scikit-learn-intelex 2025.4.0__py312-none-win_amd64.whl → 2025.6.0__py312-none-win_amd64.whl

{scikit_learn_intelex-2025.4.0.data → scikit_learn_intelex-2025.6.0.data}/data/Lib/site-packages/onedal/basic_statistics/incremental_basic_statistics.py

@@ -1,4 +1,3 @@
-# ==============================================================================
 # Copyright 2024 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -17,9 +16,14 @@
 import numpy as np
 
 from daal4py.sklearn._utils import get_dtype
+from onedal._device_offload import supports_queue
+from onedal.common._backend import bind_default_backend
+from onedal.utils import _sycl_queue_manager as QM
 
+from .._config import _get_config
 from ..datatypes import from_table, to_table
-from ..utils import _check_array
+from ..utils._array_api import _get_sycl_namespace
+from ..utils.validation import _check_array
 from .basic_statistics import BaseBasicStatistics
 
 
@@ -68,12 +72,22 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
     def __init__(self, result_options="all"):
         super().__init__(result_options, algorithm="by_default")
         self._reset()
+        self._queue = None
+
+    @bind_default_backend("basic_statistics")
+    def partial_compute_result(self): ...
+
+    @bind_default_backend("basic_statistics")
+    def partial_compute(self, *args, **kwargs): ...
+
+    @bind_default_backend("basic_statistics")
+    def finalize_compute(self, *args, **kwargs): ...
 
     def _reset(self):
         self._need_to_finalize = False
-        self._partial_result = self._get_backend(
-            "basic_statistics", None, "partial_compute_result"
-        )
+        self._queue = None
+        # get the _partial_result pointer from backend
+        self._partial_result = self.partial_compute_result()
 
     def __getstate__(self):
         # Since finalize_fit can't be dispatched without directly provided queue
@@ -85,6 +99,7 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
 
         return data
 
+    @supports_queue
     def partial_fit(self, X, weights=None, queue=None):
         """
         Computes partial data for basic statistics
@@ -104,40 +119,40 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
         self : object
             Returns the instance itself.
         """
+        use_raw_input = _get_config().get("use_raw_input", False) is True
+        sua_iface, _, _ = _get_sycl_namespace(X)
+
+        # All data should use the same sycl queue
+        if use_raw_input and sua_iface:
+            queue = X.sycl_queue
+
         self._queue = queue
-        policy = self._get_policy(queue, X)
 
-        X = _check_array(
-            X, dtype=[np.float64, np.float32], ensure_2d=False, force_all_finite=False
-        )
-        if weights is not None:
-            weights = _check_array(
-                weights,
-                dtype=[np.float64, np.float32],
-                ensure_2d=False,
-                force_all_finite=False,
+        if not use_raw_input:
+            X = _check_array(
+                X, dtype=[np.float64, np.float32], ensure_2d=False, force_all_finite=False
             )
+            if weights is not None:
+                weights = _check_array(
+                    weights,
+                    dtype=[np.float64, np.float32],
+                    ensure_2d=False,
+                    force_all_finite=False,
+                )
 
         if not hasattr(self, "_onedal_params"):
             dtype = get_dtype(X)
             self._onedal_params = self._get_onedal_params(False, dtype=dtype)
 
         X_table, weights_table = to_table(X, weights, queue=queue)
-        self._partial_result = self._get_backend(
-            "basic_statistics",
-            None,
-            "partial_compute",
-            policy,
-            self._onedal_params,
-            self._partial_result,
-            X_table,
-            weights_table,
+        self._partial_result = self.partial_compute(
+            self._onedal_params, self._partial_result, X_table, weights_table
         )
 
         self._need_to_finalize = True
-        return self
+        self._queue = queue
 
-    def finalize_fit(self, queue=None):
+    def finalize_fit(self):
         """
         Finalizes basic statistics computation and obtains result
         attributes from the current `_partial_result`.
@@ -153,19 +168,9 @@ class IncrementalBasicStatistics(BaseBasicStatistics):
             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,
-            )
+            with QM.manage_global_queue(self._queue):
+                result = self.finalize_compute(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())

{scikit_learn_intelex-2025.4.0.data → scikit_learn_intelex-2025.6.0.data}/data/Lib/site-packages/onedal/cluster/dbscan.py

