scikit-learn-intelex 2025.8.0__py312-none-win_amd64.whl → 2025.9.0__py312-none-win_amd64.whl

scikit_learn_intelex-2025.8.0.data/data/Lib/site-packages/onedal/decomposition/pca.py

@@ -1,200 +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 abc import ABCMeta
-
-import numpy as np
-from sklearn.decomposition._pca import _infer_dimension
-from sklearn.utils.extmath import stable_cumsum
-
-from onedal._device_offload import supports_queue
-from onedal.common._backend import bind_default_backend
-
-from .._config import _get_config
-from ..common.hyperparameters import get_hyperparameters
-from ..datatypes import from_table, to_table
-from ..utils._array_api import _get_sycl_namespace
-
-
-class BasePCA(metaclass=ABCMeta):
-
-    def __init__(
-        self,
-        n_components=None,
-        is_deterministic=True,
-        method="cov",
-        whiten=False,
-    ):
-        self.n_components = n_components
-        self.method = method
-        self.is_deterministic = is_deterministic
-        self.whiten = whiten
-
-    # provides direct access to the backend model constructor
-    @bind_default_backend("decomposition.dim_reduction")
-    def model(self): ...
-
-    @bind_default_backend("decomposition.dim_reduction")
-    def train(self, params, X): ...
-
-    @bind_default_backend("decomposition.dim_reduction")
-    def infer(self, params, X, model): ...
-
-    def _get_onedal_params(self, data, stage=None):
-        if stage is None:
-            n_components = self._resolve_n_components_for_training(data.shape)
-        elif stage == "predict":
-            n_components = self.n_components_
-        return {
-            "fptype": data.dtype,
-            "method": self.method,
-            "n_components": n_components,
-            "is_deterministic": self.is_deterministic,
-            "whiten": self.whiten,
-        }
-
-    def _validate_n_components(self, n_components, n_samples, n_features):
-        if n_components is None:
-            n_components = min(n_samples, n_features)
-        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 <= min(n_samples, n_features):
-            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 _resolve_n_components_for_training(self, shape_tuple):
-        if self.n_components is None or self.n_components == "mle":
-            return min(shape_tuple)
-        elif (
-            isinstance(self.n_components, float)
-            and self.n_components > 0.0
-            and self.n_components <= 1.0
-        ):
-            return min(shape_tuple)
-        else:
-            return self.n_components
-
-    def _resolve_n_components_for_result(self, shape_tuple):
-        if self.n_components is None:
-            return min(shape_tuple)
-        elif self.n_components == "mle":
-            return _infer_dimension(self.explained_variance_, shape_tuple[0])
-        elif 0.0 < self.n_components < 1.0:
-            ratio_cumsum = stable_cumsum(self.explained_variance_ratio_)
-            return np.searchsorted(ratio_cumsum, self.n_components, side="right") + 1
-        elif isinstance(self.n_components, float) and self.n_components == 1.0:
-            return min(shape_tuple)
-        else:
-            return self.n_components
-
-    def _compute_noise_variance(self, n_components, n_sf_min):
-        if n_components < n_sf_min:
-            if len(self.explained_variance_) == n_sf_min:
-                return self.explained_variance_[n_components:].mean()
-            elif len(self.explained_variance_) < n_sf_min:
-                # TODO Rename variances_ to var_ to align with sklearn/sklearnex IncrementalPCA
-                if hasattr(self, "variances_"):
-                    resid_var = self.variances_.sum()
-                elif hasattr(self, "var_"):
-                    resid_var = self.var_.sum()
-
-                resid_var -= self.explained_variance_.sum()
-                return resid_var / (n_sf_min - n_components)
-        else:
-            return 0.0
-
-    def _create_model(self):
-        m = self.model()
-        m.eigenvectors = to_table(self.components_)
-        m.means = to_table(self.mean_)
-        if self.whiten:
-            m.eigenvalues = to_table(self.explained_variance_)
-        self._onedal_model = m
-        return m
-
-    @supports_queue
-    def predict(self, X, queue=None):
-        model = self._create_model()
-        X_table = to_table(X, queue=queue)
-        params = self._get_onedal_params(X_table, stage="predict")
-        result = self.infer(params, model, X_table)
-        return from_table(result.transformed_data)
-
-    transform = predict
-
-
-class PCA(BasePCA):
-
-    @supports_queue
-    def fit(self, X, y=None, queue=None):
-        use_raw_input = _get_config().get("use_raw_input", False) is True
-        sua_iface, xp, _ = _get_sycl_namespace(X)
