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/onedal/basic_statistics/incremental_basic_statistics.py

@@ -18,7 +18,7 @@ import numpy as np
 
 from daal4py.sklearn._utils import get_dtype
 
-from ..datatypes import _convert_to_supported, from_table, to_table
+from ..datatypes import from_table, to_table
 from ..utils import _check_array
 from .basic_statistics import BaseBasicStatistics
 
@@ -70,10 +70,21 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
         self._reset()
 
     def _reset(self):
+        self._need_to_finalize = False
         self._partial_result = self._get_backend(
             "basic_statistics", None, "partial_compute_result"
         )
 
+    def __getstate__(self):
+        # Since finalize_fit can't be dispatched without directly provided queue
+        # and the dispatching policy can't be serialized, the computation is finalized
+        # here and the policy is not saved in serialized data.
+        self.finalize_fit()
+        data = self.__dict__.copy()
+        data.pop("_queue", None)
+
+        return data
+
     def partial_fit(self, X, weights=None, queue=None):
         """
         Computes partial data for basic statistics
@@ -95,7 +106,6 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
         """
         self._queue = queue
         policy = self._get_policy(queue, X)
-        X, weights = _convert_to_supported(policy, X, weights)
 
         X = _check_array(
             X, dtype=[np.float64, np.float32], ensure_2d=False, force_all_finite=False
@@ -112,7 +122,7 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
             dtype = get_dtype(X)
             self._onedal_params = self._get_onedal_params(False, dtype=dtype)
 
-        X_table, weights_table = to_table(X, weights)
+        X_table, weights_table = to_table(X, weights, queue=queue)
         self._partial_result = self._get_backend(
             "basic_statistics",
             None,
@@ -124,6 +134,9 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
             weights_table,
         )
 
+        self._need_to_finalize = True
+        return self
+
     def finalize_fit(self, queue=None):
         """
         Finalizes basic statistics computation and obtains result
@@ -139,22 +152,24 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
         self : object
             Returns the instance itself.
         """
+        if self._need_to_finalize:
+            if queue is not None:
+                policy = self._get_policy(queue)
+            else:
+                policy = self._get_policy(self._queue)
+
+            result = self._get_backend(
+                "basic_statistics",
+                None,
+                "finalize_compute",
+                policy,
+                self._onedal_params,
+                self._partial_result,
+            )
+            options = self._get_result_options(self.options).split("|")
+            for opt in options:
+                setattr(self, opt, from_table(getattr(result, opt)).ravel())
 
-        if queue is not None:
-            policy = self._get_policy(queue)
-        else:
-            policy = self._get_policy(self._queue)
-
-        result = self._get_backend(
-            "basic_statistics",
-            None,
-            "finalize_compute",
-            policy,
-            self._onedal_params,
-            self._partial_result,
-        )
-        options = self._get_result_options(self.options).split("|")
-        for opt in options:
-            setattr(self, opt, from_table(getattr(result, opt)).ravel())
+            self._need_to_finalize = False
 
         return self

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/basic_statistics/tests/test_basic_statistics.py

@@ -21,66 +21,9 @@ from scipy import sparse as sp
 
 from daal4py.sklearn._utils import daal_check_version
 from onedal.basic_statistics import BasicStatistics
+from onedal.basic_statistics.tests.utils import options_and_tests
 from onedal.tests.utils._device_selection import get_queues
 
