XGBoost is a specific implementation of gradient boosting trees, so
strictly speaking scikit-learn cannot "contain" XGBoost. That being said:
- XGBoost has a scikit-learn compatible API:
https://xgboost.readthedocs.io/en/latest/python/python_api.html#module-xgboost.sklearn.
So does LightGBM, another fast implementation of gradient boosting trees.
- scikit-learn implements "vanilla" gradient boosting
https://scikit-learn.org/stable/modules/ensemble.html#gradient-boosting
- There's an open PR in scikit learn (still very WIP) that implements
the same kind of optimization that XGBoost and LightGBM use, which will
make GBDT faster https://github.com/scikit-learn/scikit-learn/pull/12807.
Nicolas
On 1/8/19 8:23 PM, lampahome wrote:
As title
Does sklearn contain xgboost to use?
thanks
_______________________________________________
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn
_______________________________________________
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn
