scikit-learn-intelex 2024.6.0__py39-none-win_amd64.whl → 2025.0.0__py39-none-win_amd64.whl

scikit_learn_intelex-2025.0.0.data/data/Lib/site-packages/sklearnex/basic_statistics/basic_statistics.py

@@ -0,0 +1,140 @@
+# ==============================================================================
+# 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
+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 PatchingConditionsChain
+
+
+@control_n_jobs(decorated_methods=["fit"])
+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
+
+    Attributes (are existing only if corresponding result option exists)
+    ----------
+        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.
+    """
+
+    def __init__(self, result_options="all"):
+        self.options = result_options
+
+    _onedal_basic_statistics = staticmethod(onedal_BasicStatistics)
+
+    def _save_attributes(self):
+        assert hasattr(self, "_onedal_estimator")
+
+        if self.options == "all":
+            result_options = onedal_BasicStatistics.get_all_result_options()
+        else:
+            result_options = self.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 _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("1.0"):
+            X = self._validate_data(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.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()
+
+    def fit(self, X, y=None, *, sample_weight=None):
+        """Compute statistics with 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

{scikit_learn_intelex-2024.6.0.data → scikit_learn_intelex-2025.0.0.data}/data/Lib/site-packages/sklearnex/basic_statistics/incremental_basic_statistics.py

@@ -120,7 +120,7 @@ class IncrementalBasicStatistics(BaseEstimator):
 
     def _onedal_supported(self, method_name, *data):
         patching_status = PatchingConditionsChain(
-            f"sklearn.covariance.{self.__class__.__name__}.{method_name}"
+            f"sklearn.basic_statistics.{self.__class__.__name__}.{method_name}"
         )
         return patching_status
 
@@ -135,9 +135,9 @@ class IncrementalBasicStatistics(BaseEstimator):
         assert isinstance(onedal_options, str)
         return options
 
-    def _onedal_finalize_fit(self):
+    def _onedal_finalize_fit(self, queue=None):
         assert hasattr(self, "_onedal_estimator")
-        self._onedal_estimator.finalize_fit()
+        self._onedal_estimator.finalize_fit(queue=queue)
         self._need_to_finalize = False
 
     def _onedal_partial_fit(self, X, sample_weight=None, queue=None):
@@ -171,7 +171,7 @@ class IncrementalBasicStatistics(BaseEstimator):
             self._onedal_estimator = self._onedal_incremental_basic_statistics(
                 **onedal_params
             )
-        self._onedal_estimator.partial_fit(X, sample_weight, queue)
+        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):
@@ -203,7 +203,7 @@ class IncrementalBasicStatistics(BaseEstimator):
 
         self.n_features_in_ = X.shape[1]
 
-        self._onedal_finalize_fit()
+        self._onedal_finalize_fit(queue=queue)
 
         return self
 

scikit_learn_intelex-2025.0.0.data/data/Lib/site-packages/sklearnex/basic_statistics/tests/test_basic_statistics.py

