scikit-learn-intelex 2024.5.0__py39-none-manylinux1_x86_64.whl → 2024.6.0__py39-none-manylinux1_x86_64.whl

sklearnex/linear_model/incremental_linear.py

@@ -20,6 +20,7 @@ import warnings
 import numpy as np
 from sklearn.base import BaseEstimator, MultiOutputMixin, RegressorMixin
 from sklearn.exceptions import NotFittedError
+from sklearn.metrics import r2_score
 from sklearn.utils import check_array, gen_batches
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
@@ -134,6 +135,7 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
                 X,
                 dtype=[np.float64, np.float32],
                 copy=self.copy_X,
+                reset=False,
             )
         else:
             X = check_array(
@@ -147,33 +149,42 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
             self._onedal_finalize_fit()
         return self._onedal_estimator.predict(X, queue)
 
-    def _onedal_partial_fit(self, X, y, queue=None):
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return r2_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
+    def _onedal_partial_fit(self, X, y, check_input=True, queue=None):
         first_pass = not hasattr(self, "n_samples_seen_") or self.n_samples_seen_ == 0
 
         if sklearn_check_version("1.2"):
             self._validate_params()
 
-        if sklearn_check_version("1.0"):
-            X, y = self._validate_data(
-                X,
-                y,
-                dtype=[np.float64, np.float32],
-                reset=first_pass,
-                copy=self.copy_X,
-                multi_output=True,
-            )
-        else:
-            X = check_array(
-                X,
-                dtype=[np.float64, np.float32],
-                copy=self.copy_X,
-            )
-            y = check_array(
-                y,
-                dtype=[np.float64, np.float32],
-                copy=False,
-                ensure_2d=False,
-            )
+        if check_input:
+            if sklearn_check_version("1.0"):
+                X, y = self._validate_data(
+                    X,
+                    y,
+                    dtype=[np.float64, np.float32],
+                    reset=first_pass,
+                    copy=self.copy_X,
+                    multi_output=True,
+                    force_all_finite=False,
+                )
+            else:
+                X = check_array(
+                    X,
+                    dtype=[np.float64, np.float32],
+                    copy=self.copy_X,
+                    force_all_finite=False,
+                )
+                y = check_array(
+                    y,
+                    dtype=[np.float64, np.float32],
+                    copy=False,
+                    ensure_2d=False,
+                    force_all_finite=False,
+                )
 
         if first_pass:
             self.n_samples_seen_ = X.shape[0]
@@ -202,7 +213,12 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
 
         if sklearn_check_version("1.0"):
             X, y = self._validate_data(
-                X, y, dtype=[np.float64, np.float32], copy=self.copy_X, multi_output=True
+                X,
+                y,
+                dtype=[np.float64, np.float32],
+                copy=self.copy_X,
+                multi_output=True,
+                ensure_2d=True,
             )
         else:
             X = check_array(
@@ -234,7 +250,7 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
 
         for batch in gen_batches(n_samples, self.batch_size_):
             X_batch, y_batch = X[batch], y[batch]
-            self._onedal_partial_fit(X_batch, y_batch, queue=queue)
+            self._onedal_partial_fit(X_batch, y_batch, check_input=False, queue=queue)
 
         if sklearn_check_version("1.2"):
             self._validate_params()
@@ -288,7 +304,7 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
     coef_ = property(get_coef_, set_coef_)
     intercept_ = property(get_intercept_, set_intercept_)
 
-    def partial_fit(self, X, y):
+    def partial_fit(self, X, y, check_input=True):
         """
         Incremental fit linear model with X and y. All of X and y is
         processed as a single batch.
@@ -318,6 +334,7 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
             },
             X,
             y,
+            check_input=check_input,
         )
         return self
 
