scikit-learn-intelex 2024.1.0__py39-none-win_amd64.whl → 2025.1.0__py39-none-win_amd64.whl

{scikit_learn_intelex-2024.1.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/_utils.py

@@ -18,6 +18,7 @@ import logging
 import os
 import sys
 import warnings
+from abc import ABC
 
 from daal4py.sklearn._utils import (
     PatchingConditionsChain as daal4py_PatchingConditionsChain,
@@ -29,10 +30,10 @@ class PatchingConditionsChain(daal4py_PatchingConditionsChain):
     def get_status(self):
         return self.patching_is_enabled
 
-    def write_log(self, queue=None):
+    def write_log(self, queue=None, transferred_to_host=True):
         if self.patching_is_enabled:
             self.logger.info(
-                f"{self.scope_name}: {get_patch_message('onedal', queue=queue)}"
+                f"{self.scope_name}: {get_patch_message('onedal', queue=queue, transferred_to_host=transferred_to_host)}"
             )
         else:
             self.logger.debug(
@@ -43,7 +44,9 @@ class PatchingConditionsChain(daal4py_PatchingConditionsChain):
                 self.logger.debug(
                     f"{self.scope_name}: patching failed with cause - {message}"
                 )
-            self.logger.info(f"{self.scope_name}: {get_patch_message('sklearn')}")
+            self.logger.info(
+                f"{self.scope_name}: {get_patch_message('sklearn', transferred_to_host=transferred_to_host)}"
+            )
 
 
 def set_sklearn_ex_verbose():
@@ -66,7 +69,7 @@ def set_sklearn_ex_verbose():
         )
 
 
-def get_patch_message(s, queue=None):
+def get_patch_message(s, queue=None, transferred_to_host=True):
     if s == "onedal":
         message = "running accelerated version on "
         if queue is not None:
@@ -87,6 +90,10 @@ def get_patch_message(s, queue=None):
             f"Invalid input - expected one of 'onedal','sklearn',"
             f" 'sklearn_after_onedal', got {s}"
         )
+    if transferred_to_host:
+        message += (
+            ". All input data transferred to host for further backend computations."
+        )
     return message
 
 
@@ -107,3 +114,19 @@ def register_hyperparameters(hyperparameters_map):
         return estimator_class
 
     return wrap_class
+
+
+# This abstract class is meant to generate a clickable doc link for classses
+# in sklearnex that are not part of base scikit-learn. It should be inherited
+# before inheriting from a scikit-learn estimator, otherwise will get overriden
+# by the estimator's original.
+class IntelEstimator(ABC):
+    @property
+    def _doc_link_module(self) -> str:
+        return "sklearnex"
+
+    @property
+    def _doc_link_template(self) -> str:
+        module_path, _ = self.__class__.__module__.rsplit(".", 1)
+        class_name = self.__class__.__name__
+        return f"https://intel.github.io/scikit-learn-intelex/latest/non-scikit-algorithms.html#{module_path}.{class_name}"

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/basic_statistics/__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 .basic_statistics import BasicStatistics
+from .incremental_basic_statistics import IncrementalBasicStatistics
+
+__all__ = ["BasicStatistics", "IncrementalBasicStatistics"]

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/basic_statistics/basic_statistics.py

