void TMVAClassification( TString myMethodList = "" )
{
// TString curDynamicPath( gSystem->GetDynamicPath() );
// gSystem->SetDynamicPath( "/usr/local/bin/root/bin:" + curDynamicPath );
// TString curIncludePath(gSystem->GetIncludePath());
// gSystem->SetIncludePath( " -I /usr/local/bin/root/include " + curIncludePath );
// // load TMVA shared library created in local release: for MAC OSX
// if (TString(gSystem->GetBuildArch()).Contains("macosx") ) gSystem->Load( "libTMVA.so" );
// gSystem->Load( "libTMVA" );
// TMVA::Tools::Instance();
// // welcome the user
// TMVA::gTools().TMVAWelcomeMessage();
// TMVAGlob::SetTMVAStyle();
// // this loads the library
// TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 1;
// Use["Likelihood"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable("deltaEta := deta", 'F');
factory->AddVariable("deltaPhi := dphi", 'F');
factory->AddVariable("sigmaIetaIeta := sieie", 'F');
factory->AddVariable("HoverE := hoe", 'F');
factory->AddVariable("trackIso := trackiso", 'F');
factory->AddVariable("ecalIso := ecaliso", 'F');
factory->AddVariable("hcalIso := hcaliso", 'F');
//factory->AddVariable("nMissingHits := misshits", 'I');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "et", 'F' );
factory->AddSpectator( "eta", 'F' );
factory->AddSpectator( "phi", 'F' );
// read training and test data
TFile *input = TFile::Open( "SigElectrons.root" );
TFile *inputB = TFile::Open( "BkgElectrons.root" );
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree *signal = (TTree*)input->Get("ntuple");
TTree *background = (TTree*)inputB->Get("ntuple");
factory->AddSignalTree ( signal, 1.0 );
factory->AddBackgroundTree( background, 1.0 );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
//factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/correlations.C");
gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/variables.C");
}
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
// Example for usage of different event categories with classifiers
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
bool batchMode = false;
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object (see TMVAClassification.C for more information)
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// Define the input variables used for the MVA training
factory->AddVariable( "var1", 'F' );
factory->AddVariable( "var2", 'F' );
factory->AddVariable( "var3", 'F' );
factory->AddVariable( "var4", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "eta" );
// Load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname( "" );
if (UseOffsetMethod) fname = "data/toy_sigbkg_categ_offset.root";
else fname = "data/toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
/// Global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
/// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
// Fisher discriminant
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// --- Categorised classifier
TMVA::MethodCategory* mcat = 0;
// The variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// Fisher with categories
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod( "abs(eta)<=1.3", theCat1Vars, TMVA::Types::kFisher, "Category_Fisher_1","!H:!V:Fisher" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher, "Category_Fisher_2","!H:!V:Fisher" );
// Likelihood with categories
TMVA::MethodBase* liCat = factory->BookMethod( TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod( "abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVARegression( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVARegression.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 1;
Use["KNN"] = 1;
//
// --- Linear Discriminant Analysis
Use["LD"] = 1;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 1;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0;
