diff --git a/tmva/tmva/inc/TMVA/Envelope.h b/tmva/tmva/inc/TMVA/Envelope.h
index 315a1ba9367d9979143570d6a8a83edf87200a68..ae6f663316e19eeeba3a5d7027a5c85c93d6ee8a 100644
--- a/tmva/tmva/inc/TMVA/Envelope.h
+++ b/tmva/tmva/inc/TMVA/Envelope.h
@@ -44,23 +44,17 @@
#endif
-namespace TMVA {
-
- /**
- * \class Envelope
- * Base class for all machine learning algorithms
- * \ingroup TMVA
- */
-
+namespace TMVA {
+
class Envelope:public Configurable
{
protected:
OptionMap fMethod; //Booked method information
- std::shared_ptr<DataLoader> fDataLoader; //data
+ std::shared_ptr<DataLoader> fDataLoader; //data
std::shared_ptr<TFile> fFile; //!file to save the results
Bool_t fModelPersistence; //flag to save the trained model
Bool_t fVerbose; //flag for extra information
-
+
/**
Constructor for the initialization of Envelopes,
differents Envelopes may needs differents constructors then
@@ -72,13 +66,13 @@ namespace TMVA {
*/
Envelope(const TString &name,DataLoader *dataloader=nullptr,TFile *file=nullptr,const TString options="");
-
+
public:
/**
Default destructor
*/
~Envelope();
-
+
/**
Method to book the machine learning method to perform the algorithm.
\param methodname String with the name of the mva method
@@ -110,13 +104,13 @@ namespace TMVA {
\param file pointer to TFile object.
*/
void SetFile(TFile *file);
-
+
/**
Method to get the pointer to TMVA::DataLoader object.
\return pointer to TMVA::DataLoader object.
*/
DataLoader *GetDataLoader();
-
+
/**
Method to set the pointer to TMVA::DataLoader object.
\param file pointer to TFile object.
@@ -128,56 +122,56 @@ namespace TMVA {
\return Boolean with the status.
*/
Bool_t IsModelPersistence();
-
+
/**
Method enable model persistence, then algorithms model is saved in xml or serialized files.
\param status Boolean with the status.
*/
void SetModelPersistence(Bool_t status=kTRUE);
-
+
/**
Method to see if the algorithm should print extra information.
\return Boolean with the status.
*/
Bool_t IsVerbose();
-
+
/**
Method enable print extra information in the algorithms.
\param status Boolean with the status.
*/
void SetVerbose(Bool_t status);
-
+
/**
- Virtual method to be implmented with your algorithm.
+ Virtual method to be implemented with your algorithm.
*/
virtual void Evaluate() = 0;
-
+
protected:
/**
Method get the Booked method in a option map object.
\return TMVA::OptionMap with the information of the Booked method
*/
OptionMap &GetMethod();
-
+
/**
Utility method to get TMVA::DataInputHandler reference from the DataLoader.
\return TMVA::DataInputHandler reference.
*/
DataInputHandler& GetDataLoaderDataInput() { return *fDataLoader->fDataInputHandler; }
-
+
/**
Utility method to get TMVA::DataSetInfo reference from the DataLoader.
\return TMVA::DataSetInfo reference.
*/
DataSetInfo& GetDataLoaderDataSetInfo(){return fDataLoader->DefaultDataSetInfo();}
-
+
/**
Utility method to get TMVA::DataSetManager pointer from the DataLoader.
\return TMVA::DataSetManager pointer.