@@ -0,0 +1,230 @@
+# ==============================================================================
+# 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 sklearn.base import BaseEstimator
+from sklearn.utils import check_array
+from sklearn.utils.validation import _check_sample_weight
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+from onedal.basic_statistics import BasicStatistics as onedal_BasicStatistics
+
+from .._device_offload import dispatch
+from .._utils import IntelEstimator, PatchingConditionsChain
+
+if sklearn_check_version("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+    validate_data = BaseEstimator._validate_data
+
+if sklearn_check_version("1.2"):
+    from sklearn.utils._param_validation import StrOptions
+
+
+@control_n_jobs(decorated_methods=["fit"])
+class BasicStatistics(IntelEstimator, BaseEstimator):
+    """
+    Estimator for basic statistics.
+    Allows to compute basic statistics for provided data.
+
+    Parameters
+    ----------
+    result_options: string or list, default='all'
+        Used to set statistics to calculate. Possible values are ``'min'``, ``'max'``, ``'sum'``, ``'mean'``, ``'variance'``,
+        ``'variation'``, ``sum_squares'``, ``sum_squares_centered'``, ``'standard_deviation'``, ``'second_order_raw_moment'``
+        or a list containing any of these values. If set to ``'all'`` then all possible statistics will be
+        calculated.
+
+    Attributes
+    ----------
+        min_ : ndarray of shape (n_features,)
+            Minimum of each feature over all samples.
+        max_ : ndarray of shape (n_features,)
+            Maximum of each feature over all samples.
+        sum_ : ndarray of shape (n_features,)
+            Sum of each feature over all samples.
+        mean_ : ndarray of shape (n_features,)
+            Mean of each feature over all samples.
+        variance_ : ndarray of shape (n_features,)
+            Variance of each feature over all samples.
+        variation_ : ndarray of shape (n_features,)
+            Variation of each feature over all samples.
+        sum_squares_ : ndarray of shape (n_features,)
+            Sum of squares for each feature over all samples.
+        standard_deviation_ : ndarray of shape (n_features,)
+            Standard deviation of each feature over all samples.
+        sum_squares_centered_ : ndarray of shape (n_features,)
+            Centered sum of squares for each feature over all samples.
+        second_order_raw_moment_ : ndarray of shape (n_features,)
+            Second order moment of each feature over all samples.
+
+    Note
+    ----
+    Attribute exists only if corresponding result option has been provided.
+
+    Note
+    ----
+    Names of attributes without the trailing underscore are
+    supported currently but deprecated in 2025.1 and will be removed in 2026.0
+
+    Note
+    ----
+    Some results can exhibit small variations due to
+    floating point error accumulation and multithreading.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearnex.basic_statistics import BasicStatistics
+    >>> bs = BasicStatistics(result_options=['sum', 'min', 'max'])
+    >>> X = np.array([[1, 2], [3, 4]])
+    >>> bs.fit(X)
+    >>> bs.sum_
+    np.array([4., 6.])
+    >>> bs.min_
+    np.array([1., 2.])
+    """
+
+    def __init__(self, result_options="all"):
+        self.result_options = result_options
+
+    _onedal_basic_statistics = staticmethod(onedal_BasicStatistics)
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {
+            "result_options": [
+                StrOptions(
+                    {
+                        "all",
+                        "min",
+                        "max",
+                        "sum",
+                        "mean",
+                        "variance",
+                        "variation",
+                        "sum_squares",
+                        "standard_deviation",
+                        "sum_squares_centered",
+                        "second_order_raw_moment",
+                    }
+                ),
+                list,
+            ],
+        }
+
+    def _save_attributes(self):
+        assert hasattr(self, "_onedal_estimator")
+
+        if self.result_options == "all":
+            result_options = onedal_BasicStatistics.get_all_result_options()
+        else:
+            result_options = self.result_options
+
+        if isinstance(result_options, str):
+            setattr(
+                self,
+                result_options + "_",
+                getattr(self._onedal_estimator, result_options),
+            )
+        elif isinstance(result_options, list):
+            for option in result_options:
+                setattr(self, option + "_", getattr(self._onedal_estimator, option))
+
+    def __getattr__(self, attr):
+        if self.result_options == "all":
+            result_options = onedal_BasicStatistics.get_all_result_options()
+        else:
+            result_options = self.result_options
+        is_deprecated_attr = (
+            isinstance(result_options, str) and (attr == result_options)
+        ) or (isinstance(result_options, list) and (attr in result_options))
+        if is_deprecated_attr:
+            warnings.warn(
+                "Result attributes without a trailing underscore were deprecated in version 2025.1 and will be removed in 2026.0"
+            )
+            attr += "_"
+        if attr in self.__dict__:
+            return self.__dict__[attr]
+
+        raise AttributeError(
+            f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+        )
+
+    def _onedal_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearnex.basic_statistics.{self.__class__.__name__}.{method_name}"
+        )
+        return patching_status
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def _onedal_fit(self, X, sample_weight=None, queue=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        if sklearn_check_version("1.0"):
+            X = validate_data(self, X, dtype=[np.float64, np.float32], ensure_2d=False)
+        else:
+            X = check_array(X, dtype=[np.float64, np.float32])
+
+        if sample_weight is not None:
+            sample_weight = _check_sample_weight(sample_weight, X)
+
+        onedal_params = {
+            "result_options": self.result_options,
+        }
+
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_basic_statistics(**onedal_params)
+        self._onedal_estimator.fit(X, sample_weight, queue)
+        self._save_attributes()
+        self.n_features_in_ = X.shape[1] if len(X.shape) > 1 else 1
+
+    def fit(self, X, y=None, *, sample_weight=None):
+        """Calculate statistics of X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Data for compute, 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.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": None,
+            },
+            X,
+            sample_weight,
+        )
+        return self

