scikit-learn-intelex 2024.5.0__py310-none-manylinux1_x86_64.whl → 2024.7.0__py310-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

@@ -20,13 +20,13 @@ 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
 
 from .._device_offload import dispatch, wrap_output_data
 from .._utils import PatchingConditionsChain, get_patch_message, register_hyperparameters
-from ..utils.validation import _assert_all_finite
 
 if sklearn_check_version("1.0") and not sklearn_check_version("1.2"):
     from sklearn.linear_model._base import _deprecate_normalize
@@ -123,18 +123,19 @@ class LinearRegression(sklearn_LinearRegression):
             X,
         )
 
-    def _test_type_and_finiteness(self, X_in):
-        X = X_in if isinstance(X_in, np.ndarray) else np.asarray(X_in)
-
-        dtype = X.dtype
-        if "complex" in str(type(dtype)):
-            return False
-
-        try:
-            _assert_all_finite(X)
-        except BaseException:
-            return False
-        return True
+    @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 _onedal_fit_supported(self, method_name, *data):
         assert method_name == "fit"
@@ -159,7 +160,7 @@ class LinearRegression(sklearn_LinearRegression):
         # Check if equations are well defined
         is_underdetermined = n_samples < (n_features + int(self.fit_intercept))
 
-        dal_ready = patching_status.and_conditions(
+        patching_status.and_conditions(
             [
                 (sample_weight is None, "Sample weight is not supported."),
                 (
@@ -178,53 +179,33 @@ class LinearRegression(sklearn_LinearRegression):
                 ),
             ]
         )
-        if not dal_ready:
-            return patching_status
-
-        if not patching_status.and_condition(
-            self._test_type_and_finiteness(X), "Input X is not supported."
-        ):
-            return patching_status
-
-        patching_status.and_condition(
-            self._test_type_and_finiteness(y), "Input y is not supported."
-        )
 
         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(
+        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."),
             ]
         )
-        if not dal_ready:
-            return patching_status
-
-        patching_status.and_condition(
-            self._test_type_and_finiteness(*data), "Input X is not supported."
-        )
 
         return patching_status
 
     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__}")
 
@@ -245,7 +226,6 @@ class LinearRegression(sklearn_LinearRegression):
             "accept_sparse": ["csr", "csc", "coo"],
             "y_numeric": True,
             "multi_output": True,
-            "force_all_finite": False,
         }
         if sklearn_check_version("1.2"):
             X, y = self._validate_data(**check_params)
@@ -286,6 +266,11 @@ 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 +299,4 @@ 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
@@ -40,16 +28,27 @@ if daal_check_version((2024, "P", 1)):
     from sklearn.linear_model import LogisticRegression as sklearn_LogisticRegression
     from sklearn.metrics import accuracy_score
     from sklearn.utils.multiclass import type_of_target
-    from sklearn.utils.validation import check_X_y
+    from sklearn.utils.validation import check_array, check_is_fitted, check_X_y
 
     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
 
     from .._device_offload import dispatch, wrap_output_data
     from .._utils import PatchingConditionsChain, get_patch_message
-    from ..utils.validation import _assert_all_finite
+
+    _sparsity_enabled = daal_check_version((2024, "P", 700))
+
+    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=[
@@ -82,7 +81,7 @@ 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,
@@ -109,8 +108,6 @@ if daal_check_version((2024, "P", 1)):
         _onedal_cpu_fit = daal4py_fit
 
         def fit(self, X, y, sample_weight=None):
-            if sklearn_check_version("1.0"):
-                self._check_feature_names(X, reset=True)
             if sklearn_check_version("1.2"):
                 self._validate_params()
             dispatch(
@@ -128,8 +125,6 @@ if daal_check_version((2024, "P", 1)):
 
         @wrap_output_data
         def predict(self, X):
-            if sklearn_check_version("1.0"):
-                self._check_feature_names(X, reset=False)
             return dispatch(
                 self,
                 "predict",
@@ -142,11 +137,9 @@ if daal_check_version((2024, "P", 1)):
 
         @wrap_output_data
         def predict_proba(self, X):
-            if sklearn_check_version("1.0"):
-                self._check_feature_names(X, reset=False)
             return dispatch(
                 self,
-                "predict",
+                "predict_proba",
                 {
                     "onedal": self.__class__._onedal_predict_proba,
                     "sklearn": sklearn_LogisticRegression.predict_proba,
@@ -156,11 +149,9 @@ if daal_check_version((2024, "P", 1)):
 
         @wrap_output_data
         def predict_log_proba(self, X):
-            if sklearn_check_version("1.0"):
-                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,
@@ -170,8 +161,6 @@ if daal_check_version((2024, "P", 1)):
 
         @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",
@@ -189,17 +178,6 @@ if daal_check_version((2024, "P", 1)):
                 y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
             )
 
-        def _test_type_and_finiteness(self, X_in):
-            X = np.asarray(X_in)
-
-            if np.iscomplexobj(X):
-                return False
-            try:
-                _assert_all_finite(X)
-            except BaseException:
-                return False
-            return True
-
         def _onedal_gpu_fit_supported(self, method_name, *data):
             assert method_name == "fit"
             assert len(data) == 3
@@ -210,7 +188,12 @@ if daal_check_version((2024, "P", 1)):
                 f"sklearn.linear_model.{class_name}.fit"
             )
 