*/
DataSetManager* GetDataLoaderDataSetManager(){return fDataLoader->fDataSetManager;}
ClassDef(Envelope,0);
-
+
};
}
diff --git a/tmva/tmva/inc/TMVA/ExpectedErrorPruneTool.h b/tmva/tmva/inc/TMVA/ExpectedErrorPruneTool.h
index 12fce3c48afee7d16553cd62d92288c8e93e20e4..754182f912c9426c1051aea1121a2b8a40b6c2b2 100644
--- a/tmva/tmva/inc/TMVA/ExpectedErrorPruneTool.h
+++ b/tmva/tmva/inc/TMVA/ExpectedErrorPruneTool.h
@@ -33,7 +33,7 @@
// Uses an upper limit on the error made by the classification done by each node. If the S/S+B of the node //
// is f, then according to the training sample, the error rate (fraction of misclassified events by this //
// node) is (1-f). Now f has a statistical error according to the binomial distribution hence the error on //
-// f can be estimated (same error as the binomial error for efficency calculations //
+// f can be estimated (same error as the binomial error for efficiency calculations //
// ( sigma = sqrt(eff(1-eff)/nEvts ) ) //
// //
// This tool prunes branches from a tree if the expected error of a node is less than that of the sum of //
diff --git a/tmva/tmva/src/Envelope.cxx b/tmva/tmva/src/Envelope.cxx
index 6557e294afadf26fa0aff4aad02685130367e7d6..a764c16d23755c8f4f29fe95b3a7aae94e3f8503 100644
--- a/tmva/tmva/src/Envelope.cxx
+++ b/tmva/tmva/src/Envelope.cxx
@@ -1,6 +1,13 @@
// @(#)root/tmva $Id$
// Author: Omar Zapata
+/*! \class TMVA::Envelope
+\ingroup TMVA
+
+Base class for all machine learning algorithms
+
+*/
+
#include "TMVA/Envelope.h"
#include "TMVA/Configurable.h"
@@ -20,55 +27,69 @@
using namespace TMVA;
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
Envelope::Envelope(const TString &name,DataLoader *dalaloader,TFile *file,const TString options):Configurable(options),fDataLoader(dalaloader),fFile(file),fVerbose(kFALSE)
{
SetName(name.Data());
}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
Envelope::~Envelope()
{}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
Bool_t Envelope::IsSilentFile(){return fFile==nullptr;}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
TFile* Envelope::GetFile(){return fFile.get();}
// TFile* Envelope::GetFile(){return fFile==nullptr?0:fFile.get();}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void Envelope::SetFile(TFile *file){fFile=std::shared_ptr<TFile>(file);}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
Bool_t Envelope::IsVerbose(){return fVerbose;}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void Envelope::SetVerbose(Bool_t status){fVerbose=status;}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
OptionMap &Envelope::GetMethod(){ return fMethod;}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
DataLoader *Envelope::GetDataLoader(){ return fDataLoader.get();}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void Envelope::SetDataLoader(DataLoader *dalaloader){
fDataLoader=std::shared_ptr<DataLoader>(dalaloader) ;
}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
Bool_t TMVA::Envelope::IsModelPersistence(){return fModelPersistence; }
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void TMVA::Envelope::SetModelPersistence(Bool_t status){fModelPersistence=status;}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void TMVA::Envelope::BookMethod(Types::EMVA method, TString methodTitle, TString options){
return BookMethod(Types::Instance().GetMethodName( method ),methodTitle,options);
}
-//______________________________________________________________________________
+////////////////////////////////////////////////////////////////////////////////
+
void TMVA::Envelope::BookMethod(TString methodName, TString methodTitle, TString options){
fMethod["MethodName"] = methodName;
fMethod["MethodTitle"] = methodTitle;
diff --git a/tmva/tmva/src/ExpectedErrorPruneTool.cxx b/tmva/tmva/src/ExpectedErrorPruneTool.cxx
index 87709a4a9277dff0aaab77a731975dfe1893eb37..a4a064c42d9aec108d7e1994391f83361f8ba406 100644
--- a/tmva/tmva/src/ExpectedErrorPruneTool.cxx
+++ b/tmva/tmva/src/ExpectedErrorPruneTool.cxx
@@ -24,6 +24,24 @@
* *
**********************************************************************************/
+/*! \class TMVA::ExpectedErrorPruneTool
+\ingroup TMVA
+
+A helper class to prune a decision tree using the expected error (C4.5) method
+
+Uses an upper limit on the error made by the classification done by each node.
+If the \f$ \frac{S}{S+B} \f$ of the node is \f$ f \f$, then according to the
+training sample, the error rate (fraction of misclassified events by this
+node) is \f$ (1-f) \f$. Now \f$ f \f$ has a statistical error according to the
+binomial distribution hence the error on \f$ f \f$ can be estimated (same error
+as the binomial error for efficiency calculations
+\f$ (\sigma = \sqrt{\frac{(eff(1-eff)}{nEvts}}) \f$
+
+This tool prunes branches from a tree if the expected error of a node is less
+than that of the sum of the error in its descendants.