-
-def expected_sum(X):
-    return np.sum(X, axis=0)
-
-
-def expected_max(X):
-    return np.max(X, axis=0)
-
-
-def expected_min(X):
-    return np.min(X, axis=0)
-
-
-def expected_mean(X):
-    return np.mean(X, axis=0)
-
-
-def expected_standard_deviation(X):
-    return np.std(X, axis=0)
-
-
-def expected_variance(X):
-    return np.var(X, axis=0)
-
-
-def expected_variation(X):
-    return expected_standard_deviation(X) / expected_mean(X)
-
-
-def expected_sum_squares(X):
-    return np.sum(np.square(X), axis=0)
-
-
-def expected_sum_squares_centered(X):
-    return np.sum(np.square(X - expected_mean(X)), axis=0)
-
-
-def expected_standard_deviation(X):
-    return np.sqrt(expected_variance(X))
-
-
-def expected_second_order_raw_moment(X):
-    return np.mean(np.square(X), axis=0)
-
-
-options_and_tests = [
-    ("sum", expected_sum, (5e-4, 1e-7)),
-    ("min", expected_min, (1e-7, 1e-7)),
-    ("max", expected_max, (1e-7, 1e-7)),
-    ("mean", expected_mean, (5e-7, 1e-7)),
-    ("variance", expected_variance, (2e-3, 2e-3)),
-    ("variation", expected_variation, (5e-2, 5e-2)),
-    ("sum_squares", expected_sum_squares, (2e-4, 1e-7)),
-    ("sum_squares_centered", expected_sum_squares_centered, (2e-4, 1e-7)),
-    ("standard_deviation", expected_standard_deviation, (2e-3, 2e-3)),
-    ("second_order_raw_moment", expected_second_order_raw_moment, (1e-6, 1e-7)),
-]
-
 options_and_tests_csr = [
     ("sum", "sum", (5e-6, 1e-9)),
     ("min", "min", (0, 0)),
@@ -90,15 +33,15 @@ options_and_tests_csr = [
 
 
 @pytest.mark.parametrize("queue", get_queues())
-@pytest.mark.parametrize("option", options_and_tests)
+@pytest.mark.parametrize("result_option", options_and_tests.keys())
 @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(
-    queue, option, row_count, column_count, weighted, dtype
+    queue, result_option, row_count, column_count, weighted, dtype
 ):
-    result_option, function, tols = option
+    function, tols = options_and_tests[result_option]
     fp32tol, fp64tol = tols
     seed = 77
     gen = np.random.default_rng(seed)
@@ -150,15 +93,15 @@ def test_multiple_options_on_random_data(queue, row_count, column_count, weighte
     if weighted:
         weighted_data = np.diag(weights) @ data
         gtr_mean, gtr_max, gtr_sum = (
-            expected_mean(weighted_data),
-            expected_max(weighted_data),
-            expected_sum(weighted_data),
+            options_and_tests["mean"][0](weighted_data),
+            options_and_tests["max"][0](weighted_data),
+            options_and_tests["sum"][0](weighted_data),
         )
     else:
         gtr_mean, gtr_max, gtr_sum = (
-            expected_mean(data),
-            expected_max(data),
-            expected_sum(data),
+            options_and_tests["mean"][0](data),
+            options_and_tests["max"][0](data),
+            options_and_tests["sum"][0](data),
         )
 
     tol = 5e-4 if res_mean.dtype == np.float32 else 1e-7
@@ -190,8 +133,8 @@ def test_all_option_on_random_data(queue, row_count, column_count, weighted, dty
     if weighted:
         weighted_data = np.diag(weights) @ data
 
-    for option in options_and_tests:
-        result_option, function, tols = option
+    for result_option in options_and_tests:
+        function, tols = options_and_tests[result_option]
         fp32tol, fp64tol = tols
         res = getattr(result, result_option)
         if weighted:
@@ -203,12 +146,13 @@ def test_all_option_on_random_data(queue, row_count, column_count, weighted, dty
 
 
 @pytest.mark.parametrize("queue", get_queues())
-@pytest.mark.parametrize("option", options_and_tests)
+@pytest.mark.parametrize("result_option", options_and_tests.keys())
 @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(queue, option, data_size, weighted, dtype):
-    result_option, function, tols = option
+def test_1d_input_on_random_data(queue, result_option, data_size, weighted, dtype):
+
+    function, tols = options_and_tests[result_option]
     fp32tol, fp64tol = tols
     seed = 77
     gen = np.random.default_rng(seed)

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/basic_statistics/tests/test_incremental_basic_statistics.py

@@ -19,12 +19,8 @@ import pytest
 from numpy.testing import assert_allclose
 
 from onedal.basic_statistics import IncrementalBasicStatistics
-from onedal.basic_statistics.tests.test_basic_statistics import (
-    expected_max,
-    expected_mean,
-    expected_sum,
-    options_and_tests,
-)
+from onedal.basic_statistics.tests.utils import options_and_tests
+from onedal.datatypes import from_table
 from onedal.tests.utils._device_selection import get_queues
 