-            dal_ready = patching_status.and_conditions(
+            target_type = (
+                type_of_target(y, input_name="y")
+                if sklearn_check_version("1.1")
+                else type_of_target(y)
+            )
+            patching_status.and_conditions(
                 [
                     (self.penalty == "l2", "Only l2 penalty is supported."),
                     (self.dual == False, "dual=True is not supported."),
@@ -228,24 +211,12 @@ if daal_check_version((2024, "P", 1)):
                     (self.l1_ratio is None, "l1 ratio is not supported."),
                     (sample_weight is None, "Sample weight is not supported."),
                     (
-                        type_of_target(y) == "binary",
+                        target_type == "binary",
                         "Only binary classification is supported",
                     ),
                 ]
             )
 
-            if not dal_ready:
-                return patching_status
-
-            if not patching_status.and_condition(
-                self._test_type_and_finiteness(X), "Input X is not supported."
-            ):
-                return patching_status
-
-            patching_status.and_condition(
-                self._test_type_and_finiteness(y), "Input y is not supported."
-            )
-
             return patching_status
 
         def _onedal_gpu_predict_supported(self, method_name, *data):
@@ -269,7 +240,7 @@ if daal_check_version((2024, "P", 1)):
                 [
                     (n_samples > 0, "Number of samples is less than 1."),
                     (
-                        not any([issparse(i) for i in data]),
+                        (not any([issparse(i) for i in data])) or _sparsity_enabled,
                         "Sparse input is not supported.",
                     ),
                     (not model_is_sparse, "Sparse coefficients are not supported."),
@@ -279,12 +250,6 @@ if daal_check_version((2024, "P", 1)):
                     ),
                 ]
             )
-            if not dal_ready:
-                return patching_status
-
-            patching_status.and_condition(
-                self._test_type_and_finiteness(*data), "Input X is not supported."
-            )
 
             return patching_status
 
@@ -315,24 +280,29 @@ if daal_check_version((2024, "P", 1)):
             }
             self._onedal_estimator = onedal_LogisticRegression(**onedal_params)
 
-        def _onedal_fit(self, X, y, sample_weight, queue=None):
+        def _onedal_fit(self, X, y, sample_weight=None, queue=None):
             if queue is None or queue.sycl_device.is_cpu:
                 return self._onedal_cpu_fit(X, y, sample_weight)
 
             assert sample_weight is None
 
-            check_params = {
-                "X": X,
-                "y": y,
-                "dtype": [np.float64, np.float32],
-                "accept_sparse": False,
-                "multi_output": False,
-                "force_all_finite": True,
-            }
-            if sklearn_check_version("1.2"):
-                X, y = self._validate_data(**check_params)
+            if sklearn_check_version("1.0"):
+                X, y = self._validate_data(
+                    X,
+                    y,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
             else:
-                X, y = check_X_y(**check_params)
+                X, y = check_X_y(
+                    X,
+                    y,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+
             self._initialize_onedal_estimator()
             try:
                 self._onedal_estimator.fit(X, y, queue=queue)
@@ -350,7 +320,23 @@ if daal_check_version((2024, "P", 1)):
             if queue is None or queue.sycl_device.is_cpu:
                 return daal4py_predict(self, X, "computeClassLabels")
 
-            X = self._validate_data(X, accept_sparse=False, reset=False)
+            check_is_fitted(self)
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X,
+                    reset=False,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+            else:
+                X = check_array(
+                    X,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+
             assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict(X, queue=queue)
 
@@ -358,7 +344,23 @@ if daal_check_version((2024, "P", 1)):
             if queue is None or queue.sycl_device.is_cpu:
                 return daal4py_predict(self, X, "computeClassProbabilities")
 
-            X = self._validate_data(X, accept_sparse=False, reset=False)
+            check_is_fitted(self)
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X,
+                    reset=False,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+            else:
+                X = check_array(
+                    X,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+
             assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict_proba(X, queue=queue)
 
@@ -366,7 +368,23 @@ if daal_check_version((2024, "P", 1)):
             if queue is None or queue.sycl_device.is_cpu:
                 return daal4py_predict(self, X, "computeClassLogProbabilities")
 
-            X = self._validate_data(X, accept_sparse=False, reset=False)
+            check_is_fitted(self)
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X,
+                    reset=False,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+            else:
+                X = check_array(
+                    X,
+                    accept_sparse=_sparsity_enabled,
+                    accept_large_sparse=_sparsity_enabled,
+                    dtype=[np.float64, np.float32],
+                )
+
             assert hasattr(self, "_onedal_estimator")
             return self._onedal_estimator.predict_log_proba(X, queue=queue)
 

sklearnex/linear_model/ridge.py

@@ -15,3 +15,10 @@
 # ===============================================================================
 
 from daal4py.sklearn.linear_model import Ridge
+from onedal._device_offload import support_usm_ndarray
+
+# Note: `sklearnex.linear_model.Ridge` only has functional
+# sycl GPU support. No GPU device will be offloaded.
+Ridge.fit = support_usm_ndarray(queue_param=False)(Ridge.fit)
+Ridge.predict = support_usm_ndarray(queue_param=False)(Ridge.predict)
+Ridge.score = support_usm_ndarray(queue_param=False)(Ridge.score)