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/decomposition/tests/test_pca.py

@@ -0,0 +1,164 @@
+# ===============================================================================
+# 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 pytest
+import scipy.sparse as sp
+from numpy.testing import assert_allclose
+from sklearn.base import clone
+from sklearn.datasets import load_iris
+
+from daal4py.sklearn._utils import daal_check_version, sklearn_check_version
+from onedal.tests.utils._dataframes_support import (
+    _as_numpy,
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+from sklearnex.decomposition import PCA
+
+
+@pytest.fixture
+def hyperparameters(request):
+    hparams = PCA.get_hyperparameters("fit")
+
+    def restore_hyperparameters():
+        if daal_check_version((2025, "P", 700)):
+            PCA.reset_hyperparameters("fit")
+
+    request.addfinalizer(restore_hyperparameters)
+    return hparams
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("macro_block", [None, 2])
+@pytest.mark.parametrize("grain_size", [None, 2])
+def test_sklearnex_import(hyperparameters, dataframe, queue, macro_block, grain_size):
+
+    X = [[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    X_transformed_expected = [
+        [-1.38340578, -0.2935787],
+        [-2.22189802, 0.25133484],
+        [-3.6053038, -0.04224385],
+        [1.38340578, 0.2935787],
+        [2.22189802, -0.25133484],
+        [3.6053038, 0.04224385],
+    ]
+
+    if daal_check_version((2025, "P", 700)):
+        if macro_block is not None:
+            if queue and queue.sycl_device.is_gpu:
+                pytest.skip("Test for CPU-only functionality")
+            hyperparameters.cpu_macro_block = macro_block
+        if grain_size is not None:
+            if queue and queue.sycl_device.is_gpu:
+                pytest.skip("Test for CPU-only functionality")
+            hyperparameters.cpu_grain_size = grain_size
+
+    pca = PCA(n_components=2, svd_solver="covariance_eigh")
+
+    pca.fit(X)
+    X_transformed = pca.transform(X)
+    X_fit_transformed = PCA(n_components=2, svd_solver="covariance_eigh").fit_transform(X)
+
+    if daal_check_version((2024, "P", 100)):
+        assert "sklearnex" in pca.__module__
+        assert hasattr(pca, "_onedal_estimator")
+    else:
+        assert "daal4py" in pca.__module__
+
+    tol = 1e-5 if _as_numpy(X_transformed).dtype == np.float32 else 1e-7
+    assert_allclose([6.30061232, 0.54980396], _as_numpy(pca.singular_values_))
+    assert_allclose(X_transformed_expected, _as_numpy(X_transformed), rtol=tol)
+    assert_allclose(X_transformed_expected, _as_numpy(X_fit_transformed), rtol=tol)
+
+
+@pytest.mark.skipif(
+    not daal_check_version((2025, "P", 700)),
+    reason="Functionality introduced in a later version",
+)
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_non_batched_covariance(hyperparameters, dataframe, queue):
+    if queue and queue.sycl_device.is_gpu:
+        pytest.skip("Test for CPU-only functionality")
+
+    from sklearnex.decomposition import PCA
+
+    # This generates a random matrix with non-independent columns
+    rng = np.random.default_rng(seed=123)
+    S = rng.standard_normal(size=(6, 5))
+    S = S.T @ S
+    mu = rng.standard_normal(size=5)
+    X = rng.multivariate_normal(mu, S, size=20)
+
+    hyperparameters.cpu_max_cols_batched = np.iinfo(np.int32).max
+    res_batched = PCA().fit(X).components_
+
+    hyperparameters.cpu_max_cols_batched = 1
+    res_non_batched = PCA().fit(X).components_
+
+    assert_allclose(res_non_batched, res_batched)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues("numpy,dpctl"))
+def test_changed_estimated_attributes(with_array_api, dataframe, queue):
+    # check that attributes necessary for the PCA onedal estimator match
+    # changes occurring in the sklearnex estimator
+    X, y = load_iris(return_X_y=True)
+
+    X_0 = _convert_to_dataframe(X[y == 0], sycl_queue=queue, target_df=dataframe)
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+
+    est0 = PCA(n_components=4).fit(X_0)
+    est = clone(est0)
+    assert not hasattr(est, "_onedal_estimator")
+    est.fit(X)
+    assert not np.array_equal(_as_numpy(est.transform(X)), _as_numpy(est0.transform(X)))
+
+    # copy over parameters necessary for transform
+    est.mean_ = est0.mean_
+    est.components_ = est0.components_
+    est.explained_variance_ = est0.explained_variance_
+    est.n_components_ = est0.n_components_  # is trivial but exercises the logic
+
+    assert np.array_equal(_as_numpy(est.transform(X)), _as_numpy(est0.transform(X)))
+
+
+@pytest.mark.skipif(
+    not sklearn_check_version("1.5"),
+    reason='svd_solver="auto" does not support sparse inputs',
+)
+@pytest.mark.allow_sklearn_fallback
+def test_create_model_behavior():
+    # verify that fit fallbacks does not break ``transform`` as the oneDAL
+    # model is generated JIT
+
+    X, _ = load_iris(return_X_y=True)
+    # generate a onedal estimator
+    est = PCA(n_components=3)
+    X_trans = est.fit_transform(X)
+
+    # force data to sparse for a fallback to sklearn
+    X_sp = sp.csr_matrix(X)
+    est.fit(X_sp)
+    # In the case of a fallback, the model should be set to none by clobbered
+    # fitted attributes
+    assert est._onedal_estimator._onedal_model is None
+
+    X_trans_sparse = est.transform(X)
+    # use allclose as data was fit with sklearn and onedal on the same data
+    # but using different backends
+    assert_allclose(X_trans, X_trans_sparse)