@@ -385,3 +402,63 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
             },
             X,
         )
+
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        """Return the coefficient of determination of the prediction.
+
+        The coefficient of determination :math:`R^2` is defined as
+        :math:`(1 - \\frac{u}{v})`, where :math:`u` is the residual
+        sum of squares ``((y_true - y_pred)** 2).sum()`` and :math:`v`
+        is the total sum of squares ``((y_true - y_true.mean()) ** 2).sum()``.
+        The best possible score is 1.0 and it can be negative (because the
+        model can be arbitrarily worse). A constant model that always predicts
+        the expected value of `y`, disregarding the input features, would get
+        a :math:`R^2` score of 0.0.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples. For some estimators this may be a precomputed
+            kernel matrix or a list of generic objects instead with shape
+            ``(n_samples, n_samples_fitted)``, where ``n_samples_fitted``
+            is the number of samples used in the fitting for the estimator.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_outputs)
+            True values for `X`.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights.
+
+        Returns
+        -------
+        score : float
+            :math:`R^2` of ``self.predict(X)`` w.r.t. `y`.
+
+        Notes
+        -----
+        The :math:`R^2` score used when calling ``score`` on a regressor uses
+        ``multioutput='uniform_average'`` from version 0.23 to keep consistent
+        with default value of :func:`~sklearn.metrics.r2_score`.
+        This influences the ``score`` method of all the multioutput
+        regressors (except for
+        :class:`~sklearn.multioutput.MultiOutputRegressor`).
+        """
+        if not hasattr(self, "coef_"):
+            msg = (
+                "This %(name)s instance is not fitted yet. Call 'fit' or 'partial_fit' "
+                "with appropriate arguments before using this estimator."
+            )
+            raise NotFittedError(msg % {"name": self.__class__.__name__})
+
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": None,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )

sklearnex/linear_model/linear.py

@@ -20,6 +20,7 @@ from abc import ABC
 import numpy as np
 from sklearn.exceptions import NotFittedError
 from sklearn.linear_model import LinearRegression as sklearn_LinearRegression
+from sklearn.metrics import r2_score
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
@@ -123,6 +124,20 @@ class LinearRegression(sklearn_LinearRegression):
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_LinearRegression.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     def _test_type_and_finiteness(self, X_in):
         X = X_in if isinstance(X_in, np.ndarray) else np.asarray(X_in)
 
@@ -193,22 +208,19 @@ class LinearRegression(sklearn_LinearRegression):
         return patching_status
 
     def _onedal_predict_supported(self, method_name, *data):
-        assert method_name == "predict"
-        assert len(data) == 1
-
         class_name = self.__class__.__name__
         patching_status = PatchingConditionsChain(
             f"sklearn.linear_model.{class_name}.predict"
         )
 
-        n_samples = _num_samples(*data)
+        n_samples = _num_samples(data[0])
         model_is_sparse = issparse(self.coef_) or (
             self.fit_intercept and issparse(self.intercept_)
         )
         dal_ready = patching_status.and_conditions(
             [
                 (n_samples > 0, "Number of samples is less than 1."),
-                (not issparse(*data), "Sparse input is not supported."),
+                (not issparse(data[0]), "Sparse input is not supported."),
                 (not model_is_sparse, "Sparse coefficients are not supported."),
             ]
         )
@@ -216,7 +228,7 @@ class LinearRegression(sklearn_LinearRegression):
             return patching_status
 
         patching_status.and_condition(
-            self._test_type_and_finiteness(*data), "Input X is not supported."
+            self._test_type_and_finiteness(data[0]), "Input X is not supported."
         )
 
         return patching_status
@@ -224,7 +236,7 @@ class LinearRegression(sklearn_LinearRegression):
     def _onedal_supported(self, method_name, *data):
         if method_name == "fit":
             return self._onedal_fit_supported(method_name, *data)
-        if method_name == "predict":
+        if method_name in ["predict", "score"]:
             return self._onedal_predict_supported(method_name, *data)
         raise RuntimeError(f"Unknown method {method_name} in {self.__class__.__name__}")
 
@@ -286,6 +298,11 @@ class LinearRegression(sklearn_LinearRegression):
         res = self._onedal_estimator.predict(X, queue=queue)
         return res
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return r2_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
     def get_coef_(self):
         return self.coef_
 
