scikit-learn-intelex 2024.1.0__py310-none-manylinux1_x86_64.whl → 2024.2.0__py310-none-manylinux1_x86_64.whl

{scikit_learn_intelex-2024.1.0.dist-info → scikit_learn_intelex-2024.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scikit-learn-intelex
-Version: 2024.1.0
+Version: 2024.2.0
 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 (==2024.1.0)
+Requires-Dist: daal4py (==2024.2.0)
 Requires-Dist: scikit-learn (>=0.22)
 
 

{scikit_learn_intelex-2024.1.0.dist-info → scikit_learn_intelex-2024.2.0.dist-info}/RECORD

@@ -3,30 +3,34 @@ sklearnex/__main__.py,sha256=Le9BJq6aLEGSSoZwJLsOADxsV89ynBfA8BcoJHk9F24,1921
 sklearnex/_config.py,sha256=6WS3UuS4-0DxIJyGn7yQMosj-mGkLybLQrg3W7dED5o,3928
 sklearnex/_device_offload.py,sha256=J0tZqj6tfvIFonWR01PadtTLgloQk_QEfXeCoqEvJlk,7710
 sklearnex/_utils.py,sha256=EV4jC3plVdndsgrfPBsJZTzggrRdYWLwOpoIRWtTXt4,3812
-sklearnex/dispatcher.py,sha256=9prbr6QrUWjc8wq1OyTxhuFEIKlTR-Qup9ZMfNszBPE,12884
+sklearnex/dispatcher.py,sha256=89QQ508iMt6qxoCIHt4woLvz_-KBOR6UvvhJJeC77hE,12878
 sklearnex/basic_statistics/__init__.py,sha256=NA5RGlwcp27UEeCgz0ngzYYd3MAIRpxlTy86uhM2-RE,821
 sklearnex/basic_statistics/basic_statistics.py,sha256=j5jBZ3DgXjoyjCBEFfYQHyl3LgLXEWWFnNHwInThdZw,796
 sklearnex/cluster/__init__.py,sha256=TsDzdbKzEubaP86iY8a7mSW0ZQzgjzGYuPkhc5lZmlQ,853
-sklearnex/cluster/dbscan.py,sha256=o3ZJVsvQXGG5y2bUja7Xd0V57VQGmB93FWDbKVo20kw,6674
+sklearnex/cluster/dbscan.py,sha256=EegSXIFHKNhaKLoe_G8dsC5t2SXRdu3tDzsHbcubdDM,6706
 sklearnex/cluster/k_means.py,sha256=1QKcFUQcnycu8kSD8uYSaDIuedHbxZsV_gvUfcEwVAM,806
 sklearnex/cluster/tests/test_dbscan.py,sha256=AgFoKwXFVyLKLvEtJVs0qlbBs1Ci3PcRft7f-6_ENOU,1464
 sklearnex/cluster/tests/test_kmeans.py,sha256=H3a9NSHRRSASo0Eceo44Kjq6GwEoMqMzcubaNt1s1QQ,1213
+sklearnex/covariance/__init__.py,sha256=_c86wiKDGBH50ofN-_tn7lO4M2YVEWO5AHhJIfimUDk,859
+sklearnex/covariance/incremental_covariance.py,sha256=3s9gmLP48DPhlhnFcg2JB7RQ2sliSZdNroJkv8-1sIA,4526
+sklearnex/covariance/tests/test_incremental_covariance.py,sha256=JIa4p-1_RYvU2ZVLx27iz0OKp0Nwrl9sYCsT0Dlyi2I,5402
 sklearnex/decomposition/__init__.py,sha256=RJBYDWyvnn5DA-j5r4IqVdXLp6H4mdPySsSjnXhlv-U,805
 sklearnex/decomposition/pca.py,sha256=68ksLxTP5fMOUhRmiIq9QNm0YzQanBNzxsq-zA8DKaY,809
 sklearnex/decomposition/tests/test_pca.py,sha256=aP4gxjML38CFpknwNVIkZLQCc8t2rqYGlWVo03vsMfE,1146
