scikit-learn-intelex 2025.0.0__py311-none-manylinux_2_28_x86_64.whl

sklearnex/preview/covariance/__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 .covariance import EmpiricalCovariance
+
+__all__ = ["EmpiricalCovariance"]

sklearnex/preview/covariance/covariance.py

@@ -0,0 +1,133 @@
+# ===============================================================================
+# 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 warnings
+
+import numpy as np
+from scipy import sparse as sp
+from sklearn.covariance import EmpiricalCovariance as sklearn_EmpiricalCovariance
+from sklearn.utils import check_array
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import daal_check_version, sklearn_check_version
+from onedal.common.hyperparameters import get_hyperparameters
+from onedal.covariance import EmpiricalCovariance as onedal_EmpiricalCovariance
+from sklearnex import config_context
+from sklearnex.metrics import pairwise_distances
+
+from ..._device_offload import dispatch, wrap_output_data
+from ..._utils import PatchingConditionsChain, register_hyperparameters
+
+
+@register_hyperparameters({"fit": get_hyperparameters("covariance", "compute")})
+@control_n_jobs(decorated_methods=["fit", "mahalanobis"])
+class EmpiricalCovariance(sklearn_EmpiricalCovariance):
+    __doc__ = sklearn_EmpiricalCovariance.__doc__
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {
+            **sklearn_EmpiricalCovariance._parameter_constraints,
+        }
+
+    def _save_attributes(self):
+        assert hasattr(self, "_onedal_estimator")
+        if not daal_check_version((2024, "P", 400)) and self.assume_centered:
+            location = self._onedal_estimator.location_[None, :]
+            self._onedal_estimator.covariance_ += np.dot(location.T, location)
+            self._onedal_estimator.location_ = np.zeros_like(np.squeeze(location))
+        self._set_covariance(self._onedal_estimator.covariance_)
+        self.location_ = self._onedal_estimator.location_
+
+    _onedal_covariance = staticmethod(onedal_EmpiricalCovariance)
+
+    def _onedal_fit(self, X, queue=None):
+        if X.shape[0] == 1:
+            warnings.warn(
+                "Only one sample available. You may want to reshape your data array"
+            )
+
+        onedal_params = {
+            "method": "dense",
+            "bias": True,
+            "assume_centered": self.assume_centered,
+        }
+
+        self._onedal_estimator = self._onedal_covariance(**onedal_params)
+        self._onedal_estimator.fit(X, queue=queue)
+        self._save_attributes()
+
+    def _onedal_supported(self, method_name, *data):
+        class_name = self.__class__.__name__
+        patching_status = PatchingConditionsChain(
+            f"sklearn.covariance.{class_name}.{method_name}"
+        )
+        if method_name in ["fit", "mahalanobis"]:
+            (X,) = data
+            patching_status.and_conditions(
+                [
+                    (not sp.issparse(X), "X is sparse. Sparse input is not supported."),
+                ]
+            )
+            return patching_status
+        raise RuntimeError(f"Unknown method {method_name} in {self.__class__.__name__}")
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def fit(self, X, y=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+        if sklearn_check_version("0.23"):
+            X = self._validate_data(X, force_all_finite=False)
+        else:
+            X = check_array(X, force_all_finite=False)
+
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_EmpiricalCovariance.fit,
+            },
+            X,
+        )
+
+        return self
+
+    # expose sklearnex pairwise_distances if mahalanobis distance eventually supported
+    @wrap_output_data
+    def mahalanobis(self, X):
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, reset=False)
+        else:
+            X = check_array(X)
+
+        precision = self.get_precision()
+        with config_context(assume_finite=True):
+            # compute mahalanobis distances
+            dist = pairwise_distances(
+                X, self.location_[np.newaxis, :], metric="mahalanobis", VI=precision
+            )
+
+        return np.reshape(dist, (len(X),)) ** 2
+
+    error_norm = wrap_output_data(sklearn_EmpiricalCovariance.error_norm)
+    score = wrap_output_data(sklearn_EmpiricalCovariance.score)
+
+    fit.__doc__ = sklearn_EmpiricalCovariance.fit.__doc__
+    mahalanobis.__doc__ = sklearn_EmpiricalCovariance.mahalanobis
+    error_norm.__doc__ = sklearn_EmpiricalCovariance.error_norm.__doc__
+    score.__doc__ = sklearn_EmpiricalCovariance.score.__doc__

