scikit-learn-intelex 2024.4.0__py39-none-manylinux1_x86_64.whl → 2024.6.0__py39-none-manylinux1_x86_64.whl

sklearnex/ensemble/_forest.py

@@ -29,7 +29,7 @@ from sklearn.ensemble._forest import ForestClassifier as sklearn_ForestClassifie
 from sklearn.ensemble._forest import ForestRegressor as sklearn_ForestRegressor
 from sklearn.ensemble._forest import _get_n_samples_bootstrap
 from sklearn.exceptions import DataConversionWarning
-from sklearn.metrics import accuracy_score
+from sklearn.metrics import accuracy_score, r2_score
 from sklearn.tree import (
     DecisionTreeClassifier,
     DecisionTreeRegressor,
@@ -38,7 +38,7 @@ from sklearn.tree import (
 )
 from sklearn.tree._tree import Tree
 from sklearn.utils import check_random_state, deprecated
-from sklearn.utils.validation import check_array, check_is_fitted
+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 (
@@ -74,6 +74,7 @@ class BaseForest(ABC):
             accept_sparse=False,
             dtype=[np.float64, np.float32],
             force_all_finite=False,
+            ensure_2d=True,
         )
 
         if sample_weight is not None:
@@ -97,8 +98,6 @@ class BaseForest(ABC):
 
         y, expanded_class_weight = self._validate_y_class_weight(y)
 
-        self.n_features_in_ = X.shape[1]
-
         if expanded_class_weight is not None:
             if sample_weight is not None:
                 sample_weight = sample_weight * expanded_class_weight
@@ -114,7 +113,9 @@ class BaseForest(ABC):
             "min_samples_split": self.min_samples_split,
             "min_samples_leaf": self.min_samples_leaf,
             "min_weight_fraction_leaf": self.min_weight_fraction_leaf,
-            "max_features": self.max_features,
+            "max_features": self._to_absolute_max_features(
+                self.max_features, self.n_features_in_
+            ),
             "max_leaf_nodes": self.max_leaf_nodes,
             "min_impurity_decrease": self.min_impurity_decrease,
             "bootstrap": self.bootstrap,
@@ -174,6 +175,45 @@ class BaseForest(ABC):
         self._validate_estimator()
         return self
 
+    def _to_absolute_max_features(self, max_features, n_features):
+        if max_features is None:
+            return n_features
+        if isinstance(max_features, str):
+            if max_features == "auto":
+                if not sklearn_check_version("1.3"):
+                    if sklearn_check_version("1.1"):
+                        warnings.warn(
+                            "`max_features='auto'` has been deprecated in 1.1 "
+                            "and will be removed in 1.3. To keep the past behaviour, "
+                            "explicitly set `max_features=1.0` or remove this "
+                            "parameter as it is also the default value for "
+                            "RandomForestRegressors and ExtraTreesRegressors.",
+                            FutureWarning,
+                        )
+                    return (
+                        max(1, int(np.sqrt(n_features)))
+                        if isinstance(self, ForestClassifier)
+                        else n_features
+                    )
+            if max_features == "sqrt":
+                return max(1, int(np.sqrt(n_features)))
+            if max_features == "log2":
+                return max(1, int(np.log2(n_features)))
+            allowed_string_values = (
+                '"sqrt" or "log2"'
+                if sklearn_check_version("1.3")
+                else '"auto", "sqrt" or "log2"'
+            )
+            raise ValueError(
+                "Invalid value for max_features. Allowed string "
+                f"values are {allowed_string_values}."
+            )
+        if isinstance(max_features, (numbers.Integral, np.integer)):
+            return max_features
+        if max_features > 0.0:
+            return max(1, int(max_features * n_features))
+        return 0
+
     def _check_parameters(self):
         if isinstance(self.min_samples_leaf, numbers.Integral):
             if not 1 <= self.min_samples_leaf:
@@ -518,7 +558,7 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
             )
 
         if patching_status.get_status():
-            X, y = self._validate_data(
+            X, y = check_X_y(
                 X,
                 y,
                 multi_output=True,
@@ -738,6 +778,10 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
+                    (
+                        not self.oob_score,
+                        "oob_scores using r2 or accuracy not implemented.",
+                    ),
                     (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
@@ -777,26 +821,46 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
         return patching_status
 
     def _onedal_predict(self, X, queue=None):
-        X = check_array(
-            X,
-            dtype=[np.float64, np.float32],
-            force_all_finite=False,
-        )  # Warning, order of dtype matters
         check_is_fitted(self, "_onedal_estimator")
 
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )  # Warning, order of dtype matters
+            self._check_n_features(X, reset=False)
 
         res = self._onedal_estimator.predict(X, queue=queue)
         return np.take(self.classes_, res.ravel().astype(np.int64, casting="unsafe"))
 
     def _onedal_predict_proba(self, X, queue=None):
-        X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=False)
         check_is_fitted(self, "_onedal_estimator")
 
