Revision e60bc961b69056a4925f129d0a2042471f999042 authored by Rene Brun on 19 September 2006, 14:37:13 UTC, committed by Rene Brun on 19 September 2006, 14:37:13 UTC
some changes in the class TGeoPNEntry (needed for alignment purposes): 1. Constructor of TGeoPNEntry performs a check upon definition of a symbolic link to a physical node. The check is done redundantly also upon creation of a physical node starting from a symbolic link to prevent mis-usage of these objects in-between geometries. 2. Allows storage of an additional user-defined TGeoHMatrix. The matrix should be created by the user but once TGeoPNEntry::SetMatrix() is called becomes owned by TGeoManager. git-svn-id: http://root.cern.ch/svn/root/trunk@16298 27541ba8-7e3a-0410-8455-c3a389f83636
1 parent cc15e88
MethodCuts.h
// @(#)root/tmva $Id: MethodCuts.h,v 1.9 2006/05/23 09:53:10 stelzer Exp $
// Author: Andreas Hoecker, Peter Speckmayer, Helge Voss, Kai Voss
/**********************************************************************************
* Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
* Package: TMVA *
* Class : MethodCuts *
* *
* Description: *
* Multivariate optimisation of signal efficiency for given background *
* efficiency, using rectangular minimum and maximum requirements on *
* input variables *
* *
* Authors (alphabetical): *
* Andreas Hoecker <Andreas.Hocker@cern.ch> - CERN, Switzerland *
* Peter Speckmayer <speckmay@mail.cern.ch> - CERN, Switzerland *
* Helge Voss <Helge.Voss@cern.ch> - MPI-KP Heidelberg, Germany *
* Kai Voss <Kai.Voss@cern.ch> - U. of Victoria, Canada *
* *
* Copyright (c) 2005: *
* CERN, Switzerland, *
* U. of Victoria, Canada, *
* MPI-KP Heidelberg, Germany, *
* LAPP, Annecy, France *
* *
* Redistribution and use in source and binary forms, with or without *
* modification, are permitted according to the terms listed in LICENSE *
* (http://mva.sourceforge.net/license.txt) *
* *
**********************************************************************************/
#ifndef ROOT_TMVA_MethodCuts
#define ROOT_TMVA_MethodCuts
//////////////////////////////////////////////////////////////////////////
// //
// MethodCuts //
// //
// Multivariate optimisation of signal efficiency for given background //
// efficiency, using rectangular minimum and maximum requirements on //
// input variables //
// //
//////////////////////////////////////////////////////////////////////////
#ifndef ROOT_TMVA_MethodBase
#include "TMVA/MethodBase.h"
#endif
#ifndef ROOT_TMVA_BinarySearchTree
#include "TMVA/BinarySearchTree.h"
#endif
#ifndef ROOT_TMVA_PDF
#include "TMVA/PDF.h"
#endif
#ifndef ROOT_TMVA_GeneticBase
#include "TMVA/GeneticBase.h"
#endif
class TRandom;
namespace TMVA {
class MethodCuts : public MethodBase {
public:
MethodCuts( TString jobName,
vector<TString>* theVariables,
TTree* theTree = 0,
TString theOption = "MC:150:10000:",
TDirectory* theTargetFile = 0 );
MethodCuts( vector<TString> *theVariables,
TString theWeightFile,
TDirectory* theTargetDir = NULL );
virtual ~MethodCuts( void );
// training method
virtual void Train( void );
// write weights to file
virtual void WriteWeightsToFile( void );
// read weights from file
virtual void ReadWeightsFromFile( void );
// calculate the MVA value (for CUTs this is just a dummy)
virtual Double_t GetMvaValue( Event *e );
// write method specific histos to target file
virtual void WriteHistosToFile( void );
// indivudual initialistion of testing of each method test the method
virtual void TestInitLocal(TTree * testTree);
// also overwrite:
virtual Double_t GetSignificance( void ) { return 0; }
virtual Double_t GetSeparation ( void ) { return 0; }
virtual Double_t GetmuTransform ( TTree *) { return 0; }
virtual Double_t GetEfficiency ( TString, TTree *);
// accessors for Minuit
Double_t ComputeEstimator( const std::vector<Double_t> & );
void SetTestSignalEfficiency( Double_t eff ) { fTestSignalEff = eff; }
// static pointer to this object