 
@@ -67,15 +63,15 @@ def test_multiple_options_on_gold_data(queue, weighted, dtype):
 
 @pytest.mark.parametrize("queue", get_queues())
 @pytest.mark.parametrize("num_batches", [2, 10])
-@pytest.mark.parametrize("option", options_and_tests)
+@pytest.mark.parametrize("result_option", options_and_tests.keys())
 @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(
-    queue, num_batches, option, row_count, column_count, weighted, dtype
+    queue, num_batches, result_option, row_count, column_count, weighted, dtype
 ):
-    result_option, function, tols = option
+    function, tols = options_and_tests[result_option]
     fp32tol, fp64tol = tols
     seed = 77
     gen = np.random.default_rng(seed)
@@ -137,15 +133,15 @@ def test_multiple_options_on_random_data(
     if weighted:
         weighted_data = np.diag(weights) @ data
         gtr_mean, gtr_max, gtr_sum = (
-            expected_mean(weighted_data),
-            expected_max(weighted_data),
-            expected_sum(weighted_data),
+            options_and_tests["mean"][0](weighted_data),
+            options_and_tests["max"][0](weighted_data),
+            options_and_tests["sum"][0](weighted_data),
         )
     else:
         gtr_mean, gtr_max, gtr_sum = (
-            expected_mean(data),
-            expected_max(data),
-            expected_sum(data),
+            options_and_tests["mean"][0](data),
+            options_and_tests["max"][0](data),
+            options_and_tests["sum"][0](data),
         )
 
     tol = 3e-4 if res_mean.dtype == np.float32 else 1e-7
@@ -184,8 +180,8 @@ def test_all_option_on_random_data(
     if weighted:
         weighted_data = np.diag(weights) @ data
 
-    for option in options_and_tests:
-        result_option, function, tols = option
+    for result_option in options_and_tests:
+        function, tols = options_and_tests[result_option]
         fp32tol, fp64tol = tols
         res = getattr(result, result_option)
         if weighted:
@@ -194,3 +190,90 @@ def test_all_option_on_random_data(
             gtr = function(data)
         tol = fp32tol if res.dtype == np.float32 else fp64tol
         assert_allclose(gtr, res, atol=tol)
+
+
+@pytest.mark.parametrize("queue", get_queues())
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_incremental_estimator_pickle(queue, dtype):
+    import pickle
+
+    from onedal.basic_statistics import IncrementalBasicStatistics
+
+    incbs = IncrementalBasicStatistics()
+
+    # Check that estimator can be serialized without any data.
+    dump = pickle.dumps(incbs)
+    incbs_loaded = pickle.loads(dump)
+    seed = 77
+    gen = np.random.default_rng(seed)
+    X = gen.uniform(low=-0.3, high=+0.7, size=(10, 10))
+    X = X.astype(dtype)
+    X_split = np.array_split(X, 2)
+    incbs.partial_fit(X_split[0], queue=queue)
+    incbs_loaded.partial_fit(X_split[0], queue=queue)
+
+    assert incbs._need_to_finalize == True
+    assert incbs_loaded._need_to_finalize == True
+
+    # Check that estimator can be serialized after partial_fit call.
+    dump = pickle.dumps(incbs)
+    incbs_loaded = pickle.loads(dump)
+    assert incbs._need_to_finalize == False
+    # Finalize is called during serialization to make sure partial results are finalized correctly.
+    assert incbs_loaded._need_to_finalize == False
+
+    partial_n_rows = from_table(incbs._partial_result.partial_n_rows)
+    partial_n_rows_loaded = from_table(incbs_loaded._partial_result.partial_n_rows)
+    assert_allclose(partial_n_rows, partial_n_rows_loaded)
+
+    partial_min = from_table(incbs._partial_result.partial_min)
+    partial_min_loaded = from_table(incbs_loaded._partial_result.partial_min)
+    assert_allclose(partial_min, partial_min_loaded)
+
+    partial_max = from_table(incbs._partial_result.partial_max)
+    partial_max_loaded = from_table(incbs_loaded._partial_result.partial_max)
+    assert_allclose(partial_max, partial_max_loaded)
+
+    partial_sum = from_table(incbs._partial_result.partial_sum)
+    partial_sum_loaded = from_table(incbs_loaded._partial_result.partial_sum)
+    assert_allclose(partial_sum, partial_sum_loaded)
+
+    partial_sum_squares = from_table(incbs._partial_result.partial_sum_squares)
+    partial_sum_squares_loaded = from_table(
+        incbs_loaded._partial_result.partial_sum_squares
+    )
+    assert_allclose(partial_sum_squares, partial_sum_squares_loaded)
+
+    partial_sum_squares_centered = from_table(
+        incbs._partial_result.partial_sum_squares_centered
+    )
+    partial_sum_squares_centered_loaded = from_table(
+        incbs_loaded._partial_result.partial_sum_squares_centered
+    )
+    assert_allclose(partial_sum_squares_centered, partial_sum_squares_centered_loaded)
+
+    incbs.partial_fit(X_split[1], queue=queue)
+    incbs_loaded.partial_fit(X_split[1], queue=queue)
+    assert incbs._need_to_finalize == True
+    assert incbs_loaded._need_to_finalize == True
+
+    dump = pickle.dumps(incbs_loaded)
+    incbs_loaded = pickle.loads(dump)
+
+    assert incbs._need_to_finalize == True
+    assert incbs_loaded._need_to_finalize == False
+
+    incbs.finalize_fit()
+    incbs_loaded.finalize_fit()
+
+    # Check that finalized estimator can be serialized.
+    dump = pickle.dumps(incbs_loaded)
+    incbs_loaded = pickle.loads(dump)
+
+    for result_option in options_and_tests:
+        _, tols = options_and_tests[result_option]
+        fp32tol, fp64tol = tols
+        res = getattr(incbs, result_option)
+        res_loaded = getattr(incbs_loaded, result_option)
+        tol = fp32tol if res.dtype == np.float32 else fp64tol
+        assert_allclose(res, res_loaded, atol=tol)