 sklearnex/doc/third-party-programs.txt,sha256=qA1XbOqYkMRnp29p8VxXjfcH0kHE8NSO5s2heea83-8,21773
 sklearnex/ensemble/__init__.py,sha256=2xB2KfG7l7uJv0p3kfVhrs4KLM174SCsigZhYqwSYAA,1035
-sklearnex/ensemble/_forest.py,sha256=Q3foDFaNmEHVeYjK8dIvP_-6GvSEV7dYPTXCrVN0e6A,70441
+sklearnex/ensemble/_forest.py,sha256=nw_aUdgyjxKWc6yZ-8DBaqNqDODhx5uEy13GbpM7C18,70561
 sklearnex/ensemble/tests/test_forest.py,sha256=KoETKE1sSpKgp38s9bepAujJjcG21eFX5RyYINcHCUo,4516
 sklearnex/glob/__main__.py,sha256=--FAjkhh5E6a1TFOGu6_BM3MHe78jP8oSpl0xKiRtTI,2531
 sklearnex/glob/dispatcher.py,sha256=IEEPhAOCVzC2JDFvYtijbiPAbaUY5RrCAhFLRjMMe1w,3018
-sklearnex/linear_model/__init__.py,sha256=97jj68r_V3JmsO8sZJt9BXlXazAPAzAz0E56dsNu4Sk,1100
+sklearnex/linear_model/__init__.py,sha256=5XZDZh8R0SmT8D8ZtSjW7-MKRO7l1jOZ8CUnt_OzHe4,1047
 sklearnex/linear_model/coordinate_descent.py,sha256=uZOHIKfFlHoMlNXZCh2MAnZE30fRZlmtcF7UsZQ3Vq4,822
-sklearnex/linear_model/linear.py,sha256=see-YysI8U1ilseHlerfcb97BFmenaubW-3BmDy0ixI,13870
+sklearnex/linear_model/linear.py,sha256=ed7pNKKnRkwa-wC0haUCOGHQoPkA4AuFhKNMzmRL6Fw,13832
 sklearnex/linear_model/logistic_path.py,sha256=Nq3JPXSzE4bjamnP3gGQtsMKks2v7s6bSiuYRnFqrRw,849
+sklearnex/linear_model/logistic_regression.py,sha256=ezW717qpPM4EC6uvmKbvxZZZwkooLuc8mfddAu5ebJM,12547
 sklearnex/linear_model/ridge.py,sha256=0oxlM5McYYvl0KxK9OIGJKM6lOADuFSPTdfx-efJNTI,810
 sklearnex/linear_model/tests/test_linear.py,sha256=li9LLWgap6YCwvNiHQ9yHduvUIsK1lpXfuVNR3dLwig,3200
-sklearnex/linear_model/tests/test_logreg.py,sha256=KO4240ACvhLsVHC_H09lhj4APUWPxmimHBE1JoY6TB8,1175
+sklearnex/linear_model/tests/test_logreg.py,sha256=iH6pxRJ5Nh6RzO_ohFLlt-TpJpQmzKh2QMU81SnPwv4,3346
 sklearnex/manifold/__init__.py,sha256=3FU5fY1YvHAyNeSlUHsZfPnAbvlAUtZpum0Obmok2KE,809
 sklearnex/manifold/t_sne.py,sha256=U6F_dGB6taVuEJvTnVBWD-sri3x3m0Khu3HI4wXidhg,805
 sklearnex/manifold/tests/test_tsne.py,sha256=SNqe1yg45mL4qIsxpX5hDpBsIyrv9r__6wfrerjp3yU,1063
@@ -37,61 +41,61 @@ sklearnex/metrics/tests/test_metrics.py,sha256=Nwfz8UV4V4fKLLY7f9P9eg8uY09xLXaFx
 sklearnex/model_selection/__init__.py,sha256=64045Y-nzLDBepO6IRjt88LhL2DM3KdvpCF2vvj_RpA,842
 sklearnex/model_selection/split.py,sha256=qjmy8sRf_QEG8LhT0ivn_tICMCYmt7ffZZV1-rLQnko,824
 sklearnex/model_selection/tests/test_model_selection.py,sha256=3kZIq8kba8SW93DBWXupoRymNStR1_mGGYSErQRnwME,1338
-sklearnex/neighbors/__init__.py,sha256=fyxRt3wosR6Tg_QYWOOt477jLisT2iZl6CzfTL1y9ro,1077
