scikit-learn-intelex 2025.4.0__py313-none-manylinux_2_28_x86_64.whl

onedal/spmd/cluster/kmeans.py

@@ -0,0 +1,56 @@
+# ==============================================================================
+# 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 onedal.cluster import KMeans as KMeans_Batch
+from onedal.cluster import KMeansInit as KMeansInit_Batch
+from onedal.spmd.basic_statistics import BasicStatistics
+
+from ..._device_offload import support_input_format
+from .._base import BaseEstimatorSPMD
+
+
+class KMeansInit(BaseEstimatorSPMD, KMeansInit_Batch):
+    """
+    KMeansInit oneDAL implementation for SPMD iface.
+    """
+
+    pass
+
+
+class KMeans(BaseEstimatorSPMD, KMeans_Batch):
+    def _get_basic_statistics_backend(self, result_options):
+        return BasicStatistics(result_options)
+
+    def _get_kmeans_init(self, cluster_count, seed, algorithm):
+        return KMeansInit(cluster_count=cluster_count, seed=seed, algorithm=algorithm)
+
+    @support_input_format()
+    def fit(self, X, y=None, queue=None):
+        return super().fit(X, queue=queue)
+
+    @support_input_format()
+    def predict(self, X, queue=None):
+        return super().predict(X, queue=queue)
+
+    @support_input_format()
+    def fit_predict(self, X, y=None, queue=None):
+        return super().fit_predict(X, queue=queue)
+
+    def transform(self, X):
+        return super().transform(X)
+
+    def fit_transform(self, X, queue=None):
+        return super().fit_transform(X, queue=queue)

onedal/spmd/covariance/__init__.py

@@ -0,0 +1,20 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from .covariance import EmpiricalCovariance
+from .incremental_covariance import IncrementalEmpiricalCovariance
+
+__all__ = ["EmpiricalCovariance", "IncrementalEmpiricalCovariance"]

onedal/spmd/covariance/covariance.py

@@ -0,0 +1,26 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from onedal.covariance import EmpiricalCovariance as EmpiricalCovariance_Batch
+
+from ..._device_offload import support_input_format
+from .._base import BaseEstimatorSPMD
+
+
+class EmpiricalCovariance(BaseEstimatorSPMD, EmpiricalCovariance_Batch):
+    @support_input_format()
+    def fit(self, X, y=None, queue=None):
+        return super().fit(X, queue=queue)

onedal/spmd/covariance/incremental_covariance.py

@@ -0,0 +1,83 @@
+# ==============================================================================
+# 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
+
+from daal4py.sklearn._utils import get_dtype
+
+from ...covariance import (
+    IncrementalEmpiricalCovariance as base_IncrementalEmpiricalCovariance,
+)
+from ...datatypes import to_table
+from ...utils import _check_array
+from .._base import BaseEstimatorSPMD
+
+
+class IncrementalEmpiricalCovariance(
+    BaseEstimatorSPMD, base_IncrementalEmpiricalCovariance
+):
+    def _reset(self):
+        self._need_to_finalize = False
+        self._partial_result = super(
+            base_IncrementalEmpiricalCovariance, self
+        )._get_backend("covariance", None, "partial_compute_result")
+
+    def partial_fit(self, X, y=None, queue=None):
+        """
+        Computes partial data for the covariance matrix
+        from data batch X and saves it to `_partial_result`.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data batch, where `n_samples` is the number of samples
+            in the batch, and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        queue : dpctl.SyclQueue
+            If not None, use this queue for computations.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        X = _check_array(X, dtype=[np.float64, np.float32], ensure_2d=True)
+
+        self._queue = queue
+
+        policy = super(base_IncrementalEmpiricalCovariance, self)._get_policy(queue, X)
+
+        X_table = to_table(X, queue=queue)
+
+        if not hasattr(self, "_dtype"):
+            self._dtype = X_table.dtype
+
+        params = self._get_onedal_params(self._dtype)
+        self._partial_result = super(
+            base_IncrementalEmpiricalCovariance, self
+        )._get_backend(
+            "covariance",
+            None,
+            "partial_compute",
+            policy,
+            params,
+            self._partial_result,
+            X_table,
+        )
+        self._need_to_finalize = True

onedal/spmd/decomposition/__init__.py

@@ -0,0 +1,20 @@
+# ==============================================================================
+# 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 .incremental_pca import IncrementalPCA
+from .pca import PCA
+
+__all__ = ["IncrementalPCA", "PCA"]