@@ -0,0 +1,251 @@
+# ==============================================================================
+# 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 onedal.basic_statistics.tests.test_basic_statistics import (
+    expected_max,
+    expected_mean,
+    expected_sum,
+    options_and_tests,
+)
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+from sklearnex.basic_statistics import BasicStatistics
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_basic_statistics(dataframe, queue):
+    X = np.array([[0, 0], [1, 1]])
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+
+    weights = np.array([1, 0.5])
+    weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+
+    result = BasicStatistics().fit(X_df)
+
+    expected_mean = np.array([0.5, 0.5])
+    expected_min = np.array([0, 0])
+    expected_max = np.array([1, 1])
+
+    assert_allclose(expected_mean, result.mean)
+    assert_allclose(expected_max, result.max)
+    assert_allclose(expected_min, result.min)
+
+    result = BasicStatistics().fit(X_df, sample_weight=weights_df)
+
+    expected_weighted_mean = np.array([0.25, 0.25])
+    expected_weighted_min = np.array([0, 0])
+    expected_weighted_max = np.array([0.5, 0.5])
+
+    assert_allclose(expected_weighted_mean, result.mean)
+    assert_allclose(expected_weighted_min, result.min)
+    assert_allclose(expected_weighted_max, result.max)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("weighted", [True, False])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_multiple_options_on_gold_data(dataframe, queue, weighted, dtype):
+    X = np.array([[0, 0], [1, 1]])
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    if weighted:
+        weights = np.array([1, 0.5])
+        weights = weights.astype(dtype=dtype)
+        weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+    basicstat = BasicStatistics()
+
+    if weighted:
+        result = basicstat.fit(X_df, sample_weight=weights_df)
+    else:
+        result = basicstat.fit(X_df)
+
+    if weighted:
+        expected_weighted_mean = np.array([0.25, 0.25])
+        expected_weighted_min = np.array([0, 0])
+        expected_weighted_max = np.array([0.5, 0.5])
+        assert_allclose(expected_weighted_mean, result.mean)
+        assert_allclose(expected_weighted_max, result.max)
+        assert_allclose(expected_weighted_min, result.min)
+    else:
+        expected_mean = np.array([0.5, 0.5])
+        expected_min = np.array([0, 0])
+        expected_max = np.array([1, 1])
+        assert_allclose(expected_mean, result.mean)
+        assert_allclose(expected_max, result.max)
+        assert_allclose(expected_min, result.min)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("option", options_and_tests)
+@pytest.mark.parametrize("row_count", [100, 1000])
+@pytest.mark.parametrize("column_count", [10, 100])
+@pytest.mark.parametrize("weighted", [True, False])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_single_option_on_random_data(
+    dataframe, queue, option, row_count, column_count, weighted, dtype
+):
+    result_option, function, tols = option
+    fp32tol, fp64tol = tols
+    seed = 77
+    gen = np.random.default_rng(seed)
+    X = gen.uniform(low=-0.3, high=+0.7, size=(row_count, column_count))
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    if weighted:
+        weights = gen.uniform(low=-0.5, high=1.0, size=row_count)
+        weights = weights.astype(dtype=dtype)
+        weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+    basicstat = BasicStatistics(result_options=result_option)
+
+    if weighted:
+        result = basicstat.fit(X_df, sample_weight=weights_df)
+    else:
+        result = basicstat.fit(X_df)
+
+    res = getattr(result, result_option)
+    if weighted:
+        weighted_data = np.diag(weights) @ X
+        gtr = function(weighted_data)
+    else:
+        gtr = function(X)
+
+    tol = fp32tol if res.dtype == np.float32 else fp64tol
+    assert_allclose(gtr, res, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("row_count", [100, 1000])
+@pytest.mark.parametrize("column_count", [10, 100])
+@pytest.mark.parametrize("weighted", [True, False])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_multiple_options_on_random_data(
+    dataframe, queue, row_count, column_count, weighted, dtype
+):
+    seed = 77
+    gen = np.random.default_rng(seed)
+    X = gen.uniform(low=-0.3, high=+0.7, size=(row_count, column_count))
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    if weighted:
+        weights = gen.uniform(low=-0.5, high=1.0, size=row_count)
+        weights = weights.astype(dtype=dtype)
+        weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+    basicstat = BasicStatistics(result_options=["mean", "max", "sum"])
+
+    if weighted:
+        result = basicstat.fit(X_df, sample_weight=weights_df)
+    else:
+        result = basicstat.fit(X_df)
+
+    res_mean, res_max, res_sum = result.mean, result.max, result.sum
+    if weighted:
+        weighted_data = np.diag(weights) @ X
+        gtr_mean, gtr_max, gtr_sum = (
+            expected_mean(weighted_data),
+            expected_max(weighted_data),
+            expected_sum(weighted_data),
+        )
+    else:
+        gtr_mean, gtr_max, gtr_sum = (
+            expected_mean(X),
+            expected_max(X),
+            expected_sum(X),
+        )
+
+    tol = 5e-4 if res_mean.dtype == np.float32 else 1e-7
+    assert_allclose(gtr_mean, res_mean, atol=tol)
+    assert_allclose(gtr_max, res_max, atol=tol)
+    assert_allclose(gtr_sum, res_sum, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("row_count", [100, 1000])
+@pytest.mark.parametrize("column_count", [10, 100])
+@pytest.mark.parametrize("weighted", [True, False])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_all_option_on_random_data(
+    dataframe, queue, row_count, column_count, weighted, dtype
+):
+    seed = 77
+    gen = np.random.default_rng(seed)
+    X = gen.uniform(low=-0.3, high=+0.7, size=(row_count, column_count))
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    if weighted:
+        weights = gen.uniform(low=-0.5, high=+1.0, size=row_count)
+        weights = weights.astype(dtype=dtype)
+        weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+    basicstat = BasicStatistics(result_options="all")
+
+    if weighted:
+        result = basicstat.fit(X_df, sample_weight=weights_df)
+    else:
+        result = basicstat.fit(X_df)
+
+    if weighted:
+        weighted_data = np.diag(weights) @ X
+
+    for option in options_and_tests:
+        result_option, function, tols = option
+        fp32tol, fp64tol = tols
+        res = getattr(result, result_option)
+        if weighted:
+            gtr = function(weighted_data)
+        else:
+            gtr = function(X)
+        tol = fp32tol if res.dtype == np.float32 else fp64tol
+        assert_allclose(gtr, res, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("option", options_and_tests)
+@pytest.mark.parametrize("data_size", [100, 1000])
+@pytest.mark.parametrize("weighted", [True, False])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_1d_input_on_random_data(dataframe, queue, option, data_size, weighted, dtype):
+    result_option, function, tols = option
+    fp32tol, fp64tol = tols
+    seed = 77
+    gen = np.random.default_rng(seed)
+    X = gen.uniform(low=-0.3, high=+0.7, size=data_size)
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    if weighted:
+        weights = gen.uniform(low=-0.5, high=1.0, size=data_size)
+        weights = weights.astype(dtype=dtype)
+        weights_df = _convert_to_dataframe(weights, sycl_queue=queue, target_df=dataframe)
+    basicstat = BasicStatistics(result_options=result_option)
+
+    if weighted:
+        result = basicstat.fit(X_df, sample_weight=weights_df)
+    else:
+        result = basicstat.fit(X_df)
+
+    res = getattr(result, result_option)
+    if weighted:
+        weighted_data = weights * X
+        gtr = function(weighted_data)
+    else:
+        gtr = function(X)
+
+    tol = fp32tol if res.dtype == np.float32 else fp64tol
+    assert_allclose(gtr, res, atol=tol)

{scikit_learn_intelex-2024.6.0.data → scikit_learn_intelex-2025.0.0.data}/data/Lib/site-packages/sklearnex/basic_statistics/tests/test_incremental_basic_statistics.py

@@ -18,7 +18,7 @@ import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 
-from onedal.basic_statistics.tests.test_incremental_basic_statistics import (
+from onedal.basic_statistics.tests.test_basic_statistics import (
     expected_max,
     expected_mean,
     expected_sum,

{scikit_learn_intelex-2024.6.0.data → scikit_learn_intelex-2025.0.0.data}/data/Lib/site-packages/sklearnex/cluster/__init__.py

@@ -17,4 +17,4 @@
 from .dbscan import DBSCAN
 from .k_means import KMeans
 
-__all__ = ["KMeans", "DBSCAN"]
+__all__ = ["DBSCAN", "KMeans"]

{scikit_learn_intelex-2024.6.0.data → scikit_learn_intelex-2025.0.0.data}/data/Lib/site-packages/sklearnex/cluster/dbscan.py

@@ -17,7 +17,6 @@
 import numbers
 from abc import ABC
 
-import numpy as np
 from scipy import sparse as sp
 from sklearn.cluster import DBSCAN as sklearn_DBSCAN
 from sklearn.utils.validation import _check_sample_weight