@@ -16,15 +16,18 @@
 
 import numpy as np
 
-from daal4py.sklearn._utils import get_dtype, make2d
+from daal4py.sklearn._utils import make2d
+from onedal._device_offload import supports_queue
 
-from ..common._base import BaseEstimator
+from .._config import _get_config
+from ..common._backend import bind_default_backend
 from ..common._mixin import ClusterMixin
 from ..datatypes import from_table, to_table
-from ..utils import _check_array
+from ..utils._array_api import _get_sycl_namespace
+from ..utils.validation import _check_array
 
 
-class BaseDBSCAN(BaseEstimator, ClusterMixin):
+class DBSCAN(ClusterMixin):
     def __init__(
         self,
         eps=0.5,
@@ -46,6 +49,9 @@ class BaseDBSCAN(BaseEstimator, ClusterMixin):
         self.p = p
         self.n_jobs = n_jobs
 
+    @bind_default_backend("dbscan.clustering")
+    def compute(self, params, data_table, weights_table): ...
+
     def _get_onedal_params(self, dtype=np.float32):
         return {
             "fptype": dtype,
@@ -56,50 +62,37 @@ class BaseDBSCAN(BaseEstimator, ClusterMixin):
             "result_options": "core_observation_indices|responses",
         }
 
-    def _fit(self, X, y, sample_weight, module, queue):
-        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
+    @supports_queue
+    def fit(self, X, y=None, sample_weight=None, queue=None):
+        use_raw_input = _get_config().get("use_raw_input", False) is True
+        sua_iface, xp, _ = _get_sycl_namespace(X)
+
+        if not use_raw_input:
+            X = _check_array(X, accept_sparse="csr", dtype=[np.float64, np.float32])
+            X = make2d(X)
+        elif sua_iface is not None:
+            queue = X.sycl_queue
+
         X_table, sample_weight_table = to_table(X, sample_weight, queue=queue)
 
         params = self._get_onedal_params(X_table.dtype)
-        result = module.compute(policy, params, X_table, sample_weight_table)
+        result = self.compute(params, X_table, sample_weight_table)
 
-        self.labels_ = from_table(result.responses).ravel()
-        if result.core_observation_indices is not None:
+        self.labels_ = from_table(result.responses, sycl_queue=queue).ravel()
+        if (
+            result.core_observation_indices is not None
+            and not result.core_observation_indices.kind == "empty"
+        ):
             self.core_sample_indices_ = from_table(
-                result.core_observation_indices
+                result.core_observation_indices,
+                sycl_queue=queue,
             ).ravel()
         else:
-            self.core_sample_indices_ = np.array([], dtype=np.intc)
-        self.components_ = np.take(X, self.core_sample_indices_, axis=0)
+            # construct keyword arguments for different namespaces (dptcl takes sycl_queue)
+            kwargs = {"dtype": xp.int32}  # always the same
+            if xp is not np:
+                kwargs["sycl_queue"] = queue
+            self.core_sample_indices_ = xp.empty((0,), **kwargs)
+        self.components_ = xp.take(X, self.core_sample_indices_, axis=0)
         self.n_features_in_ = X.shape[1]
         return self
-
-
-class DBSCAN(BaseDBSCAN):
-    def __init__(
-        self,
-        eps=0.5,
-        *,
-        min_samples=5,
-        metric="euclidean",
-        metric_params=None,
-        algorithm="auto",
-        leaf_size=30,
-        p=None,
-        n_jobs=None,
-    ):
-        self.eps = eps
-        self.min_samples = min_samples
-        self.metric = metric
-        self.metric_params = metric_params
-        self.algorithm = algorithm
-        self.leaf_size = leaf_size
-        self.p = p
-        self.n_jobs = n_jobs
-
-    def fit(self, X, y=None, sample_weight=None, queue=None):
-        return super()._fit(
-            X, y, sample_weight, self._get_backend("dbscan", "clustering", None), queue
-        )

{scikit_learn_intelex-2025.4.0.data → scikit_learn_intelex-2025.6.0.data}/data/Lib/site-packages/onedal/cluster/kmeans.py

