scikit-learn-intelex 2025.0.0__py310-none-manylinux_2_28_x86_64.whl → 2025.0.1__py310-none-manylinux_2_28_x86_64.whl

{scikit_learn_intelex-2025.0.0.dist-info → scikit_learn_intelex-2025.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scikit-learn-intelex
-Version: 2025.0.0
+Version: 2025.0.1
 Summary: Intel(R) Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application.
 Home-page: https://github.com/intel/scikit-learn-intelex
 Author: Intel Corporation
@@ -31,7 +31,7 @@ Classifier: Topic :: Software Development
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: daal (==2025.0.0)
+Requires-Dist: daal (==2025.0.1)
 Requires-Dist: numpy (>=1.19)
 Requires-Dist: scikit-learn (>=0.22)
 

{scikit_learn_intelex-2025.0.0.dist-info → scikit_learn_intelex-2025.0.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
 daal4py/__init__.py,sha256=Z9m4-_WGRMvvv4BRTlQy9tDh6dDXyKMuvJbFdCkKm7U,2605
 daal4py/__main__.py,sha256=XkcEBDY30krQy7F6b5GRIBs1Ef3mNjv8IZE3TdcUCAs,1956
-daal4py/_daal4py.cpython-310-x86_64-linux-gnu.so,sha256=B1kL_SvPH7nNdGjOnXPmFTMDlQpDJ6Qj4YhzWeJM7f0,10340712
-daal4py/mpi_transceiver.cpython-310-x86_64-linux-gnu.so,sha256=llVxZhm2bN4wHRk9H_P0OKSECJOHPActMijxPXaAsfY,22904
+daal4py/_daal4py.cpython-310-x86_64-linux-gnu.so,sha256=uXuE1YDyvPkqeK8q0HVYfypNVFdGx4T7tZY8zGXi6Ds,10340712
+daal4py/mpi_transceiver.cpython-310-x86_64-linux-gnu.so,sha256=ivOucqN9lo1JteuleS6uTmWhE5s9cNhFpeWWfv_fuFM,22904
 daal4py/doc/third-party-programs.txt,sha256=3tB2wzQ26wLa0aa574AxPit02Cse01Sqk0MJJboyQd0,21754
 daal4py/mb/__init__.py,sha256=Gw3YCjY4oRlB-Y-io1hD9wnRs20WK-5M8ADaMh-orLE,853
 daal4py/mb/model_builders.py,sha256=kyyv7V8XG2MWiCIPjGoyozz2W9iV2zg3sg1xwZ_GCmw,15453
@@ -155,8 +155,8 @@ sklearnex/_utils.py,sha256=EV4jC3plVdndsgrfPBsJZTzggrRdYWLwOpoIRWtTXt4,3812
 sklearnex/conftest.py,sha256=ODuhlscC0HNGXiA8olEfHTDULzjevqG9_sn0yMGRkHg,2376
 sklearnex/dispatcher.py,sha256=AWsrUNRZukLscR-sBzjMLdin-9rziPuSaBfWgj2Kx9Y,18993
 sklearnex/basic_statistics/__init__.py,sha256=-lNh54F2FO0BuHDBLjhW7zp3yBcgFZ-DrXHj2H5hLXE,920
-sklearnex/basic_statistics/basic_statistics.py,sha256=EQONHwPL4xdTWL49ZyLFN3wRp5oKCdDU1Y6R6Z-su0Q,5358
-sklearnex/basic_statistics/incremental_basic_statistics.py,sha256=lQaJwT865YnW7vZ4z8BXx32LWxithcn39OVmsnbOLpU,10102
+sklearnex/basic_statistics/basic_statistics.py,sha256=KKvLBm7DABj7h8K9NQC2P9WK0mLrXZugX82CsQzkAHI,6192
+sklearnex/basic_statistics/incremental_basic_statistics.py,sha256=E19WueDyWn4ZA8WT_SGcePegmbsRdQMK1VcTrxcyn8M,11047
 sklearnex/basic_statistics/tests/test_basic_statistics.py,sha256=dsJCHOPdjwZt5Kod1VdD8sdQrpoabPPUJNGN5S8cVvU,9533
 sklearnex/basic_statistics/tests/test_incremental_basic_statistics.py,sha256=0a5zE0iMzAQMiRyKTpcvQjGHBM86aNhnQZ0l_Ry1fNY,14914
 sklearnex/cluster/__init__.py,sha256=r0CKwy-PSca0jbZc4jU2CkU__qC643751-GuX1aaY40,853
@@ -165,7 +165,7 @@ sklearnex/cluster/k_means.py,sha256=LGdCJdGRqkV00kL2zJ_BVyYIkInNd-L-NZcJ4rwju2c,