+sklearnex/neighbors/__init__.py,sha256=_GMJ2L-6YechRYI2fOFwHjy0kebUncE81z4FmdXUlb8,1078
+sklearnex/neighbors/_lof.py,sha256=HddPA9VdHEKCENr260qEAWoaB3KdqVYqHE-BssSuWPY,6605
 sklearnex/neighbors/common.py,sha256=iia-EUIRUIohDCIGpHbVx2PeDlwUvz4Mj1Tn169jidA,10781
-sklearnex/neighbors/knn_classification.py,sha256=z6-GgVnOnkyypZGyf0wFOev2Hc8iWy62gfr4dMFFdXM,11023
-sklearnex/neighbors/knn_regression.py,sha256=Ns_VPJ1ismXcPeJkUp8JxiHe-Y3QqI0d5HZuub7owkQ,9917
-sklearnex/neighbors/knn_unsupervised.py,sha256=MaapzNDA1wy2ZTuCeqpkKDEMBItrbMoW0p3JniCRCsA,7590
-sklearnex/neighbors/lof.py,sha256=XNnqrOnpIC5apeg6nToxeGqjQNIEp7sotflmm9iF4UY,16264
-sklearnex/neighbors/tests/test_neighbors.py,sha256=EAGF7Opgf-xWUAWYc6OdDgW5-2XsdkzLK_a35IX4Se4,3565
-sklearnex/preview/__init__.py,sha256=hZfIgTkkkUVaQ-SKaqI-S_SiXCkUzCUYxpSnbrhhEJU,813
+sklearnex/neighbors/knn_classification.py,sha256=C0jqL9qRQwt31JTIxjjWQWJuiy_D1I5Am1_W6ek8beY,11077
+sklearnex/neighbors/knn_regression.py,sha256=7ihpIl5SKSYDGvXtsUC0vNaOTj6_NNpXAAsu3uiQuaQ,9978
+sklearnex/neighbors/knn_unsupervised.py,sha256=Stw63vAKiaHnPQ2cfnXWD1Omf-QssT4BqhFPCMmyVCs,7620
+sklearnex/neighbors/tests/test_neighbors.py,sha256=s4jip1Ntrhp5Zu9-pHVbeIoNdNFsq03ABY-N-iF_UL8,3437
+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=hG_hq8dfHM8B97L9T6fPU5TuQB7d3URWHfnB1cskT_8,13022
+sklearnex/preview/cluster/k_means.py,sha256=jSuU8E6r4fdbbBnxBpWp4ybBa62kCnbBx7zDXyUr0Cs,13007
 sklearnex/preview/covariance/__init__.py,sha256=DPYTk8lwcVphtwU8J3CyUYH8Uz6Zr0Uz4S6nn-RY5iM,825
-sklearnex/preview/covariance/covariance.py,sha256=FXcRqdrHAhRNsyD6hG4a63ZxHMOZqdOS9yAqzfPY1LI,3614
+sklearnex/preview/covariance/covariance.py,sha256=LrNrGP62FEhTSBVaO-EOYAaq-Rszc1VS2B2IqMgh4oo,4938
 sklearnex/preview/covariance/tests/test_covariance.py,sha256=GYI4bMIhGnjmOXpt8J7R0JQmpm9eOvDjIphugRa4kD8,2140
 sklearnex/preview/decomposition/__init__.py,sha256=uRenwBGf7hHQqwAVYbBw3clUQB_HWUqJGOAKTuCnrcM,805
-sklearnex/preview/decomposition/pca.py,sha256=KkbK3NwBCvE_0eQryI3zFiwlXPiNdj4dCQd2ywgSIn8,14341
+sklearnex/preview/decomposition/pca.py,sha256=S8g5GhLdnUAb1FifNx6gnrwA8AWv8ddZtLY1Er83BkY,14342
 sklearnex/preview/decomposition/tests/test_preview_pca.py,sha256=xcllHM-jDIq33rAWTeh_gjhS2qfCNbUIAI5KeLPA8aY,1790
-sklearnex/preview/linear_model/__init__.py,sha256=Xr9Gk6mCq794GDLA2UlJPiLovOhZAx6rA5Bu123L-Rg,832
-sklearnex/preview/linear_model/logistic_regression.py,sha256=KIqpboN15BFV4BOyEokc5LF9eiqwBetlx2i27WBNIK0,13377
