CLUS::BinaryDecisionTreeNode< T_Splitter > Class Template Reference

Implements a node of the binary decision tree. More...

#include <binarydecisiontreenode.h>

Collaboration diagram for CLUS::BinaryDecisionTreeNode< T_Splitter >:

[legend]


Public Member Functions
	BinaryDecisionTreeNode (int NodeId, const Vector< int > &DDomainSize, int CsplitDim)
	~BinaryDecisionTreeNode (void)
void	StartLearningEpoch (void)
	Begin the learning process.
void	LearnSample (const int Dvars, const double Cvars, int classlabel)
	Learn a data sample.
bool	StopLearningEpoch (int minMass)
	Stop the learning process.
double	Infer (const int Dvars, const double Cvars)
	Do the inference.
void	InitializePruningStatistics (void)
	Initialize stats about pruning.
void	UpdatePruningStatistics (const int Dvars, const double Cvars, int classlabel)
	Update pruning stats with new data.
void	FinalizePruningStatistics (void)
double	PruneSubtree (void)
	Return the optimal cost for this subtree and cuts the subtree to optimal size.
void	SaveToStream (ostream &out)
	Output the node data to a stream.
Protected Types
enum	state { stable, split }
	the state of the node. At creation em. At load stable More...
Protected Attributes
int	nodeId
	unique identifier of the cluster for a regression tree.
enum CLUS::BinaryDecisionTreeNode::state	State
	the state of the node. At creation em. At load stable
int	classLabel
	the predicted class label
BinaryDecisionTreeNode< T_Splitter > *	Children [2]
	the children of this node
double	probFirstClass
	the probability to return first class, for the seccond probability is 1-probFirstClass
T_Splitter	Splitter
	splitter for split criterion
int	pruningError
	pruning error statistic
int	pruningTotalMass
	pruning total mass statistic

Detailed Description

template<class T_Splitter>
class CLUS::BinaryDecisionTreeNode< T_Splitter >

Implements a node of the binary decision tree.

Definition at line 52 of file binarydecisiontreenode.h.

Member Enumeration Documentation

template<class T_Splitter>

enum CLUS::BinaryDecisionTreeNode::state [protected]

the state of the node. At creation em. At load stable

Enumeration values:

stable

split

Definition at line 60 of file binarydecisiontreenode.h.

Constructor & Destructor Documentation

template<class T_Splitter>

CLUS::BinaryDecisionTreeNode< T_Splitter >::BinaryDecisionTreeNode ( int NodeId,

const Vector< int > & DDomainSize,

int CsplitDim

) [inline]

Definition at line 81 of file binarydecisiontreenode.h.

template<class T_Splitter>

CLUS::BinaryDecisionTreeNode< T_Splitter >::~BinaryDecisionTreeNode ( void ) [inline]

Definition at line 89 of file binarydecisiontreenode.h.

Member Function Documentation

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::FinalizePruningStatistics ( void ) [inline]

Definition at line 255 of file binarydecisiontreenode.h.

template<class T_Splitter>

double CLUS::BinaryDecisionTreeNode< T_Splitter >::Infer ( const int * Dvars,

const double * Cvars

) [inline]

Do the inference.

Parameters:

Dvars discrete variables

Cvars continuous variables

Definition at line 207 of file binarydecisiontreenode.h.

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::InitializePruningStatistics ( void ) [inline]

Initialize stats about pruning.

Definition at line 222 of file binarydecisiontreenode.h.

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::LearnSample ( const int * Dvars,

const double * Cvars,

int classlabel

) [inline]

Learn a data sample.

Parameters:

Dvars discrete variables

Cvars continuous variables

classlabel classification label

Definition at line 124 of file binarydecisiontreenode.h.

template<class T_Splitter>

double CLUS::BinaryDecisionTreeNode< T_Splitter >::PruneSubtree ( void ) [inline]

Return the optimal cost for this subtree and cuts the subtree to optimal size.

Definition at line 261 of file binarydecisiontreenode.h.

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::SaveToStream ( ostream & out ) [inline]

Output the node data to a stream.

Parameters:

out stream for output

Definition at line 307 of file binarydecisiontreenode.h.

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::StartLearningEpoch ( void ) [inline]

Begin the learning process.

Definition at line 102 of file binarydecisiontreenode.h.

template<class T_Splitter>

bool CLUS::BinaryDecisionTreeNode< T_Splitter >::StopLearningEpoch ( int minMass ) [inline]

Stop the learning process.

Returns:
true if stopped successfully false if still processing data

Definition at line 149 of file binarydecisiontreenode.h.

template<class T_Splitter>

void CLUS::BinaryDecisionTreeNode< T_Splitter >::UpdatePruningStatistics ( const int * Dvars,

const double * Cvars,

int classlabel

) [inline]

Update pruning stats with new data.

Parameters:

Dvars discrete variables

Cvars continuous variables

classlabel classification label

Definition at line 239 of file binarydecisiontreenode.h.