+
+*/
+
#include "TMVA/ExpectedErrorPruneTool.h"
#include "TMVA/DecisionTree.h"
#include "TMVA/IPruneTool.h"
@@ -62,7 +80,7 @@ TMVA::ExpectedErrorPruneTool::CalculatePruningInfo( DecisionTree* dt,
if( isAutomatic ) {
//SetAutomatic( );
isAutomatic = kFALSE;
- Log() << kWARNING << "Sorry autmoatic pruning strength determination is not implemented yet" << Endl;
+ Log() << kWARNING << "Sorry automatic pruning strength determination is not implemented yet" << Endl;
}
if( dt == NULL || (IsAutomatic() && validationSample == NULL) ) {
// must have a valid decision tree to prune, and if the prune strength
@@ -72,8 +90,8 @@ TMVA::ExpectedErrorPruneTool::CalculatePruningInfo( DecisionTree* dt,
}
fNodePurityLimit = dt->GetNodePurityLimit();
- if(IsAutomatic()) {
- Log() << kFATAL << "Sorry autmoatic pruning strength determination is not implemented yet" << Endl;
+ if(IsAutomatic()) {
+ Log() << kFATAL << "Sorry automatic pruning strength determination is not implemented yet" << Endl;
/*
dt->ApplyValidationSample(validationSample);
Double_t weights = dt->GetSumWeights(validationSample);
@@ -87,8 +105,8 @@ TMVA::ExpectedErrorPruneTool::CalculatePruningInfo( DecisionTree* dt,
Int_t errCount = 0,
lastNodeCount = nnodes;
- // find the maxiumum prune strength that still leaves the root's daughter nodes
-
+ // find the maximum prune strength that still leaves the root's daughter nodes
+
while ( nnodes > 1 && !forceStop ) {
fPruneStrength += fDeltaPruneStrength;
Log() << "----------------------------------------------------" << Endl;
@@ -151,7 +169,7 @@ TMVA::ExpectedErrorPruneTool::CalculatePruningInfo( DecisionTree* dt,
////////////////////////////////////////////////////////////////////////////////
/// recursive pruning of nodes using the Expected Error Pruning (EEP)
-void TMVA::ExpectedErrorPruneTool::FindListOfNodes( DecisionTreeNode* node )
+void TMVA::ExpectedErrorPruneTool::FindListOfNodes( DecisionTreeNode* node )
{
TMVA::DecisionTreeNode *l = (TMVA::DecisionTreeNode*)node->GetLeft();
TMVA::DecisionTreeNode *r = (TMVA::DecisionTreeNode*)node->GetRight();
@@ -169,7 +187,7 @@ void TMVA::ExpectedErrorPruneTool::FindListOfNodes( DecisionTreeNode* node )
/// calculate the expected statistical error on the subtree below "node"
/// which is used in the expected error pruning
-Double_t TMVA::ExpectedErrorPruneTool::GetSubTreeError( DecisionTreeNode* node ) const
+Double_t TMVA::ExpectedErrorPruneTool::GetSubTreeError( DecisionTreeNode* node ) const
{
DecisionTreeNode *l = (DecisionTreeNode*)node->GetLeft();
DecisionTreeNode *r = (DecisionTreeNode*)node->GetRight();
@@ -192,9 +210,10 @@ Double_t TMVA::ExpectedErrorPruneTool::GetSubTreeError( DecisionTreeNode* node )
/// this node) is (1-f)
/// Now f has a statistical error according to the binomial distribution
/// hence the error on f can be estimated (same error as the binomial error
-/// for efficency calculations ( sigma = sqrt(eff(1-eff)/nEvts ) )
+/// for efficiency calculations
+/// \f$ (\sigma = \sqrt{\frac{(eff(1-eff)}{nEvts}}) \f$
-Double_t TMVA::ExpectedErrorPruneTool::GetNodeError( DecisionTreeNode *node ) const
+Double_t TMVA::ExpectedErrorPruneTool::GetNodeError( DecisionTreeNode *node ) const
{
Double_t errorRate = 0;
@@ -224,13 +243,13 @@ Double_t TMVA::ExpectedErrorPruneTool::GetNodeError( DecisionTreeNode *node ) co
// leaf node ( N_leaf / N_parent)
// step 3:
- // Minimum Error Pruning (MEP) accordig to Niblett/Bratko
+ // Minimum Error Pruning (MEP) according to Niblett/Bratko
//# of correctly classified events by this node:
//Double_t n=f*nEvts ;
//Double_t p_apriori = 0.5, m=100;
//errorRate = (nEvts - n + (1-p_apriori) * m ) / (nEvts + m);
- // Pessimistic error Pruing (proposed by Quinlan (error estimat with continuity approximation)