@@ -20,9 +20,11 @@ from abc import ABC
 
 import numpy as np
 
-from daal4py.sklearn._utils import daal_check_version, get_dtype
-from onedal import _backend
+from daal4py.sklearn._utils import daal_check_version
+from onedal._device_offload import supports_queue
 from onedal.basic_statistics import BasicStatistics
+from onedal.common._backend import bind_default_backend
+from onedal.utils import _sycl_queue_manager as QM
 
 if daal_check_version((2023, "P", 200)):
     from .kmeans_init import KMeansInit
@@ -32,13 +34,13 @@ from sklearn.exceptions import ConvergenceWarning
 from sklearn.metrics.pairwise import euclidean_distances
 from sklearn.utils import check_random_state
 
-from ..common._base import BaseEstimator as onedal_BaseEstimator
+from .._config import _get_config
 from ..common._mixin import ClusterMixin, TransformerMixin
 from ..datatypes import from_table, to_table
-from ..utils import _check_array, _is_arraylike_not_scalar, _is_csr
+from ..utils.validation import _check_array, _is_arraylike_not_scalar, _is_csr
 
 
-class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
+class _BaseKMeans(TransformerMixin, ClusterMixin, ABC):
     def __init__(
         self,
         n_clusters,
@@ -60,6 +62,15 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
         self.random_state = random_state
         self.n_local_trials = n_local_trials
 
+    @bind_default_backend("kmeans_common", no_policy=True)
+    def _is_same_clustering(self, labels, best_labels, n_clusters): ...
+
+    @bind_default_backend("kmeans.clustering")
+    def train(self, params, X_table, centroids_table): ...
+
+    @bind_default_backend("kmeans.clustering")
+    def infer(self, params, model, centroids_table): ...
+
     def _validate_center_shape(self, X, centers):
         """Check if centers is compatible with X and n_clusters."""
         if centers.shape[0] != self.n_clusters:
@@ -73,14 +84,19 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
                 f"match the number of features of the data {X.shape[1]}."
             )
 
-    def _get_kmeans_init(self, cluster_count, seed, algorithm):
-        return KMeansInit(cluster_count=cluster_count, seed=seed, algorithm=algorithm)
+    def _get_kmeans_init(self, cluster_count, seed, algorithm, is_csr):
+        return KMeansInit(
+            cluster_count=cluster_count,
+            seed=seed,
+            algorithm=algorithm,
+            is_csr=is_csr,
+        )
 
     # Get appropriate backend (required for SPMD)
     def _get_basic_statistics_backend(self, result_options):
         return BasicStatistics(result_options)
 
-    def _tolerance(self, X_table, rtol, is_csr, policy, dtype):
+    def _tolerance(self, X_table, rtol, is_csr, dtype):
         """Compute absolute tolerance from the relative tolerance"""
         if rtol == 0.0:
             return rtol
@@ -88,13 +104,13 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
 
         bs = self._get_basic_statistics_backend("variance")
 
-        res = bs._compute_raw(X_table, dummy, policy, dtype, is_csr)
+        res = bs._compute_raw(X_table, dummy, dtype, is_csr)
         mean_var = from_table(res["variance"]).mean()
 
         return mean_var * rtol
 
     def _check_params_vs_input(
-        self, X_table, is_csr, policy, default_n_init=10, dtype=np.float32
+        self, X_table, is_csr, default_n_init=10, dtype=np.float32
     ):
         # n_clusters
         if X_table.shape[0] < self.n_clusters:
@@ -103,7 +119,7 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
             )
 
         # tol
-        self._tol = self._tolerance(X_table, self.tol, is_csr, policy, dtype)
+        self._tol = self._tolerance(X_table, self.tol, is_csr, dtype)
 
         # n-init
         # TODO(1.4): Remove
@@ -159,42 +175,34 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
         X_table,
         init,
         random_seed,
-        policy,
         is_csr,
         dtype=np.float32,
         n_centroids=None,
     ):
         n_clusters = self.n_clusters if n_centroids is None else n_centroids
-        # Use host policy for KMeans init, only for csr data
-        # as oneDAL KMeansInit for CSR data is not implemented on GPU
-        if is_csr:
-            init_policy = self._get_policy(None, None)
-            logging.getLogger("sklearnex").info("Running Sparse KMeansInit on CPU")
-        else:
-            init_policy = policy
 