scikit_learn_intelex-2025.2.0.data/data/Lib/site-packages/onedal/basic_statistics/tests/utils.py

@@ -0,0 +1,50 @@
+# ===============================================================================
+# 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
+
+
+# Compute unbiased variation for the columns of array-like X
+def variation(X):
+    X_mean = np.mean(X, axis=0)
+    if np.all(X_mean):
+        # Avoid division by zero
+        return np.std(X, axis=0, ddof=1) / X_mean
+    else:
+        return np.array(
+            [
+                x / y if y != 0 else np.nan
+                for x, y in zip(np.std(X, axis=0, ddof=1), X_mean)
+            ]
+        )
+
+
+options_and_tests = {
+    "sum": (lambda X: np.sum(X, axis=0), (5e-4, 1e-7)),
+    "min": (lambda X: np.min(X, axis=0), (1e-7, 1e-7)),
+    "max": (lambda X: np.max(X, axis=0), (1e-7, 1e-7)),
+    "mean": (lambda X: np.mean(X, axis=0), (5e-7, 1e-7)),
+    # sklearnex computes unbiased variance and standard deviation that is why ddof=1
+    "variance": (lambda X: np.var(X, axis=0, ddof=1), (2e-4, 1e-7)),
+    "variation": (lambda X: variation(X), (1e-3, 1e-6)),
+    "sum_squares": (lambda X: np.sum(np.square(X), axis=0), (2e-4, 1e-7)),
+    "sum_squares_centered": (
+        lambda X: np.sum(np.square(X - np.mean(X, axis=0)), axis=0),
+        (1e-3, 1e-7),
+    ),
+    "standard_deviation": (lambda X: np.std(X, axis=0, ddof=1), (2e-3, 1e-7)),
+    "second_order_raw_moment": (lambda X: np.mean(np.square(X), axis=0), (1e-6, 1e-7)),
+}

