Model Dump Parser (like XGBFI) for LightGBM and CatBoost

Question

Currently my employer has multiple GLM in a live environment. I am interested in identifying new features and interactions to enhance the accuracy of these GLM; for now I am limited to the GLM structure so simply deploying a solution which automatically accounts for interactions is not possible.

I have in the past used XGBoost to identify powerful feature interactions through the use of XGBFI / XGBFIR. I am now looking in to using LightGBM and CatBoost to do the same but cannot seem to find a tool like XGBFI which works on those models.

Question: Does anything similar to XGBFI exist for LightGBM and CatBoost?

Answer 1

Both LightGBM and CatBoost have functions that give you the models' feature importances. They are described in the respective docs here:

• LightGBM: plot_importance and lightgbm.importance
• Catboost: has get_feature_importance which is described in more detail on its concepts page