scikit-learn-intelex 2024.5.0__py39-none-manylinux1_x86_64.whl → 2024.6.0__py39-none-manylinux1_x86_64.whl

{scikit_learn_intelex-2024.5.0.dist-info → scikit_learn_intelex-2024.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scikit-learn-intelex
-Version: 2024.5.0
+Version: 2024.6.0
 Summary: Intel(R) Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application.
 Home-page: https://github.com/intel/scikit-learn-intelex
 Author: Intel Corporation
@@ -31,7 +31,7 @@ Classifier: Topic :: Software Development
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: daal4py (==2024.5.0)
+Requires-Dist: daal4py (==2024.6.0)
 Requires-Dist: scikit-learn (>=0.22)
 
 

{scikit_learn_intelex-2024.5.0.dist-info → scikit_learn_intelex-2024.6.0.dist-info}/RECORD

@@ -3,38 +3,38 @@ sklearnex/__main__.py,sha256=Le9BJq6aLEGSSoZwJLsOADxsV89ynBfA8BcoJHk9F24,1921
 sklearnex/_config.py,sha256=6WS3UuS4-0DxIJyGn7yQMosj-mGkLybLQrg3W7dED5o,3928
 sklearnex/_device_offload.py,sha256=m8Hspffwx6Tn3f-OYLqwf5cUCKq4vZ3aSLmhY92qp08,8876
 sklearnex/_utils.py,sha256=EV4jC3plVdndsgrfPBsJZTzggrRdYWLwOpoIRWtTXt4,3812
-sklearnex/conftest.py,sha256=ZvcfQljZNBa3zlE1iITvuacHblugVtK6X80LwNXrnWI,2130
-sklearnex/dispatcher.py,sha256=FtPF7nezu67wKhG33FAxJCWK8jCj65G87k7AITOIxtw,15390
+sklearnex/conftest.py,sha256=ODuhlscC0HNGXiA8olEfHTDULzjevqG9_sn0yMGRkHg,2376
+sklearnex/dispatcher.py,sha256=XElvy9dDJ8XNOci8asKUnWXJpr6JROXHehdWBc_od3g,15876
 sklearnex/basic_statistics/__init__.py,sha256=-lNh54F2FO0BuHDBLjhW7zp3yBcgFZ-DrXHj2H5hLXE,920
 sklearnex/basic_statistics/basic_statistics.py,sha256=j5jBZ3DgXjoyjCBEFfYQHyl3LgLXEWWFnNHwInThdZw,796
 sklearnex/basic_statistics/incremental_basic_statistics.py,sha256=NNWF9zdxBz2jT7dzt5hL6HRvjQIGosvViQE3KJMF1L4,10048
 sklearnex/basic_statistics/tests/test_incremental_basic_statistics.py,sha256=zTb_04DBGYSfwcpRaP0OJzi4Z6jz4jqV_kDRAp1x-no,14926
 sklearnex/cluster/__init__.py,sha256=TsDzdbKzEubaP86iY8a7mSW0ZQzgjzGYuPkhc5lZmlQ,853
-sklearnex/cluster/dbscan.py,sha256=JJaNVhV4dVK0xte9xzQpCAka80xVu3M7_SzmvD3k-EY,6736
+sklearnex/cluster/dbscan.py,sha256=EiAMRZq53KhGQ_d4_c867-frgG-pz8S1J88vd8hLAn4,6844
 sklearnex/cluster/k_means.py,sha256=1QKcFUQcnycu8kSD8uYSaDIuedHbxZsV_gvUfcEwVAM,806
-sklearnex/cluster/tests/test_dbscan.py,sha256=AgFoKwXFVyLKLvEtJVs0qlbBs1Ci3PcRft7f-6_ENOU,1464
