scikit-learn-intelex 2025.4.0__py313-none-win_amd64.whl

scikit_learn_intelex-2025.4.0.data/data/Lib/site-packages/onedal/linear_model/linear_model.py

@@ -0,0 +1,325 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from abc import ABCMeta, abstractmethod
+from numbers import Number
+
+import numpy as np
+
+from daal4py.sklearn._utils import daal_check_version, get_dtype, make2d
+
+from ..common._base import BaseEstimator
+from ..common._estimator_checks import _check_is_fitted
+from ..common.hyperparameters import get_hyperparameters
+from ..datatypes import from_table, to_table
+from ..utils import _check_array, _check_n_features, _check_X_y, _num_features
+
+
+class BaseLinearRegression(BaseEstimator, metaclass=ABCMeta):
+    """
+    Base class for LinearRegression oneDAL implementation.
+    """
+
+    @abstractmethod
+    def __init__(self, fit_intercept, copy_X, algorithm, alpha=0.0):
+        self.fit_intercept = fit_intercept
+        self.alpha = alpha
+        self.copy_X = copy_X
+        self.algorithm = algorithm
+
+    def _get_onedal_params(self, dtype=np.float32):
+        intercept = "intercept|" if self.fit_intercept else ""
+        params = {
+            "fptype": dtype,
+            "method": self.algorithm,
+            "intercept": self.fit_intercept,
+            "result_option": (intercept + "coefficients"),
+        }
+        if daal_check_version((2024, "P", 600)):
+            params["alpha"] = self.alpha
+
+        return params
+
+    def _create_model(self, policy):
+        module = self._get_backend("linear_model", "regression")
+        model = module.model()
+
+        coefficients = self.coef_
+        dtype = get_dtype(coefficients)
+
+        if coefficients.ndim == 2:
+            n_features_in = coefficients.shape[1]
+            n_targets_in = coefficients.shape[0]
+        else:
+            n_features_in = coefficients.size
+            n_targets_in = 1
+
+        intercept = self.intercept_
+        if isinstance(intercept, Number):
+            assert n_targets_in == 1
+        else:
+            if not isinstance(intercept, np.ndarray):
+                intercept = np.asarray(intercept, dtype=dtype)
+            assert n_targets_in == intercept.size
+
+        coefficients, intercept = make2d(coefficients), make2d(intercept)
+        coefficients = coefficients.T if n_targets_in == 1 else coefficients
+
+        assert coefficients.shape == (
+            n_targets_in,
+            n_features_in,
+        ), f"{coefficients.shape}, {n_targets_in}, {n_features_in}"
+        assert intercept.shape == (n_targets_in, 1), f"{intercept.shape}, {n_targets_in}"
+
+        desired_shape = (n_targets_in, n_features_in + 1)
+        packed_coefficients = np.zeros(desired_shape, dtype=dtype)
+
+        packed_coefficients[:, 1:] = coefficients
+        if self.fit_intercept:
+            packed_coefficients[:, 0][:, np.newaxis] = intercept
+
+        model.packed_coefficients = to_table(
+            packed_coefficients, queue=getattr(policy, "_queue", None)
+        )
+
+        self._onedal_model = model
+
+        return model
+
+    def predict(self, X, queue=None):
+        """
+        Predict using the linear model.
+        Parameters
+        ----------
+        X : array-like or sparse matrix, shape (n_samples, n_features)
+            Samples.
+
+        queue : dpctl.SyclQueue
+            If not None, uses this queue for computations.
+
+        Returns
+        -------
+        C : array, shape (n_samples, n_targets)
+            Returns predicted values.
+        """
+        module = self._get_backend("linear_model", "regression")
+
+        _check_is_fitted(self)
+
+        policy = self._get_policy(queue, X)
+
+        X = _check_array(
+            X, dtype=[np.float64, np.float32], force_all_finite=False, ensure_2d=False
+        )
+        _check_n_features(self, X, False)
+
+        if hasattr(self, "_onedal_model"):
+            model = self._onedal_model
+        else:
+            model = self._create_model(policy)
+
+        X_table = to_table(X, queue=queue)
+        params = self._get_onedal_params(X_table.dtype)
+
+        result = module.infer(policy, params, model, X_table)
+        y = from_table(result.responses)
+
+        if y.shape[1] == 1 and self.coef_.ndim == 1:
+            return y.ravel()
+        else:
+            return y
+
+
+class LinearRegression(BaseLinearRegression):
+    """
+    Linear Regression oneDAL implementation.