+ // Pessimistic error Pruning (proposed by Quinlan (error estimat with continuity approximation)
//# of correctly classified events by this node:
//Double_t n=f*nEvts ;
//errorRate = (nEvts - n + 0.5) / nEvts ;
@@ -246,4 +265,3 @@ Double_t TMVA::ExpectedErrorPruneTool::GetNodeError( DecisionTreeNode *node ) co
return errorRate;
}
-
diff --git a/tmva/tmva/src/FitterBase.cxx b/tmva/tmva/src/FitterBase.cxx
index 55e57429ae3033b15d2a1df1d63d0a6e49303562..7c87288de15210a84803629d5f7c6d36baf9f40a 100644
--- a/tmva/tmva/src/FitterBase.cxx
+++ b/tmva/tmva/src/FitterBase.cxx
@@ -1,4 +1,4 @@
-// @(#)root/tmva $Id$
+// @(#)root/tmva $Id$
// Author: Andreas Hoecker, Peter Speckmayer, Joerg Stelzer, Helge Voss
/**********************************************************************************
@@ -17,22 +17,20 @@
* Helge Voss <Helge.Voss@cern.ch> - MPI-K Heidelberg, Germany *
* *
* Copyright (c) 2005: *
- * CERN, Switzerland *
- * MPI-K Heidelberg, Germany *
+ * CERN, Switzerland *
+ * MPI-K Heidelberg, Germany *
* *
* Redistribution and use in source and binary forms, with or without *
* modification, are permitted according to the terms listed in LICENSE *
* (http://tmva.sourceforge.net/LICENSE) *
**********************************************************************************/
-////////////////////////////////////////////////////////////////////////////////
+/*! \class TMVA::FitterBase
+\ingroup TMVA
-/*
- FitterBase
+Base class for TMVA fitters. Also defines generalised fitting interface
- Baseclass for TMVA fitters. Also defines generalised fitting interface
*/
-//_______________________________________________________________________
#include "TMVA/FitterBase.h"
#ifndef ROOT_TMVA_Interval
@@ -57,12 +55,12 @@ ClassImp(TMVA::FitterBase)
#endif
////////////////////////////////////////////////////////////////////////////////
-/// constructor
+/// constructor
-TMVA::FitterBase::FitterBase( IFitterTarget& target,
- const TString& name,
- const std::vector<Interval*> ranges,
- const TString& theOption )
+TMVA::FitterBase::FitterBase( IFitterTarget& target,
+ const TString& name,
+ const std::vector<Interval*> ranges,
+ const TString& theOption )
: Configurable( theOption ),
fFitterTarget( target ),
fRanges( ranges ),
@@ -75,7 +73,7 @@ TMVA::FitterBase::FitterBase( IFitterTarget& target,
}
////////////////////////////////////////////////////////////////////////////////
-/// estimator function interface for fitting
+/// estimator function interface for fitting
Double_t TMVA::FitterBase::Run()
{
@@ -83,13 +81,13 @@ Double_t TMVA::FitterBase::Run()
for (std::vector<Interval*>::const_iterator parIt = fRanges.begin(); parIt != fRanges.end(); parIt++) {
pars.push_back( (*parIt)->GetMean() );
}
-
+
// delete fLogger;
return this->Run( pars );
}
////////////////////////////////////////////////////////////////////////////////
-/// estimator function interface for fitting
+/// estimator function interface for fitting
Double_t TMVA::FitterBase::EstimatorFunction( std::vector<Double_t>& parameters )
{
diff --git a/tmva/tmva/src/GeneticAlgorithm.cxx b/tmva/tmva/src/GeneticAlgorithm.cxx
index 0083f5d9f634068890ea993b7a2b5f54cc66a115..09c4745f591ccd2cc90b2c6fb5b142bc72139c19 100644
--- a/tmva/tmva/src/GeneticAlgorithm.cxx
+++ b/tmva/tmva/src/GeneticAlgorithm.cxx
@@ -1,4 +1,4 @@
-// @(#)root/tmva $Id$
+// @(#)root/tmva $Id$
// Author: Peter Speckmayer
/**********************************************************************************
@@ -22,10 +22,12 @@
* (http://tmva.sourceforge.net/LICENSE) *
**********************************************************************************/
-//_______________________________________________________________________
-//
-// Base definition for genetic algorithm
-//_______________________________________________________________________
