GitLab

[python-package] Add `feature_names_in_` attribute for scikit-learn estimators (fixes #6279) (#6310)

[python-package] Add support for NumPy 2.0, test against nightly versions of dependencies (fixes #6454) (#6467)

[python-package] remove uses of deprecated NumPy random number generation APIs, require 'numpy>=1.17.0' (#6468)

* [python-package] Allow to pass early stopping min delta in params

* Fix test

* Add separate test

* Fix

* Add to cpp config

* Adjust test

* Adjust test

* Debug

* Revert

* Apply suggestions from code review

---------
Co-authored-by: James Lamb <jaylamb20@gmail.com>

[ci] Skip Arrow tests on AppVeyor, use Intel macOS runners, upgrade to XCode 14.3 on macOS jobs, disable MacOS MPI jobs (#6425)

[python-package] allow use of early_stopping_round<=0 to turn off early stopping (fixes #6401) (#6406)

* support quantized training with categorical features on cpu

* remove white spaces

* add tests for quantized training with categorical features

* skip tests for cuda version

* fix cases when only 1 data block in row-wise quantized histogram construction with 8 inner bits

* remove useless capture

* fix compilation warnings

revert useless changes

* revert useless change

* separate functions in feature histogram into cpp file

* add feature_histogram.o in Makevars

[R-package] [c++] add tighter multithreading control, avoid global OpenMP side effects (fixes #4705, fixes #5102) (#6226)

[python-package] fix access to Dataset metadata in scikit-learn custom metrics and objectives (#6108)

* fix leaf splits update after split in quantized training

* fix preparation ordered gradients for quantized training

* remove force_row_wise in distributed test for quantized training

* Update src/treelearner/leaf_splits.hpp

---------
Co-authored-by: James Lamb <jaylamb20@gmail.com>