+
+    Parameters
+    ----------
+    fit_intercept : bool, default=True
+        Whether to calculate the intercept for this model. If set
+        to False, no intercept will be used in calculations
+        (i.e. data is expected to be centered).
+
+    copy_X : bool, default=True
+        If True, X will be copied; else, it may be overwritten.
+
+    algorithm : string, default="norm_eq"
+        Algorithm used for computation on oneDAL side
+    """
+
+    def __init__(
+        self,
+        fit_intercept=True,
+        copy_X=False,
+        *,
+        algorithm="norm_eq",
+        **kwargs,
+    ):
+        super().__init__(fit_intercept=fit_intercept, copy_X=copy_X, algorithm=algorithm)
+
+    def fit(self, X, y, queue=None):
+        """
+        Fit linear model.
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training data.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_targets)
+            Target values. Will be cast to X's dtype if necessary.
+
+        queue : dpctl.SyclQueue
+            If not None, use this queue for computations.
+
+        Returns
+        -------
+        self : object
+            Fitted Estimator.
+        """
+        module = self._get_backend("linear_model", "regression")
+
+        # TODO Fix _check_X_y to make sure this conversion is there
+        if not isinstance(X, np.ndarray):
+            X = np.asarray(X)
+
+        dtype = get_dtype(X)
+        if dtype not in [np.float32, np.float64]:
+            dtype = np.float64
+            X = X.astype(dtype, copy=self.copy_X)
+
+        y = np.asarray(y).astype(dtype=dtype)
+
+        X, y = _check_X_y(X, y, force_all_finite=False, accept_2d_y=True)
+
+        policy = self._get_policy(queue, X, y)
+
+        self.n_features_in_ = _num_features(X, fallback_1d=True)
+
+        X_table, y_table = to_table(X, y, queue=queue)
+        params = self._get_onedal_params(X_table.dtype)
+
+        hparams = get_hyperparameters("linear_regression", "train")
+        if hparams is not None and not hparams.is_default:
+            result = module.train(policy, params, hparams.backend, X_table, y_table)
+        else:
+            result = module.train(policy, params, X_table, y_table)
+
+        self._onedal_model = result.model
+
+        packed_coefficients = from_table(result.model.packed_coefficients)
+        self.coef_, self.intercept_ = (
+            packed_coefficients[:, 1:],
+            packed_coefficients[:, 0],
+        )
+
+        if self.coef_.shape[0] == 1 and y.ndim == 1:
+            self.coef_ = self.coef_.ravel()
+            self.intercept_ = self.intercept_[0]
+
+        return self
+
+
+class Ridge(BaseLinearRegression):
+    """
+    Ridge Regression oneDAL implementation.
+
+    Parameters
+    ----------
+    alpha : float, default=1.0
+        Regularization strength; must be a positive float. Regularization
+        improves the conditioning of the problem and reduces the variance of
+        the estimates. Larger values specify stronger regularization.
+
+    fit_intercept : bool, default=True
+        Whether to calculate the intercept for this model. If set
+        to False, no intercept will be used in calculations
+        (i.e. data is expected to be centered).
+
+    copy_X : bool, default=True
+        If True, X will be copied; else, it may be overwritten.
+
+    algorithm : string, default="norm_eq"
+        Algorithm used for computation on oneDAL side.
+    """
+
+    def __init__(
+        self,
+        alpha=1.0,
+        fit_intercept=True,
+        copy_X=False,
+        *,
+        algorithm="norm_eq",
+        **kwargs,
+    ):
+        super().__init__(
+            fit_intercept=fit_intercept, alpha=alpha, copy_X=copy_X, algorithm=algorithm
+        )
+
+    def fit(self, X, y, queue=None):
+        """
+        Fit linear model.
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training data.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_targets)
+            Target values. Will be cast to X's dtype if necessary.
+
+        queue : dpctl.SyclQueue
+            If not None, use this queue for computations.
+
+        Returns
+        -------
+        self : object
+            Fitted Estimator.