Use["BDTG"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TString outfileName( "TMVAReg.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "var1", "Variable 1", "units", 'F' );
factory->AddVariable( "var2", "Variable 2", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
factory->AddTarget( "fvalue" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// Read training and test data (see TMVAClassification for reading ASCII files)
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = "./tmva_reg_example.root";
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_reg_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
// --- Register the regression tree
TTree *regTree = (TTree*)input->Get("TreeR");
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddRegressionTree( regTree, regWeight );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
factory->SetWeightExpression( "var1", "Regression" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = ""; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=40:NEventsMax=60:VarTransform=None" );
// And the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:MultiTargetRegression=F:TargetSelection=Mpv:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Compress=T:Kernel=None:Nmin=10:VarTransform=None" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// Linear discriminant
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD",
"!H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=MC:SampleSize=100000:Sigma=0.1:VarTransform=D" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options) .. the formula of this example is good for parabolas
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:PopSize=100:Cycles=3:Steps=30:Trim=True:SaveBestGen=1:VarTransform=Norm" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
// Neural network (MLP)
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=20000:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDT"])
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=100:MinNodeSize=1.0%:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
if (Use["BDTG"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000::BoostType=Grad:Shrinkage=0.1:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=3:MaxDepth=4" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVARegGui( outfileName );
}
int main( int argc, char** argv )
{//main
std::string folder;
if (argc > 1) {
folder = argv[1];
}
else {
folder = "output_tmva/nunu/MET130/";
}
bool useQCD = true;
bool useOthers = false;
bool useOthersAsSignal = true;
//List of input signal files
std::vector<std::string> sigfiles;
//sigfiles.push_back("MC_VBF_HToZZTo4Nu_M-120");
sigfiles.push_back("MC_Powheg-Htoinv-mH125");
if (useOthersAsSignal) {
sigfiles.push_back("MC_TTJets");
//powheg samples
//sigfiles.push_back("MC_TT-v1");
//sigfiles.push_back("MC_TT-v2");
//
sigfiles.push_back("MC_T-tW");
sigfiles.push_back("MC_Tbar-tW");
sigfiles.push_back("MC_SingleT-s-powheg-tauola");
sigfiles.push_back("MC_SingleTBar-s-powheg-tauola");
sigfiles.push_back("MC_SingleT-t-powheg-tauola");
sigfiles.push_back("MC_SingleTBar-t-powheg-tauola");
sigfiles.push_back("MC_WW-pythia6-tauola");
sigfiles.push_back("MC_WZ-pythia6-tauola");
sigfiles.push_back("MC_ZZ-pythia6-tauola");
sigfiles.push_back("MC_W1JetsToLNu_enu");
sigfiles.push_back("MC_W2JetsToLNu_enu");
sigfiles.push_back("MC_W3JetsToLNu_enu");
sigfiles.push_back("MC_W4JetsToLNu_enu");
sigfiles.push_back("MC_WJetsToLNu-v1_enu");
sigfiles.push_back("MC_WJetsToLNu-v2_enu");
sigfiles.push_back("MC_W1JetsToLNu_munu");
sigfiles.push_back("MC_W2JetsToLNu_munu");
sigfiles.push_back("MC_W3JetsToLNu_munu");
sigfiles.push_back("MC_W4JetsToLNu_munu");
sigfiles.push_back("MC_WJetsToLNu-v1_munu");
sigfiles.push_back("MC_WJetsToLNu-v2_munu");
sigfiles.push_back("MC_W1JetsToLNu_taunu");
sigfiles.push_back("MC_W2JetsToLNu_taunu");
sigfiles.push_back("MC_W3JetsToLNu_taunu");
sigfiles.push_back("MC_W4JetsToLNu_taunu");
