When trying to interpret the results of a gradient boosting (or any decision tree) one can plot the feature importance.
There are same parameters in the xgb api such as: weight, gain, cover, total_gain and total_cover. I am not quite getting cover.
”cover” is the average coverage of splits which use the feature where coverage is defined as the number of samples affected by the split
I am looking for a better definition of cover and perhaps some pseudocode to understand it better.