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/basic_statistics/incremental_basic_statistics.py

@@ -0,0 +1,345 @@
+# ==============================================================================
+# 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.base import BaseEstimator
+from sklearn.utils import check_array, gen_batches
+from sklearn.utils.validation import _check_sample_weight
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+from onedal.basic_statistics import (
+    IncrementalBasicStatistics as onedal_IncrementalBasicStatistics,
+)
+
+from .._device_offload import dispatch
+from .._utils import IntelEstimator, PatchingConditionsChain
+
+if sklearn_check_version("1.2"):
+    from sklearn.utils._param_validation import Interval, StrOptions
+
+import numbers
+import warnings
+
+if sklearn_check_version("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+    validate_data = BaseEstimator._validate_data
+
+
+@control_n_jobs(decorated_methods=["partial_fit", "_onedal_finalize_fit"])
+class IncrementalBasicStatistics(IntelEstimator, BaseEstimator):
+    """
+    Calculates basic statistics on the given data, allows for computation when the data are split into
+    batches. The user can use ``partial_fit`` method to provide a single batch of data or use the ``fit`` method to provide
+    the entire dataset.
+
+    Parameters
+    ----------
+    result_options: string or list, default='all'
+        List of statistics to compute
+
+    batch_size : int, default=None
+        The number of samples to use for each batch. Only used when calling
+        ``fit``. If ``batch_size`` is ``None``, then ``batch_size``
+        is inferred from the data and set to ``5 * n_features``.
+
+    Attributes
+    ----------
+        min_ : ndarray of shape (n_features,)
+            Minimum of each feature over all samples.
+
+        max_ : ndarray of shape (n_features,)
+            Maximum of each feature over all samples.
+
+        sum_ : ndarray of shape (n_features,)
+            Sum of each feature over all samples.
+
+        mean_ : ndarray of shape (n_features,)
+            Mean of each feature over all samples.
+
+        variance_ : ndarray of shape (n_features,)
+            Variance of each feature over all samples.
+
+        variation_ : ndarray of shape (n_features,)
+            Variation of each feature over all samples.
+
+        sum_squares_ : ndarray of shape (n_features,)
+            Sum of squares for each feature over all samples.
+
+        standard_deviation_ : ndarray of shape (n_features,)
+            Standard deviation of each feature over all samples.
+
+        sum_squares_centered_ : ndarray of shape (n_features,)
+            Centered sum of squares for each feature over all samples.
+
+        second_order_raw_moment_ : ndarray of shape (n_features,)
+            Second order moment of each feature over all samples.
+
+        n_samples_seen_ : int
+            The number of samples processed by the estimator. Will be reset on
+            new calls to ``fit``, but increments across ``partial_fit`` calls.
+
+        batch_size_ : int
+            Inferred batch size from ``batch_size``.
+
+        n_features_in_ : int
+            Number of features seen during ``fit`` or  ``partial_fit``.
+
+    Note
+    ----
+    Attribute exists only if corresponding result option has been provided.
+
+    Note
+    ----
+    Names of attributes without the trailing underscore are
+    supported currently but deprecated in 2025.1 and will be removed in 2026.0
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearnex.basic_statistics import IncrementalBasicStatistics
+    >>> incbs = IncrementalBasicStatistics(batch_size=1)
+    >>> X = np.array([[1, 2], [3, 4]])
+    >>> incbs.partial_fit(X[:1])
+    >>> incbs.partial_fit(X[1:])
+    >>> incbs.sum_
+    np.array([4., 6.])
+    >>> incbs.min_
+    np.array([1., 2.])
+    >>> incbs.fit(X)
+    >>> incbs.sum_
+    np.array([4., 6.])
+    >>> incbs.max_
+    np.array([3., 4.])
+    """
+
+    _onedal_incremental_basic_statistics = staticmethod(onedal_IncrementalBasicStatistics)
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {
+            "result_options": [
+                StrOptions(
+                    {
+                        "all",
+                        "min",
+                        "max",
+                        "sum",
+                        "mean",
+                        "variance",
+                        "variation",
+                        "sum_squares",
+                        "standard_deviation",
+                        "sum_squares_centered",
+                        "second_order_raw_moment",
+                    }
+                ),
+                list,
+            ],
+            "batch_size": [Interval(numbers.Integral, 1, None, closed="left"), None],
+        }
+
+    def __init__(self, result_options="all", batch_size=None):