+/*! \class TMVA::GeneticAlgorithm
+\ingroup TMVA
+
+Base definition for genetic algorithm
+
+*/
#include <iostream>
#include <algorithm>
@@ -50,19 +52,22 @@ namespace TMVA {
}
ClassImp(TMVA::GeneticAlgorithm)
-
+
////////////////////////////////////////////////////////////////////////////////
/// Constructor
-/// Parameters:
-/// int populationSize : defines the number of "Individuals" which are created and tested
+///
+/// Parameters:
+///
+/// - int populationSize : defines the number of "Individuals" which are created and tested
/// within one Generation (Iteration of the Evolution)
-/// std::vector<TMVA::Interval*> ranges : Interval holds the information of an interval, where the GetMin
+/// - std::vector<TMVA::Interval*> ranges : Interval holds the information of an interval, where the GetMin
/// gets the low and GetMax gets the high constraint of the variable
/// the size of "ranges" is the number of coefficients which are optimised
-/// Purpose:
+/// Purpose:
+///
/// Creates a random population with individuals of the size ranges.size()
-TMVA::GeneticAlgorithm::GeneticAlgorithm( IFitterTarget& target, Int_t populationSize,
+TMVA::GeneticAlgorithm::GeneticAlgorithm( IFitterTarget& target, Int_t populationSize,
const std::vector<Interval*>& ranges, UInt_t seed )
: fConvCounter(-1),
fFitterTarget( target ),
@@ -81,7 +86,7 @@ TMVA::GeneticAlgorithm::GeneticAlgorithm( IFitterTarget& target, Int_t populatio
fPopulation.SetRandomSeed( seed );
}
-TMVA::GeneticAlgorithm::~GeneticAlgorithm()
+TMVA::GeneticAlgorithm::~GeneticAlgorithm()
{
// destructor; deletes fLogger
delete fLogger;
@@ -89,10 +94,10 @@ TMVA::GeneticAlgorithm::~GeneticAlgorithm()
////////////////////////////////////////////////////////////////////////////////
-/// calls evolution, but if it is not the first time.
+/// calls evolution, but if it is not the first time.
/// If it's the first time, the random population created by the
-/// constructor is still not evaluated, .. therefore we wait for the
-/// second time init is called.
+/// constructor is still not evaluated, .. therefore we wait for the
+/// second time init is called.
void TMVA::GeneticAlgorithm::Init()
{
@@ -103,16 +108,16 @@ void TMVA::GeneticAlgorithm::Init()
}
////////////////////////////////////////////////////////////////////////////////
-/// if the "fitnessFunction" is called multiple times for one set of
-/// factors (because i.e. each event of a TTree has to be assessed with
-/// each set of Factors proposed by the Genetic Algorithm) the value
+/// if the "fitnessFunction" is called multiple times for one set of
+/// factors (because i.e. each event of a TTree has to be assessed with
+/// each set of Factors proposed by the Genetic Algorithm) the value
/// of the current calculation has to be added(? or else) to the value
-/// obtained up to now.
-/// example: some chi-square is calculated for every event,
+/// obtained up to now.
+/// example: some chi-square is calculated for every event,
/// after every event the new chi-square (newValue) has to be simply
-/// added to the oldValue.
+/// added to the oldValue.
///
-/// this function has to be overridden eventually
+/// this function has to be overridden eventually
/// it might contain only the following return statement.
/// return oldValue + newValue;
@@ -123,10 +128,10 @@ Double_t TMVA::GeneticAlgorithm::NewFitness( Double_t /*oldValue*/, Double_t new
////////////////////////////////////////////////////////////////////////////////
/// starts the evaluation of the fitness of all different individuals of
-/// the population.
+/// the population.
///
/// this function calls implicitly (many times) the "fitnessFunction" which
-/// has been overridden by the user.
+/// has been overridden by the user.