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

@@ -45,26 +45,19 @@ def get_patch_map_core(preview=False):
 
         if _is_new_patching_available():
             import sklearn.covariance as covariance_module
+            import sklearn.decomposition as decomposition_module
 
             # Preview classes for patching
-            from .preview.cluster import KMeans as KMeans_sklearnex
             from .preview.covariance import (
                 EmpiricalCovariance as EmpiricalCovariance_sklearnex,
             )
+            from .preview.decomposition import IncrementalPCA as IncrementalPCA_sklearnex
 
             # Since the state of the lru_cache without preview cannot be
             # guaranteed to not have already enabled sklearnex algorithms
             # when preview is used, setting the mapping element[1] to None
             # should NOT be done. This may lose track of the unpatched
             # sklearn estimator or function.
-            # KMeans
-            cluster_module, _, _ = mapping["kmeans"][0][0]
-            sklearn_obj = mapping["kmeans"][0][1]
-            mapping.pop("kmeans")
-            mapping["kmeans"] = [
-                [(cluster_module, "kmeans", KMeans_sklearnex), sklearn_obj]
-            ]
-
             # Covariance
             mapping["empiricalcovariance"] = [
                 [
@@ -76,6 +69,19 @@ def get_patch_map_core(preview=False):
                     None,
                 ]
             ]
+
+            # IncrementalPCA
+            mapping["incrementalpca"] = [
+                [
+                    (
+                        decomposition_module,
+                        "IncrementalPCA",
+                        IncrementalPCA_sklearnex,
+                    ),
+                    None,
+                ]
+            ]
+
         return mapping
 
     from daal4py.sklearn.monkeypatch.dispatcher import _get_map_of_algorithms
@@ -93,9 +99,19 @@ def get_patch_map_core(preview=False):
         # Scikit-learn* modules
         import sklearn as base_module
         import sklearn.cluster as cluster_module
+        import sklearn.covariance as covariance_module
         import sklearn.decomposition as decomposition_module
+        import sklearn.dummy as dummy_module
         import sklearn.ensemble as ensemble_module
+
+        if sklearn_check_version("1.4"):
+            import sklearn.ensemble._gb as _gb_module
+        else:
+            import sklearn.ensemble._gb_losses as _gb_module
         import sklearn.linear_model as linear_model_module
+        import sklearn.manifold as manifold_module
+        import sklearn.metrics as metrics_module
+        import sklearn.model_selection as model_selection_module
         import sklearn.neighbors as neighbors_module
         import sklearn.svm as svm_module
 
