|
ROOT
Reference Guide |
|
Go to the documentation of this file.
31 #ifndef ROOT_TMVA_MethodCategory
32 #define ROOT_TMVA_MethodCategory
55 namespace Experimental {
67 const TString& theOption =
"" );
virtual Bool_t HasAnalysisType(Types::EAnalysisType type, UInt_t numberClasses, UInt_t)
check whether method category has analysis type the method type has to be the same for all sub-method...
TMVA::IMethod * AddMethod(const TCut &, const TString &theVariables, Types::EMVA theMethod, const TString &theTitle, const TString &theOptions)
adds sub-classifier for a category
A specialized string object used for TTree selections.
Ranking for variables in method (implementation)
virtual const std::vector< Float_t > & GetRegressionValues()
returns the mva value of the right sub-classifier
A TTree represents a columnar dataset.
void ProcessOptions()
process user options
std::vector< IMethod * > fMethods
std::vector< UInt_t > fCategorySpecIdx
Class for categorizing the phase space.
Bool_t PassesCut(const Event *ev, UInt_t methodIdx)
Virtual base class for combining several TMVA method.
void DeclareOptions()
options for this method
void AddWeightsXMLTo(void *parent) const
create XML description of Category classifier
virtual ~MethodCategory(void)
destructor
std::vector< std::vector< UInt_t > > fVarMaps
Class that contains all the data information.
void Train(void)
train all sub-classifiers
virtual void MakeClass(const TString &=TString("")) const
create reader class for method (classification only at present)
Class for boosting a TMVA method.
friend class MethodCategory
const Ranking * CreateRanking()
no ranking
void InitCircularTree(const DataSetInfo &dsi)
initialize the circular tree
void Init()
initialize the method
virtual Double_t GetMvaValue(Double_t *errLower=0, Double_t *errUpper=0)=0
This is the main MVA steering class.
virtual const std::vector< Float_t > & GetMulticlassValues()
returns the mva values of the multi-class right sub-classifier
std::vector< TTreeFormula * > fCatFormulas
needed in conjunction with TTreeFormulas for evaluation category expressions
Interface for all concrete MVA method implementations.
Class that contains all the data information.
TMVA::DataSetInfo & CreateCategoryDSI(const TCut &, const TString &, const TString &)
create a DataSetInfo object for a sub-classifier
#define ClassDef(name, id)
DataSetManager * fDataSetManager
std::vector< TCut > fCategoryCuts
void ReadWeightsFromXML(void *wghtnode)
read weights of sub-classifiers of MethodCategory from xml weight file
The Reader class serves to use the MVAs in a specific analysis context.
void GetHelpMessage() const
Get help message text.
Class to perform two class classification.
std::vector< TString > fVars
create variable transformations