Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
MethodFDA.h
Go to the documentation of this file.
1// @(#)root/tmva $Id$
2// Author: Andreas Hoecker, Peter Speckmayer
3
4/**********************************************************************************
5 * Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
6 * Package: TMVA *
7 * Class : MethodFDA *
8 * *
9 * *
10 * Description: *
11 * Function discriminant analysis (FDA). This simple classifier *
12 * fits any user-defined TFormula (via option configuration string) to *
13 * the training data by requiring a formula response of 1 (0) to signal *
14 * (background) events. The parameter fitting is done via the abstract *
15 * class FitterBase, featuring Monte Carlo sampling, Genetic *
16 * Algorithm, Simulated Annealing, MINUIT and combinations of these. *
17 * *
18 * Authors (alphabetical): *
19 * Andreas Hoecker <Andreas.Hocker@cern.ch> - CERN, Switzerland *
20 * Peter Speckmayer <speckmay@mail.cern.ch> - CERN, Switzerland *
21 * *
22 * Copyright (c) 2005-2010: *
23 * CERN, Switzerland *
24 * MPI-K Heidelberg, Germany *
25 * *
26 * Redistribution and use in source and binary forms, with or without *
27 * modification, are permitted according to the terms listed in LICENSE *
28 * (see tmva/doc/LICENSE) *
29 **********************************************************************************/
30
31#ifndef ROOT_TMVA_MethodFDA
32#define ROOT_TMVA_MethodFDA
33
34//////////////////////////////////////////////////////////////////////////
35// //
36// MethodFDA //
37// //
38// Function discriminant analysis (FDA). This simple classifier //
39// fits any user-defined TFormula (via option configuration string) to //
40// the training data by requiring a formula response of 1 (0) to signal //
41// (background) events. The parameter fitting is done via the abstract //
42// class FitterBase, featuring Monte Carlo sampling, Genetic //
43// Algorithm, Simulated Annealing, MINUIT and combinations of these. //
44// //
45// Can compute one-dimensional regression //
46// //
47//////////////////////////////////////////////////////////////////////////
48
49#include "TMVA/MethodBase.h"
50#include "TMVA/IFitterTarget.h"
51#include <vector>
52
53class TFormula;
54
55namespace TMVA {
56
57 class Interval;
58 class Event;
59 class FitterBase;
60
61 class MethodFDA : public MethodBase, public IFitterTarget {
62
63 public:
64
65 MethodFDA( const TString& jobName,
66 const TString& methodTitle,
67 DataSetInfo& theData,
68 const TString& theOption = "");
69
70 MethodFDA( DataSetInfo& theData,
71 const TString& theWeightFile);
72
73 virtual ~MethodFDA( void );
74
75 Bool_t HasAnalysisType( Types::EAnalysisType type, UInt_t numberClasses, UInt_t numberTargets );
76
77 // training method
78 void Train( void );
79
81
82 void AddWeightsXMLTo ( void* parent ) const;
83
84 void ReadWeightsFromStream( std::istream & i );
85 void ReadWeightsFromXML ( void* wghtnode );
86
87 // calculate the MVA value
88 Double_t GetMvaValue( Double_t* err = nullptr, Double_t* errUpper = nullptr );
89
90 virtual const std::vector<Float_t>& GetRegressionValues();
91 virtual const std::vector<Float_t>& GetMulticlassValues();
92
93 void Init( void );
94
95 // ranking of input variables
96 const Ranking* CreateRanking() { return nullptr; }
97
98 Double_t EstimatorFunction( std::vector<Double_t>& );
99
100 // no check of options at this place
101 void CheckSetup() {}
102
103 protected:
104
105 // make ROOT-independent C++ class for classifier response (classifier-specific implementation)
106 void MakeClassSpecific( std::ostream&, const TString& ) const;
107
108 // get help message text
109 void GetHelpMessage() const;
110
111 private:
112
113 // compute multiclass values
114 void CalculateMulticlassValues( const TMVA::Event*& evt, std::vector<Double_t>& parameters, std::vector<Float_t>& values);
115
116
117 // create and interpret formula expression and compute estimator
118 void CreateFormula ();
119 Double_t InterpretFormula( const Event*, std::vector<Double_t>::iterator begin, std::vector<Double_t>::iterator end );
120
121 // clean up
122 void ClearAll();
123
124 // print fit results
125 void PrintResults( const TString&, std::vector<Double_t>&, const Double_t ) const;
126
127 // the option handling methods
128 void DeclareOptions();
129 void ProcessOptions();
130
131 TString fFormulaStringP; ///< string with function
132 TString fParRangeStringP; ///< string with ranges of parameters
133 TString fFormulaStringT; ///< string with function
134 TString fParRangeStringT; ///< string with ranges of parameters
135
136 TFormula* fFormula; ///< the discrimination function
137 UInt_t fNPars; ///< number of parameters
138 std::vector<Interval*> fParRange; ///< ranges of parameters
139 std::vector<Double_t> fBestPars; ///< the pars that optimise (minimise) the estimator
140 TString fFitMethod; ///< estimator optimisation method
141 TString fConverger; ///< fit method uses fConverger as intermediate step to converge into local minimas
142 FitterBase* fFitter; ///< the fitter used in the training
143 IFitterTarget* fConvergerFitter; ///< intermediate fitter
144
145
146 // sum of weights (this should become centrally available through the dataset)
147 Double_t fSumOfWeightsSig; ///< sum of weights (signal)
148 Double_t fSumOfWeightsBkg; ///< sum of weights (background)
149 Double_t fSumOfWeights; ///< sum of weights
150
151 //
152 Int_t fOutputDimensions; ///< number of output values
153
154 ClassDef(MethodFDA,0); // Function Discriminant Analysis
155 };
156
157} // namespace TMVA
158
159#endif // MethodFDA_H
double Double_t
Definition RtypesCore.h:59
#define ClassDef(name, id)
Definition Rtypes.h:337
Option_t Option_t TPoint TPoint const char GetTextMagnitude GetFillStyle GetLineColor GetLineWidth GetMarkerStyle GetTextAlign GetTextColor GetTextSize void char Point_t Rectangle_t WindowAttributes_t Float_t Float_t Float_t Int_t Int_t UInt_t UInt_t Rectangle_t Int_t Int_t Window_t TString Int_t GCValues_t GetPrimarySelectionOwner GetDisplay GetScreen GetColormap GetNativeEvent const char const char dpyName wid window const char font_name cursor keysym reg const char only_if_exist regb h Point_t winding char text const char depth char const char Int_t count const char ColorStruct_t color const char Pixmap_t Pixmap_t PictureAttributes_t attr const char char ret_data h unsigned char height h Atom_t Int_t ULong_t ULong_t unsigned char prop_list Atom_t Atom_t Atom_t Time_t type
The Formula class.