-sklearnex/preview/linear_model/tests/test_preview_logistic_regression.py,sha256=UjHXFhlea2P7feUKC64uHGNOhJpEaM2EZoAK0JJbz3I,2422
-sklearnex/spmd/__init__.py,sha256=8cxQy-oCFy1TJto0qoRf4lt98siPx2c-YV99YC-sk6s,871
+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
 sklearnex/spmd/cluster/__init__.py,sha256=qBBfrCHh6_82EROLbu54XKk7SmmRwS1XJyCj0zwkoUw,1029
 sklearnex/spmd/cluster/dbscan.py,sha256=23YNzPhx4MZijU0md-E3ZkHpTkhUh5cmtS3loHe-KhI,1824
 sklearnex/spmd/cluster/kmeans.py,sha256=Rnb9tr9LXVto5vCAumk7ZJfa9BYYDhdD1qUWL-QK5bY,868
+sklearnex/spmd/covariance/__init__.py,sha256=5xeL1REMIxCv5M1ya99GGKaVjctUngboZ3uXgxcZ04o,823
+sklearnex/spmd/covariance/covariance.py,sha256=_oIlr1W1vqDHqIPnsCb04HcBCen5oBHQr5-_n9OSvIA,884
 sklearnex/spmd/decomposition/__init__.py,sha256=dBh0ZMIiaqdf3DKbt8FWNB2K9Iacs395m8OxaDFQg_M,784
 sklearnex/spmd/decomposition/pca.py,sha256=CUrsVD2jae-A9H8RB_emza_fe82CwnFa5PEy0fW_EZ8,871
 sklearnex/spmd/ensemble/__init__.py,sha256=B3yi7hWoVogMIiw0QRT_x5atsAFS-OO72YPLGeUQJ8M,873
 sklearnex/spmd/ensemble/forest.py,sha256=ao6lyzcxoRW-RG9xIYwtDFyM7JIjlF8wmQKpOv_oSRQ,3113
-sklearnex/spmd/linear_model/__init__.py,sha256=eCJGleo00O6c280G97i18KNmSvi6uwX7wM1ZN5JMqhw,819
+sklearnex/spmd/linear_model/__init__.py,sha256=WwqCr2DOyUnkSIHlP0yq0UI2yFDgSl5MHV7wu3QGJtA,893
 sklearnex/spmd/linear_model/linear_model.py,sha256=7QPCIQTWKBiZBTDZZbpZXi-REgxQCfRMt6rHPJAnc5E,883
+sklearnex/spmd/linear_model/logistic_regression.py,sha256=q_HkfWcg0RgFbk2t9FeV0ZY28HHAOtkGEnUj4tLuwt4,885
 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=Dt1Iyz1g04zOW6hn9cHa9ruzM_MHAIq0ZEEIxh5s7nI,7167
-sklearnex/svm/nusvc.py,sha256=0-18XPzyhxQpD1nqVaUS-cymdnqZDCqZbCznD-oLr_U,8983
-sklearnex/svm/nusvr.py,sha256=BJiQYQV5-YS5P0DZTh3k-vvbGuu-GWZI3QBUsuxLMak,5215
-sklearnex/svm/svc.py,sha256=FL5GLMh82nhqUfaWjbAivghXq5iM9V_AVtkp_MAhCnI,10263
-sklearnex/svm/svr.py,sha256=dsVkOGsJ5qqx7uaWkkc5Dv7zwYaZrC1mUgcPQOadq7s,5219
+sklearnex/svm/nusvc.py,sha256=Bvs_FmC1CYH23tXyrQE3Ti1h3BqK0YeX-_PBTZMRM0k,9008
+sklearnex/svm/nusvr.py,sha256=XHlDAGwnx1NVkkt8c9EUST8zVRLQY7Mwu335TPCcuRk,5237
+sklearnex/svm/svc.py,sha256=4f-vJlPGeAcquz7nkSCeu0LJTTXCbdU2M54HkT49TeQ,10288
+sklearnex/svm/svr.py,sha256=fmYi0dghOmmyFFVI59COX9-tyouQnSDfHIbs8GY8AHs,5241
 sklearnex/svm/tests/test_svm.py,sha256=Ru-aGNGCsRJts7SEEYbnKcVqUx-DqPyUtw-hEoMVpW8,4190