+sklearnex/cluster/tests/test_dbscan.py,sha256=JYpwyuPkGQHdbE_IPbQv4qNj7clMm4UPdz_lrpRzKXE,1504
 sklearnex/cluster/tests/test_kmeans.py,sha256=H3a9NSHRRSASo0Eceo44Kjq6GwEoMqMzcubaNt1s1QQ,1213
 sklearnex/covariance/__init__.py,sha256=_c86wiKDGBH50ofN-_tn7lO4M2YVEWO5AHhJIfimUDk,859
 sklearnex/covariance/incremental_covariance.py,sha256=0MvYlGnmuZ8_kRBaIkMzg3RyGdcSMjO-I7dhw2VpTsg,11010
 sklearnex/covariance/tests/test_incremental_covariance.py,sha256=ZbEfup4ICm278RW4hZIHPciOiqhFhx_k1l3lpnw0M6s,6763
 sklearnex/decomposition/__init__.py,sha256=RJBYDWyvnn5DA-j5r4IqVdXLp6H4mdPySsSjnXhlv-U,805
 sklearnex/decomposition/pca.py,sha256=JkyxsSz_8vVGUjJrfxyAwwY1Yf2uht-qxwOisEHv9mY,15550
-sklearnex/decomposition/tests/test_pca.py,sha256=-3r3QwALcZregRq-MX8aUFSVaHu0D2ffGt-V5JOnNgE,2223
+sklearnex/decomposition/tests/test_pca.py,sha256=EoCgpSojE2S2e7hOUwW0Bh3vVGTUywawAhU7ThVAlW0,2319
 sklearnex/doc/third-party-programs.txt,sha256=qA1XbOqYkMRnp29p8VxXjfcH0kHE8NSO5s2heea83-8,21773
 sklearnex/ensemble/__init__.py,sha256=2xB2KfG7l7uJv0p3kfVhrs4KLM174SCsigZhYqwSYAA,1035
-sklearnex/ensemble/_forest.py,sha256=6vyyQvg60Df-0v9ITIgwrSj2J1RQvGPa2-8Xs5_qXrQ,70003
-sklearnex/ensemble/tests/test_forest.py,sha256=r1GSPQuVVuWYoNB3ZLiGKfMSwq3lp5i6k-Rgr7InonQ,4456
+sklearnex/ensemble/_forest.py,sha256=tElkh0jezrp9QK2T3_kDCgye6El9W6hOlJepaeMIOM4,73494
+sklearnex/ensemble/tests/test_forest.py,sha256=UXj6pfSuOr8wm_KZciyE9zt6hh-we1U8s0XU9bShqHI,4735
 sklearnex/glob/__main__.py,sha256=--FAjkhh5E6a1TFOGu6_BM3MHe78jP8oSpl0xKiRtTI,2531
-sklearnex/glob/dispatcher.py,sha256=IEEPhAOCVzC2JDFvYtijbiPAbaUY5RrCAhFLRjMMe1w,3018
+sklearnex/glob/dispatcher.py,sha256=o6XKGKM3M91F7FlXBOt1IhnpWQK4R1VY2WS-0uIghcw,3906
 sklearnex/linear_model/__init__.py,sha256=mzZ0EaBhDH66ETNt2vylznSoZbCYexgL2qE_jKppYYc,1144
 sklearnex/linear_model/coordinate_descent.py,sha256=uZOHIKfFlHoMlNXZCh2MAnZE30fRZlmtcF7UsZQ3Vq4,822
-sklearnex/linear_model/incremental_linear.py,sha256=26XywxAyyTM6kUCJsuayRtCijKKmSfckiNjrkn5VzHc,13021
-sklearnex/linear_model/linear.py,sha256=2VPcB7SNWlZKK1iHeAQagM2OxBPGFKK4FlY8TjBSZ3U,11162
+sklearnex/linear_model/incremental_linear.py,sha256=iDad4Z4xMDImvG-Jgtt0Hz3Qp9MVhSi-IjUPcV0Y_ks,16101
+sklearnex/linear_model/linear.py,sha256=SUoFFvpl4Eb308sYBp6FNbZls-4G69eg8wSeuPs0oAg,11765
 sklearnex/linear_model/logistic_path.py,sha256=Nq3JPXSzE4bjamnP3gGQtsMKks2v7s6bSiuYRnFqrRw,849
-sklearnex/linear_model/logistic_regression.py,sha256=6TRaDJ8nIHxjofIfUvmeJOP9_EwmUgVKKK1sxe9vS5A,14171
+sklearnex/linear_model/logistic_regression.py,sha256=jmsNs7MYHm-PncuG20m_TSqXbM5jXx_vHsoH-hReEFQ,14271
 sklearnex/linear_model/ridge.py,sha256=0oxlM5McYYvl0KxK9OIGJKM6lOADuFSPTdfx-efJNTI,810
-sklearnex/linear_model/tests/test_incremental_linear.py,sha256=AfebVKne6fb36Vyr8uPSKYWa9upfPHYZUURHa4Q-mPs,7303
-sklearnex/linear_model/tests/test_linear.py,sha256=nw5EqvF4sAy1dFBQobX0blvHUxZieDbt3wztQcuHrME,4315
+sklearnex/linear_model/tests/test_incremental_linear.py,sha256=e0ZADjB0myq1QcdwYxlVYl6tGFs4tVZIfBoV1xkdFuw,7337
+sklearnex/linear_model/tests/test_linear.py,sha256=9YQgyYmcGSL2rEgIfhZZxTIlj5v-Z6-ygBqYR6ly3oE,4357
 sklearnex/linear_model/tests/test_logreg.py,sha256=mUYDwTDUekERlzxjnVeOeCUcNv4KJAXdTIiELZNSaDc,3283
 sklearnex/manifold/__init__.py,sha256=3FU5fY1YvHAyNeSlUHsZfPnAbvlAUtZpum0Obmok2KE,809
 sklearnex/manifold/t_sne.py,sha256=U6F_dGB6taVuEJvTnVBWD-sri3x3m0Khu3HI4wXidhg,805
@@ -50,16 +50,19 @@ sklearnex/neighbors/__init__.py,sha256=_GMJ2L-6YechRYI2fOFwHjy0kebUncE81z4FmdXUl
 sklearnex/neighbors/_lof.py,sha256=5MPkWIb6FS55Q8xWzgc22Ec_PsouuN94SPovt-vsBGE,8648
 sklearnex/neighbors/common.py,sha256=8DxDoYtXtEM4RNoMCimpTVSDOOxUIJlNVOQvBXBhkd4,10875
 sklearnex/neighbors/knn_classification.py,sha256=ONoBbtwb5xoVLcpg5COpRNu1ZBOQ2EDh03RzbWDy5yo,8537
-sklearnex/neighbors/knn_regression.py,sha256=YBjvh6h56OaJHSZNGq8ZV8lsB-XpSWduEcVeHRuPorQ,6692
+sklearnex/neighbors/knn_regression.py,sha256=ge8VAMa8aJ58M5ccN5NMILFHuRYtYKzyoLF8fxxgGfo,7462
 sklearnex/neighbors/knn_unsupervised.py,sha256=qkj-hSEq8QetYsWlofnik3PpFvo1iBUbIOhywo8wFWk,5362
 sklearnex/neighbors/tests/test_neighbors.py,sha256=yAlMnLt9GrdT6Ceph5B7iFuMJXpDURiHWTE99oO8EDw,3417
-sklearnex/preview/__init__.py,sha256=OXC_k2kudA13rVesXb5ZlEC7_mKUS7uUra_BR-Tin30,780
+sklearnex/preview/__init__.py,sha256=1QcbV6xCSP7QCXRxYLVPc_b4lxE0cQiyTrMm4xOnosM,797
 sklearnex/preview/cluster/__init__.py,sha256=FONzOuTGAb5NwdfFhLco99P_VccRk9NBkDHU3EKuAIs,794
 sklearnex/preview/cluster/_common.py,sha256=bgpzijxgyrAtdNCCHyCNsZ-N70KQYNwMuoCTNdUna6o,2718
 sklearnex/preview/cluster/k_means.py,sha256=RdF9mwgvZ1xgyeLhCQA2WaPvPsS1ndktXXcaNj6S460,10464
 sklearnex/preview/covariance/__init__.py,sha256=DPYTk8lwcVphtwU8J3CyUYH8Uz6Zr0Uz4S6nn-RY5iM,825