@@ -314,3 +331,4 @@ class LinearRegression(sklearn_LinearRegression):
 
     fit.__doc__ = sklearn_LinearRegression.fit.__doc__
     predict.__doc__ = sklearn_LinearRegression.predict.__doc__
+    score.__doc__ = sklearn_LinearRegression.score.__doc__

sklearnex/linear_model/logistic_regression.py

@@ -21,18 +21,6 @@ from daal4py.sklearn._utils import daal_check_version
 from daal4py.sklearn.linear_model.logistic_path import (
     LogisticRegression as LogisticRegression_daal4py,
 )
-from daal4py.sklearn.linear_model.logistic_path import daal4py_fit, daal4py_predict
-
-
-class BaseLogisticRegression(ABC):
-    def _save_attributes(self):
-        assert hasattr(self, "_onedal_estimator")
-        self.classes_ = self._onedal_estimator.classes_
-        self.coef_ = self._onedal_estimator.coef_
-        self.intercept_ = self._onedal_estimator.intercept_
-        self.n_features_in_ = self._onedal_estimator.n_features_in_
-        self.n_iter_ = self._onedal_estimator.n_iter_
-
 
 if daal_check_version((2024, "P", 1)):
     import numpy as np
@@ -44,6 +32,7 @@ if daal_check_version((2024, "P", 1)):
 
     from daal4py.sklearn._n_jobs_support import control_n_jobs
     from daal4py.sklearn._utils import sklearn_check_version
+    from daal4py.sklearn.linear_model.logistic_path import daal4py_fit, daal4py_predict
     from onedal.linear_model import LogisticRegression as onedal_LogisticRegression
     from onedal.utils import _num_samples
 
@@ -51,6 +40,15 @@ if daal_check_version((2024, "P", 1)):
     from .._utils import PatchingConditionsChain, get_patch_message
     from ..utils.validation import _assert_all_finite
 
+    class BaseLogisticRegression(ABC):
+        def _save_attributes(self):
+            assert hasattr(self, "_onedal_estimator")
+            self.classes_ = self._onedal_estimator.classes_
+            self.coef_ = self._onedal_estimator.coef_
+            self.intercept_ = self._onedal_estimator.intercept_
+            self.n_features_in_ = self._onedal_estimator.n_features_in_
+            self.n_iter_ = self._onedal_estimator.n_iter_
+
     @control_n_jobs(
         decorated_methods=[
             "fit",
@@ -82,7 +80,7 @@ if daal_check_version((2024, "P", 1)):
             random_state=None,
             solver="lbfgs",
             max_iter=100,
-            multi_class="auto",
+            multi_class="deprecated" if sklearn_check_version("1.5") else "auto",
             verbose=0,
             warm_start=False,
             n_jobs=None,
@@ -146,7 +144,7 @@ if daal_check_version((2024, "P", 1)):
                 self._check_feature_names(X, reset=False)
             return dispatch(
                 self,
-                "predict",
+                "predict_proba",
                 {
                     "onedal": self.__class__._onedal_predict_proba,
                     "sklearn": sklearn_LogisticRegression.predict_proba,
@@ -160,7 +158,7 @@ if daal_check_version((2024, "P", 1)):
                 self._check_feature_names(X, reset=False)
             return dispatch(
                 self,
-                "predict",
+                "predict_log_proba",
                 {
                     "onedal": self.__class__._onedal_predict_log_proba,
                     "sklearn": sklearn_LogisticRegression.predict_log_proba,

sklearnex/linear_model/tests/test_incremental_linear.py

@@ -47,7 +47,7 @@ def test_sklearnex_fit_on_gold_data(dataframe, queue, fit_intercept, macro_block
 
     y_pred = inclin.predict(X_df)
 
-    tol = 2e-6 if dtype == np.float32 else 1e-7
+    tol = 2e-6 if y_pred.dtype == np.float32 else 1e-7
     assert_allclose(inclin.coef_, [1], atol=tol)
     if fit_intercept:
         assert_allclose(inclin.intercept_, [0], atol=tol)
@@ -82,15 +82,15 @@ def test_sklearnex_partial_fit_on_gold_data(
         )
         inclin.partial_fit(X_split_df, y_split_df)
 
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y_pred = inclin.predict(X_df)
+
     assert inclin.n_features_in_ == 1
-    tol = 2e-6 if dtype == np.float32 else 1e-7
+    tol = 2e-6 if y_pred.dtype == np.float32 else 1e-7
     assert_allclose(inclin.coef_, [[1]], atol=tol)
     if fit_intercept:
         assert_allclose(inclin.intercept_, 3, atol=tol)
 
