Intel® Extension for Scikit-learn* 2024.5.0

Intel® Extension for Scikit-learn* is happy to introduce 2024.5.0 release!

🚨 What's New

• Introduced new Intel® Extension for Scikit-learn* functionality:
  • IncrementalLinearRegression interface
  • IncrementalEmpiricalCovariance interface to patch_map

🪲 Bug Fixes

• Fix dpnp/dpctl F-contiguous data processing

Acknowledgements

Thanks to everyone who helped us make 2024.5.0 release possible!

@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam

Full Changelog: 2024.4.0...2024.5.0

Intel® Extension for Scikit-learn* 2024.4.0

Intel® Extension for Scikit-learn* is happy to introduce 2024.4.0 release!

🚨 What's New

• Introduced new Intel® Extension for Scikit-learn* functionality:

  • IncrementalBasicStatistics interface
  • Added _n_inner_iter attribute for Logistic Regression
  • Added assume_centered capability to EmpiricalCovariance

• Improved Intel® Extension for Scikit-learn* performance for the following algorithms:

  • PCA

🪲 Bug Fixes

• Fix sample_weight check for IncrementalBasicStatistics
• Fix dpnp/dpctl slowdown in fit method of neighbors algorithms

Acknowledgements

Thanks to everyone who helped us make 2024.4.0 release possible!

@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam

Full Changelog: 2024.3.0...2024.4.0

Intel® Extension for Scikit-learn* 2024.3.0

Intel® Extension for Scikit-learn* is happy to introduce 2024.3.0 release!

🚨 What's New

• Introduced new Intel® Extension for Scikit-learn* functionality:

  • model_selection in sklearnex namespace
  • SPMD backend library is separated from dpc backend
  • PCA algorithm is moved out of preview namespace

• Improved Intel® Extension for Scikit-learn* performance for the following algorithms:

  • PCA

🪲 Bug Fixes

• Fix test_patching routines for intelex-only sklearnex estimators
• Update sklearnex init based on SPMD backend changes
• Fix import error by adding conditional check of OFF_ONEDAL_IFACE flag when importing onedal

❌ Deprecation Notice

• Sklearn estimators in onedal4py LinReg and k-Means algorithms is deprecated for usage

Acknowledgements

Thanks to everyone who helped us make 2024.3.0 release possible!

@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @maria-Petrova, @avolkov-intel, @md-shafiul-alam

Full Changelog: 2024.2.0...2024.3.0

Intel® Extension for Scikit-learn* 2024.2.0

Intel® Extension for Scikit-learn* is happy to introduce 2024.2.0 release!

🚨 What's New

• Introduced new Intel(R) Extension for Scikit-learn* functionality:
  • Incremental Covariance algorithm
  • Logistic Regression algorithm is moved out of preview namespace
  • SPMD interfaces support: Logistic Regression, Covariance

🔨 Library Engineering

• Enabled scikit-learn 1.4 support

🪲 Bug Fixes

• Adjusted n_jobs parameter setting
• Updated DPCPP detection in setup
• Fix of k-Means SPMD timeout
• Correct disabling of CatBoost SHAP
• Fix LocalOutlierFactor kneighbors method

Acknowledgements

Thanks to everyone who helped us make 2024.2.0 release possible!

@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @maria-Petrova, @avolkov-intel

Full Changelog: 2024.1.0...2024.2.0

Intel® Extension for Scikit-learn* 2024.1.0

Intel® Extension for Scikit-learn* is happy to introduce 2024.1.0 release!

🚨 What's New

• New Intel® Extension for Scikit-learn* functionality:
  • SHAP support for symmetric CatBoost models
  • Added oneDAL LinReg and Covariance hyperparameters API
  • Added LogisticRegression interface to the preview section
  • Initial support of n_jobs parameter

Acknowledgements

Thanks to everyone who helped us make 2024.1.0 release possible!

@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @KulikovNikita, @maria-Petrova, @avolkov-intel

Full Changelog: 2024.0.1...2024.1.0

Intel® Extension for Scikit-learn* 2024.0.1

Intel® Extension for Scikit-learn* is happy to introduce 2024.0.1 release!

🚨 What's New

• New Intel(R) Extension for Scikit-learn* functionality:
  • Linear Regression and ensemble algorithms are moved out of preview namespace
• New Model Builders functionality:
  • SHAP calculation is added to GBT regression

🔨 Library Engineering

• Added Python 3.12 support for daal4py and Intel(R) Extension for Scikit-learn* packages

📚 Support Materials

Faster XGBoost*, LightGBM, and CatBoost Inference on the CPU
PS-S3-Ep23-with-scikit-learn-intelex
pss3e23 fusion_model with scikit-learn-intelex
PS S3E25: Faster regression tuning with sklearnex

🔀 Adoption

TPOT2 AutoML integration

Acknowledgements

Thanks to everyone who helped us make 2024.0.1 release possible!

@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @KulikovNikita, @maria-Petrova, @avolkov-intel

Intel(R) Extension for Scikit-learn* 2024.0.0

Intel(R) Extension for Scikit-learn* is happy to introduce 2024.0 release!

What's New

• New functionality:
  • DBSCAN and SPMD DBSCAN algorithms

Acknowledgements

Thanks to everyone who helped us make 2024.0 release possible!

@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @KulikovNikita, @maria-Petrova, @avolkov-intel

Intel® Extension for Scikit-learn 2023.2.1

The release of Intel® Extension for Scikit-learn 2023.2.1 introduces the following changes:

🚨 What's New

• sklearn 1.3 support fixes (1, 2, 3)
• Model builders API update

Intel® Extension for Scikit-learn 2023.2.0

The release of Intel® Extension for Scikit-learn 2023.2.0 introduces the following changes:

❌ Deprecation Notice

• The compression functionality in the Intel® oneDAL library is deprecated. Starting with the 2024.0 release, oneDAL will not support the compression functionality
• The DAAL CPP SYCL Interfaces in the Intel® oneDAL library are deprecated. Starting with the 2024.0 release, oneDAL will not support the DAAL CPP SYCL Interfaces
• The Java* interfaces in the Intel® oneDAL library are marked as deprecated. The future releases of the oneDAL library may no longer include support for these Java* interfaces
• ABI compatibility is to be broken as part of the 2024.0 release of Intel® oneDAL. The library’s major version is to be incremented to two to enforce the relinking of existing applications
• macOS* support is deprecated for oneDAL. The 2023.x releases are the last to provide it

🛠️ Library Engineering

• CSR tables interface has been changed and moved from detail namespace

🚨 What's New

• Introduced new Intel® oneDAL functionality:
  • Distributed KMeans++ algorithm
  • Logistic Loss objective algorithm
• Introduced new functionality for Intel® Extension for Scikit-learn:
  • NaN(missing values) support was added to Model Builders
• Improved performance for the following Intel® Extension for Scikit-learn algorithms:
  • Model Builders performance has been improved up to 2x

Intel® Extension for Scikit-learn 2023.1.1

The release of Intel® Extension for Scikit-learn 2023.1.1 introduces the following changes:

🚨 What's New

• Splitting mode for Random Forest algorithm 4abff0d
• SPMD interface for Random Forest, kNN and PCA e887d99, 97f0d47, 2405630
• Native support for DPCTL ca28499
• Patching for sklearn's LocalOutlierFactor 7ae0171