Feature Selection Toolbox FST4
UTIA · Czech Academy of Sciences
Loading...
Searching...
No Matches
FST::Classifier_Random_Forest< RETURNTYPE, DATATYPE, REALTYPE, IDXTYPE, DIMTYPE, SUBSET, DATAACCESSOR >::Node Struct Reference

#include <classifier_rf.hpp>

Public Attributes

DIMTYPE feature
 split feature, given as a subset position (see _index for the raw feature index)
REALTYPE threshold
 split threshold; a pattern routes to left when its value is <=threshold
long left
 left-child index into the tree's node vector; <0 marks this node a leaf
long right
 right-child index into the tree's node vector (meaningful only when left>=0)
DIMTYPE leaf_class
 predicted class (meaningful only when left<0, i.e. at a leaf)

Detailed Description

template<class RETURNTYPE, typename DATATYPE, typename REALTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET, class DATAACCESSOR>
struct FST::Classifier_Random_Forest< RETURNTYPE, DATATYPE, REALTYPE, IDXTYPE, DIMTYPE, SUBSET, DATAACCESSOR >::Node

one CART node; left<0 marks a leaf (leaf_class valid), otherwise feature/threshold/left/right. A tree is a flat vector of these: the root is always index 0, and a split appends its two children at the end of the vector, so child indices always exceed the parent's.


The documentation for this struct was generated from the following file:
Copyright © 2000–present ÚTIA, Institute of Information Theory and Automation of the Czech Academy of Sciences · Contacts · This site sets no cookies and uses no analytics.