Definition TFormula.h:89
Class that contains all the data information.
Definition DataSetInfo.h:62
Base class for TMVA fitters.
Definition FitterBase.h:51
Interface for a fitter 'target'.
Virtual base Class for all MVA method.
Definition MethodBase.h:111
virtual void ReadWeightsFromStream(std::istream &)=0
Function discriminant analysis (FDA).
Definition MethodFDA.h:61
void Train(void)
FDA training.
TString fFormulaStringT
string with function
Definition MethodFDA.h:133
void AddWeightsXMLTo(void *parent) const
create XML description for LD classification and regression (for arbitrary number of output classes/t...
Double_t EstimatorFunction(std::vector< Double_t > &)
compute estimator for given parameter set (to be minimised)
void CheckSetup()
check may be overridden by derived class (sometimes, eg, fitters are used which can only be implement...
Definition MethodFDA.h:101
virtual ~MethodFDA(void)
destructor
Double_t InterpretFormula(const Event *, std::vector< Double_t >::iterator begin, std::vector< Double_t >::iterator end)
formula interpretation
Bool_t HasAnalysisType(Types::EAnalysisType type, UInt_t numberClasses, UInt_t numberTargets)
FDA can handle classification with 2 classes and regression with one regression-target.
void ReadWeightsFromXML(void *wghtnode)
read coefficients from xml weight file
void CalculateMulticlassValues(const TMVA::Event *&evt, std::vector< Double_t > &parameters, std::vector< Float_t > &values)
calculate the values for multiclass
void ReadWeightsFromStream(std::istream &i)
read back the training results from a file (stream)
virtual const std::vector< Float_t > & GetMulticlassValues()
Double_t fSumOfWeightsBkg
sum of weights (background)
Definition MethodFDA.h:148
Int_t fOutputDimensions
number of output values
Definition MethodFDA.h:152
void Init(void)
default initialisation
void ClearAll()
delete and clear all class members
std::vector< Interval * > fParRange
ranges of parameters
Definition MethodFDA.h:138
void PrintResults(const TString &, std::vector< Double_t > &, const Double_t) const
display fit parameters check maximum length of variable name
void MakeClassSpecific(std::ostream &, const TString &) const
write FDA-specific classifier response
Double_t fSumOfWeightsSig
sum of weights (signal)
Definition MethodFDA.h:147
TString fParRangeStringP
string with ranges of parameters
Definition MethodFDA.h:132
TFormula * fFormula
the discrimination function
Definition MethodFDA.h:136
const Ranking * CreateRanking()
Definition MethodFDA.h:96
virtual const std::vector< Float_t > & GetRegressionValues()
void ProcessOptions()
the option string is decoded, for available options see "DeclareOptions"
std::vector< Double_t > fBestPars
the pars that optimise (minimise) the estimator
Definition MethodFDA.h:139
IFitterTarget * fConvergerFitter
intermediate fitter
Definition MethodFDA.h:143
FitterBase * fFitter
the fitter used in the training
Definition MethodFDA.h:142
Double_t fSumOfWeights
sum of weights
Definition MethodFDA.h:149
TString fParRangeStringT
string with ranges of parameters
Definition MethodFDA.h:134
TString fFitMethod
estimator optimisation method
Definition MethodFDA.h:140
void CreateFormula()
translate formula string into TFormula, and parameter string into par ranges
void DeclareOptions()
define the options (their key words) that can be set in the option string
Double_t GetMvaValue(Double_t *err=nullptr, Double_t *errUpper=nullptr)
returns MVA value for given event
UInt_t fNPars
number of parameters
Definition MethodFDA.h:137
TString fConverger
fit method uses fConverger as intermediate step to converge into local minimas
Definition MethodFDA.h:141
void GetHelpMessage() const
get help message text
TString fFormulaStringP
string with function
Definition MethodFDA.h:131
Ranking for variables in method (implementation)
Definition Ranking.h:48
Basic string class.
Definition TString.h:139
create variable transformations