Load LightGBM/XGBoost model to sklearn

user_6810832 0
Viewed 918

LightGBM and XGBoost models can be dumped to plain text files containing human-readable model structure. In the end, they are just tree ensembles.

Is there any library to load these dumped models to the scikit-learn framework, e.g. construct sklearn ensembles with same splits and values?

That could be quiet convinient as there are some nice libraries attached to sklearn API, e.g. treeinterpreter.

lightgbm xgboost scikit-learn
1 Answers

For XGBoost you can use the xgbfir library which parses the xgb model display feature interactions and ranking. Install it with:

pip install xgbfir

For lightGBM, I'm not aware of good options. Microsoft's lightGBM library allows PMML export, so perhaps you could export then use some PMML parsers.

user_29978370
Related