         if isinstance(init, str) and init == "k-means++":
-            if not is_csr:
-                alg = self._get_kmeans_init(
-                    cluster_count=n_clusters,
-                    seed=random_seed,
-                    algorithm="plus_plus_dense",
-                )
-            else:
-                alg = self._get_kmeans_init(
-                    cluster_count=n_clusters, seed=random_seed, algorithm="plus_plus_csr"
-                )
-            centers_table = alg.compute_raw(X_table, init_policy, dtype)
+            algorithm = "plus_plus_dense" if not is_csr else "plus_plus_csr"
+            alg = self._get_kmeans_init(
+                cluster_count=n_clusters,
+                seed=random_seed,
+                algorithm=algorithm,
+                is_csr=is_csr,
+            )
+            # We pass down the queue that was set through the KMeans.fit()
+            queue = QM.get_global_queue()
+            centers_table = alg.compute_raw(X_table, dtype, queue=queue)
         elif isinstance(init, str) and init == "random":
-            if not is_csr:
-                alg = self._get_kmeans_init(
-                    cluster_count=n_clusters, seed=random_seed, algorithm="random_dense"
-                )
-            else:
-                alg = self._get_kmeans_init(
-                    cluster_count=n_clusters, seed=random_seed, algorithm="random_csr"
-                )
-            centers_table = alg.compute_raw(X_table, init_policy, dtype)
+            algorithm = "random_dense" if not is_csr else "random_csr"
+            alg = self._get_kmeans_init(
+                cluster_count=n_clusters,
+                seed=random_seed,
+                algorithm=algorithm,
+                is_csr=is_csr,
+            )
+            # We pass down the queue that was set through the KMeans.fit()
+            queue = QM.get_global_queue()
+            centers_table = alg.compute_raw(X_table, dtype, queue=queue)
         elif _is_arraylike_not_scalar(init):
             if _is_csr(init):
                 # oneDAL KMeans only supports Dense Centroids
@@ -205,13 +213,13 @@ 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_table = to_table(centers, queue=getattr(policy, "_queue", None))
+            centers_table = to_table(centers, queue=QM.get_global_queue())
         else:
             raise TypeError("Unsupported type of the `init` value")
 
         return centers_table
 
-    def _init_centroids_sklearn(self, X, init, random_state, policy, dtype=np.float32):
+    def _init_centroids_sklearn(self, X, init, random_state, dtype=np.float32):
         # For oneDAL versions < 2023.2 or callable init,
         # using the scikit-learn implementation
         logging.getLogger("sklearnex").info("Computing KMeansInit with Stock sklearn")
@@ -239,16 +247,14 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
                 f"callable, got '{ init }' instead."
             )
 
-        return to_table(centers, queue=getattr(policy, "_queue", None))
+        return to_table(centers, queue=getattr(QM.get_global_queue(), "_queue", None))
 
-    def _fit_backend(
-        self, X_table, centroids_table, module, policy, dtype=np.float32, is_csr=False
-    ):
+    def _fit_backend(self, X_table, centroids_table, dtype=np.float32, is_csr=False):
         params = self._get_onedal_params(is_csr, dtype)
 
         assert X_table.dtype == dtype
 
-        result = module.train(policy, params, X_table, centroids_table)
+        result = self.train(params, X_table, centroids_table)
 
         return (
             result.responses,
@@ -257,16 +263,20 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
             result.iteration_count,
         )
 
-    def _fit(self, X, module, queue=None):
-        policy = self._get_policy(queue, X)
+    def _fit(self, X):
         is_csr = _is_csr(X)
-        X = _check_array(
-            X, dtype=[np.float64, np.float32], accept_sparse="csr", force_all_finite=False
-        )
-        X_table = to_table(X, queue=queue)
+
+        if _get_config()["use_raw_input"] is False:
+            X = _check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                accept_sparse="csr",
+                force_all_finite=False,
+            )
+        X_table = to_table(X, queue=QM.get_global_queue())
         dtype = X_table.dtype
 
-        self._check_params_vs_input(X_table, is_csr, policy, dtype=dtype)
+        self._check_params_vs_input(X_table, is_csr, dtype=dtype)
 
         self.n_features_in_ = X_table.column_count
 
@@ -277,12 +287,10 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
             if best_inertia is None:
                 return True
             else:
-                mod = self._get_backend("kmeans_common", None, None)
                 better_inertia = inertia < best_inertia
-                same_clusters = mod._is_same_clustering(
+                return better_inertia and not self._is_same_clustering(
                     labels, best_labels, self.n_clusters
                 )
-                return better_inertia and not same_clusters
 
         random_state = check_random_state(self.random_state)
 