-    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
-    y_pred = inclin.predict(X_df)
-
     assert_allclose(_as_numpy(y_pred), y, atol=tol)
 
 
@@ -122,15 +122,15 @@ def test_sklearnex_partial_fit_multitarget_on_gold_data(
         )
         inclin.partial_fit(X_split_df, y_split_df)
 
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y_pred = inclin.predict(X_df)
+
     assert inclin.n_features_in_ == 2
-    tol = 7e-6 if dtype == np.float32 else 1e-7
+    tol = 7e-6 if y_pred.dtype == np.float32 else 1e-7
     assert_allclose(inclin.coef_, [1.0, 2.0], atol=tol)
     if fit_intercept:
         assert_allclose(inclin.intercept_, 3.0, atol=tol)
 
-    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
-    y_pred = inclin.predict(X_df)
-
     assert_allclose(_as_numpy(y_pred), y, atol=tol)
 
 
@@ -181,7 +181,7 @@ def test_sklearnex_partial_fit_on_random_data(
         )
         inclin.partial_fit(X_split_df, y_split_df)
 
-    tol = 1e-4 if dtype == np.float32 else 1e-7
+    tol = 1e-4 if inclin.coef_.dtype == np.float32 else 1e-7
     assert_allclose(coef, inclin.coef_.T, atol=tol)
 
     if fit_intercept:

sklearnex/linear_model/tests/test_linear.py

@@ -52,7 +52,7 @@ def test_sklearnex_import_linear(dataframe, queue, dtype, macro_block):
     assert "sklearnex" in linreg.__module__
     assert linreg.n_features_in_ == 2
 
-    tol = 1e-5 if dtype == np.float32 else 1e-7
+    tol = 1e-5 if _as_numpy(linreg.coef_).dtype == np.float32 else 1e-7
     assert_allclose(_as_numpy(linreg.intercept_), 3.0, rtol=tol)
     assert_allclose(_as_numpy(linreg.coef_), [1.0, 2.0], rtol=tol)
 
@@ -113,5 +113,5 @@ def test_sklearnex_reconstruct_model(dataframe, queue, dtype):
 
     y_pred = linreg.predict(X)
 
-    tol = 1e-5 if dtype == np.float32 else 1e-7
+    tol = 1e-5 if _as_numpy(y_pred).dtype == np.float32 else 1e-7
     assert_allclose(gtr, _as_numpy(y_pred), rtol=tol)

sklearnex/neighbors/knn_regression.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 # ==============================================================================
 
+from sklearn.metrics import r2_score
 from sklearn.neighbors._regression import (
     KNeighborsRegressor as sklearn_KNeighborsRegressor,
 )
@@ -117,6 +118,23 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        check_is_fitted(self)
+        if sklearn_check_version("1.0"):
+            self._check_feature_names(X, reset=False)
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_KNeighborsRegressor.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     @wrap_output_data
     def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
@@ -184,6 +202,11 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
             X, n_neighbors, return_distance, queue=queue
         )
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return r2_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
     def _save_attributes(self):
         self.n_features_in_ = self._onedal_estimator.n_features_in_
         self.n_samples_fit_ = self._onedal_estimator.n_samples_fit_
@@ -196,3 +219,4 @@ class KNeighborsRegressor(sklearn_KNeighborsRegressor, KNeighborsDispatchingBase
     predict.__doc__ = sklearn_KNeighborsRegressor.predict.__doc__
     kneighbors.__doc__ = sklearn_KNeighborsRegressor.kneighbors.__doc__
     radius_neighbors.__doc__ = sklearn_NearestNeighbors.radius_neighbors.__doc__
+    score.__doc__ = sklearn_KNeighborsRegressor.score.__doc__

sklearnex/preview/__init__.py

@@ -14,4 +14,4 @@
 # limitations under the License.
 # ==============================================================================
 
-__all__ = ["cluster", "covariance"]
+__all__ = ["cluster", "covariance", "decomposition"]

sklearnex/preview/decomposition/__init__.py

@@ -0,0 +1,19 @@
+# ===============================================================================
+# 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 .incremental_pca import IncrementalPCA
+
+__all__ = ["IncrementalPCA"]