ROOT » TMVA » TMVA » TMVA::CostComplexityPruneTool

class TMVA::CostComplexityPruneTool: public TMVA::IPruneTool

Function Members (Methods)

Data Members

TMVA::MsgLogger*fLogger! output stream to save logging information
Int_tfOptimalK! the optimal index of the prune sequence
vector<TMVA::DecisionTreeNode*>fPruneSequence! map of weakest links (i.e., branches to prune) -> pruning index
vector<Double_t>fPruneStrengthList! map of alpha -> pruning index
vector<Double_t>fQualityIndexList! map of R(T) -> pruning index
TMVA::SeparationBase*fQualityIndexTool! the quality index used to calculate R(t), R(T) = sum[t in ~T]{ R(t) }

Class Charts

Inheritance Inherited Members Includes Libraries
Class Charts

Function documentation

CostComplexityPruneTool( SeparationBase* qualityIndex )
 the constructor for the cost complexity prunig
 the destructor for the cost complexity prunig
CalculatePruningInfo(TMVA::DecisionTree* dt, const TMVA::IPruneTool::EventSample* testEvents = __null, Bool_t isAutomatic = kFALSE)
void InitTreePruningMetaData(TMVA::DecisionTreeNode* n)
 initialise "meta data" for the pruning, like the "costcomplexity", the
 critical alpha, the minimal alpha down the tree, etc...  for each node!!
void Optimize(TMVA::DecisionTree* dt, Double_t weights)
 after the critical alpha values (at which the corresponding nodes would
 be pruned away) had been established in the "InitMetaData" we need now:
 automatic pruning:
   find the value of "alpha" for which the test sample gives minimal error,
   on the tree with all nodes pruned that have alpha_critital < alpha,
 fixed parameter pruning

CostComplexityPruneTool( SeparationBase* qualityIndex = NULL )