Merge branch 'uxlfoundation:main' into dev/dlpack_integration

onedal/basic_statistics/basic_statistics.py

@@ -82,7 +82,13 @@ def fit(self, data, sample_weight=None, queue=None):
             sample_weight = _check_array(sample_weight, ensure_2d=False)
 
         is_single_dim = data.ndim == 1
-        data_table, weights_table = to_table(data, sample_weight, queue=queue)
+
+        data_table = to_table(data, queue=queue)
+        weights_table = (
+            to_table(sample_weight, queue=queue)
+            if sample_weight is not None
+            else to_table(None)
+        )
 
         dtype = data_table.dtype
         raw_result = self._compute_raw(data_table, weights_table, policy, dtype, is_csr)

onedal/basic_statistics/tests/utils.py

@@ -16,18 +16,35 @@
 
 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)),
-    "variance": (lambda X: np.var(X, axis=0), (2e-3, 2e-3)),
-    "variation": (lambda X: np.std(X, axis=0) / np.mean(X, axis=0), (5e-2, 5e-2)),
+    # 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),
-        (2e-4, 1e-7),
+        (1e-3, 1e-7),
     ),
-    "standard_deviation": (lambda X: np.std(X, axis=0), (2e-3, 2e-3)),
+    "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)),
 }

onedal/cluster/kmeans.py

@@ -246,8 +246,7 @@ def _fit_backend(
     ):
         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)
 

onedal/dal.cpp

@@ -51,7 +51,6 @@ ONEDAL_PY_INIT_MODULE(sycl);
 ONEDAL_PY_INIT_MODULE(policy);
 /* datatypes*/
 ONEDAL_PY_INIT_MODULE(table);
-ONEDAL_PY_INIT_MODULE(table_metadata);
 
 /* primitives */
 ONEDAL_PY_INIT_MODULE(get_tree);
@@ -115,7 +114,6 @@ PYBIND11_MODULE(_onedal_py_host, m) {
 #endif
     init_policy(m);
     init_table(m);
-    init_table_metadata(m);
 
     init_linear_kernel(m);
     init_rbf_kernel(m);

requirements-doc.txt

@@ -1,6 +1,6 @@
 alabaster==1.0.0
 async-generator==1.10
-attrs==24.3.0
+attrs==25.1.0
 Babel==2.16.0
 backcall==0.2.0
 beautifulsoup4==4.12.3

sklearnex/basic_statistics/basic_statistics.py

@@ -17,13 +17,15 @@
 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 IntelEstimator, PatchingConditionsChain
@@ -62,13 +64,13 @@ class BasicStatistics(IntelEstimator, BaseEstimator):
         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.
+            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.
+            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.
+            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,)
@@ -166,21 +168,50 @@ def __getattr__(self, attr):
             f"'{self.__class__.__name__}' object has no attribute '{attr}'"
         )
 
-    def _onedal_supported(self, method_name, *data):
+    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 = validate_data(self, 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])