        self.dual_coef_ = self._onedal_estimator.dual_coef_
-        self.shape_fit_ = self._onedal_estimator.class_weight_
-        self.classes_ = self._onedal_estimator.classes_
-        self.class_weight_ = self._onedal_estimator.class_weight_
-        self.support_ = self._onedal_estimator.support_
-
-        self._intercept_ = self._onedal_estimator.intercept_
-        self._n_support = self._onedal_estimator._n_support
-        self._sparse = False
-        self._gamma = self._onedal_estimator._gamma
-        if self.probability:
-            length = int(len(self.classes_) * (len(self.classes_) - 1) / 2)
-            self._probA = np.zeros(length)
-            self._probB = np.zeros(length)
-        else:
-            self._probA = np.empty(0)
-            self._probB = np.empty(0)
-
-        self._dual_coef_ = property(get_dual_coef, set_dual_coef)
-        self.intercept_ = property(get_intercept, set_intercept)
-
-        self._is_in_fit = True
-        self._dual_coef_ = self.dual_coef_
-        self.intercept_ = self._intercept_
-        self._is_in_fit = False
-
-        if sklearn_check_version("1.1"):
-            length = int(len(self.classes_) * (len(self.classes_) - 1) / 2)
-            self.n_iter_ = np.full((length,), self._onedal_estimator.n_iter_)
-
-
-class BaseSVR(BaseSVM):
-    def _save_attributes(self):
-        self.support_vectors_ = self._onedal_estimator.support_vectors_
-        self.n_features_in_ = self._onedal_estimator.n_features_in_
-        self.fit_status_ = 0
-        self.dual_coef_ = self._onedal_estimator.dual_coef_
-        self.shape_fit_ = self._onedal_estimator.shape_fit_
-        self.support_ = self._onedal_estimator.support_
-
-        self._intercept_ = self._onedal_estimator.intercept_
-        self._n_support = [self.support_vectors_.shape[0]]
-        self._sparse = False
-        self._gamma = self._onedal_estimator._gamma
-        self._probA = None
-        self._probB = None
-
-        self._dual_coef_ = property(get_dual_coef, set_dual_coef)
-        self.intercept_ = property(get_intercept, set_intercept)
-
-        self._is_in_fit = True
-        self._dual_coef_ = self.dual_coef_
-        self.intercept_ = self._intercept_
-        self._is_in_fit = False
-
-        if sklearn_check_version("1.1"):
-            self.n_iter_ = self._onedal_estimator.n_iter_