+        """
+        module = self._get_backend("linear_model", "regression")
+
+        if not isinstance(X, np.ndarray):
+            X = np.asarray(X)
+
+        dtype = get_dtype(X)
+        if dtype not in [np.float32, np.float64]:
+            dtype = np.float64
+            X = X.astype(dtype, copy=self.copy_X)
+
+        y = np.asarray(y).astype(dtype=dtype)
+
+        X, y = _check_X_y(X, y, force_all_finite=False, accept_2d_y=True)
+
+        policy = self._get_policy(queue, X, y)
+
+        self.n_features_in_ = _num_features(X, fallback_1d=True)
+
+        X_table, y_table = to_table(X, y, queue=queue)
+        params = self._get_onedal_params(X.dtype)
+
+        result = module.train(policy, params, X_table, y_table)
+        self._onedal_model = result.model
+
+        packed_coefficients = from_table(result.model.packed_coefficients)
+        self.coef_, self.intercept_ = (
+            packed_coefficients[:, 1:],
+            packed_coefficients[:, 0],
+        )
+
+        if self.coef_.shape[0] == 1 and y.ndim == 1:
+            self.coef_ = self.coef_.ravel()
+            self.intercept_ = self.intercept_[0]
+
+        return self

scikit_learn_intelex-2025.4.0.data/data/Lib/site-packages/onedal/linear_model/logistic_regression.py

@@ -0,0 +1,247 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from abc import ABCMeta, abstractmethod
+from numbers import Number
+
+import numpy as np
+
+from daal4py.sklearn._utils import daal_check_version, get_dtype, make2d
+
+from ..common._base import BaseEstimator as onedal_BaseEstimator
+from ..common._estimator_checks import _check_is_fitted
+from ..common._mixin import ClassifierMixin
+from ..datatypes import from_table, to_table
+from ..utils import (
+    _check_array,
+    _check_n_features,
+    _check_X_y,
+    _is_csr,
+    _num_features,
+    _type_of_target,
+)
+
+
+class BaseLogisticRegression(onedal_BaseEstimator, metaclass=ABCMeta):
+    @abstractmethod
+    def __init__(self, tol, C, fit_intercept, solver, max_iter, algorithm):
+        self.tol = tol
+        self.C = C
+        self.fit_intercept = fit_intercept
+        self.solver = solver
+        self.max_iter = max_iter
+        self.algorithm = algorithm
+
+    def _get_onedal_params(self, is_csr, dtype=np.float32):
+        intercept = "intercept|" if self.fit_intercept else ""
+        return {
+            "fptype": dtype,
+            "method": "sparse" if is_csr else self.algorithm,
+            "intercept": self.fit_intercept,
+            "tol": self.tol,
+            "max_iter": self.max_iter,
+            "C": self.C,
+            "optimizer": self.solver,
+            "result_option": (
+                intercept
+                + "coefficients|iterations_count"
+                + ("|inner_iterations_count" if self.solver == "newton-cg" else "")
+            ),
+        }
+
+    def _fit(self, X, y, module, queue):
+        sparsity_enabled = daal_check_version((2024, "P", 700))
+        X, y = _check_X_y(
+            X,
+            y,
+            accept_sparse=sparsity_enabled,
+            force_all_finite=True,
+            accept_2d_y=False,
+            dtype=[np.float64, np.float32],
+        )
+        is_csr = _is_csr(X)
+
+        self.n_features_in_ = _num_features(X, fallback_1d=True)
+
+        if _type_of_target(y) != "binary":
+            raise ValueError("Only binary classification is supported")
+
+        self.classes_, y = np.unique(y, return_inverse=True)
+        y = y.astype(dtype=np.int32)
+
+        policy = self._get_policy(queue, X, y)
+        X_table, y_table = to_table(X, y, queue=queue)
+        params = self._get_onedal_params(is_csr, X_table.dtype)
+
+        result = module.train(policy, params, X_table, y_table)
+
+        self._onedal_model = result.model
+        self.n_iter_ = np.array([result.iterations_count])
+
+        # _n_inner_iter is the total number of cg-solver iterations
+        if daal_check_version((2024, "P", 300)) and self.solver == "newton-cg":
+            self._n_inner_iter = result.inner_iterations_count
+
+        coeff = from_table(result.model.packed_coefficients)
+        self.coef_, self.intercept_ = coeff[:, 1:], coeff[:, 0]
+
+        return self
+
+    def _create_model(self, module, policy):
+        m = module.model()
+