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/cluster/dbscan.py

@@ -20,7 +20,7 @@ from daal4py.sklearn._utils import get_dtype, make2d
 
 from ..common._base import BaseEstimator
 from ..common._mixin import ClusterMixin
-from ..datatypes import _convert_to_supported, from_table, to_table
+from ..datatypes import from_table, to_table
 from ..utils import _check_array
 
 
@@ -48,7 +48,7 @@ class BaseDBSCAN(BaseEstimator, ClusterMixin):
 
     def _get_onedal_params(self, dtype=np.float32):
         return {
-            "fptype": "float" if dtype == np.float32 else "double",
+            "fptype": dtype,
             "method": "by_default",
             "min_observations": int(self.min_samples),
             "epsilon": float(self.eps),
@@ -60,15 +60,10 @@ class BaseDBSCAN(BaseEstimator, ClusterMixin):
         policy = self._get_policy(queue, X)
         X = _check_array(X, accept_sparse="csr", dtype=[np.float64, np.float32])
         sample_weight = make2d(sample_weight) if sample_weight is not None else None
-        X = make2d(X)
+        X_table, sample_weight_table = to_table(X, sample_weight, queue=queue)
 
-        types = [np.float32, np.float64]
-        if get_dtype(X) not in types:
-            X = X.astype(np.float64)
-        X = _convert_to_supported(policy, X)
-        dtype = get_dtype(X)
-        params = self._get_onedal_params(dtype)
-        result = module.compute(policy, params, to_table(X), to_table(sample_weight))
+        params = self._get_onedal_params(X_table.dtype)
+        result = module.compute(policy, params, X_table, sample_weight_table)
 
         self.labels_ = from_table(result.responses).ravel()
         if result.core_observation_indices is not None:

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/cluster/kmeans.py

@@ -34,7 +34,7 @@ from sklearn.utils import check_random_state
 
 from ..common._base import BaseEstimator as onedal_BaseEstimator
 from ..common._mixin import ClusterMixin, TransformerMixin
-from ..datatypes import _convert_to_supported, from_table, to_table
+from ..datatypes import from_table, to_table
 from ..utils import _check_array, _is_arraylike_not_scalar, _is_csr
 
 
@@ -145,7 +145,7 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
     def _get_onedal_params(self, is_csr=False, dtype=np.float32, result_options=None):
         thr = self._tol if hasattr(self, "_tol") else self.tol
         return {
-            "fptype": "float" if dtype == np.float32 else "double",
+            "fptype": dtype,
             "method": "lloyd_csr" if is_csr else "by_default",
             "seed": -1,
             "max_iteration_count": self.max_iter,
@@ -205,8 +205,7 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
             assert centers.shape[1] == X_table.column_count
             # KMeans is implemented on both CPU and GPU for Dense and CSR data
             # The original policy can be used here
-            centers = _convert_to_supported(policy, centers)
-            centers_table = to_table(centers)
+            centers_table = to_table(centers, queue=getattr(policy, "_queue", None))
         else:
             raise TypeError("Unsupported type of the `init` value")
 
@@ -240,16 +239,14 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
                 f"callable, got '{ init }' instead."
             )
 
-        centers = _convert_to_supported(policy, centers)
-        return to_table(centers)
+        return to_table(centers, queue=getattr(policy, "_queue", None))
 
     def _fit_backend(
         self, X_table, centroids_table, module, policy, dtype=np.float32, is_csr=False
     ):
         params = self._get_onedal_params(is_csr, dtype)
 
-        meta = _backend.get_table_metadata(X_table)
-        assert meta.get_npy_dtype(0) == dtype
+        assert X_table.dtype == dtype
 
         result = module.train(policy, params, X_table, centroids_table)
 
@@ -266,14 +263,11 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
         X = _check_array(
             X, dtype=[np.float64, np.float32], accept_sparse="csr", force_all_finite=False
         )
-        X = _convert_to_supported(policy, X)
-        dtype = get_dtype(X)
-        X_table = to_table(X)
+        X_table = to_table(X, queue=queue)
+        dtype = X_table.dtype
 
         self._check_params_vs_input(X_table, is_csr, policy, dtype=dtype)
 