onedal/spmd/decomposition/incremental_pca.py

@@ -0,0 +1,124 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from daal4py.sklearn._utils import get_dtype
+
+from ...datatypes import from_table, to_table
+from ...decomposition import IncrementalPCA as base_IncrementalPCA
+from ...utils import _check_array
+from .._base import BaseEstimatorSPMD
+
+
+class IncrementalPCA(BaseEstimatorSPMD, base_IncrementalPCA):
+    """
+    Distributed incremental estimator for PCA based on oneDAL implementation.
+    Allows for distributed PCA computation if data is split into batches.
+
+    API is the same as for `onedal.decomposition.IncrementalPCA`
+    """
+
+    def _reset(self):
+        self._need_to_finalize = False
+        self._partial_result = super(base_IncrementalPCA, self)._get_backend(
+            "decomposition", "dim_reduction", "partial_train_result"
+        )
+        if hasattr(self, "components_"):
+            del self.components_
+
+    def partial_fit(self, X, y=None, queue=None):
+        """Incremental fit with X. All of X is processed as a single batch.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        X = _check_array(X)
+        n_samples, n_features = X.shape
+
+        first_pass = not hasattr(self, "components_")
+        if first_pass:
+            self.components_ = None
+            self.n_samples_seen_ = n_samples
+            self.n_features_in_ = n_features
+        else:
+            self.n_samples_seen_ += n_samples
+
+        if self.n_components is None:
+            if self.components_ is None:
+                self.n_components_ = min(n_samples, n_features)
+            else:
+                self.n_components_ = self.components_.shape[0]
+        else:
+            self.n_components_ = self.n_components
+
+        self._queue = queue
+
+        policy = super(base_IncrementalPCA, self)._get_policy(queue, X)
+        X_table = to_table(X, queue=queue)
+
+        if not hasattr(self, "_dtype"):
+            self._dtype = X_table.dtype
+            self._params = self._get_onedal_params(X_table)
+
+        self._partial_result = super(base_IncrementalPCA, self)._get_backend(
+            "decomposition",
+            "dim_reduction",
+            "partial_train",
+            policy,
+            self._params,
+            self._partial_result,
+            X_table,
+        )
+        self._need_to_finalize = True
+        return self
+
+    def _create_model(self):
+        m = super(base_IncrementalPCA, self)._get_backend(
+            "decomposition", "dim_reduction", "model"
+        )
+        m.eigenvectors = to_table(self.components_)
+        m.means = to_table(self.mean_)
+        if self.whiten:
+            m.eigenvalues = to_table(self.explained_variance_)
+        self._onedal_model = m
+        return m
+
+    def predict(self, X, queue=None):
+        policy = super(base_IncrementalPCA, self)._get_policy(queue, X)
+        model = self._create_model()
+        X = to_table(X, queue=queue)
+        params = self._get_onedal_params(X, stage="predict")
+
+        result = super(base_IncrementalPCA, self)._get_backend(
+            "decomposition",
+            "dim_reduction",
+            "infer",
+            policy,
+            params,
+            model,
+            X,
+        )
+        return from_table(result.transformed_data)

onedal/spmd/decomposition/pca.py

@@ -0,0 +1,26 @@
+# ==============================================================================
+# 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 onedal.decomposition.pca import PCA as PCABatch
+
+from ..._device_offload import support_input_format
+from .._base import BaseEstimatorSPMD
+
+
+class PCA(BaseEstimatorSPMD, PCABatch):
+    @support_input_format()
+    def fit(self, X, y=None, queue=None):
+        return super().fit(X, queue=queue)

onedal/spmd/ensemble/__init__.py

@@ -0,0 +1,19 @@
+# ==============================================================================
+# 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 .forest import RandomForestClassifier, RandomForestRegressor
+
+__all__ = ["RandomForestClassifier", "RandomForestRegressor"]

onedal/spmd/ensemble/forest.py

@@ -0,0 +1,28 @@
+# ==============================================================================
+# 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 onedal.ensemble import RandomForestClassifier as RandomForestClassifier_Batch
+from onedal.ensemble import RandomForestRegressor as RandomForestRegressor_Batch
+
+from .._base import BaseEstimatorSPMD
+
+
+class RandomForestClassifier(BaseEstimatorSPMD, RandomForestClassifier_Batch):
+    pass
+
+
+class RandomForestRegressor(BaseEstimatorSPMD, RandomForestRegressor_Batch):
+    pass

onedal/spmd/linear_model/__init__.py

@@ -0,0 +1,21 @@
+# ==============================================================================
+# 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 .incremental_linear_model import IncrementalLinearRegression
+from .linear_model import LinearRegression
+from .logistic_regression import LogisticRegression
+
+__all__ = ["IncrementalLinearRegression", "LinearRegression", "LogisticRegression"]