+        if result_options == "all":
+            self.result_options = (
+                self._onedal_incremental_basic_statistics.get_all_result_options()
+            )
+        else:
+            self.result_options = result_options
+        self._need_to_finalize = False
+        self.batch_size = batch_size
+
+    def _onedal_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearn.basic_statistics.{self.__class__.__name__}.{method_name}"
+        )
+        return patching_status
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    def _get_onedal_result_options(self, options):
+        if isinstance(options, list):
+            onedal_options = "|".join(self.result_options)
+        else:
+            onedal_options = options
+        assert isinstance(onedal_options, str)
+        return options
+
+    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_partial_fit(self, X, sample_weight=None, queue=None, check_input=True):
+        first_pass = not hasattr(self, "n_samples_seen_") or self.n_samples_seen_ == 0
+
+        if check_input:
+            if sklearn_check_version("1.0"):
+                X = validate_data(
+                    self,
+                    X,
+                    dtype=[np.float64, np.float32],
+                    reset=first_pass,
+                )
+            else:
+                X = check_array(
+                    X,
+                    dtype=[np.float64, np.float32],
+                )
+
+        if sample_weight is not None:
+            sample_weight = _check_sample_weight(sample_weight, X)
+
+        if first_pass:
+            self.n_samples_seen_ = X.shape[0]
+            self.n_features_in_ = X.shape[1]
+        else:
+            self.n_samples_seen_ += X.shape[0]
+
+        onedal_params = {
+            "result_options": self._get_onedal_result_options(self.result_options)
+        }
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_incremental_basic_statistics(
+                **onedal_params
+            )
+        self._onedal_estimator.partial_fit(X, weights=sample_weight, queue=queue)
+        self._need_to_finalize = True
+
+    def _onedal_fit(self, X, sample_weight=None, queue=None):
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        if sklearn_check_version("1.0"):
+            X = validate_data(self, X, dtype=[np.float64, np.float32])
+        else:
+            X = check_array(X, dtype=[np.float64, np.float32])
+
+        if sample_weight is not None:
+            sample_weight = _check_sample_weight(sample_weight, X)
+
+        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(X.shape[0], self.batch_size_):
+            X_batch = X[batch]
+            weights_batch = sample_weight[batch] if sample_weight is not None else None
+            self._onedal_partial_fit(
+                X_batch, weights_batch, queue=queue, check_input=False
+            )
+
+        self.n_features_in_ = X.shape[1]
+
+        self._onedal_finalize_fit(queue=queue)
+
+        return self
+
+    def __getattr__(self, attr):
+        result_options = self.__dict__["result_options"]
+        sattr = attr.removesuffix("_")
+        is_statistic_attr = (
+            isinstance(result_options, str) and (sattr == result_options)
+        ) or (isinstance(result_options, list) and (sattr in result_options))
+        if is_statistic_attr:
+            if self._need_to_finalize:
+                self._onedal_finalize_fit()
+            if sattr == attr:
+                warnings.warn(
+                    "Result attributes without a trailing underscore were deprecated in version 2025.1 and will be removed in 2026.0"
+                )
+            return getattr(self._onedal_estimator, sattr)
+        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, sample_weight=None, check_input=True):
+        """Incremental fit with X. All of X is processed as a single batch.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Data for compute, 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.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
+
+        check_input : bool, default=True
+            Run ``check_array`` on X.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        dispatch(
+            self,
+            "partial_fit",
+            {
+                "onedal": self.__class__._onedal_partial_fit,
+                "sklearn": None,
+            },
+            X,
+            sample_weight,
+            check_input=check_input,
+        )
+        return self
+
+    def fit(self, X, y=None, sample_weight=None):
+        """Calculate statistics of X using minibatches of size batch_size.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Data for compute, 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.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": None,
+            },
+            X,
+            sample_weight,
+        )
+        return self