@@ -108,20 +124,30 @@ def get_patch_map_core(preview=False):
         from ._config import config_context as config_context_sklearnex
         from ._config import get_config as get_config_sklearnex
         from ._config import set_config as set_config_sklearnex
-
-        if sklearn_check_version("1.2.1"):
-            from .utils.parallel import _FuncWrapper as _FuncWrapper_sklearnex
-        else:
-            from .utils.parallel import _FuncWrapperOld as _FuncWrapper_sklearnex
-
         from .cluster import DBSCAN as DBSCAN_sklearnex
+        from .cluster import KMeans as KMeans_sklearnex
+        from .covariance import (
+            IncrementalEmpiricalCovariance as IncrementalEmpiricalCovariance_sklearnex,
+        )
         from .decomposition import PCA as PCA_sklearnex
+        from .dummy import DummyRegressor as DummyRegressor_sklearnex
         from .ensemble import ExtraTreesClassifier as ExtraTreesClassifier_sklearnex
         from .ensemble import ExtraTreesRegressor as ExtraTreesRegressor_sklearnex
         from .ensemble import RandomForestClassifier as RandomForestClassifier_sklearnex
         from .ensemble import RandomForestRegressor as RandomForestRegressor_sklearnex
+        from .linear_model import ElasticNet as ElasticNet_sklearnex
+        from .linear_model import (
+            IncrementalLinearRegression as IncrementalLinearRegression_sklearnex,
+        )
+        from .linear_model import IncrementalRidge as IncrementalRidge_sklearnex
+        from .linear_model import Lasso as Lasso_sklearnex
         from .linear_model import LinearRegression as LinearRegression_sklearnex
         from .linear_model import LogisticRegression as LogisticRegression_sklearnex
+        from .linear_model import Ridge as Ridge_sklearnex
+        from .manifold import TSNE as TSNE_sklearnex
+        from .metrics import pairwise_distances as pairwise_distances_sklearnex
+        from .metrics import roc_auc_score as roc_auc_score_sklearnex
+        from .model_selection import train_test_split as train_test_split_sklearnex
         from .neighbors import KNeighborsClassifier as KNeighborsClassifier_sklearnex
         from .neighbors import KNeighborsRegressor as KNeighborsRegressor_sklearnex
         from .neighbors import LocalOutlierFactor as LocalOutlierFactor_sklearnex
@@ -130,11 +156,16 @@ def get_patch_map_core(preview=False):
         from .svm import SVR as SVR_sklearnex
         from .svm import NuSVC as NuSVC_sklearnex
         from .svm import NuSVR as NuSVR_sklearnex
+        from .utils.parallel import _FuncWrapper as _FuncWrapper_sklearnex
 
         # DBSCAN
         mapping.pop("dbscan")
         mapping["dbscan"] = [[(cluster_module, "DBSCAN", DBSCAN_sklearnex), None]]
 
+        # KMeans
+        mapping.pop("kmeans")
+        mapping["kmeans"] = [[(cluster_module, "KMeans", KMeans_sklearnex), None]]
+
         # PCA
         mapping.pop("pca")
         mapping["pca"] = [[(decomposition_module, "PCA", PCA_sklearnex), None]]
@@ -147,6 +178,32 @@ def get_patch_map_core(preview=False):
         mapping["nusvr"] = [[(svm_module, "NuSVR", NuSVR_sklearnex), None]]
         mapping["nusvc"] = [[(svm_module, "NuSVC", NuSVC_sklearnex), None]]
 
+        # ElasticNet
+        mapping.pop("elasticnet")
+        mapping["elasticnet"] = [
+            [
+                (
+                    linear_model_module,
+                    "ElasticNet",
+                    ElasticNet_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
+        # Lasso
+        mapping.pop("lasso")
+        mapping["lasso"] = [
+            [
+                (
+                    linear_model_module,
+                    "Lasso",
+                    Lasso_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
         # Linear Regression
         mapping.pop("linear")
         mapping.pop("linearregression")
@@ -180,6 +237,54 @@ def get_patch_map_core(preview=False):
         ]
         mapping["logisticregression"] = mapping["log_reg"]
 
