Currently many more Python projects like dask and optuna are using Python type hints. With the Python package of xgboost gaining more and more features, we should also adopt mypy as a safe guard against some type errors and for better code documentation.

Summary

LightGBM supports aliases for most parameter. For example, you can use bagging_fraction or sub_row to say "% of rows sampled during bagging".

The new dask API added in #3515 should be changed to support such aliases for the parameters it references.

See these comments for details on a few parameters that need to be updated to use aliases.

• https://github.com/microsoft/L

Hi!

There is no opportunity to get fitted models after cv, because catboost.cv returns only evaluation metric scores. At the same time popular ml libraries have such option in some kind.

For LightGBM there is optional argument return_cvbooster:

cv = lgb.cv(params, X_train, show_stdv=False, stratified=True