 sklearnex/preview/covariance/covariance.py,sha256=NjRTWLie7UbpfN16wGSxJSRHRhUnvTn03cPPc8PpPd8,5131
 sklearnex/preview/covariance/tests/test_covariance.py,sha256=FOgvhJxFQo9sNG4Uo-ebuw3ZXJ9tSxdk8qKm0ZJzTdc,2487
+sklearnex/preview/decomposition/__init__.py,sha256=9VcJPWKgSrWDFEXUY6ZCpAT2XGbOVA4a1j_XgfJBnTM,839
+sklearnex/preview/decomposition/incremental_pca.py,sha256=SsY1-AQt0mFTJGP5yzVxZvopNz2tSeXUO9p9c_3uVus,7820
+sklearnex/preview/decomposition/tests/test_incremental_pca.py,sha256=tsAlM18nzfIQxic7Ry986Ue0ovUdbopWFNckqQLK5xU,10776
 sklearnex/spmd/__init__.py,sha256=ChQy2kEWlo4KGvs0RnbPoPEVhdgl8URV099B1rZtF5Y,889
 sklearnex/spmd/basic_statistics/__init__.py,sha256=NA5RGlwcp27UEeCgz0ngzYYd3MAIRpxlTy86uhM2-RE,821
 sklearnex/spmd/basic_statistics/basic_statistics.py,sha256=_dQ9mhVYxeuChATEpAmHpXDpgW3YvtK1qrG-kLr2MtI,886
@@ -78,27 +81,28 @@ sklearnex/spmd/linear_model/logistic_regression.py,sha256=q_HkfWcg0RgFbk2t9FeV0Z
 sklearnex/spmd/neighbors/__init__.py,sha256=S16sH8N_18LN_8AgC_wGK5EDSNyuN-F-gI6GVlaiWVE,906
 sklearnex/spmd/neighbors/neighbors.py,sha256=SiKAS_RVt34MUcGytBS5pHnI_5vFNxJn8jqt1MOhDh8,940
 sklearnex/svm/__init__.py,sha256=f3e4ZFwZfx6MsXsn94VK1xVm6mWKT5XCiHczo6zNyAQ,1057
-sklearnex/svm/_common.py,sha256=52csEWTYWEVgUVWUm3RjX1VD_5VyyawXBvc7lBBp5qY,7010
-sklearnex/svm/nusvc.py,sha256=J4F_Tm9oYC-WK1Nf_CNqSnvuYEEZZ9xa3VY-x0G_2cw,9871
-sklearnex/svm/nusvr.py,sha256=ZFBnQzMgD4aRSk3BRIxwKfwErVyDJnNoR7vrIMm5WLk,3655
-sklearnex/svm/svc.py,sha256=u9wQ8dsvQvO4XP_3JSfYFBNJcuDyv3HVG5NY6jZqhZk,11125
-sklearnex/svm/svr.py,sha256=ldNWehrU4vgqX_0T8splmBjPsQln7w_h8L4XNpIgP6A,3655
+sklearnex/svm/_common.py,sha256=wH4LT6QIoe7xM3btaUBC7fpKJcqKLfNHJj16rAaEZ1k,12797
+sklearnex/svm/nusvc.py,sha256=-SfYz2bUMLaosYg_qeTBYf1Ra-bFuGmI62xIerf3XeE,11262
+sklearnex/svm/nusvr.py,sha256=9nbRaPCoDQ5SBGH_jLgcaX_PWGDh667w-gW5X2YbHBM,4764
+sklearnex/svm/svc.py,sha256=fZ9oVpKkgH5OYBXo4mPdZ-8cP07hSzPHoJsyItpXmcQ,12470
+sklearnex/svm/svr.py,sha256=NIWVUu7NjV4Fe4L-Y4vIqd3KePFdMJ1-jupeH4ZvNsg,4733
 sklearnex/svm/tests/test_svm.py,sha256=Ru-aGNGCsRJts7SEEYbnKcVqUx-DqPyUtw-hEoMVpW8,4190
-sklearnex/tests/_utils.py,sha256=bQR9PJ3GZzp3eZD35pLE8y-ts2a1VGq9ZbwFzh0e5q8,5598
+sklearnex/tests/_utils.py,sha256=zRNpggSrZs4H0L-__UuiYRPm_ASqrqWm226ZQzlBQ7I,6252
+sklearnex/tests/test_common.py,sha256=MYx0y7oomArxWu9qe2zNs7YL-ScPGFnzvw8PZ1or04A,1813