sigfiles.push_back("MC_WJetsToLNu-v1_taunu");
sigfiles.push_back("MC_WJetsToLNu-v2_taunu");
sigfiles.push_back("MC_DYJetsToLL");
sigfiles.push_back("MC_DY1JetsToLL");
sigfiles.push_back("MC_DY2JetsToLL");
sigfiles.push_back("MC_DY3JetsToLL");
sigfiles.push_back("MC_DY4JetsToLL");
sigfiles.push_back("MC_ZJetsToNuNu_100_HT_200");
sigfiles.push_back("MC_ZJetsToNuNu_200_HT_400");
sigfiles.push_back("MC_ZJetsToNuNu_400_HT_inf");
sigfiles.push_back("MC_ZJetsToNuNu_50_HT_100");
sigfiles.push_back("MC_GJets-HT-200To400-madgraph");
sigfiles.push_back("MC_GJets-HT-400ToInf-madgraph");
sigfiles.push_back("MC_WGamma");
sigfiles.push_back("MC_EWK-Z2j");
sigfiles.push_back("MC_EWK-Z2jiglep");
sigfiles.push_back("MC_EWK-W2jminus_enu");
sigfiles.push_back("MC_EWK-W2jplus_enu");
sigfiles.push_back("MC_EWK-W2jminus_munu");
sigfiles.push_back("MC_EWK-W2jplus_munu");
sigfiles.push_back("MC_EWK-W2jminus_taunu");
sigfiles.push_back("MC_EWK-W2jplus_taunu");
}
//List of input files
std::vector<std::string> bkgfiles;
if (useQCD){
bkgfiles.push_back("MC_QCD-Pt-30to50-pythia6");
bkgfiles.push_back("MC_QCD-Pt-50to80-pythia6");
bkgfiles.push_back("MC_QCD-Pt-80to120-pythia6");
bkgfiles.push_back("MC_QCD-Pt-120to170-pythia6");
bkgfiles.push_back("MC_QCD-Pt-170to300-pythia6");
bkgfiles.push_back("MC_QCD-Pt-300to470-pythia6");
bkgfiles.push_back("MC_QCD-Pt-470to600-pythia6");
bkgfiles.push_back("MC_QCD-Pt-600to800-pythia6");
bkgfiles.push_back("MC_QCD-Pt-800to1000-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1000to1400-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1400to1800-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1800-pythia6");
}
if (useOthers) {
bkgfiles.push_back("MC_TTJets");
//powheg samples
//bkgfiles.push_back("MC_TT-v1");
//bkgfiles.push_back("MC_TT-v2");
//
bkgfiles.push_back("MC_T-tW");
bkgfiles.push_back("MC_Tbar-tW");
bkgfiles.push_back("MC_SingleT-s-powheg-tauola");
bkgfiles.push_back("MC_SingleTBar-s-powheg-tauola");
bkgfiles.push_back("MC_SingleT-t-powheg-tauola");
bkgfiles.push_back("MC_SingleTBar-t-powheg-tauola");
bkgfiles.push_back("MC_WW-pythia6-tauola");
bkgfiles.push_back("MC_WZ-pythia6-tauola");
bkgfiles.push_back("MC_ZZ-pythia6-tauola");
bkgfiles.push_back("MC_W1JetsToLNu_enu");
bkgfiles.push_back("MC_W2JetsToLNu_enu");
bkgfiles.push_back("MC_W3JetsToLNu_enu");
bkgfiles.push_back("MC_W4JetsToLNu_enu");
bkgfiles.push_back("MC_WJetsToLNu-v1_enu");
bkgfiles.push_back("MC_WJetsToLNu-v2_enu");
bkgfiles.push_back("MC_W1JetsToLNu_munu");
bkgfiles.push_back("MC_W2JetsToLNu_munu");
bkgfiles.push_back("MC_W3JetsToLNu_munu");
bkgfiles.push_back("MC_W4JetsToLNu_munu");
bkgfiles.push_back("MC_WJetsToLNu-v1_munu");
bkgfiles.push_back("MC_WJetsToLNu-v2_munu");
bkgfiles.push_back("MC_W1JetsToLNu_taunu");
bkgfiles.push_back("MC_W2JetsToLNu_taunu");
bkgfiles.push_back("MC_W3JetsToLNu_taunu");
bkgfiles.push_back("MC_W4JetsToLNu_taunu");
bkgfiles.push_back("MC_WJetsToLNu-v1_taunu");
bkgfiles.push_back("MC_WJetsToLNu-v2_taunu");
bkgfiles.push_back("MC_DYJetsToLL");
bkgfiles.push_back("MC_DY1JetsToLL");
bkgfiles.push_back("MC_DY2JetsToLL");
bkgfiles.push_back("MC_DY3JetsToLL");
bkgfiles.push_back("MC_DY4JetsToLL");
bkgfiles.push_back("MC_ZJetsToNuNu_100_HT_200");
bkgfiles.push_back("MC_ZJetsToNuNu_200_HT_400");
bkgfiles.push_back("MC_ZJetsToNuNu_400_HT_inf");
bkgfiles.push_back("MC_ZJetsToNuNu_50_HT_100");
bkgfiles.push_back("MC_GJets-HT-200To400-madgraph");
bkgfiles.push_back("MC_GJets-HT-400ToInf-madgraph");
bkgfiles.push_back("MC_WGamma");
bkgfiles.push_back("MC_EWK-Z2j");
bkgfiles.push_back("MC_EWK-Z2jiglep");
bkgfiles.push_back("MC_EWK-W2jminus_enu");
bkgfiles.push_back("MC_EWK-W2jplus_enu");
bkgfiles.push_back("MC_EWK-W2jminus_munu");
bkgfiles.push_back("MC_EWK-W2jplus_munu");
bkgfiles.push_back("MC_EWK-W2jminus_taunu");
bkgfiles.push_back("MC_EWK-W2jplus_taunu");
}