sklearnex/preview/covariance/tests/test_covariance.py

@@ -0,0 +1,66 @@
+# ===============================================================================
+# 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
+from numpy.testing import assert_allclose
+
+from daal4py.sklearn._utils import daal_check_version
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("assume_centered", [True, False])
+def test_sklearnex_import_covariance(dataframe, queue, macro_block, assume_centered):
+    from sklearnex.preview.covariance import EmpiricalCovariance
+
+    X = np.array([[0, 1], [0, 1]])
+
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    empcov = EmpiricalCovariance(assume_centered=assume_centered)
+    if daal_check_version((2024, "P", 0)) and macro_block is not None:
+        hparams = empcov.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+    result = empcov.fit(X)
+
+    expected_covariance = np.array([[0, 0], [0, 0]])
+    expected_means = np.array([0, 0])
+
+    if assume_centered:
+        expected_covariance = np.array([[0, 0], [0, 1]])
+    else:
+        expected_means = np.array([0, 1])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)
+
+    X = np.array([[1, 2], [3, 6]])
+
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    result = empcov.fit(X)
+
+    if assume_centered:
+        expected_covariance = np.array([[5, 10], [10, 20]])
+    else:
+        expected_covariance = np.array([[1, 2], [2, 4]])
+        expected_means = np.array([2, 4])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)

sklearnex/preview/decomposition/__init__.py

@@ -0,0 +1,19 @@
+# ===============================================================================
+# 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 .incremental_pca import IncrementalPCA
+
+__all__ = ["IncrementalPCA"]

