scikit-learn-intelex 2024.4.0__py312-none-win_amd64.whl → 2025.10.0__py312-none-win_amd64.whl

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/sklearnex/ensemble/tests/test_forest.py

@@ -0,0 +1,196 @@
+# ===============================================================================
+# 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 numpy as np
+import pandas as pd
+import pytest
+from numpy.testing import assert_allclose
+from sklearn.datasets import make_classification, make_regression
+
+from daal4py.sklearn._utils import daal_check_version
+from onedal.tests.utils._dataframes_support import (
+    _as_numpy,
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+
+hparam_values = [
+    (None, None, None, None),
+    (8, 100, 32, 0.3),
+    (16, 100, 32, 0.3),
+    (32, 100, 32, 0.3),
+    (64, 10, 32, 0.1),
+    (128, 100, 1000, 1.0),
+]
+
+
+@pytest.fixture
+def hyperparameters(request):
+    from sklearnex.ensemble import RandomForestClassifier
+
+    hparams = RandomForestClassifier.get_hyperparameters("predict")
+
+    def restore_hyperparameters():
+        RandomForestClassifier.reset_hyperparameters("predict")
+
+    request.addfinalizer(restore_hyperparameters)
+    return hparams
+
+
+@pytest.mark.parametrize("dataframe, queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("block, trees, rows, scale", hparam_values)
+def test_sklearnex_import_rf_classifier(
+    hyperparameters, dataframe, queue, block, trees, rows, scale
+):
+    from sklearnex.ensemble import RandomForestClassifier
+
+    X, y = make_classification(
+        n_samples=1000,
+        n_features=4,
+        n_informative=2,
+        n_redundant=0,
+        random_state=0,
+        shuffle=False,
+    )
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    rf = RandomForestClassifier(max_depth=2, random_state=0).fit(X, y)
+
+    if hyperparameters and block is not None:
+        hyperparameters.block_size = block
+        hyperparameters.min_trees_for_threading = trees
+        hyperparameters.min_number_of_rows_for_vect_seq_compute = rows
+        hyperparameters.scale_factor_for_vect_parallel_compute = scale
+    assert "sklearnex" in rf.__module__
+    assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_rf_regression(dataframe, queue):
+    if (not daal_check_version((2025, "P", 200))) and queue and queue.sycl_device.is_gpu:
+        pytest.skip("Skipping due to bug in histogram merges fixed in 2025.2.")
+    from sklearnex.ensemble import RandomForestRegressor
+
+    X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    rf = RandomForestRegressor(max_depth=2, random_state=0).fit(X, y)
+    assert "sklearnex" in rf.__module__
+    pred = _as_numpy(rf.predict([[0, 0, 0, 0]]))
+
+    # Check that the prediction is within a reasonable range.
+    # 'y' should be in the neighborhood of zero for x=0.
+    assert pred[0] >= -10
+    assert pred[0] <= 10
+
+    # Check that the trees aren't just empty nodes predicting the mean
+    for estimator in rf.estimators_:
+        assert estimator.tree_.children_left.shape[0] > 1
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_et_classifier(dataframe, queue):
+    if (not daal_check_version((2025, "P", 200))) and queue and queue.sycl_device.is_gpu:
+        pytest.skip("Skipping due to bug in histogram merges fixed in 2025.2.")
+    from sklearnex.ensemble import ExtraTreesClassifier
+
+    X, y = make_classification(
+        n_samples=1000,
+        n_features=4,
+        n_informative=2,
+        n_redundant=0,
+        random_state=0,
+        shuffle=False,
+    )
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    # For the 2023.2 release, random_state is not supported
+    # defaults to seed=777, although it is set to 0
+    rf = ExtraTreesClassifier(max_depth=2, random_state=0).fit(X, y)
+    assert "sklearnex" in rf.__module__
+    assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_et_regression(dataframe, queue):
+    if (not daal_check_version((2025, "P", 200))) and queue and queue.sycl_device.is_gpu:
+        pytest.skip("Skipping due to bug in histogram merges fixed in 2025.2.")
+    from sklearnex.ensemble import ExtraTreesRegressor
+
+    X, y = make_regression(n_features=1, random_state=0, shuffle=False)
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    # For the 2023.2 release, random_state is not supported
+    # defaults to seed=777, although it is set to 0
+    rf = ExtraTreesRegressor(random_state=0).fit(X, y)
+    assert "sklearnex" in rf.__module__
+    pred = _as_numpy(
+        rf.predict(
+            [
+                [
+                    0,
+                ]
+            ]
+        )
+    )
+
+    # Check that the prediction is within a reasonable range.
+    # 'y' should be in the neighborhood of zero for x=0.
+    assert pred[0] >= -10
+    assert pred[0] <= 10
+
+    # Check that the trees aren't just empty nodes predicting the mean
+    for estimator in rf.estimators_:
+        assert estimator.tree_.children_left.shape[0] > 1
+
+
+@pytest.mark.allow_sklearn_fallback
+@pytest.mark.parametrize("dataframe, queue", get_dataframes_and_queues())
+def test_classifiers_work_on_single_class(dataframe, queue):
+    from sklearnex.ensemble import ExtraTreesClassifier, RandomForestClassifier
+
+    rng = np.random.default_rng(seed=123)
+    X = rng.standard_normal(size=(20, 10))
+    y = np.zeros(X.shape[0])
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+
+    np.testing.assert_array_equal(
+        _as_numpy(RandomForestClassifier(n_estimators=1).fit(X, y).predict(X)),
+        _as_numpy(y),
+    )
+    np.testing.assert_array_equal(
+        _as_numpy(ExtraTreesClassifier(n_estimators=1).fit(X, y).predict(X)),
+        _as_numpy(y),
+    )
+
+
+@pytest.mark.allow_sklearn_fallback
+def test_classifiers_work_on_single_class_non_numeric():
+    from sklearnex.ensemble import ExtraTreesClassifier, RandomForestClassifier
+
+    rng = np.random.default_rng(seed=123)
+    X = rng.standard_normal(size=(20, 10))
+    y = pd.Series(np.repeat("qwerty", X.shape[0]))
+
+    np.testing.assert_array_equal(
+        RandomForestClassifier(n_estimators=1).fit(X, y).predict(X),
+        y,
+    )
+    np.testing.assert_array_equal(
+        ExtraTreesClassifier(n_estimators=1).fit(X, y).predict(X),
+        y,
+    )

