How is the feature score(/importance) in the XGBoost package calculated?

How is the feature score(/importance) in the XGBoost package calculated?

python r classification feature-selection xgboost

r

How to handle date variable in machine learning data pre-processing

python r machine-learning logistic-regression feature-selection

r

Difference between varImp (caret) and importance (randomForest) for Random Forest

r random-forest r-caret feature-selection

r