quantlab.model.predefined.catboost_model#
Qlib’s CatBoost benchmark model.
CatBoostRegressor reproduces Qlib’s CatBoostModel
(qlib/contrib/model/catboost_model.py) with its Alpha158 benchmark parameters
(workflow_config_catboost_Alpha158.yaml): a CatBoost model fit on the
training rows with the validation rows as its eval_set, CatBoost’s early
stopping and use_best_model, on the GPU when CatBoost sees one. CatBoost ships
in the gbdt extra.
The module is named catboost_model.py, as in Qlib, so it does not shadow the
catboost package.
Classes
Qlib's CatBoost on the rows of the cross-sectional rank target. |