v0.10.0

[Chi Wang (sonichi)]

This release contains an important new feature: zero-shot AutoML and mete learning. It provides a new way of doing AutoML without tuning. You can now use the existing training API from lightgbm, xgboost etc. while getting the benefit of AutoML in choosing high-performance hyperparameter configurations per task. Recommended for everyone currently using lightgbm, xgboost or random forest, regardless of previous experience in AutoML. This feature also enables continuous improvement of AutoML from historical AutoML experiments.

Other changes can be found below.

What's Changed

• Typo on the webpage's Getting Started section by Camila Martinez (@cammarb) in Typo on the webpage's Getting Started section #457
• Bump follow-redirects from 1.14.7 to 1.14.8 in /website by Chi Wang (@sonichi) in Bump follow-redirects from 1.14.7 to 1.14.8 in /website #459
• Docstr update by Qingyun Wu (@qingyun-wu) in Docstr update #460
• update regression metrics in notebooks by Chi Wang (@sonichi) in update regression metrics in notebooks #454
• make AutoML.classes_ an array by Chi Wang (@sonichi) in make AutoML.classes_ an array #467
• Bump prismjs from 1.25.0 to 1.27.0 in /website by Chi Wang (@sonichi) in Bump prismjs from 1.25.0 to 1.27.0 in /website #471
• Zero-shot AutoML by Chi Wang (@sonichi) in Zero-shot AutoML #468
• don't init global search with points_to_evaluate unless evaluated_rewards is provided; handle callbacks in fit kwargs by Chi Wang (@sonichi) in don't init global search with points_to_evaluate unless evaluated_rewards is provided; handle callbacks in fit kwargs #469

New Contributors

• Camila Martinez (@cammarb) made their first contribution in Typo on the webpage's Getting Started section #457

Full Changelog: v0.9.7...v0.10.0

---

This discussion was created from the release v0.10.0.