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2025.10.0.data}/data/Lib/site-packages/sklearnex/glob/__main__.py

@@ -30,7 +30,7 @@ def _main():
     parser = argparse.ArgumentParser(
         prog="python -m sklearnex.glob",
         description="""
-            Patch all your Scikit-learn applications using Intel(R) Extension for
+            Patch all your Scikit-learn applications using Extension for
             scikit-learn.""",
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2025.10.0.data}/data/Lib/site-packages/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"""
 
@@ -56,7 +70,7 @@ def patch_sklearn_global(name=None, verbose=True):
         distributor_file.write(lines + "\n" + get_patch_str(name, verbose) + "\n")
         print(
             "Scikit-learn was successfully globally patched"
-            " by Intel(R) Extension for Scikit-learn"
+            " by Extension for Scikit-learn"
         )
         return
 

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/sklearnex/linear_model/__init__.py

@@ -0,0 +1,32 @@
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+from .coordinate_descent import ElasticNet, Lasso
+from .incremental_linear import IncrementalLinearRegression
+from .incremental_ridge import IncrementalRidge
+from .linear import LinearRegression
+from .logistic_regression import LogisticRegression
+from .ridge import Ridge
+
+__all__ = [
+    "ElasticNet",
+    "IncrementalLinearRegression",
+    "IncrementalRidge",
+    "Lasso",
+    "LinearRegression",
+    "LogisticRegression",
+    "Ridge",
+]

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/sklearnex/linear_model/coordinate_descent.py

@@ -0,0 +1,44 @@
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+from daal4py.sklearn._utils import sklearn_check_version
+from daal4py.sklearn.linear_model import ElasticNet, Lasso
+from onedal._device_offload import support_input_format
+
+from ..base import oneDALEstimator
+
+# Note: `sklearnex.linear_model.ElasticNet` only has functional
+# sycl GPU support. No GPU device will be offloaded.
+ElasticNet.fit = support_input_format(ElasticNet.fit)
+ElasticNet.predict = support_input_format(ElasticNet.predict)
+ElasticNet.path = staticmethod(support_input_format(ElasticNet.path))
+ElasticNet.score = support_input_format(ElasticNet.score)
+if sklearn_check_version("1.4"):
+    ElasticNet._doc_link_module = "daal4py"
+    ElasticNet._doc_link_url_param_generator = (
+        oneDALEstimator._doc_link_url_param_generator
+    )
+
+
+# Note: `sklearnex.linear_model.Lasso` only has functional
+# sycl GPU support. No GPU device will be offloaded.
+Lasso.fit = support_input_format(Lasso.fit)
+Lasso.predict = support_input_format(Lasso.predict)
+Lasso.path = staticmethod(support_input_format(Lasso.path))
+Lasso.score = support_input_format(Lasso.score)
+if sklearn_check_version("1.4"):
+    Lasso._doc_link_module = "daal4py"
+    Lasso._doc_link_url_param_generator = oneDALEstimator._doc_link_url_param_generator