Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
GeneticFitter.cxx
Go to the documentation of this file.
1// @(#)root/tmva $Id$
2// Author: Peter Speckmayer
3
4/**********************************************************************************
5 * Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
6 * Package: TMVA *
7 * Class : GeneticFitter *
8 * Web : http://tmva.sourceforge.net *
9 * *
10 * Description: *
11 * Implementation *
12 * *
13 * Authors (alphabetical): *
14 * Peter Speckmayer <speckmay@mail.cern.ch> - CERN, Switzerland *
15 * *
16 * Copyright (c) 2005: *
17 * CERN, Switzerland *
18 * MPI-K Heidelberg, Germany *
19 * *
20 * Redistribution and use in source and binary forms, with or without *
21 * modification, are permitted according to the terms listed in LICENSE *
22 * (http://tmva.sourceforge.net/LICENSE) *
23 **********************************************************************************/
24
25/*! \class TMVA::GeneticFitter
26\ingroup TMVA
27
28Fitter using a Genetic Algorithm.
29
30*/
31
32#include "TMVA/GeneticFitter.h"
33
34#include "TMVA/Configurable.h"
36#include "TMVA/Interval.h"
37#include "TMVA/FitterBase.h"
38#include "TMVA/MsgLogger.h"
39#include "TMVA/Timer.h"
40#include "TMVA/Types.h"
41
42#include "Rtypes.h"
43#include "TString.h"
44
46
47////////////////////////////////////////////////////////////////////////////////
48/// constructor
49
51 const TString& name,
52 const std::vector<TMVA::Interval*>& ranges,
53 const TString& theOption )
54: FitterBase( target, name, ranges, theOption )
55{
56 // default parameters settings for Genetic Algorithm
59}
60
61////////////////////////////////////////////////////////////////////////////////
62/// declare GA options
63
65{
66 DeclareOptionRef( fPopSize=300, "PopSize", "Population size for GA" );
67 DeclareOptionRef( fNsteps=40, "Steps", "Number of steps for convergence" );
68 DeclareOptionRef( fCycles=3, "Cycles", "Independent cycles of GA fitting" );
69 DeclareOptionRef( fSC_steps=10, "SC_steps", "Spread control, steps" );
70 DeclareOptionRef( fSC_rate=5, "SC_rate", "Spread control, rate: factor is changed depending on the rate" );
71 DeclareOptionRef( fSC_factor=0.95, "SC_factor", "Spread control, factor" );
72 DeclareOptionRef( fConvCrit=0.001, "ConvCrit", "Convergence criteria" );
73
74 DeclareOptionRef( fSaveBestFromGeneration=1, "SaveBestGen",
75 "Saves the best n results from each generation. They are included in the last cycle" );
76 DeclareOptionRef( fSaveBestFromCycle=10, "SaveBestCycle",
77 "Saves the best n results from each cycle. They are included in the last cycle. The value should be set to at least 1.0" );
78
79 DeclareOptionRef( fTrim=kFALSE, "Trim",
80 "Trim the population to PopSize after assessing the fitness of each individual" );
81 DeclareOptionRef( fSeed=100, "Seed", "Set seed of random generator (0 gives random seeds)" );
82}
83
84////////////////////////////////////////////////////////////////////////////////
85/// set GA configuration parameters
86
88 Int_t nsteps,
89 Int_t popSize,
90 Int_t SC_steps,
91 Int_t SC_rate,
92 Double_t SC_factor,
93 Double_t convCrit)
94{
95 fNsteps = nsteps;
96 fCycles = cycles;
97 fPopSize = popSize;
98 fSC_steps = SC_steps;
99 fSC_rate = SC_rate;
100 fSC_factor = SC_factor;
101 fConvCrit = convCrit;
102}
103
104////////////////////////////////////////////////////////////////////////////////
105/// Execute fitting
106
107Double_t TMVA::GeneticFitter::Run( std::vector<Double_t>& pars )
108{
109 Log() << kHEADER << "<GeneticFitter> Optimisation, please be patient "
110 << "... (inaccurate progress timing for GA)" << Endl;
111
112 GetFitterTarget().ProgressNotifier( "GA", "init" );
113
114 GeneticAlgorithm gstore( GetFitterTarget(), fPopSize, fRanges);
115 // gstore.SetMakeCopies(kTRUE); // commented out, because it reduces speed
116
117 // timing of GA
118 Timer timer( 100*(fCycles), GetName() );
119 if (fIPyMaxIter) *fIPyMaxIter = 100*(fCycles);
120 timer.DrawProgressBar( 0 );
121
122 Double_t progress = 0.;
123
124 for (Int_t cycle = 0; cycle < fCycles; cycle++) {
125 if (fIPyCurrentIter) *fIPyCurrentIter = 100*(cycle);
126 if (fExitFromTraining && *fExitFromTraining) break;
