OOB_Error Class Reference

#include <vigra/random_forest/rf_visitors.hxx>

Inheritance diagram for OOB_Error:

Public Member Functions
template<class RF , class PR >
void	visit_at_end (RF &rf, PR &pr)
Public Member Functions inherited from VisitorBase
double	return_val ()
template<class Tree , class Split , class Region , class Feature_t , class Label_t >
void	visit_after_split (Tree &tree, Split &split, Region &parent, Region &leftChild, Region &rightChild, Feature_t &features, Label_t &labels)
template<class RF , class PR , class SM , class ST >
void	visit_after_tree (RF &rf, PR &pr, SM &sm, ST &st, int index)
template<class RF , class PR >
void	visit_at_beginning (RF const &rf, PR const &pr)
template<class RF , class PR >
void	visit_at_end (RF const &rf, PR const &pr)
template<class TR , class IntT , class TopT , class Feat >
void	visit_external_node (TR &tr, IntT index, TopT node_t, Feat &features)
template<class TR , class IntT , class TopT , class Feat >
void	visit_internal_node (TR &, IntT, TopT, Feat &)

Public Attributes
double	oob_breiman

Detailed Description

Visitor that calculates the oob error of the ensemble

This rate serves as a quick estimate for the crossvalidation error rate. Here, each sample is put down the trees for which this sample is OOB, i.e., if sample #1 is OOB for trees 1, 3 and 5, we calculate the output using the ensemble consisting only of trees 1 3 and 5.

Using normal bagged sampling each sample is OOB for approx. 33% of trees. The error rate obtained as such therefore corresponds to a crossvalidation rate obtained using a ensemble containing 33% of the trees.

Member Function Documentation

void visit_at_end	(	RF &	rf,
		PR &	pr
	)

Normalise variable importance after the number of trees is known.

Member Data Documentation

double oob_breiman

Ensemble oob error rate

---

The documentation for this class was generated from the following file:

• vigra/random_forest/rf_visitors.hxx