 sklearnex/tests/test_config.py,sha256=SnSJjxAAysISDyC3bYKSJiRHStkB9X-yjLeF11LpRog,1372
-sklearnex/tests/test_memory_usage.py,sha256=nNVYn6S05q_J-eepNeGDfUKvzZCcHpCnm5jaZhCoPB8,7540
+sklearnex/tests/test_memory_usage.py,sha256=FTtQgaa7p5ScDGscB93LkpU4B3DzfqnVMi84b2vSL30,10957
 sklearnex/tests/test_monkeypatch.py,sha256=_9s_4jFvbttOf8uCuBrS4rn_AzQdFlKyRlthnGacUcU,9669
 sklearnex/tests/test_n_jobs_support.py,sha256=NziTP4GwZEDoBe1CDvhHZnp8JpwjYQmCNvXEDfS7Wo4,4313
 sklearnex/tests/test_parallel.py,sha256=0zzlh2VJZWcHw5W4QSUthtAygOb6K0Bg1ekNsrdGJQE,1770
-sklearnex/tests/test_patching.py,sha256=mDTw-tzO8yibUeRp_ZE560fXnwfnsSq-JAHmXihx1hI,14920
-sklearnex/tests/test_run_to_run_stability_tests.py,sha256=DFKMdIGyzGOBbi7A-o3zPZHLPAIDGIfLRxWzKIYa4hw,14019
+sklearnex/tests/test_patching.py,sha256=LKi-x0ELu_y5HEa86UYhDzOalJphiEBtEe5own89PEs,14782
+sklearnex/tests/test_run_to_run_stability.py,sha256=49WnqTcAaGGa5eP7RBwEePvr_dA9hfYsCK4-pZA8OPw,9984
 sklearnex/utils/__init__.py,sha256=FFlM8zc2qnSdPYpLjSt4Ma_9FjC8qk8wXJa-5B8hCs0,898
-sklearnex/utils/_namespace.py,sha256=lWzvzcObxq350A-Ms8JyTbaQStR8rgH4DgQYhWruHL4,3166
+sklearnex/utils/_namespace.py,sha256=ohr8gOgEFgrccLecllMVYQPqbqqyye9uT-cWLtyxHFs,3167
 sklearnex/utils/parallel.py,sha256=VBcS-KUdyq7XpJUN6ygmNjyWtYLroghbvCxQ8nVU3YI,2085
 sklearnex/utils/validation.py,sha256=fjfhQiKnBQnD7LCBlacMyvsrhGnlMLRXk5Q69uoZIP4,827
 sklearnex/utils/tests/test_finite.py,sha256=AzJRY71X0VvDUicUI8Ey9Le6_yKp5O-3ZikhDVJNWms,2943
-scikit_learn_intelex-2024.5.0.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
-scikit_learn_intelex-2024.5.0.dist-info/METADATA,sha256=dvtXeQgf40S23qHORmZUGIJaFgl0KF5sqtvHueNvq3Y,12449
-scikit_learn_intelex-2024.5.0.dist-info/WHEEL,sha256=rxMEw7jRW2YnjujGudhK0a-ZC6J_VMIRJJ7uhbmewD4,107
-scikit_learn_intelex-2024.5.0.dist-info/top_level.txt,sha256=kzKChSWGJEYFmdj5PwE63HNuP_PVOhWfD32ytH9rL9Q,10
-scikit_learn_intelex-2024.5.0.dist-info/RECORD,,
+scikit_learn_intelex-2024.6.0.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
+scikit_learn_intelex-2024.6.0.dist-info/METADATA,sha256=HAyHGB0wdXHb5FaRHSiitrRZgs5yDtXkjfAigVtQJxA,12449
+scikit_learn_intelex-2024.6.0.dist-info/WHEEL,sha256=rxMEw7jRW2YnjujGudhK0a-ZC6J_VMIRJJ7uhbmewD4,107
+scikit_learn_intelex-2024.6.0.dist-info/top_level.txt,sha256=kzKChSWGJEYFmdj5PwE63HNuP_PVOhWfD32ytH9rL9Q,10
+scikit_learn_intelex-2024.6.0.dist-info/RECORD,,