-        if use_raw_input and sua_iface:
-            queue = X.sycl_queue
-
-        n_samples, n_features = X.shape
-        n_sf_min = min(n_samples, n_features)
-        self._validate_n_components(self.n_components, n_samples, n_features)
-
-        # TODO: investigate why np.ndarray with OWNDATA=FALSE flag
-        # fails to be converted to oneDAL table
-        if isinstance(X, np.ndarray) and not X.flags["OWNDATA"]:
-            X = X.copy()
-
-        X = to_table(X, queue=queue)
-        params = self._get_onedal_params(X)
-        hparams = get_hyperparameters("pca", "train")
-        if hparams is not None and not hparams.is_default:
-            result = self.train(params, hparams.backend, X)
-        else:
-            result = self.train(params, X)
-
-        self.mean_ = from_table(result.means).ravel()
-        self.variances_ = from_table(result.variances)
-        self.components_ = from_table(result.eigenvectors)
-        self.singular_values_ = from_table(result.singular_values).ravel()
-        self.explained_variance_ = np.maximum(from_table(result.eigenvalues).ravel(), 0)
-        self.explained_variance_ratio_ = from_table(
-            result.explained_variances_ratio
-        ).ravel()
-        self.n_samples_ = n_samples
-        self.n_features_ = n_features
-
-        n_components = self._resolve_n_components_for_result(X.shape)
-        self.n_components_ = n_components
-        self.noise_variance_ = self._compute_noise_variance(n_components, n_sf_min)
-
-        if n_components < params["n_components"]:
-            self.explained_variance_ = self.explained_variance_[:n_components]
-            self.components_ = self.components_[:n_components]
-            self.singular_values_ = self.singular_values_[:n_components]
-            self.explained_variance_ratio_ = self.explained_variance_ratio_[:n_components]
-
-        return self

scikit_learn_intelex-2025.8.0.data/data/Lib/site-packages/sklearnex/decomposition/pca.py

@@ -1,428 +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.
-# ===============================================================================
-
-import logging
-
-from daal4py.sklearn._utils import daal_check_version
-
-if daal_check_version((2024, "P", 100)):
-    import numbers
-    from math import sqrt
-    from warnings import warn
-
-    import numpy as np
-    from scipy.sparse import issparse
-    from sklearn.utils.validation import check_array, check_is_fitted
-
-    from daal4py.sklearn._n_jobs_support import control_n_jobs
-    from daal4py.sklearn._utils import sklearn_check_version
-
-    from .._device_offload import dispatch, wrap_output_data
-    from .._utils import PatchingConditionsChain, register_hyperparameters
-    from ..base import oneDALEstimator
-    from ..utils._array_api import get_namespace
-    from ..utils.validation import validate_data
-
-    if sklearn_check_version("1.1") and not sklearn_check_version("1.2"):
-        from sklearn.utils import check_scalar
-
-    if sklearn_check_version("1.2"):
-        from sklearn.utils._param_validation import StrOptions
-
-    from sklearn.decomposition import PCA as _sklearn_PCA
-
-    from onedal._device_offload import support_sycl_format
-    from onedal.decomposition import PCA as onedal_PCA
-    from onedal.utils._array_api import _is_numpy_namespace
-
-    @register_hyperparameters({"fit": ("pca", "train")})
-    @control_n_jobs(decorated_methods=["fit", "transform", "fit_transform"])
-    class PCA(oneDALEstimator, _sklearn_PCA):
-        __doc__ = _sklearn_PCA.__doc__
-
-        if sklearn_check_version("1.2"):
-            _parameter_constraints: dict = {**_sklearn_PCA._parameter_constraints}
-            # "onedal_svd" solver uses oneDAL's PCA-SVD algorithm
-            # and required for testing purposes to fully enable it in future.
-            # "covariance_eigh" solver is added for ability to explicitly request
-            # oneDAL's PCA-Covariance algorithm using any sklearn version < 1.5.
-            _parameter_constraints["svd_solver"] = [
-                StrOptions(
-                    _parameter_constraints["svd_solver"][0].options
-                    | {"onedal_svd", "covariance_eigh"}
-                )
-            ]
-
-        if sklearn_check_version("1.1"):
-
-            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
-
-        else:
-
-            def __init__(
-                self,
-                n_components=None,
-                copy=True,
-                whiten=False,
-                svd_solver="auto",
-                tol=0.0,
-                iterated_power="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.random_state = random_state
-
-        # guarantee operability with dpnp/dpctl, runs on CPU unless
-        # array_api_dispatch is enabled.
