scikit-learn-intelex 2025.10.0__py313-none-win_amd64.whl

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/onedal/basic_statistics/tests/utils.py

@@ -0,0 +1,50 @@
+# ===============================================================================
+# Copyright 2024 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
+
+
+# Compute unbiased variation for the columns of array-like X
+def variation(X):
+    X_mean = np.mean(X, axis=0)
+    if np.all(X_mean):
+        # Avoid division by zero
+        return np.std(X, axis=0, ddof=1) / X_mean
+    else:
+        return np.array(
+            [
+                x / y if y != 0 else np.nan
+                for x, y in zip(np.std(X, axis=0, ddof=1), X_mean)
+            ]
+        )
+
+
+options_and_tests = {
+    "sum": (lambda X: np.sum(X, axis=0), (5e-4, 1e-7)),
+    "min": (lambda X: np.min(X, axis=0), (1e-7, 1e-7)),
+    "max": (lambda X: np.max(X, axis=0), (1e-7, 1e-7)),
+    "mean": (lambda X: np.mean(X, axis=0), (5e-7, 1e-7)),
+    # sklearnex computes unbiased variance and standard deviation that is why ddof=1
+    "variance": (lambda X: np.var(X, axis=0, ddof=1), (2e-4, 1e-7)),
+    "variation": (lambda X: variation(X), (1e-3, 1e-6)),
+    "sum_squares": (lambda X: np.sum(np.square(X), axis=0), (2e-4, 1e-7)),
+    "sum_squares_centered": (
+        lambda X: np.sum(np.square(X - np.mean(X, axis=0)), axis=0),
+        (1e-3, 1e-7),
+    ),
+    "standard_deviation": (lambda X: np.std(X, axis=0, ddof=1), (2e-3, 1e-7)),
+    "second_order_raw_moment": (lambda X: np.mean(np.square(X), axis=0), (1e-6, 1e-7)),
+}

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/onedal/cluster/__init__.py

@@ -0,0 +1,27 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from daal4py.sklearn._utils import daal_check_version
+
+from .dbscan import DBSCAN
+from .kmeans import KMeans, k_means
+
+__all__ = ["DBSCAN", "KMeans", "k_means"]
+
+if daal_check_version((2023, "P", 200)):
+    from .kmeans_init import KMeansInit, kmeans_plusplus
+
+    __all__ += ["KMeansInit", "kmeans_plusplus"]

scikit_learn_intelex-2025.10.0.data/data/Lib/site-packages/onedal/cluster/dbscan.py

@@ -0,0 +1,80 @@
+# ===============================================================================
+# 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
+
+from onedal._device_offload import supports_queue
+
+from ..common._backend import bind_default_backend
+from ..common._mixin import ClusterMixin
+from ..datatypes import from_table, to_table
+
+
+class DBSCAN(ClusterMixin):
+    def __init__(
+        self,
+        eps=0.5,
+        *,
+        min_samples=5,
+        metric="euclidean",
+        metric_params=None,
+        algorithm="auto",
+        leaf_size=30,
+        p=None,
+        n_jobs=None,
+    ):
+        self.eps = eps
+        self.min_samples = min_samples
+        self.metric = metric
+        self.metric_params = metric_params
+        self.algorithm = algorithm
+        self.leaf_size = leaf_size
+        self.p = p
+        self.n_jobs = n_jobs
+
+    @bind_default_backend("dbscan.clustering")
+    def compute(self, params, data_table, weights_table): ...
+
+    def _get_onedal_params(self, dtype=np.float32):
+        return {
+            "fptype": dtype,
+            "method": "by_default",
+            "min_observations": int(self.min_samples),
+            "epsilon": float(self.eps),
+            "mem_save_mode": False,
+            "result_options": "core_observation_indices|responses",
+        }
+
+    @supports_queue
+    def fit(self, X, y=None, sample_weight=None, queue=None):
+        X_table, sample_weight_table = to_table(X, sample_weight, queue=queue)
+
+        params = self._get_onedal_params(X_table.dtype)
+        result = self.compute(params, X_table, sample_weight_table)
+
+        # 2d table but only 1d of information
+        self.labels_ = from_table(result.responses, like=X)[:, 0]
+        if (
+            result.core_observation_indices is not None
+            and result.core_observation_indices.kind != "empty"
+        ):
+            # 2d table to 1d
+            self.core_sample_indices_ = from_table(
+                result.core_observation_indices, like=X
+            )[:, 0]
+        else:
+            self.core_sample_indices_ = None
+        return self