scikit-learn-intelex 2025.0.1__py311-none-win_amd64.whl → 2025.2.0__py311-none-win_amd64.whl

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/sklearnex/basic_statistics/basic_statistics.py

@@ -14,21 +14,33 @@
 # limitations under the License.
 # ==============================================================================
 
+import warnings
+
 import numpy as np
+from scipy.sparse import issparse
 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 daal4py.sklearn._utils import daal_check_version, sklearn_check_version
 from onedal.basic_statistics import BasicStatistics as onedal_BasicStatistics
+from onedal.utils import _is_csr
 
 from .._device_offload import dispatch
-from .._utils import PatchingConditionsChain
+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(BaseEstimator):
+class BasicStatistics(IntelEstimator, BaseEstimator):
     """
     Estimator for basic statistics.
     Allows to compute basic statistics for provided data.
@@ -43,31 +55,36 @@ class BasicStatistics(BaseEstimator):
 
     Attributes
     ----------
-        min : ndarray of shape (n_features,)
+        min_ : ndarray of shape (n_features,)
             Minimum of each feature over all samples.
-        max : ndarray of shape (n_features,)
+        max_ : ndarray of shape (n_features,)
             Maximum of each feature over all samples.
-        sum : ndarray of shape (n_features,)
+        sum_ : ndarray of shape (n_features,)
             Sum of each feature over all samples.
-        mean : ndarray of shape (n_features,)
+        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,)
+        variance_ : ndarray of shape (n_features,)
+            Variance of each feature over all samples. Bessel's correction is used.
+        variation_ : ndarray of shape (n_features,)
+            Variation of each feature over all samples. Bessel's correction is used.
+        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,)
+        standard_deviation_ : ndarray of shape (n_features,)
+            Unbiased standard deviation of each feature over all samples. Bessel's correction is used.
+        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_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
@@ -87,36 +104,114 @@ class BasicStatistics(BaseEstimator):
     """
 
     def __init__(self, result_options="all"):
-        self.options = result_options
+        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.options == "all":
+        if self.result_options == "all":
             result_options = onedal_BasicStatistics.get_all_result_options()
         else:
-            result_options = self.options
+            result_options = self.result_options
 
         if isinstance(result_options, str):
-            setattr(self, result_options, getattr(self._onedal_estimator, result_options))
+            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))
+                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]
 
-    def _onedal_supported(self, method_name, *data):
+        raise AttributeError(
+            f"'{self.__class__.__name__}' object has no attribute '{attr}'"
+        )
+
+    def _onedal_cpu_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_gpu_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearnex.basic_statistics.{self.__class__.__name__}.{method_name}"
+        )
+        X, sample_weight = data
+
+        is_data_supported = not issparse(X) or (
+            _is_csr(X) and daal_check_version((2025, "P", 200))
+        )
+
+        is_sample_weight_supported = sample_weight is None or not issparse(X)
+
+        patching_status.and_conditions(
+            [
+                (
+                    is_sample_weight_supported,
+                    "Sample weights are not supported for CSR data format",
+                ),
+                (
+                    is_data_supported,
+                    "Supported data formats: Dense, CSR (oneDAL version >= 2025.2.0).",
+                ),
+            ]
+        )
+        return patching_status
 
     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 = self._validate_data(X, dtype=[np.float64, np.float32], ensure_2d=False)
+            X = validate_data(
+                self,
+                X,
+                dtype=[np.float64, np.float32],
+                ensure_2d=False,
+                accept_sparse="csr",
+            )
         else:
             X = check_array(X, dtype=[np.float64, np.float32])
 
@@ -124,16 +219,17 @@ class BasicStatistics(BaseEstimator):
             sample_weight = _check_sample_weight(sample_weight, X)
 
         onedal_params = {
-            "result_options": self.options,
+            "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):
-        """Compute statistics with X, using minibatches of size batch_size.
+        """Calculate statistics of X.
 