Double_t TMVA::GeneticAlgorithm::CalculateFitness()
{
@@ -145,46 +150,47 @@ Double_t TMVA::GeneticAlgorithm::CalculateFitness()
for ( int index = 0; index < fPopulation.GetPopulationSize(); ++index )
{
GeneticGenes* genes = fPopulation.GetGenes(index);
- Double_t fitness = NewFitness( genes->GetFitness(),
+ Double_t fitness = NewFitness( genes->GetFitness(),
fFitterTarget.EstimatorFunction(genes->GetFactors()) );
genes->SetFitness( fitness );
-
+
if ( bests[thread_number] > fitness )
bests[thread_number] = fitness;
}
}
-
+
fBestFitness = *std::min_element(bests, bests+nt);
-#else
+#else
for ( int index = 0; index < fPopulation.GetPopulationSize(); ++index ) {
GeneticGenes* genes = fPopulation.GetGenes(index);
Double_t fitness = NewFitness( genes->GetFitness(),
fFitterTarget.EstimatorFunction(genes->GetFactors()) );
genes->SetFitness( fitness );
-
+
if ( fBestFitness > fitness )
fBestFitness = fitness;
-
+
}
#endif
fPopulation.Sort();
- return fBestFitness;
+ return fBestFitness;
}
////////////////////////////////////////////////////////////////////////////////
-/// this function is called from "init" and controls the evolution of the
-/// individuals.
-/// the function can be overridden to change the parameters for mutation rate
+/// this function is called from "init" and controls the evolution of the
+/// individuals.
+///
+/// The function can be overridden to change the parameters for mutation rate
/// sexual reproduction and so on.
void TMVA::GeneticAlgorithm::Evolution()
{
- if ( fMakeCopies )
+ if ( fMakeCopies )
fPopulation.MakeCopies( 5 );
fPopulation.MakeChildren();
@@ -194,27 +200,28 @@ void TMVA::GeneticAlgorithm::Evolution()
////////////////////////////////////////////////////////////////////////////////
/// this function provides the ability to change the stepSize of a mutation according to
-/// the success of the last generations.
-///
+/// the success of the last generations.
+///
/// Parameters:
-/// int ofSteps : = if OF the number of STEPS given in this variable (ofSteps)
-/// int successSteps : >sucessSteps Generations could improve the result
-/// double factor : than multiply the stepSize ( spread ) by this factor
+///
+/// - int ofSteps : = if OF the number of STEPS given in this variable (ofSteps)
+/// - int successSteps : >sucessSteps Generations could improve the result
+/// - double factor : than multiply the stepSize ( spread ) by this factor
+///
/// (if ofSteps == successSteps nothing is changed, if ofSteps < successSteps, the spread
-/// is divided by the factor)
+/// is divided by the factor)
///
-/// using this function one can increase the stepSize of the mutation when we have
+/// using this function one can increase the stepSize of the mutation when we have
/// good success (to pass fast through the easy phase-space) and reduce the stepSize
-/// if we are in a difficult "territory" of the phase-space.
-///
+/// if we are in a difficult "territory" of the phase-space.
Double_t TMVA::GeneticAlgorithm::SpreadControl( Int_t ofSteps, Int_t successSteps, Double_t factor )
{
// < is valid for "less" comparison
- if ( fBestFitness < fLastResult || fSuccessList.size() <=0 ) {
+ if ( fBestFitness < fLastResult || fSuccessList.size() <=0 ) {
fLastResult = fBestFitness;
fSuccessList.push_front( 1 ); // it got better
- }
+ }
else {
fSuccessList.push_front( 0 ); // it stayed the same
}
@@ -247,10 +254,9 @@ Double_t TMVA::GeneticAlgorithm::SpreadControl( Int_t ofSteps, Int_t successStep
////////////////////////////////////////////////////////////////////////////////
/// gives back true if the last "steps" steps have lead to an improvement of the
/// "fitness" of the "individuals" of at least "improvement"
-///
-/// this gives a simple measure of if the fitness of the individuals is
-/// converging and no major improvement is to be expected soon.
///
+/// this gives a simple measure of if the fitness of the individuals is
+/// converging and no major improvement is to be expected soon.
Bool_t TMVA::GeneticAlgorithm::HasConverged( Int_t steps, Double_t improvement )
{
@@ -259,7 +265,7 @@ Bool_t TMVA::GeneticAlgorithm::HasConverged( Int_t steps, Double_t improvement )
}
if (TMath::Abs(fBestFitness - fConvValue) <= improvement || steps<0) {
fConvCounter ++;
- }
+ }
else {
fConvCounter = 0;
fConvValue = fBestFitness;