I am using XGBClassifier with GridSearchCV(cv=KFold(n_splits=5, random_state=42, shuffle=True)). I want to explore variable importance, so I am getting it from the model.best estimator: model.best_estimator_.feature_importances_
.
However, it is not clear what type of variable importance is used (gain, or weight).
When I am printing model.best_estimator_.importance_type
I get None.
I remember I could print the type of variable when using XGBRegressor in the past.
Could someone help me?
Asked
Active
Viewed 31 times
0

Vicky
- 33
- 5
-
Does this answer your question? [xgboost feature importance for classification](https://stackoverflow.com/questions/76095884/xgboost-feature-importance-for-classification) – Flavia Giammarino May 01 '23 at 16:34