scikit-learn-intelex 2025.1.0__py39-none-manylinux_2_28_x86_64.whl

sklearnex/ensemble/tests/test_forest.py

@@ -0,0 +1,135 @@
+# ===============================================================================
+# 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 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.mark.parametrize("dataframe, queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("block, trees, rows, scale", hparam_values)
+def test_sklearnex_import_rf_classifier(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)
+    hparams = rf.get_hyperparameters("infer")
+    if hparams and block is not None:
+        hparams.block_size = block
+        hparams.min_trees_for_threading = trees
+        hparams.min_number_of_rows_for_vect_seq_compute = rows
+        hparams.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 queue and queue.sycl_device.is_gpu:
+        pytest.skip("RF regressor predict for the GPU sycl_queue is buggy.")
+    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]]))
+
+    if queue is not None and queue.sycl_device.is_gpu:
+        assert_allclose([-0.011208], pred, atol=1e-2)
+    else:
+        if daal_check_version((2024, "P", 0)):
+            assert_allclose([-6.971], pred, atol=1e-2)
+        else:
+            assert_allclose([-6.839], pred, atol=1e-2)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_et_classifier(dataframe, queue):
+    if queue and queue.sycl_device.is_gpu:
+        pytest.skip("ET classifier predict for the GPU sycl_queue is buggy.")
+    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 queue and queue.sycl_device.is_gpu:
+        pytest.skip("ET regressor predict for the GPU sycl_queue is buggy.")
+    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,
+                ]
+            ]
+        )
+    )
+
+    if queue is not None and queue.sycl_device.is_gpu:
+        assert_allclose([1.909769], pred, atol=1e-2)
+    else:
+        assert_allclose([0.445], pred, atol=1e-2)

sklearnex/glob/__main__.py

@@ -0,0 +1,72 @@
+# ===============================================================================
+# 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 sklearnex import patch_sklearn, unpatch_sklearn
+
+
+def _main():
+    import argparse
+
+    # Adding custom extend action for support all python versions
+    class ExtendAction(argparse.Action):
+        def __call__(self, parser, namespace, values, option_string=None):
+            items = getattr(namespace, self.dest) or []
+            items.extend(values)
+            setattr(namespace, self.dest, items)
+
+    parser = argparse.ArgumentParser(
+        prog="python -m sklearnex.glob",
+        description="""
+            Patch all your Scikit-learn applications using Intel(R) Extension for
+            scikit-learn.""",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+
+    parser.register("action", "extend", ExtendAction)
+    parser.add_argument(
+        "action",
+        choices=["patch_sklearn", "unpatch_sklearn"],
+        help="Enable or Disable patching",
+    )
+    parser.add_argument(
+        "--no-verbose",
+        "-nv",
+        action="store_false",
+        help="Disable additional information about enabling patching",
+    )
+    parser.add_argument(
+        "--algorithm",
+        "-a",
+        action="extend",
+        type=str,
+        nargs="+",
+        help="The name of an algorithm to be patched globally",
+    )
+    args = parser.parse_args()
+
+    if args.action == "patch_sklearn":
+        patch_sklearn(name=args.algorithm, verbose=args.no_verbose, global_patch=True)
+    elif args.action == "unpatch_sklearn":
+        unpatch_sklearn(global_unpatch=True)
+    else:
+        raise RuntimeError(
+            "Invalid choice for the action attribute."
+            " Expected: patch_sklearn or unpatch_sklearn."
+            f" Got {args.action}"
+        )
+
+
+_main()

sklearnex/glob/dispatcher.py

@@ -0,0 +1,101 @@
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+
+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, 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, sklearn._threadpool_controller
+except ImportError:
+    pass\n"""
+
+
+def patch_sklearn_global(name=None, verbose=True):
+    import os
+    import re
+
+    try:
+        import sklearn
+    except ImportError:
+        raise ImportError("Scikit-learn could not be imported. Nothing to patch\n")
+
+    init_file_path = sklearn.__file__
+    distributor_file_path = os.path.join(
+        os.path.dirname(init_file_path), "_distributor_init.py"
+    )
+
+    with open(distributor_file_path, "r", encoding="utf-8") as distributor_file:
+        lines = distributor_file.read()
+        if re.search(get_patch_str_re(), lines):
+            lines = re.sub(get_patch_str_re(), "", lines)
+
+    with open(distributor_file_path, "w", encoding="utf-8") as distributor_file:
+        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"
+        )
+        return
+
+
+def unpatch_sklearn_global():
+    import os
+    import re
+
+    try:
+        import sklearn
+    except ImportError:
+        raise ImportError("Scikit-learn could not be imported. Nothing to unpatch\n")
+
+    init_file_path = sklearn.__file__
+    distributor_file_path = os.path.join(
+        os.path.dirname(init_file_path), "_distributor_init.py"
+    )
+
+    with open(distributor_file_path, "r", encoding="utf-8") as distributor_file:
+        lines = distributor_file.read()
+        if not re.search(get_patch_str_re(), lines):
+            print("Nothing to unpatch: Scikit-learn is not patched\n")
+            return
+        lines = re.sub(get_patch_str_re(), "", lines)
+
+    with open(distributor_file_path, "w", encoding="utf-8") as distributor_file:
+        distributor_file.write(lines)
+        print("Scikit-learn was successfully globally unpatched")

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",
+]

sklearnex/linear_model/coordinate_descent.py

@@ -0,0 +1,30 @@
+# ===============================================================================
+# 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.linear_model import ElasticNet, Lasso
+from onedal._device_offload import support_input_format
+
+# Note: `sklearnex.linear_model.ElasticNet` only has functional
+# sycl GPU support. No GPU device will be offloaded.
+ElasticNet.fit = support_input_format(queue_param=False)(ElasticNet.fit)
+ElasticNet.predict = support_input_format(queue_param=False)(ElasticNet.predict)
+ElasticNet.score = support_input_format(queue_param=False)(ElasticNet.score)
+
+# Note: `sklearnex.linear_model.Lasso` only has functional
+# sycl GPU support. No GPU device will be offloaded.
+Lasso.fit = support_input_format(queue_param=False)(Lasso.fit)
+Lasso.predict = support_input_format(queue_param=False)(Lasso.predict)
+Lasso.score = support_input_format(queue_param=False)(Lasso.score)