-        params = self._get_onedal_params(is_csr, dtype)
-
         self.n_features_in_ = X_table.column_count
 
         best_model, best_n_iter = None, None
@@ -349,7 +343,8 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
 
         return self
 
-    def _get_cluster_centers(self):
+    @property
+    def cluster_centers_(self):
         if not hasattr(self, "_cluster_centers_"):
             if hasattr(self, "model_"):
                 centroids = self.model_.centroids
@@ -358,7 +353,8 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
                 raise NameError("This model have not been trained")
         return self._cluster_centers_
 
-    def _set_cluster_centers(self, cluster_centers):
+    @cluster_centers_.setter
+    def cluster_centers_(self, cluster_centers):
         self._cluster_centers_ = np.asarray(cluster_centers)
 
         self.n_iter_ = 0
@@ -371,15 +367,16 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
 
         return self
 
-    cluster_centers_ = property(_get_cluster_centers, _set_cluster_centers)
+    @cluster_centers_.deleter
+    def cluster_centers_(self):
+        del self._cluster_centers_
 
     def _predict(self, X, module, queue=None, result_options=None):
         is_csr = _is_csr(X)
 
         policy = self._get_policy(queue, X)
-        X = _convert_to_supported(policy, X)
-        X_table, dtype = to_table(X), X.dtype
-        params = self._get_onedal_params(is_csr, dtype, result_options)
+        X_table = to_table(X, queue=queue)
+        params = self._get_onedal_params(is_csr, X_table.dtype, result_options)
 
         result = module.infer(policy, params, self.model_, X_table)
 

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/cluster/kmeans_init.py

@@ -21,7 +21,7 @@ from sklearn.utils import check_random_state
 from daal4py.sklearn._utils import daal_check_version, get_dtype
 
 from ..common._base import BaseEstimator as onedal_BaseEstimator
-from ..datatypes import _convert_to_supported, from_table, to_table
+from ..datatypes import from_table, to_table
 from ..utils import _check_array
 
 if daal_check_version((2023, "P", 200)):
@@ -50,26 +50,23 @@ if daal_check_version((2023, "P", 200)):
 
         def _get_onedal_params(self, dtype=np.float32):
             return {
-                "fptype": "float" if dtype == np.float32 else "double",
+                "fptype": dtype,
                 "local_trials_count": self.local_trials_count,
                 "method": self.algorithm,
                 "seed": self.seed,
                 "cluster_count": self.cluster_count,
             }
 
-        def _get_params_and_input(self, X, policy):
+        def _get_params_and_input(self, X, queue):
             X = _check_array(
                 X,
                 dtype=[np.float64, np.float32],
                 accept_sparse="csr",
                 force_all_finite=False,
             )
-
-            X = _convert_to_supported(policy, X)
-
-            dtype = get_dtype(X)
-            params = self._get_onedal_params(dtype)
-            return (params, to_table(X), dtype)
+            X = to_table(X, queue=queue)
+            params = self._get_onedal_params(X.dtype)
+            return (params, X, X.dtype)
 
         def _compute_raw(self, X_table, module, policy, dtype=np.float32):
             params = self._get_onedal_params(dtype)
@@ -83,7 +80,7 @@ if daal_check_version((2023, "P", 200)):
             # oneDAL KMeans Init for sparse data does not have GPU support
             if issparse(X):
                 policy = self._get_policy(None, None)
-            _, X_table, dtype = self._get_params_and_input(X, policy)
+            _, X_table, dtype = self._get_params_and_input(X, queue)
 
             centroids = self._compute_raw(X_table, module, policy, dtype)
 

{scikit_learn_intelex-2025.0.1.data → scikit_learn_intelex-2025.2.0.data}/data/Lib/site-packages/onedal/common/_policy.py

@@ -48,12 +48,8 @@ class _HostInteropPolicy(_backend.host_policy):
 
 
 if _is_dpc_backend:
-    from onedal._device_offload import DummySyclQueue
 
     class _DataParallelInteropPolicy(_backend.data_parallel_policy):
         def __init__(self, queue):
             self._queue = queue
-            if isinstance(queue, DummySyclQueue):
-                super().__init__(self._queue.sycl_device.get_filter_string())
-                return
             super().__init__(self._queue)