 sklearnex/cluster/tests/test_dbscan.py,sha256=JYpwyuPkGQHdbE_IPbQv4qNj7clMm4UPdz_lrpRzKXE,1504
 sklearnex/cluster/tests/test_kmeans.py,sha256=e3RAVsxo6qOZeEFSbrsI_nvjPSPosTn3QGvKHvSIInE,6049
 sklearnex/covariance/__init__.py,sha256=_c86wiKDGBH50ofN-_tn7lO4M2YVEWO5AHhJIfimUDk,859
-sklearnex/covariance/incremental_covariance.py,sha256=pYaRgI4xHnS_ZiuH9VwQptk4ZtuEhgg1PTliIb2ufAw,13096
+sklearnex/covariance/incremental_covariance.py,sha256=K_t9Do0GcTaxTKVtfAVrbxzLAPAo1XSwiErqAsmBYYU,13729
 sklearnex/covariance/tests/test_incremental_covariance.py,sha256=9iJZyj43YKAgx11i7y_fhHc_S7dvKrMuEW2lYIe_AdU,8592
 sklearnex/decomposition/__init__.py,sha256=RJBYDWyvnn5DA-j5r4IqVdXLp6H4mdPySsSjnXhlv-U,805
 sklearnex/decomposition/pca.py,sha256=XNW8Bo_S0iC-NmVUnyFzkUTNJJ10SjEeJEYuaUjkO1M,16597
@@ -178,7 +178,7 @@ sklearnex/glob/__main__.py,sha256=--FAjkhh5E6a1TFOGu6_BM3MHe78jP8oSpl0xKiRtTI,25
 sklearnex/glob/dispatcher.py,sha256=o6XKGKM3M91F7FlXBOt1IhnpWQK4R1VY2WS-0uIghcw,3906
 sklearnex/linear_model/__init__.py,sha256=5ZHAppxcqKlq5MOZTfigFU9MuN1L5Use_F_cZqo_-p4,1218
 sklearnex/linear_model/coordinate_descent.py,sha256=SKNVTYYX8ysZ8M9h32qIaof3Fc2OKcBRXaCOySUBOiE,1554
-sklearnex/linear_model/incremental_linear.py,sha256=UmpbntBFcx1AIHMEZBvCQfzR2BNB8X8Sa_Lwb65RUwM,16146
+sklearnex/linear_model/incremental_linear.py,sha256=jnov2niAehvxSsl-j5MQYJQqSPFYFMyy1FQWxh559d0,16783
 sklearnex/linear_model/incremental_ridge.py,sha256=bOP9WFKQqFeLzlanPLG3XAtafQ6ZVscXSSfUaImTY74,14388
 sklearnex/linear_model/linear.py,sha256=BDexE22Nl6egzHoMiruBp6L_biUfy0eWaZWbHMG9rJc,10740
 sklearnex/linear_model/logistic_path.py,sha256=Nq3JPXSzE4bjamnP3gGQtsMKks2v7s6bSiuYRnFqrRw,849
@@ -271,8 +271,8 @@ sklearnex/utils/_array_api.py,sha256=c5AFRaxYn3pjInTXeFzcXZB8SrRxQ-4UQARQv1HchFI
 sklearnex/utils/parallel.py,sha256=VBcS-KUdyq7XpJUN6ygmNjyWtYLroghbvCxQ8nVU3YI,2085
 sklearnex/utils/validation.py,sha256=fjfhQiKnBQnD7LCBlacMyvsrhGnlMLRXk5Q69uoZIP4,827
 sklearnex/utils/tests/test_finite.py,sha256=AzJRY71X0VvDUicUI8Ey9Le6_yKp5O-3ZikhDVJNWms,2943
-scikit_learn_intelex-2025.0.0.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
-scikit_learn_intelex-2025.0.0.dist-info/METADATA,sha256=lDZFW4nuu2-BVZppQrIWcxISuzP4XzWQuaP-IG8WsJg,12476
-scikit_learn_intelex-2025.0.0.dist-info/WHEEL,sha256=AbDXtI07YbmAOyulr4lTLqgtukIt8PjPDO5guTSVq0s,112
-scikit_learn_intelex-2025.0.0.dist-info/top_level.txt,sha256=Qa0CGteT1uguKJdxiwylb90eW-a1R8FcENgN6P7IKfs,25
-scikit_learn_intelex-2025.0.0.dist-info/RECORD,,
+scikit_learn_intelex-2025.0.1.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
+scikit_learn_intelex-2025.0.1.dist-info/METADATA,sha256=IbsY1MTgZ5DkuhoKjZupR95U22d1M-DYXfQX_8Ixm1A,12476
+scikit_learn_intelex-2025.0.1.dist-info/WHEEL,sha256=AbDXtI07YbmAOyulr4lTLqgtukIt8PjPDO5guTSVq0s,112
+scikit_learn_intelex-2025.0.1.dist-info/top_level.txt,sha256=Qa0CGteT1uguKJdxiwylb90eW-a1R8FcENgN6P7IKfs,25
+scikit_learn_intelex-2025.0.1.dist-info/RECORD,,

