Giters

WillKoehrsen / feature-selector

Feature selector is a tool for dimensionality reduction of machine learning datasets

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why only GBT?

sodaliAyran opened this issue · comments

commented

I understand why you use tree based algorithms to find Zero Importance Features. But why Gradient Boosted Trees is the only option? I think RandomForest and maybe DecisionTree algorithms should be one of the options. Or are they already?

commented

Random forests would also work for model-based feature importances. This is an option I'm looking to add when I have some time. Thanks for the suggestion.