onedal/spmd/linear_model/incremental_linear_model.py

@@ -0,0 +1,101 @@
+# ==============================================================================
+# 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
+
+from daal4py.sklearn._utils import get_dtype
+
+from ...common.hyperparameters import get_hyperparameters
+from ...datatypes import to_table
+from ...linear_model import (
+    IncrementalLinearRegression as base_IncrementalLinearRegression,
+)
+from ...utils import _check_X_y, _num_features
+from .._base import BaseEstimatorSPMD
+
+
+class IncrementalLinearRegression(BaseEstimatorSPMD, base_IncrementalLinearRegression):
+    """
+    Distributed incremental Linear Regression oneDAL implementation.
+
+    API is the same as for `onedal.linear_model.IncrementalLinearRegression`.
+    """
+
+    def _reset(self):
+        self._need_to_finalize = False
+        self._partial_result = super(base_IncrementalLinearRegression, self)._get_backend(
+            "linear_model", "regression", "partial_train_result"
+        )
+
+    def partial_fit(self, X, y, queue=None):
+        """
+        Computes partial data for linear regression
+        from data batch X and saves it to `_partial_result`.
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data batch, where `n_samples` is the number of samples
+            in the batch, and `n_features` is the number of features.
+
+        y: array-like of shape (n_samples,) or (n_samples, n_targets) in
+            case of multiple targets
+            Responses for training data.
+
+        queue : dpctl.SyclQueue
+            If not None, use this queue for computations.
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        module = super(base_IncrementalLinearRegression, self)._get_backend(
+            "linear_model", "regression"
+        )
+
+        self._queue = queue
+        policy = super(base_IncrementalLinearRegression, self)._get_policy(queue, X)
+
+        X, y = _check_X_y(
+            X, y, dtype=[np.float64, np.float32], accept_2d_y=True, force_all_finite=False
+        )
+
+        X_table, y_table = to_table(X, y, queue=queue)
+
+        if not hasattr(self, "_dtype"):
+            self._dtype = X_table.dtype
+            self._params = self._get_onedal_params(self._dtype)
+
+        y = np.asarray(y, dtype=self._dtype)
+
+        self.n_features_in_ = _num_features(X, fallback_1d=True)
+
+        hparams = get_hyperparameters("linear_regression", "train")
+        if hparams is not None and not hparams.is_default:
+            self._partial_result = module.partial_train(
+                policy,
+                self._params,
+                hparams.backend,
+                self._partial_result,
+                X_table,
+                y_table,
+            )
+        else:
+            self._partial_result = module.partial_train(
+                policy, self._params, self._partial_result, X_table, y_table
+            )
+
+        self._need_to_finalize = True
+        return self

onedal/spmd/linear_model/linear_model.py

@@ -0,0 +1,30 @@
+# ==============================================================================
+# 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 onedal.linear_model import LinearRegression as LinearRegression_Batch
+
+from ..._device_offload import support_input_format
+from .._base import BaseEstimatorSPMD
+
+
+class LinearRegression(BaseEstimatorSPMD, LinearRegression_Batch):
+    @support_input_format()
+    def fit(self, X, y, queue=None):
+        return super().fit(X, y, queue=queue)
+
+    @support_input_format()
+    def predict(self, X, queue=None):
+        return super().predict(X, queue=queue)

onedal/spmd/linear_model/logistic_regression.py

@@ -0,0 +1,38 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from onedal.linear_model import LogisticRegression as LogisticRegression_Batch
+
+from ..._device_offload import support_input_format
+from .._base import BaseEstimatorSPMD
+
+
+class LogisticRegression(BaseEstimatorSPMD, LogisticRegression_Batch):
+    @support_input_format()
+    def fit(self, X, y, queue=None):
+        return super().fit(X, y, queue=queue)
+
+    @support_input_format()
+    def predict(self, X, queue=None):
+        return super().predict(X, queue=queue)
+
+    @support_input_format()
+    def predict_proba(self, X, queue=None):
+        return super().predict_proba(X, queue=queue)
+
+    @support_input_format()
+    def predict_log_proba(self, X, queue=None):
+        return super().predict_log_proba(X, queue=queue)

onedal/spmd/neighbors/__init__.py

@@ -0,0 +1,19 @@
+# ==============================================================================
+# 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 .neighbors import KNeighborsClassifier, KNeighborsRegressor, NearestNeighbors
+
+__all__ = ["KNeighborsClassifier", "KNeighborsRegressor", "NearestNeighbors"]