sklearnex/preview/decomposition/incremental_pca.py

@@ -0,0 +1,228 @@
+# ===============================================================================
+# 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 sklearn.decomposition import IncrementalPCA as sklearn_IncrementalPCA
+from sklearn.utils import check_array, gen_batches
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+from onedal.decomposition import IncrementalPCA as onedal_IncrementalPCA
+
+from ..._device_offload import dispatch, wrap_output_data
+from ..._utils import PatchingConditionsChain
+
+
+@control_n_jobs(
+    decorated_methods=["fit", "partial_fit", "transform", "_onedal_finalize_fit"]
+)
+class IncrementalPCA(sklearn_IncrementalPCA):
+
+    def __init__(self, n_components=None, *, whiten=False, copy=True, batch_size=None):
+        super().__init__(
+            n_components=n_components, whiten=whiten, copy=copy, batch_size=batch_size
+        )
+        self._need_to_finalize = False
+        self._need_to_finalize_attrs = {
+            "mean_",
+            "explained_variance_",
+            "explained_variance_ratio_",
+            "n_components_",
+            "components_",
+            "noise_variance_",
+            "singular_values_",
+            "var_",
+        }
+
+    _onedal_incremental_pca = staticmethod(onedal_IncrementalPCA)
+
+    def _onedal_transform(self, X, queue=None):
+        assert hasattr(self, "_onedal_estimator")
+        if self._need_to_finalize:
+            self._onedal_finalize_fit()
+        X = check_array(X, dtype=[np.float64, np.float32])
+        return self._onedal_estimator.predict(X, queue)
+
+    def _onedal_fit_transform(self, X, queue=None):
+        self._onedal_fit(X, queue)
+        return self._onedal_transform(X, queue)
+
+    def _onedal_partial_fit(self, X, check_input=True, queue=None):
+        first_pass = not hasattr(self, "_onedal_estimator")
+
+        if check_input:
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X, dtype=[np.float64, np.float32], reset=first_pass
+                )
+            else:
+                X = check_array(
+                    X,
+                    dtype=[np.float64, np.float32],
+                    copy=self.copy,
+                )
+
+        n_samples, n_features = X.shape
+
+        if self.n_components is None:
+            if not hasattr(self, "_components_shape"):
+                self.n_components_ = min(n_samples, n_features)
+                self._components_shape = self.n_components_
+
+        elif not self.n_components <= n_features:
+            raise ValueError(
+                "n_components=%r invalid for n_features=%d, need "
+                "more rows than columns for IncrementalPCA "
+                "processing" % (self.n_components, n_features)
+            )
+        elif not self.n_components <= n_samples:
+            raise ValueError(
+                "n_components=%r must be less or equal to "
+                "the batch number of samples "
+                "%d." % (self.n_components, n_samples)
+            )
+        else:
+            self.n_components_ = self.n_components
+
+        if not hasattr(self, "n_samples_seen_"):
+            self.n_samples_seen_ = n_samples
+        else:
+            self.n_samples_seen_ += n_samples
+
+        onedal_params = {"n_components": self.n_components_, "whiten": self.whiten}
+
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_incremental_pca(**onedal_params)
+        self._onedal_estimator.partial_fit(X, queue=queue)
+        self._need_to_finalize = True
+
+    def _onedal_finalize_fit(self, queue=None):
+        assert hasattr(self, "_onedal_estimator")
+        self._onedal_estimator.finalize_fit(queue=queue)
+        self._need_to_finalize = False
+
+    def _onedal_fit(self, X, queue=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, dtype=[np.float64, np.float32], copy=self.copy)
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                copy=self.copy,
+            )
+
+        n_samples, n_features = X.shape
+
+        if self.batch_size is None:
+            self.batch_size_ = 5 * n_features
+        else:
+            self.batch_size_ = self.batch_size
+
+        self.n_samples_seen_ = 0
+        if hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator._reset()
+
+        for batch in gen_batches(n_samples, self.batch_size_):
+            X_batch = X[batch]
+            self._onedal_partial_fit(X_batch, queue=queue)
+
+        self._onedal_finalize_fit(queue=queue)
+
+        return self
+
+    def _onedal_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearn.decomposition.{self.__class__.__name__}.{method_name}"
+        )
+        return patching_status
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def __getattr__(self, attr):
+        if attr in self._need_to_finalize_attrs:
+            if hasattr(self, "_onedal_estimator"):
+                if self._need_to_finalize:
+                    self._onedal_finalize_fit()
+                return getattr(self._onedal_estimator, attr)
+            else:
+                raise AttributeError(
+                    f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+                )
+        if attr in self.__dict__:
+            return self.__dict__[attr]
+
+        raise AttributeError(
+            f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+        )
+
+    def partial_fit(self, X, y=None, check_input=True):
+        dispatch(
+            self,
+            "partial_fit",
+            {
+                "onedal": self.__class__._onedal_partial_fit,
+                "sklearn": sklearn_IncrementalPCA.partial_fit,
+            },
+            X,
+            check_input=check_input,
+        )
+        return self
+
+    def fit(self, X, y=None):
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_IncrementalPCA.fit,
+            },
+            X,
+        )
+        return self
+
+    @wrap_output_data
+    def transform(self, X):
+        return dispatch(
+            self,
+            "transform",
+            {
+                "onedal": self.__class__._onedal_transform,
+                "sklearn": sklearn_IncrementalPCA.transform,
+            },
+            X,
+        )
+
+    @wrap_output_data
+    def fit_transform(self, X, y=None, **fit_params):
+        return dispatch(
+            self,
+            "fit_transform",
+            {
+                "onedal": self.__class__._onedal_fit_transform,
+                "sklearn": sklearn_IncrementalPCA.fit_transform,
+            },
+            X,
+        )
+
+    __doc__ = sklearn_IncrementalPCA.__doc__
+    fit.__doc__ = sklearn_IncrementalPCA.fit.__doc__
+    fit_transform.__doc__ = sklearn_IncrementalPCA.fit_transform.__doc__
+    transform.__doc__ = sklearn_IncrementalPCA.transform.__doc__
+    partial_fit.__doc__ = sklearn_IncrementalPCA.partial_fit.__doc__