@@ -300,18 +308,18 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
             if use_onedal_init:
                 random_seed = random_state.randint(np.iinfo("i").max)
                 centroids_table = self._init_centroids_onedal(
-                    X_table, init, random_seed, policy, is_csr, dtype=dtype
+                    X_table, init, random_seed, is_csr, dtype=dtype
                 )
             else:
                 centroids_table = self._init_centroids_sklearn(
-                    X, init, random_state, policy, dtype=dtype
+                    X, init, random_state, dtype=dtype
                 )
 
             if self.verbose:
                 print("Initialization complete")
 
             labels, inertia, model, n_iter = self._fit_backend(
-                X_table, centroids_table, module, policy, dtype, is_csr
+                X_table, centroids_table, dtype, is_csr
             )
 
             if self.verbose:
@@ -350,7 +358,7 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
                 centroids = self.model_.centroids
                 self._cluster_centers_ = from_table(centroids)
             else:
-                raise NameError("This model have not been trained")
+                raise NameError("This model has not been trained")
         return self._cluster_centers_
 
     @cluster_centers_.setter
@@ -360,7 +368,6 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
         self.n_iter_ = 0
         self.inertia_ = 0
 
-        self.model_ = self._get_backend("kmeans", "clustering", "model")
         self.model_.centroids = to_table(self._cluster_centers_)
         self.n_features_in_ = self.model_.centroids.column_count
         self.labels_ = np.arange(self.model_.centroids.row_count)
@@ -371,27 +378,26 @@ class _BaseKMeans(onedal_BaseEstimator, TransformerMixin, ClusterMixin, ABC):
     def cluster_centers_(self):
         del self._cluster_centers_
 
-    def _predict(self, X, module, queue=None, result_options=None):
+    def _predict(self, X, result_options=None):
         is_csr = _is_csr(X)
 
-        policy = self._get_policy(queue, X)
-        X_table = to_table(X, queue=queue)
+        X_table = to_table(X, queue=QM.get_global_queue())
         params = self._get_onedal_params(is_csr, X_table.dtype, result_options)
 
-        result = module.infer(policy, params, self.model_, X_table)
+        result = self.infer(params, self.model_, X_table)
 
-        if (
-            result_options == "compute_exact_objective_function"
-        ):  # This is only set for score function
-            return result.objective_function_value * (-1)
+        if result_options == "compute_exact_objective_function":
+            # This is only set for score function
+            return -1 * result.objective_function_value
         else:
             return from_table(result.responses).ravel()
 
-    def _score(self, X, module, queue=None):
+    def _score(self, X):
         result_options = "compute_exact_objective_function"
 
         return self._predict(
-            X, self._get_backend("kmeans", "clustering", None), queue, result_options
+            X,
+            result_options,
         )
 
     def _transform(self, X):
@@ -426,9 +432,11 @@ class KMeans(_BaseKMeans):
         self.algorithm = algorithm
         assert self.algorithm == "lloyd"
 
+    @supports_queue
     def fit(self, X, y=None, queue=None):
-        return super()._fit(X, self._get_backend("kmeans", "clustering", None), queue)
+        return self._fit(X)
 
+    @supports_queue
     def predict(self, X, queue=None):
         """Predict the closest cluster each sample in X belongs to.
 
@@ -446,7 +454,7 @@ class KMeans(_BaseKMeans):
         labels : ndarray of shape (n_samples,)
             Index of the cluster each sample belongs to.
         """
-        return super()._predict(X, self._get_backend("kmeans", "clustering", None), queue)
+        return self._predict(X)
 
     def fit_predict(self, X, y=None, queue=None):
         """Compute cluster centers and predict cluster index for each sample.
@@ -509,6 +517,7 @@ class KMeans(_BaseKMeans):
 
         return self._transform(X)
 
+    @supports_queue
     def score(self, X, queue=None):
         """Opposite of the value of X on the K-means objective.
 
@@ -522,7 +531,7 @@ class KMeans(_BaseKMeans):
         score: float
             Opposite of the value of X on the K-means objective.
         """
-        return super()._score(X, self._get_backend("kmeans", "clustering", None), queue)
+        return self._score(X)
 
 
 def k_means(