-        score_samples = support_sycl_format(_sklearn_PCA.score_samples)
-
-        def fit(self, X, y=None):
-            self._fit(X)
-            return self
-
-        @wrap_output_data
-        def _fit(self, X):
-            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,
-                )
-
-            return dispatch(
-                self,
-                "fit",
-                {
-                    "onedal": self.__class__._onedal_fit,
-                    "sklearn": _sklearn_PCA._fit,
-                },
-                X,
-            )
-
-        def _onedal_fit(self, X, queue=None):
-            X = validate_data(
-                self,
-                X,
-                dtype=[np.float64, np.float32],
-                ensure_2d=True,
-                copy=self.copy,
-            )
-
-            onedal_params = {
-                "n_components": self.n_components,
-                "is_deterministic": True,
-                "method": "svd" if self._fit_svd_solver == "onedal_svd" else "cov",
-                "whiten": self.whiten,
-            }
-            self._onedal_estimator = onedal_PCA(**onedal_params)
-            self._onedal_estimator.fit(X, queue=queue)
-            self._save_attributes()
-
-            U = None
-            S = self.singular_values_
-            Vt = self.components_
-
-            if sklearn_check_version("1.5"):
-                xp, _ = get_namespace(X)
-                x_is_centered = not self.copy
-
-                return U, S, Vt, X, x_is_centered, xp
-            else:
-                return U, S, Vt
-
-        @wrap_output_data
-        def transform(self, X):
-            check_is_fitted(self)
-            return dispatch(
-                self,
-                "transform",
-                {
-                    "onedal": self.__class__._onedal_transform,
-                    "sklearn": _sklearn_PCA.transform,
-                },
-                X,
-            )
-
-        def _onedal_transform(self, X, queue=None):
-            X = validate_data(
-                self,
-                X,
-                dtype=[np.float64, np.float32],
-                reset=False,
-            )
-            self._validate_n_features_in_after_fitting(X)
-
-            return self._onedal_estimator.predict(X, queue=queue)
-
-        def fit_transform(self, X, y=None):
-            if sklearn_check_version("1.5"):
-                U, S, Vt, X_fit, x_is_centered, xp = self._fit(X)
-            else:
-                U, S, Vt = self._fit(X)
-                X_fit = X
-            if hasattr(self, "_onedal_estimator"):
-                # oneDAL PCA was fit
-                return self.transform(X)
-            elif U is not None:
-                # Scikit-learn PCA was fit
-                U = U[:, : self.n_components_]
-
-                if self.whiten:
-                    U *= sqrt(X_fit.shape[0] - 1)
-                else:
-                    U *= S[: self.n_components_]
-
-                return U
-            else:
-                # Scikit-learn PCA["covariance_eigh"] was fit
-                return self._transform(X_fit, xp, x_is_centered=x_is_centered)
-
-        def inverse_transform(self, X):
-            # sklearn does not properly input check inverse_transform using
-            # ``validate_data`` (as of sklearn 1.7). Yielding the namespace
-            # in this way will conform to sklearn and various inputs without
-            # causing issues with dimensionality checks, array api support,
-            # etc. evaluated in ``validate_data``. This is a special solution.
-            xp = (
-                func()
-                if (func := getattr(X, "__array_namespace__", None))
-                else get_namespace(X)[0]
-            )
-
-            mean = self.mean_
-            if self.whiten:
-                components = (
-                    xp.sqrt(self.explained_variance_[:, np.newaxis]) * self.components_
-                )
-            else:
-                components = self.components_
-
-            if not _is_numpy_namespace(xp):
-                # Force matching type to input data if possible
-                components = xp.asarray(components, device=X.device)
-                mean = xp.asarray(mean, device=X.device)
-
-            return X @ components + mean
-
-        def _onedal_supported(self, method_name, X):
-            class_name = self.__class__.__name__
-            patching_status = PatchingConditionsChain(
-                f"sklearn.decomposition.{class_name}.{method_name}"
-            )
-
-            if method_name == "fit":
-                shape_tuple, _is_shape_compatible = self._get_shape_compatibility(X)
-                patching_status.and_conditions(
-                    [
-                        (
-                            _is_shape_compatible,
-                            "Data shape is not compatible.",
-                        ),
-                        (
-                            self._is_solver_compatible_with_onedal(shape_tuple),
-                            (
-                                "Only 'covariance_eigh' and 'onedal_svd' "
-                                "solvers are supported."
-                                if sklearn_check_version("1.5")
-                                else "Only 'full', 'covariance_eigh' and 'onedal_svd' "
-                                "solvers are supported."