sklearnex/basic_statistics/basic_statistics.py

@@ -32,12 +32,16 @@ class BasicStatistics(BaseEstimator):
     """
     Estimator for basic statistics.
     Allows to compute basic statistics for provided data.
+
     Parameters
     ----------
     result_options: string or list, default='all'
-        List of statistics to compute
+        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 (are existing only if corresponding result option exists)
+    Attributes
     ----------
         min : ndarray of shape (n_features,)
             Minimum of each feature over all samples.
@@ -59,6 +63,27 @@ class BasicStatistics(BaseEstimator):
             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
+    ----
+    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"):
@@ -113,14 +138,14 @@ class BasicStatistics(BaseEstimator):
         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.
+            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.
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
 
         Returns
         -------

sklearnex/basic_statistics/incremental_basic_statistics.py

@@ -37,8 +37,10 @@ import numbers
 @control_n_jobs(decorated_methods=["partial_fit", "_onedal_finalize_fit"])
 class IncrementalBasicStatistics(BaseEstimator):
     """
-    Incremental estimator for basic statistics.
-    Allows to compute basic statistics if data are splitted into batches.
+    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'
@@ -47,10 +49,9 @@ class IncrementalBasicStatistics(BaseEstimator):
     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``, to provide a
-        balance between approximation accuracy and memory consumption.
+        is inferred from the data and set to ``5 * n_features``.
 
-    Attributes (are existing only if corresponding result option exists)
+    Attributes
     ----------
         min : ndarray of shape (n_features,)
             Minimum of each feature over all samples.
@@ -81,6 +82,38 @@ class IncrementalBasicStatistics(BaseEstimator):
 
         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.
+
+    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)
@@ -229,14 +262,14 @@ class IncrementalBasicStatistics(BaseEstimator):
         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.
+            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.
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
 
         Returns
         -------
@@ -261,14 +294,14 @@ class IncrementalBasicStatistics(BaseEstimator):
         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.
+            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.
+            Weights for compute weighted statistics, where ``n_samples`` is the number of samples.
 
         Returns
         -------

sklearnex/covariance/incremental_covariance.py

@@ -44,9 +44,9 @@ if sklearn_check_version("1.2"):
 @control_n_jobs(decorated_methods=["partial_fit", "fit", "_onedal_finalize_fit"])
 class IncrementalEmpiricalCovariance(BaseEstimator):
     """
-    Incremental estimator for covariance.
-    Allows to compute empirical covariance estimated by maximum
-    likelihood method if data are splitted into batches.
+    Maximum likelihood covariance estimator that allows for the estimation when the data are split into
+    batches. The user can use the ``partial_fit`` method to provide a single batch of data or use the ``fit`` method to provide
+    the entire dataset.
 
     Parameters
     ----------
@@ -79,13 +79,31 @@ class IncrementalEmpiricalCovariance(BaseEstimator):
 
     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.
+        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 :term:`fit` `partial_fit`.
+        Number of features seen during ``fit`` or ``partial_fit``.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearnex.covariance import IncrementalEmpiricalCovariance
+    >>> inccov = IncrementalEmpiricalCovariance(batch_size=1)
+    >>> X = np.array([[1, 2], [3, 4]])
+    >>> inccov.partial_fit(X[:1])
+    >>> inccov.partial_fit(X[1:])
+    >>> inccov.covariance_
+    np.array([[1., 1.],[1., 1.]])
+    >>> inccov.location_
+    np.array([2., 3.])
+    >>> inccov.fit(X)
+    >>> inccov.covariance_
+    np.array([[1., 1.],[1., 1.]])
+    >>> inccov.location_
+    np.array([2., 3.])
     """
 
