NaiveDecisionStumpOracle< FeatureGenerator, Aggregator > Class Template Reference

#include <NaiveDecisionStumpOracle.h>

Public Types
typedef FeatureGenerator::FeatureType	FeatureType
	The Feature Extracted by FeatureGenerator.
typedef BinaryClassifier < FeatureType, NaiveDecisionStump >	WeakClassifierType
	The weak classifier.
typedef BoostableClassifier < WeakClassifierType >	ClassifierType
	The weak classifier reported by this oracle.

Public Member Functions
void	SetTrainingSet (const DataSetHandle< Aggregator > &set)
	Set the training set used to recover the threshold.
void	SetFeatureGenerator (FeatureGenerator &f)
	Associate a Feature Generator to Decision Stump Generator.
DataSetHandle< Aggregator > &	GetTrainingSet ()
	return R/W the training set More...
void	SetNumberOfThreads (int th)
	Change the thread number used in Multi Threading training.
void	SetPreloadSize (int n)
void	SetFastHeuristic (bool enable, bool reoptimize, int size)
double	Optimize (WeakClassifierType &h)
bool	GetHypothesis (WeakClassifierType &bestH)

Detailed Description

template<class FeatureGenerator, class Aggregator>
class NaiveDecisionStumpOracle< FeatureGenerator, Aggregator >

The hypothesis generator for NaiveDecisionStump Weak Classifier

Member Function Documentation

template<class FeatureGenerator , class Aggregator >

DataSetHandle<Aggregator>& NaiveDecisionStumpOracle< FeatureGenerator, Aggregator >::GetTrainingSet ( )

inline

return R/W the training set

MAdaBoost limits the weight of training set

template<class FeatureGenerator , class Aggregator >

double NaiveDecisionStumpOracle< FeatureGenerator, Aggregator >::Optimize ( WeakClassifierType &  h )

inline

Using current metrics try to recompute parameters associated to this feature since the threshold is fixed, this code can only evaluate performance (at least invert polarity of classifier)

---

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

• include/Oracle/NaiveDecisionStumpOracle.h