sklearnex/cluster/dbscan.py

@@ -85,6 +85,9 @@ class DBSCAN(sklearn_DBSCAN, BaseDBSCAN):
         self.n_jobs = n_jobs
 
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, force_all_finite=False)
+
         onedal_params = {
             "eps": self.eps,
             "min_samples": self.min_samples,

sklearnex/cluster/tests/test_dbscan.py

@@ -18,16 +18,18 @@ import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
 
-# TODO:
-# adding this parameterized testing
-# somehow breaks other test with preview module patch:
-# sklearnex/tests/test_monkeypatch.py::test_preview_namespace.
-# @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
-def test_sklearnex_import_dbscan():
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_dbscan(dataframe, queue):
     from sklearnex.cluster import DBSCAN
 
     X = np.array([[1, 2], [2, 2], [2, 3], [8, 7], [8, 8], [25, 80]])
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
     dbscan = DBSCAN(eps=3, min_samples=2).fit(X)
     assert "sklearnex" in dbscan.__module__
 

sklearnex/conftest.py

@@ -19,7 +19,8 @@ import logging
 
 import pytest
 
-from sklearnex import patch_sklearn, unpatch_sklearn
+from daal4py.sklearn._utils import sklearn_check_version
+from sklearnex import config_context, patch_sklearn, unpatch_sklearn
 
 
 def pytest_configure(config):
@@ -61,3 +62,12 @@ def with_sklearnex():
     patch_sklearn()
     yield
     unpatch_sklearn()
+
+
+@pytest.fixture
+def with_array_api():
+    if sklearn_check_version("1.2"):
+        with config_context(array_api_dispatch=True):
+            yield
+    else:
+        yield

sklearnex/decomposition/tests/test_pca.py

@@ -51,6 +51,8 @@ def test_sklearnex_import(dataframe, queue):
         assert hasattr(pca, "_onedal_estimator")
     else:
         assert "daal4py" in pca.__module__
+
+    tol = 1e-5 if _as_numpy(X_transformed).dtype == np.float32 else 1e-7
     assert_allclose([6.30061232, 0.54980396], _as_numpy(pca.singular_values_))
-    assert_allclose(X_transformed_expected, _as_numpy(X_transformed))
-    assert_allclose(X_transformed_expected, _as_numpy(X_fit_transformed))
+    assert_allclose(X_transformed_expected, _as_numpy(X_transformed), rtol=tol)
+    assert_allclose(X_transformed_expected, _as_numpy(X_fit_transformed), rtol=tol)

sklearnex/dispatcher.py

@@ -45,12 +45,14 @@ def get_patch_map_core(preview=False):
 
         if _is_new_patching_available():
             import sklearn.covariance as covariance_module
+            import sklearn.decomposition as decomposition_module
 
             # Preview classes for patching
             from .preview.cluster import KMeans as KMeans_sklearnex
             from .preview.covariance import (
                 EmpiricalCovariance as EmpiricalCovariance_sklearnex,
             )
+            from .preview.decomposition import IncrementalPCA as IncrementalPCA_sklearnex
 
             # Since the state of the lru_cache without preview cannot be
             # guaranteed to not have already enabled sklearnex algorithms
@@ -62,7 +64,7 @@ def get_patch_map_core(preview=False):
             sklearn_obj = mapping["kmeans"][0][1]
             mapping.pop("kmeans")
             mapping["kmeans"] = [
-                [(cluster_module, "kmeans", KMeans_sklearnex), sklearn_obj]
+                [(cluster_module, "KMeans", KMeans_sklearnex), sklearn_obj]
             ]
 
             # Covariance
@@ -76,6 +78,18 @@ def get_patch_map_core(preview=False):
                     None,
                 ]
             ]
+
+            # IncrementalPCA
+            mapping["incrementalpca"] = [
+                [
+                    (
+                        decomposition_module,
+                        "IncrementalPCA",
+                        IncrementalPCA_sklearnex,
+                    ),
+                    None,
+                ]
+            ]
         return mapping
 
     from daal4py.sklearn.monkeypatch.dispatcher import _get_map_of_algorithms

sklearnex/ensemble/_forest.py

@@ -29,7 +29,7 @@ from sklearn.ensemble._forest import ForestClassifier as sklearn_ForestClassifie
 from sklearn.ensemble._forest import ForestRegressor as sklearn_ForestRegressor
 from sklearn.ensemble._forest import _get_n_samples_bootstrap
 from sklearn.exceptions import DataConversionWarning
-from sklearn.metrics import accuracy_score
+from sklearn.metrics import accuracy_score, r2_score
 from sklearn.tree import (
     DecisionTreeClassifier,
     DecisionTreeRegressor,
@@ -38,7 +38,7 @@ from sklearn.tree import (
 )
 from sklearn.tree._tree import Tree
 from sklearn.utils import check_random_state, deprecated
-from sklearn.utils.validation import check_array, check_is_fitted
+from sklearn.utils.validation import check_array, check_is_fitted, check_X_y
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import (
@@ -74,6 +74,7 @@ class BaseForest(ABC):
             accept_sparse=False,
             dtype=[np.float64, np.float32],
             force_all_finite=False,
+            ensure_2d=True,
         )
 
         if sample_weight is not None:
@@ -97,8 +98,6 @@ class BaseForest(ABC):
 
         y, expanded_class_weight = self._validate_y_class_weight(y)
 