+        # Ridge
+        mapping.pop("ridge")
+        mapping["ridge"] = [
+            [
+                (
+                    linear_model_module,
+                    "Ridge",
+                    Ridge_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
+        # manifold
+        mapping.pop("tsne")
+        mapping["tsne"] = [
+            [
+                (manifold_module, "TSNE", TSNE_sklearnex),
+                None,
+            ]
+        ]
+
+        # metrics
+        mapping.pop("distances")
+        mapping.pop("roc_auc_score")
+        mapping["distances"] = [
+            [
+                (metrics_module, "pairwise_distances", pairwise_distances_sklearnex),
+                None,
+            ]
+        ]
+        mapping["pairwise_distances"] = mapping["distances"]
+        mapping["roc_auc_score"] = [
+            [
+                (metrics_module, "roc_auc_score", roc_auc_score_sklearnex),
+                None,
+            ]
+        ]
+
+        # model_selection
+        mapping.pop("train_test_split")
+        mapping["train_test_split"] = [
+            [
+                (model_selection_module, "train_test_split", train_test_split_sklearnex),
+                None,
+            ]
+        ]
+
         # kNN
         mapping.pop("knn_classifier")
         mapping.pop("kneighborsclassifier")
@@ -273,6 +378,68 @@ def get_patch_map_core(preview=False):
         ]
         mapping["localoutlierfactor"] = mapping["lof"]
 
+        # IncrementalEmpiricalCovariance
+        mapping["incrementalempiricalcovariance"] = [
+            [
+                (
+                    covariance_module,
+                    "IncrementalEmpiricalCovariance",
+                    IncrementalEmpiricalCovariance_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
+        # IncrementalLinearRegression
+        mapping["incrementallinearregression"] = [
+            [
+                (
+                    linear_model_module,
+                    "IncrementalLinearRegression",
+                    IncrementalLinearRegression_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
+        if daal_check_version((2024, "P", 600)):
+            # IncrementalRidge
+            mapping["incrementalridge"] = [
+                [
+                    (
+                        linear_model_module,
+                        "IncrementalRidge",
+                        IncrementalRidge_sklearnex,
+                    ),
+                    None,
+                ]
+            ]
+
+        # DummyRegressor
+        mapping["dummyregressor"] = [
+            [
+                (
+                    dummy_module,
+                    "DummyRegressor",
+                    DummyRegressor_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
+        # Required patching of DummyRegressor in the gradient boosting
+        # module as it is used in the GradientBoosting algorithms
+        mapping["gb_dummyregressor"] = [
+            [
+                (
+                    _gb_module,
+                    "DummyRegressor",
+                    DummyRegressor_sklearnex,
+                ),
+                None,
+            ]
+        ]
+
         # Configs
         mapping["set_config"] = [
             [(base_module, "set_config", set_config_sklearnex), None]
@@ -314,10 +481,10 @@ def get_patch_names():
 def patch_sklearn(name=None, verbose=True, global_patch=False, preview=False):
     if preview:
         os.environ["SKLEARNEX_PREVIEW"] = "enabled_via_patch_sklearn"
-    if not sklearn_check_version("0.24"):
+    if not sklearn_check_version("1.0"):
         raise NotImplementedError(
-            "Intel(R) Extension for Scikit-learn* patches apply "
-            "for scikit-learn >= 0.24 only ..."
+            "Extension for Scikit-learn* patches apply "
+            "for scikit-learn >= 1.0 only ..."
         )
 
     if global_patch:
@@ -342,8 +509,8 @@ def patch_sklearn(name=None, verbose=True, global_patch=False, preview=False):
 
     if verbose and sys.stderr is not None:
         sys.stderr.write(
-            "Intel(R) Extension for Scikit-learn* enabled "
-            "(https://github.com/intel/scikit-learn-intelex)\n"
+            "Extension for Scikit-learn* enabled "
+            "(https://github.com/uxlfoundation/scikit-learn-intelex)\n"
         )
 
 
@@ -389,6 +556,17 @@ def sklearn_is_patched(name=None, return_map=False):
 
 
 def is_patched_instance(instance: object) -> bool:
-    """Returns True if the `instance` is patched with scikit-learn-intelex"""
+    """Check if given instance is patched with scikit-learn-intelex.
+
+    Parameters
+    ----------
+    instance : object
+        Python object, usually a scikit-learn estimator instance.
+
+    Returns
+    -------
+    Check : bool
+        Boolean whether instance is a daal4py or sklearnex estimator.
+    """
     module = getattr(instance, "__module__", "")
     return ("daal4py" in module) or ("sklearnex" in module)