 sklearnex/tests/_models_info.py,sha256=xhjvnU3TvQg8J5Cih2hphWAOSsT8DnKmCyYbtwa0Qvs,4785
 sklearnex/tests/test_config.py,sha256=SnSJjxAAysISDyC3bYKSJiRHStkB9X-yjLeF11LpRog,1372
-sklearnex/tests/test_memory_usage.py,sha256=-9S5EY9Ivy6WRW18IJEY1uyJxo9073GwXHybnFrJULc,7381
-sklearnex/tests/test_monkeypatch.py,sha256=D1ATlQtrNAtpHE7zmIxl7Mv41HxmRDRFAnjBmkUDGW8,8233
-sklearnex/tests/test_n_jobs_support.py,sha256=fa_XVNbBm5YQIguz5mgiQM8jmf2pQ7IwE8mgutyAbxk,1242
+sklearnex/tests/test_memory_usage.py,sha256=lwm63gSyRR82n3LGBdsophU_NvZK5RHkxAoTDZ2AcWI,7309
+sklearnex/tests/test_monkeypatch.py,sha256=wmtEeDNGoiPBlAh4Vmts86eFQLk8Wbzjbj6Busf6V3o,8663
+sklearnex/tests/test_n_jobs_support.py,sha256=ynfCSdCMnR3yEq1YEf_cilVD7zSe0sS-ZQ9jC0hHo8M,3903
 sklearnex/tests/test_parallel.py,sha256=bMu22noUvGiDX4oyxKIHPiOEoBP9lRQQUq6wq8ZD730,1776
-sklearnex/tests/test_patching.py,sha256=6H0Um6N5qhD5OZ875HhAcKPFXM81les5XWCCsaNyMb8,3759
+sklearnex/tests/test_patching.py,sha256=IySMpMdWVgoAZgs1cRKvdJeb8RXElFwjjNdHcE4jJz0,4247
 sklearnex/tests/test_run_to_run_stability_tests.py,sha256=4HDOeJruA1EDILbyQJtsHFmEXC0D1upSHuOT-KyTlEc,14008
 sklearnex/tests/utils/_launch_algorithms.py,sha256=pJT5tAW9rWvk7GT37R-B0-e8SLz8e9FSZw8yu4LWNJ4,3724
 sklearnex/utils/__init__.py,sha256=I8mbJQ3Zsm_F3sCLAhJQb7tUrG30kVsQ-wZoqA8vDdA,842
 sklearnex/utils/parallel.py,sha256=VBcS-KUdyq7XpJUN6ygmNjyWtYLroghbvCxQ8nVU3YI,2085
 sklearnex/utils/validation.py,sha256=fjfhQiKnBQnD7LCBlacMyvsrhGnlMLRXk5Q69uoZIP4,827
-scikit_learn_intelex-2024.1.0.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
-scikit_learn_intelex-2024.1.0.dist-info/METADATA,sha256=qYwrcOCj5B6HvCitweNkQDzI5qgtww7X6MdAeKdLElo,12449
-scikit_learn_intelex-2024.1.0.dist-info/WHEEL,sha256=8HLRuLcXtw8zhRBAbl72hZgSmSYmdfyBfCzEjumF0eI,108
-scikit_learn_intelex-2024.1.0.dist-info/top_level.txt,sha256=kzKChSWGJEYFmdj5PwE63HNuP_PVOhWfD32ytH9rL9Q,10
-scikit_learn_intelex-2024.1.0.dist-info/RECORD,,
+scikit_learn_intelex-2024.2.0.dist-info/LICENSE.txt,sha256=7micbUpzQXphq9e_2oL7PpZcvoXzPuQHIDEXyKXC81s,10797
+scikit_learn_intelex-2024.2.0.dist-info/METADATA,sha256=nNiD7x2RPhuhzEKH-Hg0-iOk3kqAUlLd3f--6KmLP-c,12449
+scikit_learn_intelex-2024.2.0.dist-info/WHEEL,sha256=8HLRuLcXtw8zhRBAbl72hZgSmSYmdfyBfCzEjumF0eI,108
+scikit_learn_intelex-2024.2.0.dist-info/top_level.txt,sha256=kzKChSWGJEYFmdj5PwE63HNuP_PVOhWfD32ytH9rL9Q,10
+scikit_learn_intelex-2024.2.0.dist-info/RECORD,,