-        self.n_features_in_ = X.shape[1]
-
         if expanded_class_weight is not None:
             if sample_weight is not None:
                 sample_weight = sample_weight * expanded_class_weight
@@ -114,7 +113,9 @@ class BaseForest(ABC):
             "min_samples_split": self.min_samples_split,
             "min_samples_leaf": self.min_samples_leaf,
             "min_weight_fraction_leaf": self.min_weight_fraction_leaf,
-            "max_features": self.max_features,
+            "max_features": self._to_absolute_max_features(
+                self.max_features, self.n_features_in_
+            ),
             "max_leaf_nodes": self.max_leaf_nodes,
             "min_impurity_decrease": self.min_impurity_decrease,
             "bootstrap": self.bootstrap,
@@ -174,6 +175,45 @@ class BaseForest(ABC):
         self._validate_estimator()
         return self
 
+    def _to_absolute_max_features(self, max_features, n_features):
+        if max_features is None:
+            return n_features
+        if isinstance(max_features, str):
+            if max_features == "auto":
+                if not sklearn_check_version("1.3"):
+                    if sklearn_check_version("1.1"):
+                        warnings.warn(
+                            "`max_features='auto'` has been deprecated in 1.1 "
+                            "and will be removed in 1.3. To keep the past behaviour, "
+                            "explicitly set `max_features=1.0` or remove this "
+                            "parameter as it is also the default value for "
+                            "RandomForestRegressors and ExtraTreesRegressors.",
+                            FutureWarning,
+                        )
+                    return (
+                        max(1, int(np.sqrt(n_features)))
+                        if isinstance(self, ForestClassifier)
+                        else n_features
+                    )
+            if max_features == "sqrt":
+                return max(1, int(np.sqrt(n_features)))
+            if max_features == "log2":
+                return max(1, int(np.log2(n_features)))
+            allowed_string_values = (
+                '"sqrt" or "log2"'
+                if sklearn_check_version("1.3")
+                else '"auto", "sqrt" or "log2"'
+            )
+            raise ValueError(
+                "Invalid value for max_features. Allowed string "
+                f"values are {allowed_string_values}."
+            )
+        if isinstance(max_features, (numbers.Integral, np.integer)):
+            return max_features
+        if max_features > 0.0:
+            return max(1, int(max_features * n_features))
+        return 0
+
     def _check_parameters(self):
         if isinstance(self.min_samples_leaf, numbers.Integral):
             if not 1 <= self.min_samples_leaf:
@@ -518,7 +558,7 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
             )
 
         if patching_status.get_status():
-            X, y = self._validate_data(
+            X, y = check_X_y(
                 X,
                 y,
                 multi_output=True,
@@ -738,6 +778,10 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
+                    (
+                        not self.oob_score,
+                        "oob_scores using r2 or accuracy not implemented.",
+                    ),
                     (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
@@ -780,24 +824,43 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
         check_is_fitted(self, "_onedal_estimator")
 
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
-
-        X = check_array(
-            X,
-            dtype=[np.float64, np.float32],
-            force_all_finite=False,
-        )  # Warning, order of dtype matters
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )  # Warning, order of dtype matters
+            self._check_n_features(X, reset=False)
 
         res = self._onedal_estimator.predict(X, queue=queue)
         return np.take(self.classes_, res.ravel().astype(np.int64, casting="unsafe"))
 
     def _onedal_predict_proba(self, X, queue=None):
-        X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=False)
         check_is_fitted(self, "_onedal_estimator")
 