static MethodCuts* ThisCuts( void ) { return fgThisCuts; }
protected:
private:
// determines type of data to be optimised
enum ConstrainType { kConstrainEffS = 0,
kConstrainEffB } fConstrainType;
// optimisation method
enum FitMethodType { kUseMonteCarlo = 0,
kUseGeneticAlgorithm };
// efficiency calculation method
// - kUseEventSelection: computes efficiencies from given data sample
// - kUsePDFs : creates smoothed PDFs from data samples, and
// uses this to compute efficiencies
enum EffMethod { kUseEventSelection = 0,
kUsePDFs };
// improve the Monte Carlo by providing some additional information
enum FitParameters { kNotEnforced = 0,
kForceMin,
kForceMax,
kForceSmart,
kForceVerySmart };
// general
FitMethodType fFitMethod; // chosen fit method
EffMethod fEffMethod; // chosen efficiency calculation method
vector<FitParameters>* fFitParams; // vector for series of fit methods
Double_t fTestSignalEff; // used to test optimized signal efficiency
Double_t fEffSMin; // used to test optimized signal efficiency
Double_t fEffSMax; // used to test optimized signal efficiency
// for the use of the binary tree method
BinarySearchTree* fBinaryTreeS;
BinarySearchTree* fBinaryTreeB;
// GA
Int_t fGa_nsteps; // GA settings: number of steps
Int_t fGa_preCalc; // GA settings: number of pre-calc steps
Int_t fGa_SC_steps; // GA settings: SC_steps
Int_t fGa_SC_offsteps; // GA settings: SC_offsteps
Double_t fGa_SC_factor; // GA settings: SC_factor
Double_t fEffRef; // reference efficiency
vector<Int_t>* fRangeSign; // used to match cuts to fit parameters (and vice versa)
TRandom* fTrandom; // random generator for MC optimisation method
Int_t fNpar; // number of parameters in fit (default: 2*Nvar)
// basic statistics
vector<Double_t>* fMeanS; // means of variables (signal)
vector<Double_t>* fMeanB; // means of variables (background)
vector<Double_t>* fRmsS; // RMSs of variables (signal)
vector<Double_t>* fRmsB; // RMSs of variables (background)
vector<Double_t>* fXmin; // minimum values of variables
vector<Double_t>* fXmax; // maximum values of variables
TH1* fEffBvsSLocal; // intermediate eff. background versus eff signal histo
// PDF section
vector<TH1*>* fVarHistS; // reference histograms (signal)
vector<TH1*>* fVarHistB; // reference histograms (background)
vector<TH1*>* fVarHistS_smooth; // smoothed reference histograms (signal)
vector<TH1*>* fVarHistB_smooth; // smoothed reference histograms (background)
vector<PDF*>* fVarPdfS; // reference PDFs (signal)
vector<PDF*>* fVarPdfB; // reference PDFs (background)
// MC method
Int_t fNRandCuts; // number of random cut samplings
Double_t** fCutMin; // minimum requirement
Double_t** fCutMax; // maximum requirement
Double_t* fTmpCutMin; // temporary minimum requirement
Double_t* fTmpCutMax; // temporary maximum requirement
static MethodCuts* fgThisCuts; // needed for function reference (GA)
// the definition of fit parameters can be different from the actual
// cut requirements; these functions provide the matching
void MatchParsToCuts ( const std::vector<Double_t> &, Double_t*, Double_t* );
void MatchParsToCuts ( Double_t*, Double_t*, Double_t* );
void MatchCutsToPars ( Double_t*, Double_t*, Double_t* );
// creates PDFs in case these are used to compute efficiencies
// (corresponds to: EffMethod == kUsePDFs)
void CreateVariablePDFs ( void );
// checks ordering of variables in vectors
Bool_t SanityChecks ( void );
// returns signal and background efficiencies for given cuts - using event counting
void GetEffsfromSelection( Double_t* cutMin, Double_t* cutMax,
Double_t& effS, Double_t& effB);
// returns signal and background efficiencies for given cuts - using PDFs
void GetEffsfromPDFs ( Double_t* cutMin, Double_t* cutMax,
Double_t& effS, Double_t& effB );
// default initialisation method called by all constructors
void InitCuts( void );
ClassDef(MethodCuts,0) // Multivariate optimisation of signal efficiency
};
} // namespace TMVA
#endif
Computing file changes ...