sklearnex/cluster/dbscan.py

@@ -22,7 +22,8 @@ from scipy import sparse as sp
 from sklearn.cluster import DBSCAN as sklearn_DBSCAN
 from sklearn.utils.validation import _check_sample_weight
 
-from daal4py.sklearn._utils import control_n_jobs, run_with_n_jobs, sklearn_check_version
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
 from onedal.cluster import DBSCAN as onedal_DBSCAN
 
 from .._device_offload import dispatch, wrap_output_data
@@ -45,7 +46,7 @@ class BaseDBSCAN(ABC):
         self.n_features_in_ = self._onedal_estimator.n_features_in_
 
 
-@control_n_jobs
+@control_n_jobs(decorated_methods=["fit"])
 class DBSCAN(sklearn_DBSCAN, BaseDBSCAN):
     __doc__ = sklearn_DBSCAN.__doc__
 
@@ -83,7 +84,6 @@ class DBSCAN(sklearn_DBSCAN, BaseDBSCAN):
         self.p = p
         self.n_jobs = n_jobs
 
-    @run_with_n_jobs
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
         onedal_params = {
             "eps": self.eps,

sklearnex/{preview/linear_model → covariance}/__init__.py

@@ -1,5 +1,5 @@
 # ===============================================================================
-# Copyright 2023 Intel Corporation
+# 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.
@@ -14,6 +14,6 @@
 # limitations under the License.
 # ===============================================================================
 
-from .logistic_regression import LogisticRegression
+from .incremental_covariance import IncrementalEmpiricalCovariance
 
-__all__ = ["LogisticRegression"]
+__all__ = ["IncrementalEmpiricalCovariance"]

sklearnex/covariance/incremental_covariance.py

@@ -0,0 +1,130 @@
+# ===============================================================================
+# 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
+from sklearn.utils import check_array, gen_batches
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from onedal._device_offload import support_usm_ndarray
+from onedal.covariance import (
+    IncrementalEmpiricalCovariance as onedal_IncrementalEmpiricalCovariance,
+)
+
+
+@control_n_jobs(decorated_methods=["partial_fit"])
+class IncrementalEmpiricalCovariance:
+    """
+    Incremental estimator for covariance.
+    Allows to compute empirical covariance estimated by maximum
+    likelihood method if data are splitted into batches.
+
+    Parameters
+    ----------
+    batch_size : int, default=None
+        The number of samples to use for each batch. Only used when calling
+        ``fit``. If ``batch_size`` is ``None``, then ``batch_size``
+        is inferred from the data and set to ``5 * n_features``, to provide a
+        balance between approximation accuracy and memory consumption.
+
+    Attributes
+    ----------
+    location_ : ndarray of shape (n_features,)
+        Estimated location, i.e. the estimated mean.
+
+    covariance_ : ndarray of shape (n_features, n_features)
+        Estimated covariance matrix
+    """
+
+    _onedal_incremental_covariance = staticmethod(onedal_IncrementalEmpiricalCovariance)
+
+    def __init__(self, batch_size=None):
+        self._need_to_finalize = False  # If True then finalize compute should
+        #      be called to obtain covariance_ or location_ from partial compute data
+        self.batch_size = batch_size
+
+    def _onedal_finalize_fit(self):
+        assert hasattr(self, "_onedal_estimator")
+        self._onedal_estimator.finalize_fit()
+        self._need_to_finalize = False
+
+    def _onedal_partial_fit(self, X, queue):
+        onedal_params = {
+            "method": "dense",
+            "bias": True,
+        }
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_incremental_covariance(**onedal_params)
+        self._onedal_estimator.partial_fit(X, queue)
+        self._need_to_finalize = True
+
+    @property
+    def covariance_(self):
+        if self._need_to_finalize:
+            self._onedal_finalize_fit()
+        return self._onedal_estimator.covariance_
+
+    @property
+    def location_(self):
+        if self._need_to_finalize:
+            self._onedal_finalize_fit()
+        return self._onedal_estimator.location_
+
+    @support_usm_ndarray()
+    def partial_fit(self, X, queue=None):
+        """
+        Incremental fit with X. All of X is processed as a single batch.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        X = check_array(X, dtype=[np.float64, np.float32])
+        self._onedal_partial_fit(X, queue)
+        return self
+
+    def fit(self, X, queue=None):
+        """
+        Fit the model with X, using minibatches of size batch_size.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        n_samples, n_features = X.shape
+        if self.batch_size is None:
+            batch_size_ = 5 * n_features
+        else:
+            batch_size_ = self.batch_size
+        for batch in gen_batches(n_samples, batch_size_):
+            X_batch = X[batch]
+            self.partial_fit(X_batch, queue=queue)
+
+        self._onedal_finalize_fit()
+        return self