-        self._check_n_features(X, reset=False)
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )  # Warning, order of dtype matters
+            self._check_n_features(X, reset=False)
+
         return self._onedal_estimator.predict_proba(X, queue=queue)
 
     def _onedal_score(self, X, y, sample_weight=None, queue=None):
@@ -913,7 +977,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
             )
 
         if patching_status.get_status():
-            X, y = self._validate_data(
+            X, y = check_X_y(
                 X,
                 y,
                 multi_output=True,
@@ -995,7 +1059,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
                 ]
             )
 
-        elif method_name == "predict":
+        elif method_name in ["predict", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -1045,11 +1109,12 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
+                    (not self.oob_score, "oob_score value is not sklearn conformant."),
                     (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
 
-        elif method_name == "predict":
+        elif method_name in ["predict", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -1082,16 +1147,28 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
         return patching_status
 
     def _onedal_predict(self, X, queue=None):
-        X = check_array(
-            X, dtype=[np.float64, np.float32], force_all_finite=False
-        )  # Warning, order of dtype matters
         check_is_fitted(self, "_onedal_estimator")
 
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )  # Warning, order of dtype matters
+        else:
+            X = check_array(
+                X, dtype=[np.float64, np.float32], force_all_finite=False
+            )  # Warning, order of dtype matters
 
         return self._onedal_estimator.predict(X, 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 fit(self, X, y, sample_weight=None):
         dispatch(
             self,
@@ -1118,8 +1195,23 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_ForestRegressor.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     fit.__doc__ = sklearn_ForestRegressor.fit.__doc__
     predict.__doc__ = sklearn_ForestRegressor.predict.__doc__
+    score.__doc__ = sklearn_ForestRegressor.score.__doc__
 
 
 @control_n_jobs(decorated_methods=["fit", "predict", "predict_proba", "score"])

sklearnex/ensemble/tests/test_forest.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 # ===============================================================================
 
+import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 from sklearn.datasets import make_classification, make_regression
@@ -45,7 +46,10 @@ def test_sklearnex_import_rf_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix RF regressor predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_rf_regression(dataframe, queue):
     from sklearnex.ensemble import RandomForestRegressor
 
@@ -65,7 +69,10 @@ def test_sklearnex_import_rf_regression(dataframe, queue):
             assert_allclose([-6.839], pred, atol=1e-2)
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix ET classifier predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_et_classifier(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesClassifier
 
@@ -86,7 +93,10 @@ def test_sklearnex_import_et_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix ET regressor predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_et_regression(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesRegressor
 

sklearnex/glob/dispatcher.py

@@ -17,18 +17,32 @@
 
 def get_patch_str(name=None, verbose=True):
     return f"""try:
+    # TEMP. FIX: sklearnex.patch_sklearn imports sklearn beforehand
+    # when it didn't initialized _threadpool_controller required for
+    # pairwise distances dispatching during imports.
+    # Manually setting and deleting _threadpool_controller during patch fixes it.
+    import sklearn
+    from threadpoolctl import ThreadpoolController
+    sklearn._threadpool_controller = ThreadpoolController()
     from sklearnex import patch_sklearn
     patch_sklearn(name={str(name)}, verbose={str(verbose)})
-    del patch_sklearn
+    del patch_sklearn, sklearn._threadpool_controller
 except ImportError:
     pass"""
 
 
 def get_patch_str_re():
     return r"""\ntry:
+    \# TEMP. FIX: sklearnex.patch_sklearn imports sklearn beforehand
+    \# when it didn't initialized _threadpool_controller required for
+    \# pairwise distances dispatching during imports.
+    \# Manually setting and deleting _threadpool_controller during patch fixes it.
+    import sklearn
+    from threadpoolctl import ThreadpoolController
+    sklearn._threadpool_controller = ThreadpoolController\(\)
     from sklearnex import patch_sklearn
     patch_sklearn\(name=.*, verbose=.*\)
-    del patch_sklearn
+    del patch_sklearn, sklearn._threadpool_controller
 except ImportError:
     pass\n"""
 

sklearnex/linear_model/__init__.py

@@ -15,14 +15,16 @@
 # ===============================================================================
 
 from .coordinate_descent import ElasticNet, Lasso
+from .incremental_linear import IncrementalLinearRegression
 from .linear import LinearRegression
 from .logistic_regression import LogisticRegression
 from .ridge import Ridge
 
 __all__ = [
-    "Ridge",
-    "LinearRegression",
-    "LogisticRegression",
     "ElasticNet",
+    "IncrementalLinearRegression",
     "Lasso",
+    "LinearRegression",
+    "LogisticRegression",
+    "Ridge",
 ]