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TFile *output_tmva = TFile::Open((folder+"/TMVA_QCDrej.root").c_str(),"RECREATE");
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", output_tmva,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
//fill the variables with event weight from the trees
//const unsigned nVars = 4;
factory->AddSpectator("jet1_pt","Jet 1 p_{T}", "GeV", 'F');
factory->AddSpectator("jet2_pt","Jet 2 p_{T}", "GeV", 'F');
factory->AddSpectator("jet1_eta","Jet 1 #eta", "", 'F');
factory->AddVariable("jet2_eta","Jet 2 #eta", "", 'F');// **
factory->AddSpectator("jet1_phi","Jet 1 #phi", "", 'F');
factory->AddSpectator("jet2_phi","Jet 2 #phi", "", 'F');
factory->AddSpectator("dijet_M","M_{jj}", " GeV", 'F');
factory->AddSpectator("dijet_deta","#Delta#eta_{jj}", "", 'F');
factory->AddSpectator("dijet_sumeta","#eta_{j1}+#eta_{j2}", "", 'F');
factory->AddSpectator("dijet_dphi","#Delta#phi_{jj}", "", 'F');
factory->AddSpectator("met","MET", "GeV", 'F');// **
factory->AddSpectator("met_phi","MET #phi", "", 'F');
factory->AddVariable("met_significance","MET significance", "", 'F');// **
factory->AddSpectator("sumet","#Sum E_{T}", "GeV", 'F');
factory->AddSpectator("ht","H_{T}", "GeV", 'F');
factory->AddVariable("mht","MH_{T}", "GeV", 'F');// **
factory->AddSpectator("sqrt_ht","#sqrt{H_{T}}", "GeV^{0.5}", 'F');
factory->AddSpectator("unclustered_et","Unclustered E_{T}", "GeV", 'F');
factory->AddSpectator("unclustered_phi","Unclustered #phi", "GeV", 'F');
factory->AddSpectator("jet1met_dphi","#Delta#phi(MET,jet1)", "", 'F');
factory->AddVariable("jet2met_dphi","#Delta#phi(MET,jet2)", "", 'F');// **
factory->AddVariable("jetmet_mindphi","minimum #Delta#phi(MET,jet)", "", 'F');// **
factory->AddVariable("jetunclet_mindphi","minimum #Delta#phi(unclustered,jet)", "", 'F');// **
factory->AddVariable("metunclet_dphi","#Delta#phi(MET,unclustered)", "", 'F');// **
factory->AddVariable("dijetmet_scalarSum_pt", "p_{T}^{jet1}+p_{T}^{jet2}+MET", "GeV", 'F');// **
factory->AddSpectator("dijetmet_vectorialSum_pt","p_{T}(#vec{j1}+#vec{j2}+#vec{MET})", "GeV", 'F');
factory->AddVariable("dijetmet_ptfraction","p_{T}^{dijet}/(p_{T}^{dijet}+MET)", "", 'F');// **
//factory->AddVariable("jet1met_scalarprod := (jet1_pt*cos(jet1_phi)*met_x+jet1_pt*sin(jet1_phi)*met_y)/met", "#vec{p_{T}^{jet1}}.#vec{MET}/MET", "GeV" , 'F');
//factory->AddVariable("jet2met_scalarprod := (jet2_pt*cos(jet2_phi)*met_x+jet2_pt*sin(jet2_phi)*met_y)/met", "#vec{p_{T}^{jet2}}.#vec{MET}/MET", "GeV" , 'F');
factory->AddVariable("jet1met_scalarprod", "#vec{p_{T}^{jet1}}.#vec{MET}/MET", "GeV" , 'F');// **
factory->AddVariable("jet2met_scalarprod", "#vec{p_{T}^{jet2}}.#vec{MET}/MET", "GeV" , 'F');// **
factory->AddVariable("jet1met_scalarprod_frac := jet1met_scalarprod/met", "#vec{p_{T}^{jet1}}.#vec{MET}/MET^{2}", "" , 'F');// **
factory->AddVariable("jet2met_scalarprod_frac := jet2met_scalarprod/met", "#vec{p_{T}^{jet2}}.#vec{MET}/MET^{2}", "" , 'F');// **
factory->AddSpectator("n_jets_cjv_30","CJV jets (30 GeV)", "" , 'I');
factory->AddSpectator("n_jets_cjv_20EB_30EE","CJV jets (|#eta|<2.4 and 20 GeV, or 30 GeV)", "" , 'I');
//test with only VBF variables used in cut-based analysis
//factory->AddVariable("dijet_M","M_{jj}", " GeV", 'F');
//factory->AddVariable("dijet_deta","#Delta#eta_{jj}", "", 'F');
//factory->AddVariable("dijet_dphi","#Delta#phi_{jj}", "", 'F');
//factory->AddVariable("met","MET", "GeV", 'F');
//factory->AddVariable("n_jets_cjv_30","CJV jets (30 GeV)", "" , 'I');
//get input files
//signal
//TFile *signalfile = TFile::Open((folder+"/"+"MC_VBF_HToZZTo4Nu_M-120.root").c_str());
//TTree *signal = (TTree*)signalfile->Get("TmvaInputTree");
//Double_t signalWeight = 1.0;
//factory->AddSignalTree(signal,signalWeight);
//Set individual event weights (the variables must exist in the original TTree)
//factory->SetSignalWeightExpression("total_weight");
//background
