How can I use xgboost_ray to train a model and use origin xgboost for predict?

[WZFish]

Because when I train a model the dataset is very large. But when predict there are small dataset and predict more than 1000 times,But xgboost_ray is slower than origin xgboost in predict,How can I solve it

[Yard1]

The model returned by xgboost-ray is a standard xgboost model which you can use in a non-distributed fashion as well. Refer to xgboost documentation on how to do predictions with it - https://xgboost.readthedocs.io/en/stable/python/python_api.html#xgboost.Booster.predict

[WZFish]

I use the sklearn API and when I use model.predict(x) it still run 4 actors(I set n_jobs=4) and very slow. How can I use standard xgboost sklearn API to predict? Thank you very much

[Yard1]

You can obtain the underlying model from the sklearn API by calling model.get_booster() to obtain an xgboost.Booster object you can use as in the link above, or use it to instantiate non-distributed XGBoost sklearn estimator.