127 GetFitterTarget().ProgressNotifier( "GA", "cycle" );
128 // ---- perform series of fits to achieve best convergence
129
130 // "m_ga_spread" times the number of variables
131 GeneticAlgorithm ga( GetFitterTarget(), fPopSize, fRanges, fSeed );
132 // ga.SetMakeCopies(kTRUE); // commented out, because it reduces speed
133
134 if ( pars.size() == fRanges.size() ){
135 ga.GetGeneticPopulation().GiveHint( pars, 0.0 );
136 }
137 if (cycle==fCycles-1) {
138 GetFitterTarget().ProgressNotifier( "GA", "last" );
140 }
141
142 GetFitterTarget().ProgressNotifier( "GA", "iteration" );
143
144 ga.CalculateFitness();
146
147 Double_t n=0.;
148 do {
149 GetFitterTarget().ProgressNotifier( "GA", "iteration" );
150 ga.Init();
151 ga.CalculateFitness();
152 if ( fTrim ) ga.GetGeneticPopulation().TrimPopulation();
153 ga.SpreadControl( fSC_steps, fSC_rate, fSC_factor );
154
155 // monitor progrss
156 if (ga.fConvCounter > n) n = Double_t(ga.fConvCounter);
157 progress = 100*((Double_t)cycle) + 100*(n/Double_t(fNsteps));
158
159 timer.DrawProgressBar( (Int_t)progress );
160
161 // Copy the best genes of the generation
163 for ( Int_t i = 0; i<fSaveBestFromGeneration && i<fPopSize; i++ ) {
166 }
167 } while (!ga.HasConverged( fNsteps, fConvCrit ));
168
169 timer.DrawProgressBar( 100*(cycle+1) );
170
172 for ( Int_t i = 0; i<fSaveBestFromGeneration && i<fPopSize; i++ ) {
175 }
176 }
177
178 // get elapsed time
179 Log() << kINFO << "Elapsed time: " << timer.GetElapsedTime()
180 << " " << Endl;
181
182 Double_t fitness = gstore.CalculateFitness();
183 gstore.GetGeneticPopulation().Sort();
184 pars.swap( gstore.GetGeneticPopulation().GetGenes(0)->GetFactors() );
185
186 GetFitterTarget().ProgressNotifier( "GA", "stop" );
187 return fitness;
188}
constexpr Bool_t kFALSE
Definition RtypesCore.h:101
double Double_t
Definition RtypesCore.h:59
#define ClassImp(name)
Definition Rtypes.h:377
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 target
char name[80]
Definition TGX11.cxx:110
virtual void ParseOptions()
options parser
Base class for TMVA fitters.
Definition FitterBase.h:51
Double_t Run()
estimator function interface for fitting
Base definition for genetic algorithm.
virtual Double_t SpreadControl(Int_t steps, Int_t ofSteps, Double_t factor)
this function provides the ability to change the stepSize of a mutation according to the success of t...
virtual Bool_t HasConverged(Int_t steps=10, Double_t ratio=0.1)
gives back true if the last "steps" steps have lead to an improvement of the "fitness" of the "indivi...
GeneticPopulation & GetGeneticPopulation()
void Init()
calls evolution, but if it is not the first time.
virtual Double_t CalculateFitness()
starts the evaluation of the fitness of all different individuals of the population.
Fitter using a Genetic Algorithm.
void DeclareOptions()
declare GA options
void SetParameters(Int_t cycles, Int_t nsteps, Int_t popSize, Int_t SC_steps, Int_t SC_rate, Double_t SC_factor, Double_t convCrit)
set GA configuration parameters
GeneticFitter(IFitterTarget &target, const TString &name, const std::vector< TMVA::Interval * > &ranges, const TString &theOption)
constructor
std::vector< Double_t > & GetFactors()
Double_t GetFitness() const
void Sort()
sort the genepool according to the fitness of the individuals
void TrimPopulation()
trim the population to the predefined size
GeneticGenes * GetGenes(Int_t index)
gives back the "Genes" of the population with the given index.
void GiveHint(std::vector< Double_t > &hint, Double_t fitness=0)
add an individual (a set of variables) to the population if there is a set of variables which is know...
void AddPopulation(GeneticPopulation *strangers)
add another population (strangers) to the one of this GeneticPopulation
Interface for a fitter 'target'.
Timing information for training and evaluation of MVA methods.
Definition Timer.h:58
TString GetElapsedTime(Bool_t Scientific=kTRUE)
returns pretty string with elapsed time
Definition Timer.cxx:146
void DrawProgressBar(Int_t, const TString &comment="")
draws progress bar in color or B&W caution:
Definition Timer.cxx:202
Basic string class.
Definition TString.h:139
const Int_t n
Definition legend1.C:16
MsgLogger & Endl(MsgLogger &ml)
Definition MsgLogger.h:148