std::map<std::string, TFile *> tfiles;
for (unsigned i = 0; i < bkgfiles.size(); ++i) {
std::string filename = (bkgfiles[i]+".root");
TFile * tmp = new TFile((folder+"/"+filename).c_str());
if (!tmp) {
std::cerr << "Warning, file " << filename << " could not be opened." << std::endl;
} else {
tfiles[bkgfiles[i]] = tmp;
}
}
TTree *background[bkgfiles.size()];
//signal
std::map<std::string, TFile *> sfiles;
for (unsigned i = 0; i < sigfiles.size(); ++i) {
std::string filename = (sigfiles[i]+".root");
TFile * tmp = new TFile((folder+"/"+filename).c_str());
if (!tmp) {
std::cerr << "Warning, file " << filename << " could not be opened." << std::endl;
} else {
sfiles[sigfiles[i]] = tmp;
}
}
TTree *signal[sigfiles.size()];
for (unsigned i = 0; i < bkgfiles.size(); ++i) {
std::string f = bkgfiles[i];
if (tfiles[f]){
background[i] = (TTree*)tfiles[f]->Get("TmvaInputTree");
//if (f.find("QCD-Pt")!=f.npos){
//}
Double_t backgroundWeight = 1.0;
factory->AddBackgroundTree(background[i],backgroundWeight);
factory->SetBackgroundWeightExpression("total_weight");
}//if file exist
else {
std::cout << " Cannot find background file " << f << std::endl;
}
}//loop on files
for (unsigned i = 0; i < sigfiles.size(); ++i) {
std::string f = sigfiles[i];
if (sfiles[f]){
signal[i] = (TTree*)sfiles[f]->Get("TmvaInputTree");
//if (f.find("QCD-Pt")!=f.npos){
//}
Double_t signalWeight = 1.0;
factory->AddSignalTree(signal[i],signalWeight);
factory->SetSignalWeightExpression("total_weight");
}//if file exist
else {
std::cout << " Cannot find signal file " << f << std::endl;
}
}//loop on files
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";//dijet_deta>3.8 && dijet_M > 1100 && met > 100 && met_significance>5";
TCut mycutb = "";//dijet_deta>3.8 && dijet_M > 1100 && met > 100 && met_significance>5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Likelihood ("naive Bayes estimator")
//factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
//"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Linear discriminant (same as Fisher discriminant)
//factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
//factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=60:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
// Boosted Decision Trees
// Gradient Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDTG",
//"!H:!V:NTrees=1000:MinNodeSize=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:nCuts=20:MaxDepth=2" );
// Adaptive Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDT1000",
// "!H:!V:NTrees=1000:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=1000:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.2:SeparationType=GiniIndex:nCuts=20" );
// Bagging
//factory->BookMethod( TMVA::Types::kBDT, "BDTB",
// "!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
// Decorrelation + Adaptive Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDTD",
// "!H:!V:NTrees=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
// Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
//factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
// "!H:!V:NTrees=50:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
output_tmva->Close();
std::cout << "==> Wrote root file: " << output_tmva->GetName() << std::endl
<< "==> TMVAClassification is done!" << std::endl
<< std::endl
<< "==> To view the results, launch the GUI: \"root -l ./TMVAGui.C\"" << std::endl
<< std::endl;
// Clean up
delete factory;
return 0;
}//main
//require mumucl>0.6
//opening angle >10
//coplanarity >90
//pang<90
void TMVAClassification_cc1pcoh_bdt_ver6noveract( TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
// Choose method
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// ---------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA_cc1pcoh_bdt_ver6noveract.root" );//newchange
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object.