         Parameters
         ----------

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/sklearnex/basic_statistics/incremental_basic_statistics.py

@@ -26,16 +26,22 @@ from onedal.basic_statistics import (
 )
 
 from .._device_offload import dispatch
-from .._utils import PatchingConditionsChain
+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(BaseEstimator):
+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
@@ -53,34 +59,34 @@ class IncrementalBasicStatistics(BaseEstimator):
 
     Attributes
     ----------
-        min : ndarray of shape (n_features,)
+        min_ : ndarray of shape (n_features,)
             Minimum of each feature over all samples.
 
-        max : ndarray of shape (n_features,)
+        max_ : ndarray of shape (n_features,)
             Maximum of each feature over all samples.
 
-        sum : ndarray of shape (n_features,)
+        sum_ : ndarray of shape (n_features,)
             Sum of each feature over all samples.
 
-        mean : ndarray of shape (n_features,)
+        mean_ : ndarray of shape (n_features,)
             Mean of each feature over all samples.
 
-        variance : ndarray of shape (n_features,)
+        variance_ : ndarray of shape (n_features,)
             Variance of each feature over all samples.
 
-        variation : ndarray of shape (n_features,)
+        variation_ : ndarray of shape (n_features,)
             Variation of each feature over all samples.
 
-        sum_squares : ndarray of shape (n_features,)
+        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_ : ndarray of shape (n_features,)
             Standard deviation of each feature over all samples.
 
-        sum_squares_centered : ndarray of shape (n_features,)
+        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_raw_moment_ : ndarray of shape (n_features,)
             Second order moment of each feature over all samples.
 
         n_samples_seen_ : int
@@ -97,6 +103,18 @@ class IncrementalBasicStatistics(BaseEstimator):
     ----
     Attribute exists only if corresponding result option has been provided.
 
+    Note
+    ----
+    Serializing instances of this class will trigger a forced finalization of calculations.
+    Since finalize_fit can't be dispatched without directly provided queue
+    and the dispatching policy can't be serialized, the computation is finalized
+    during serialization call and the policy is not saved in serialized data.
+
+    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
@@ -173,20 +191,22 @@ class IncrementalBasicStatistics(BaseEstimator):
         self._onedal_estimator.finalize_fit(queue=queue)
         self._need_to_finalize = False
 
-    def _onedal_partial_fit(self, X, sample_weight=None, queue=None):
+    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 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],
-            )
+        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)
@@ -208,8 +228,11 @@ class IncrementalBasicStatistics(BaseEstimator):
         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 = self._validate_data(X, dtype=[np.float64, np.float32])
+            X = validate_data(self, X, dtype=[np.float64, np.float32])
         else:
             X = check_array(X, dtype=[np.float64, np.float32])
 
@@ -229,10 +252,9 @@ class IncrementalBasicStatistics(BaseEstimator):
         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)
-
-        if sklearn_check_version("1.2"):
-            self._validate_params()
+            self._onedal_partial_fit(
+                X_batch, weights_batch, queue=queue, check_input=False
+            )
 
         self.n_features_in_ = X.shape[1]
 
@@ -242,13 +264,18 @@ class IncrementalBasicStatistics(BaseEstimator):
 
     def __getattr__(self, attr):
         result_options = self.__dict__["result_options"]
+        sattr = attr.removesuffix("_")
         is_statistic_attr = (
-            isinstance(result_options, str) and (attr == result_options)
-        ) or (isinstance(result_options, list) and (attr in result_options))
+            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()
-            return getattr(self._onedal_estimator, attr)
+            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]
 
@@ -256,7 +283,7 @@ class IncrementalBasicStatistics(BaseEstimator):
             f"'{self.__class__.__name__}' object has no attribute '{attr}'"
         )
 
-    def partial_fit(self, X, sample_weight=None):
+    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
@@ -271,6 +298,9 @@ class IncrementalBasicStatistics(BaseEstimator):
         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
@@ -285,11 +315,12 @@ class IncrementalBasicStatistics(BaseEstimator):
             },
             X,
             sample_weight,
+            check_input=check_input,
         )
         return self
 
     def fit(self, X, y=None, sample_weight=None):
-        """Compute statistics with X, using minibatches of size batch_size.
+        """Calculate statistics of X using minibatches of size batch_size.
 
         Parameters
         ----------