-        self._check_n_features(X, reset=False)
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )
+        else:
+            X = check_array(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )  # Warning, order of dtype matters
+            self._check_n_features(X, reset=False)
+
         return self._onedal_estimator.predict_proba(X, queue=queue)
 
     def _onedal_score(self, X, y, sample_weight=None, queue=None):
@@ -914,7 +977,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
             )
 
         if patching_status.get_status():
-            X, y = self._validate_data(
+            X, y = check_X_y(
                 X,
                 y,
                 multi_output=True,
@@ -996,7 +1059,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
                 ]
             )
 
-        elif method_name == "predict":
+        elif method_name in ["predict", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -1046,11 +1109,12 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
+                    (not self.oob_score, "oob_score value is not sklearn conformant."),
                     (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
 
-        elif method_name == "predict":
+        elif method_name in ["predict", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -1083,16 +1147,28 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
         return patching_status
 
     def _onedal_predict(self, X, queue=None):
-        X = check_array(
-            X, dtype=[np.float64, np.float32], force_all_finite=False
-        )  # Warning, order of dtype matters
         check_is_fitted(self, "_onedal_estimator")
 
         if sklearn_check_version("1.0"):
-            self._check_feature_names(X, reset=False)
+            X = self._validate_data(
+                X,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+                reset=False,
+                ensure_2d=True,
+            )  # Warning, order of dtype matters
+        else:
+            X = check_array(
+                X, dtype=[np.float64, np.float32], force_all_finite=False
+            )  # Warning, order of dtype matters
 
         return self._onedal_estimator.predict(X, queue=queue)
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return r2_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
     def fit(self, X, y, sample_weight=None):
         dispatch(
             self,
@@ -1119,8 +1195,23 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
             X,
         )
 
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_ForestRegressor.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     fit.__doc__ = sklearn_ForestRegressor.fit.__doc__
     predict.__doc__ = sklearn_ForestRegressor.predict.__doc__
+    score.__doc__ = sklearn_ForestRegressor.score.__doc__
 
 
 @control_n_jobs(decorated_methods=["fit", "predict", "predict_proba", "score"])

sklearnex/ensemble/tests/test_forest.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 # ===============================================================================
 
+import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 from sklearn.datasets import make_classification, make_regression
@@ -45,7 +46,10 @@ def test_sklearnex_import_rf_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix RF regressor predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_rf_regression(dataframe, queue):
     from sklearnex.ensemble import RandomForestRegressor
 
@@ -65,7 +69,10 @@ def test_sklearnex_import_rf_regression(dataframe, queue):
             assert_allclose([-6.839], pred, atol=1e-2)
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix ET classifier predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_et_classifier(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesClassifier
 
@@ -86,7 +93,10 @@ def test_sklearnex_import_et_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+# TODO: fix ET regressor predict for the GPU sycl_queue.
+@pytest.mark.parametrize(
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
+)
 def test_sklearnex_import_et_regression(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesRegressor
 

sklearnex/glob/dispatcher.py

@@ -17,18 +17,32 @@
 
 def get_patch_str(name=None, verbose=True):
     return f"""try:
+    # TEMP. FIX: sklearnex.patch_sklearn imports sklearn beforehand
+    # when it didn't initialized _threadpool_controller required for
+    # pairwise distances dispatching during imports.
+    # Manually setting and deleting _threadpool_controller during patch fixes it.
+    import sklearn
+    from threadpoolctl import ThreadpoolController
+    sklearn._threadpool_controller = ThreadpoolController()
     from sklearnex import patch_sklearn
     patch_sklearn(name={str(name)}, verbose={str(verbose)})
-    del patch_sklearn
+    del patch_sklearn, sklearn._threadpool_controller
 except ImportError:
     pass"""
 
 
 def get_patch_str_re():
     return r"""\ntry:
+    \# TEMP. FIX: sklearnex.patch_sklearn imports sklearn beforehand
+    \# when it didn't initialized _threadpool_controller required for
+    \# pairwise distances dispatching during imports.
+    \# Manually setting and deleting _threadpool_controller during patch fixes it.
+    import sklearn
+    from threadpoolctl import ThreadpoolController
+    sklearn._threadpool_controller = ThreadpoolController\(\)
     from sklearnex import patch_sklearn
     patch_sklearn\(name=.*, verbose=.*\)
-    del patch_sklearn
+    del patch_sklearn, sklearn._threadpool_controller
 except ImportError:
     pass\n"""