sklearnex/covariance/tests/test_incremental_covariance.py

@@ -0,0 +1,143 @@
+# ===============================================================================
+# 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
+import pytest
+from numpy.testing import assert_allclose
+
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype):
+    from sklearnex.covariance import IncrementalEmpiricalCovariance
+
+    X = np.array([[0, 1], [0, 1]])
+    X = X.astype(dtype)
+    X_split = np.array_split(X, 2)
+    inccov = IncrementalEmpiricalCovariance()
+
+    for i in range(2):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        result = inccov.partial_fit(X_split_df)
+
+    expected_covariance = np.array([[0, 0], [0, 0]])
+    expected_means = np.array([0, 1])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)
+
+    X = np.array([[1, 2], [3, 6]])
+    X = X.astype(dtype)
+    X_split = np.array_split(X, 2)
+    inccov = IncrementalEmpiricalCovariance()
+
+    for i in range(2):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        result = inccov.partial_fit(X_split_df)
+
+    expected_covariance = np.array([[1, 2], [2, 4]])
+    expected_means = np.array([2, 4])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("batch_size", [2, 4])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_fit_on_gold_data(dataframe, queue, batch_size, dtype):
+    from sklearnex.covariance import IncrementalEmpiricalCovariance
+
+    X = np.array([[0, 1, 2, 3], [0, -1, -2, -3], [0, 1, 2, 3], [0, 1, 2, 3]])
+    X = X.astype(dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    inccov = IncrementalEmpiricalCovariance(batch_size=batch_size)
+
+    result = inccov.fit(X_df)
+
+    expected_covariance = np.array(
+        [[0, 0, 0, 0], [0, 0.75, 1.5, 2.25], [0, 1.5, 3, 4.5], [0, 2.25, 4.5, 6.75]]
+    )
+    expected_means = np.array([0, 0.5, 1, 1.5])
+
+    assert_allclose(expected_covariance, result.covariance_)
+    assert_allclose(expected_means, result.location_)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("num_batches", [2, 4, 6, 8, 10])
+@pytest.mark.parametrize("row_count", [100, 1000, 2000])
+@pytest.mark.parametrize("column_count", [10, 100, 200])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_partial_fit_on_random_data(
+    dataframe, queue, num_batches, row_count, column_count, dtype
+):
+    from sklearnex.covariance import IncrementalEmpiricalCovariance
+
+    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)
+    X_split = np.array_split(X, num_batches)
+    inccov = IncrementalEmpiricalCovariance()
+
+    for i in range(num_batches):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        result = inccov.partial_fit(X_split_df)
+
+    expected_covariance = np.cov(X.T, bias=1)
+    expected_means = np.mean(X, axis=0)
+
+    assert_allclose(expected_covariance, result.covariance_, atol=1e-6)
+    assert_allclose(expected_means, result.location_, atol=1e-6)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("num_batches", [2, 4, 6, 8, 10])
+@pytest.mark.parametrize("row_count", [100, 1000, 2000])
+@pytest.mark.parametrize("column_count", [10, 100, 200])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_fit_on_random_data(
+    dataframe, queue, num_batches, row_count, column_count, dtype
+):
+    from sklearnex.covariance import IncrementalEmpiricalCovariance
+
+    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)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    batch_size = row_count // num_batches
+    inccov = IncrementalEmpiricalCovariance(batch_size=batch_size)
+
+    result = inccov.fit(X_df)
+
+    expected_covariance = np.cov(X.T, bias=1)
+    expected_means = np.mean(X, axis=0)
+
+    assert_allclose(expected_covariance, result.covariance_, atol=1e-6)
+    assert_allclose(expected_means, result.location_, atol=1e-6)

sklearnex/dispatcher.py

@@ -69,6 +69,7 @@ def get_patch_map():
         from .ensemble import RandomForestClassifier as RandomForestClassifier_sklearnex
         from .ensemble import RandomForestRegressor as RandomForestRegressor_sklearnex
         from .linear_model import LinearRegression as LinearRegression_sklearnex
+        from .linear_model import LogisticRegression as LogisticRegression_sklearnex
         from .neighbors import KNeighborsClassifier as KNeighborsClassifier_sklearnex
         from .neighbors import KNeighborsRegressor as KNeighborsRegressor_sklearnex
         from .neighbors import LocalOutlierFactor as LocalOutlierFactor_sklearnex
@@ -80,9 +81,6 @@ def get_patch_map():
             EmpiricalCovariance as EmpiricalCovariance_sklearnex,
         )
         from .preview.decomposition import PCA as PCA_sklearnex
-        from .preview.linear_model import (
-            LogisticRegression as LogisticRegression_sklearnex,
-        )
         from .svm import SVC as SVC_sklearnex
         from .svm import SVR as SVR_sklearnex
         from .svm import NuSVC as NuSVC_sklearnex
@@ -119,21 +117,6 @@ def get_patch_map():
                 ]
             ]
 