-                            ),
-                        ),
-                        (not issparse(X), "oneDAL PCA does not support sparse data"),
-                    ]
-                )
-                return patching_status
-
-            if method_name == "transform":
-                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)
-
-        def _get_shape_compatibility(self, X):
-            _is_shape_compatible = False
-            _empty_shape = (0, 0)
-            if hasattr(X, "shape"):
-                shape_tuple = X.shape
-                if len(shape_tuple) == 1:
-                    shape_tuple = (1, shape_tuple[0])
-            elif isinstance(X, list):
-                if np.ndim(X) == 1:
-                    shape_tuple = (1, len(X))
-                elif np.ndim(X) == 2:
-                    shape_tuple = (len(X), len(X[0]))
-            else:
-                return _empty_shape, _is_shape_compatible
-
-            if shape_tuple[0] > 0 and shape_tuple[1] > 0 and len(shape_tuple) == 2:
-                _is_shape_compatible = shape_tuple[1] / shape_tuple[0] < 2
-
-            return shape_tuple, _is_shape_compatible
-
-        def _is_solver_compatible_with_onedal(self, shape_tuple):
-            self._fit_svd_solver = self.svd_solver
-            n_sf_min = min(shape_tuple)
-            n_components = n_sf_min if self.n_components is None else self.n_components
-
-            if self._fit_svd_solver == "auto":
-                if sklearn_check_version("1.1"):
-                    if (
-                        sklearn_check_version("1.5")
-                        and shape_tuple[1] <= 1_000
-                        and shape_tuple[0] >= 10 * shape_tuple[1]
-                    ):
-                        self._fit_svd_solver = "covariance_eigh"
-                    elif max(shape_tuple) <= 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:
-                        # check if sklearnex is faster than randomized sklearn
-                        # Refer to daal4py
-                        regression_coefs = np.array(
-                            [
-                                [
-                                    9.779873e-11,
-                                    shape_tuple[0] * shape_tuple[1] * n_components,
-                                ],
-                                [
-                                    -1.122062e-11,
-                                    shape_tuple[0] * shape_tuple[1] * shape_tuple[1],
-                                ],
-                                [1.127905e-09, shape_tuple[0] ** 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"
-
-            # Use oneDAL in next cases:
-            # 1. oneDAL SVD solver is explicitly set
-            # 2. solver is set or dispatched to "covariance_eigh"
-            # 3. solver is set or dispatched to "full" and sklearn version < 1.5
-            # 4. solver is set to "auto" and dispatched to "full"
-            if self._fit_svd_solver in ["onedal_svd", "covariance_eigh"]:
-                return True
-            elif not sklearn_check_version("1.5") and self._fit_svd_solver == "full":
-                self._fit_svd_solver = "covariance_eigh"
-                return True
-            elif self.svd_solver == "auto" and self._fit_svd_solver == "full":
-                warn(
-                    "Sklearnex always uses `covariance_eigh` solver instead of `full` "
-                    "when `svd_solver` parameter is set to `auto` "
-                    "for performance purposes."
-                )
-                self._fit_svd_solver = "covariance_eigh"
-                return True
-            else:
-                return False
-
-        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_
-            else:
-                self.n_features_ = self._onedal_estimator.n_features_
-                self.n_features_in_ = self._onedal_estimator.n_features_
-            self.n_components_ = self._onedal_estimator.n_components_
-            self.components_ = self._onedal_estimator.components_
-            self.mean_ = self._onedal_estimator.mean_
-            self.singular_values_ = self._onedal_estimator.singular_values_
-            self.explained_variance_ = self._onedal_estimator.explained_variance_.ravel()
-            self.explained_variance_ratio_ = (
-                self._onedal_estimator.explained_variance_ratio_
-            )
-            self.noise_variance_ = self._onedal_estimator.noise_variance_
-
-        def _validate_n_features_in_after_fitting(self, X):
-            if sklearn_check_version("1.2"):
-                expected_n_features = self.n_features_in_
-            else:
-                expected_n_features = self.n_features_
-            if X.shape[1] != expected_n_features:
-                raise ValueError(
-                    (
-                        f"X has {X.shape[1]} features, "
-                        f"but PCA is expecting {expected_n_features} features as input"
-                    )
-                )
-
-        fit.__doc__ = _sklearn_PCA.fit.__doc__
-        transform.__doc__ = _sklearn_PCA.transform.__doc__
-        fit_transform.__doc__ = _sklearn_PCA.fit_transform.__doc__
-        inverse_transform.__doc__ = _sklearn_PCA.inverse_transform.__doc__
-        score_samples.__doc__ = _sklearn_PCA.score_samples.__doc__
-
-else:
-    from daal4py.sklearn.decomposition import PCA
-
-    logging.warning(
-        "Sklearnex PCA requires oneDAL version >= 2024.1.0 but it was not found"
-    )