+        coefficients = self.coef_
+        dtype = get_dtype(coefficients)
+        coefficients = np.asarray(coefficients, dtype=dtype)
+
+        if coefficients.ndim == 2:
+            n_features_in = coefficients.shape[1]
+            assert coefficients.shape[0] == 1
+        else:
+            n_features_in = coefficients.size
+
+        intercept = self.intercept_
+        if not isinstance(intercept, Number):
+            intercept = np.asarray(intercept, dtype=dtype)
+            assert intercept.size == 1
+
+        intercept = _check_array(
+            intercept,
+            dtype=[np.float64, np.float32],
+            force_all_finite=True,
+            ensure_2d=False,
+        )
+        coefficients = _check_array(
+            coefficients,
+            dtype=[np.float64, np.float32],
+            force_all_finite=True,
+            ensure_2d=False,
+        )
+
+        coefficients, intercept = make2d(coefficients), make2d(intercept)
+
+        assert coefficients.shape == (1, n_features_in)
+        assert intercept.shape == (1, 1)
+
+        desired_shape = (1, n_features_in + 1)
+        packed_coefficients = np.zeros(desired_shape, dtype=dtype)
+
+        packed_coefficients[:, 1:] = coefficients
+        if self.fit_intercept:
+            packed_coefficients[:, 0][:, np.newaxis] = intercept
+
+        m.packed_coefficients = to_table(
+            packed_coefficients, queue=getattr(policy, "_queue", None)
+        )
+
+        self._onedal_model = m
+
+        return m
+
+    def _infer(self, X, module, queue):
+        _check_is_fitted(self)
+        sparsity_enabled = daal_check_version((2024, "P", 700))
+
+        X = _check_array(
+            X,
+            dtype=[np.float64, np.float32],
+            accept_sparse=sparsity_enabled,
+            force_all_finite=True,
+            ensure_2d=False,
+            accept_large_sparse=sparsity_enabled,
+        )
+        is_csr = _is_csr(X)
+        _check_n_features(self, X, False)
+
+        X = make2d(X)
+        policy = self._get_policy(queue, X)
+
+        if hasattr(self, "_onedal_model"):
+            model = self._onedal_model
+        else:
+            model = self._create_model(module, policy)
+
+        X_table = to_table(X, queue=queue)
+        params = self._get_onedal_params(is_csr, X.dtype)
+
+        result = module.infer(policy, params, model, X_table)
+        return result
+
+    def _predict(self, X, module, queue):
+        result = self._infer(X, module, queue)
+        y = from_table(result.responses)
+        y = np.take(self.classes_, y.ravel(), axis=0)
+        return y
+
+    def _predict_proba(self, X, module, queue):
+        result = self._infer(X, module, queue)
+
+        y = from_table(result.probabilities)
+        y = y.reshape(-1, 1)
+        return np.hstack([1 - y, y])
+
+    def _predict_log_proba(self, X, module, queue):
+        y_proba = self._predict_proba(X, module, queue)
+        return np.log(y_proba)
+
+
+class LogisticRegression(ClassifierMixin, BaseLogisticRegression):
+    """
+    Logistic Regression oneDAL implementation.
+    """
+
+    def __init__(
+        self,
+        tol=1e-4,
+        C=1.0,
+        fit_intercept=True,
+        solver="newton-cg",
+        max_iter=100,
+        *,
+        algorithm="dense_batch",
+        **kwargs,
+    ):
+        super().__init__(
+            tol=tol,
+            C=C,
+            fit_intercept=fit_intercept,
+            solver=solver,
+            max_iter=max_iter,
+            algorithm=algorithm,
+        )
+
+    def fit(self, X, y, queue=None):
+        return super()._fit(
+            X, y, self._get_backend("logistic_regression", "classification", None), queue
+        )
+
+    def predict(self, X, queue=None):
+        y = super()._predict(
+            X, self._get_backend("logistic_regression", "classification", None), queue
+        )
+        return y
+
+    def predict_proba(self, X, queue=None):
+        y = super()._predict_proba(
+            X, self._get_backend("logistic_regression", "classification", None), queue
+        )
+        return y
+
+    def predict_log_proba(self, X, queue=None):
+        y = super()._predict_log_proba(
+            X, self._get_backend("logistic_regression", "classification", None), queue
+        )
+        return y