-            # LogisticRegression
-            mapping.pop("logisticregression")
-            mapping.pop("log_reg")
-            mapping["log_reg"] = [
-                [
-                    (
-                        linear_model_module,
-                        "LogisticRegression",
-                        LogisticRegression_sklearnex,
-                    ),
-                    None,
-                ]
-            ]
-            mapping["logisticregression"] = mapping["log_reg"]
-
         # DBSCAN
         mapping.pop("dbscan")
         mapping["dbscan"] = [[(cluster_module, "DBSCAN", DBSCAN_sklearnex), None]]
@@ -161,6 +144,24 @@ def get_patch_map():
         ]
         mapping["linearregression"] = mapping["linear"]
 
+        # Logistic Regression
+
+        mapping.pop("logisticregression")
+        mapping.pop("log_reg")
+        mapping.pop("logistic")
+        mapping.pop("_logistic_regression_path")
+        mapping["log_reg"] = [
+            [
+                (
+                    linear_model_module,
+                    "LogisticRegression",
+                    LogisticRegression_sklearnex,
+                ),
+                None,
+            ]
+        ]
+        mapping["logisticregression"] = mapping["log_reg"]
+
         # kNN
         mapping.pop("knn_classifier")
         mapping.pop("kneighborsclassifier")

sklearnex/ensemble/_forest.py

@@ -42,11 +42,10 @@ from sklearn.utils.validation import (
     check_X_y,
 )
 
+from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import (
     check_tree_nodes,
-    control_n_jobs,
     daal_check_version,
-    run_with_n_jobs,
     sklearn_check_version,
 )
 from onedal.ensemble import ExtraTreesClassifier as onedal_ExtraTreesClassifier
@@ -78,7 +77,6 @@ if sklearn_check_version("1.4"):
 class BaseForest(ABC):
     _onedal_factory = None
 
-    @run_with_n_jobs
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
         if sklearn_check_version("0.24"):
             X, y = self._validate_data(
@@ -787,7 +785,6 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
 
         return patching_status
 
-    @run_with_n_jobs
     def _onedal_predict(self, X, queue=None):
         X = check_array(
             X,
@@ -802,7 +799,6 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
         res = self._onedal_estimator.predict(X, queue=queue)
         return np.take(self.classes_, res.ravel().astype(np.int64, casting="unsafe"))
 
-    @run_with_n_jobs
     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")
@@ -1096,7 +1092,6 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
 
         return patching_status
 
-    @run_with_n_jobs
     def _onedal_predict(self, X, queue=None):
         X = check_array(
             X, dtype=[np.float64, np.float32], force_all_finite=False
@@ -1138,7 +1133,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
     predict.__doc__ = sklearn_ForestRegressor.predict.__doc__
 
 
-@control_n_jobs
+@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba"])
 class RandomForestClassifier(ForestClassifier):
     __doc__ = sklearn_RandomForestClassifier.__doc__
     _onedal_factory = onedal_RandomForestClassifier
@@ -1348,7 +1343,7 @@ class RandomForestClassifier(ForestClassifier):
             self.min_bin_size = min_bin_size
 
 
-@control_n_jobs
+@control_n_jobs(decorated_methods=["fit", "predict"])
 class RandomForestRegressor(ForestRegressor):
     __doc__ = sklearn_RandomForestRegressor.__doc__
     _onedal_factory = onedal_RandomForestRegressor
@@ -1549,7 +1544,7 @@ class RandomForestRegressor(ForestRegressor):
             self.min_bin_size = min_bin_size
 
 
-@control_n_jobs
+@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba"])
 class ExtraTreesClassifier(ForestClassifier):
     __doc__ = sklearn_ExtraTreesClassifier.__doc__
     _onedal_factory = onedal_ExtraTreesClassifier
@@ -1759,7 +1754,7 @@ class ExtraTreesClassifier(ForestClassifier):
             self.min_bin_size = min_bin_size
 
 
-@control_n_jobs
+@control_n_jobs(decorated_methods=["fit", "predict"])
 class ExtraTreesRegressor(ForestRegressor):
     __doc__ = sklearn_ExtraTreesRegressor.__doc__
     _onedal_factory = onedal_ExtraTreesRegressor

sklearnex/linear_model/__init__.py

@@ -16,14 +16,13 @@
 
 from .coordinate_descent import ElasticNet, Lasso
 from .linear import LinearRegression
-from .logistic_path import LogisticRegression, logistic_regression_path
+from .logistic_regression import LogisticRegression
 from .ridge import Ridge
 
 __all__ = [
     "Ridge",
     "LinearRegression",
     "LogisticRegression",
-    "logistic_regression_path",
     "ElasticNet",
     "Lasso",
 ]