I'm trying to use gradient boosting and I'm using sklearn's GradientBoostingClassifier class.
My problem is that I'm having a data frame with 5 columns and I want to use these columns as features. I want to use them continuously. I mean I want each tree based classifier uses the residue of the previous tree which is based on the previous feature. As I know, by default, this classifier uses a feature and passes the residue of the previous tree to the next tree, which both are based on a single feature. How can I do this?
Should I do this on my own or there is a library which does this?
