| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-12-04 | 1.8 kB | |
| v0.4.2 source code.tar.gz | 2025-12-04 | 21.8 MB | |
| v0.4.2 source code.zip | 2025-12-04 | 22.0 MB | |
| Totals: 3 Items | 43.8 MB | 0 | |
New features:
- New MLAlgos: TabM and TabICL by @dev-rinchin and @Uptimolli in https://github.com/sb-ai-lab/LightAutoML/commit/c31d660cca16b4113825b2519e5526c16dfe54c1 and https://github.com/sb-ai-lab/LightAutoML/commit/5a79d05c2e58dc259be278ba171bea96b785c418
- PiecewiseLinearEmbeddings by @dev-rinchin in https://github.com/sb-ai-lab/LightAutoML/commit/c31d660cca16b4113825b2519e5526c16dfe54c1
- "Auto select device at inference" by @Uptimolli in https://github.com/sb-ai-lab/LightAutoML/commit/cc808f7faaec123756ac161e6a5976e4e4d791f3
Dependencies:
- Numpy 2.0+ and Pandas 2.0+ support by @Uptimolli and @dev-rinchin in https://github.com/sb-ai-lab/LightAutoML/commit/b9f8ca1ad153d7e7b8d131beb3a20e76e3e20c8a
- Replacing fasttext with fasttext-numpy2 by @Uptimolli in https://github.com/sb-ai-lab/LightAutoML/commit/f48c76ab1011b5f03a8f3c2caf361bc04d040254
Bugfixes:
- Fix multiclass in XGBoost by @Uptimolli in https://github.com/sb-ai-lab/LightAutoML/commit/1ca9074f4193b64aaf1cacebfbf582996b76c288 and https://github.com/sb-ai-lab/LightAutoML/commit/01f5fda52ad253e5b719208730809b533c84657a
- Fix https://github.com/sb-ai-lab/LightAutoML/issues/173 by @dev-rinchin in https://github.com/sb-ai-lab/LightAutoML/commit/bf0d518b070c9f2c3bdc425fd305b0a7918767ed
- Fix groupby for new category by @dev-rinchin in https://github.com/sb-ai-lab/LightAutoML/commit/208ee8ba08d43a2b69abcef62799e83c757346ab
- Fix forced_features calculation by @Uptimolli in https://github.com/sb-ai-lab/LightAutoML/commit/e95496c620756bcf08243c1953cc687eebdf6488
- Fix Optuna Exception brackets bug by @dwemer8 in https://github.com/sb-ai-lab/LightAutoML/pull/174
Full Changelog: https://github.com/sb-ai-lab/LightAutoML/compare/v.0.4.1...v.0.4.2