     _onedal_incremental_covariance = staticmethod(onedal_IncrementalEmpiricalCovariance)

sklearnex/linear_model/incremental_linear.py

@@ -49,8 +49,9 @@ from .._utils import PatchingConditionsChain, register_hyperparameters
 )
 class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimator):
     """
-    Incremental estimator for linear regression.
-    Allows to train linear regression if data are splitted into batches.
+    Trains a linear regression model, allows for computation if the data are split into
+    batches. The user can use the ``partial_fit`` method to provide a single batch of data or use the ``fit`` method to provide
+    the entire dataset.
 
     Parameters
     ----------
@@ -68,8 +69,7 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
     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``, to provide a
-        balance between approximation accuracy and memory consumption.
+        is inferred from the data and set to ``5 * n_features``.
 
     Attributes
     ----------
@@ -83,12 +83,9 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
         Independent term in the linear model. Set to 0.0 if
         `fit_intercept = False`.
 
-    n_features_in_ : int
-        Number of features seen during :term:`fit`.
-
     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.
+        new calls to ``fit``, but increments across ``partial_fit`` calls.
         It should be not less than `n_features_in_` if `fit_intercept`
         is False and not less than `n_features_in_` + 1 if `fit_intercept`
         is True to obtain regression coefficients.
@@ -97,8 +94,26 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
         Inferred batch size from ``batch_size``.
 
     n_features_in_ : int
-        Number of features seen during :term:`fit` `partial_fit`.
-
+        Number of features seen during ``fit`` or ``partial_fit``.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearnex.linear_model import IncrementalLinearRegression
+    >>> inclr = IncrementalLinearRegression(batch_size=2)
+    >>> X = np.array([[1, 2], [3, 4], [5, 6], [7, 10]])
+    >>> y = np.array([1.5, 3.5, 5.5, 8.5])
+    >>> inclr.partial_fit(X[:2], y[:2])
+    >>> inclr.partial_fit(X[2:], y[2:])
+    >>> inclr.coef_
+    np.array([0.5., 0.5.])
+    >>> inclr.intercept_
+    np.array(0.)
+    >>> inclr.fit(X)
+    >>> inclr.coef_
+    np.array([0.5., 0.5.])
+    >>> inclr.intercept_
+    np.array(0.)
     """
 
     _onedal_incremental_linear = staticmethod(onedal_IncrementalLinearRegression)
@@ -311,12 +326,12 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
         Parameters
         ----------
         X : array-like of shape (n_samples, n_features)
-            Training data, where `n_samples` is the number of samples and
+            Training data, where ``n_samples`` is the number of samples and
             `n_features` is the number of features.
 
         y : array-like of shape (n_samples,) or (n_samples, n_targets)
-            Target values, where `n_samples` is the number of samples and
-            `n_targets` is the number of targets.
+            Target values, where ``n_samples`` is the number of samples and
+            ``n_targets`` is the number of targets.
 
         Returns
         -------
@@ -339,20 +354,20 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
 
     def fit(self, X, y):
         """
-        Fit the model with X and y, using minibatches of size batch_size.
+        Fit the model with X and y, using minibatches of size ``batch_size``.
 
         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. It is necessary for
-            `n_samples` to be not less than `n_features` if `fit_intercept`
-            is False and not less than `n_features` + 1 if `fit_intercept`
+            Training data, where ``n_samples`` is the number of samples and
+            ``n_features`` is the number of features. It is necessary for
+            ``n_samples`` to be not less than ``n_features`` if ``fit_intercept``
+            is False and not less than ``n_features + 1`` if ``fit_intercept``
             is True
 
         y : array-like of shape (n_samples,) or (n_samples, n_targets)
-            Target values, where `n_samples` is the number of samples and
-            `n_targets` is the number of targets.
+            Target values, where ``n_samples`` is the number of samples and
+            ``n_targets`` is the number of targets.
 
         Returns
         -------
@@ -376,10 +391,15 @@ class IncrementalLinearRegression(MultiOutputMixin, RegressorMixin, BaseEstimato
     def predict(self, X, y=None):
         """
         Predict using the linear model.
+
         Parameters
         ----------
         X : array-like or sparse matrix, shape (n_samples, n_features)
             Samples.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
         Returns
         -------
         C : array, shape (n_samples, n_targets)