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification_ver6noveract", outputFile,//newchange
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// Add variable
//sprintf(select, "Ntrack==2&&mumucl>0.6&&pmucl>0.25&&pang<90&&muang_t<15 && veract*7.66339869e-2<34");
//factory->AddVariable( "Ntrack", 'F' );
factory->AddVariable( "mumucl", 'F' );
factory->AddVariable( "pmucl", 'F' );
factory->AddVariable( "pang_t", 'F' );//use pang instead of pang_t
factory->AddVariable( "muang_t", 'F' );
//factory->AddVariable( "veract", 'F' );
factory->AddVariable( "ppe", 'F');
factory->AddVariable( "mupe", 'F');
factory->AddVariable( "range", 'F');
factory->AddVariable( "coplanarity", 'F');
factory->AddVariable( "opening", 'F');//newadd
// Add spectator
factory->AddSpectator( "fileIndex", 'I' );
factory->AddSpectator( "nuE", 'F' );
factory->AddSpectator( "inttype", 'I' );
factory->AddSpectator( "norm", 'F' );
factory->AddSpectator( "totcrsne", 'F' );
factory->AddSpectator( "veract", 'F' );
factory->AddSpectator( "pang", 'F' );
factory->AddSpectator( "mupdg", 'I' );
factory->AddSpectator( "ppdg", 'I' );
// ---------------------------------------------------------------
// --- Get weight
TString fratioStr="/home/kikawa/macros/nd34_tuned_11bv3.1_250ka.root";
// ---------------------------------------------------------------
// --- Add sample
TString fsignalStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/pm_merged_ccqe_tot.root";
TString fbarStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/pmbar_merged_ccqe.root";
TString fbkgStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/wall_merged_ccqe_tot.root";
TString fbkg2Str="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/ingrid_merged_nd3_ccqe_tot.root";
/*TString fsignalStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/pm_merged_ccqe_tot.root";
TString fbarStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/pmbar_merged_ccqe.root";
TString fbkgStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/wall_merged_ccqe_tot.root";
TString fbkg2Str="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/ingrid_merged_nd3_ccqe_tot.root";*/
TFile *pfileSignal = new TFile(fsignalStr);
TFile *pfileBar = new TFile(fbarStr);
TFile *pfileBkg = new TFile(fbkgStr);
TFile *pfileBkg2 = new TFile(fbkg2Str);
TFile *pfileRatio = new TFile(fratioStr);
TTree *ptree_sig = (TTree*)pfileSignal->Get("tree");
TTree *ptree_bar = (TTree*)pfileBar->Get("tree");
TTree *ptree_bkg = (TTree*)pfileBkg->Get("tree");
TTree *ptree_bkg2 = (TTree*)pfileBkg2->Get("tree");
// POT normalization
const int nmcFile = 3950;
const int nbarFile = 986;
const int nbkgFile = 55546;//(31085+24461);
const int nbkg2File = 7882;//(3941+3941);
// global event weights per tree (see below for setting event-wise weights)
// adding for signal sample
// using this as standard and add other later
Double_t signalWeight_sig = 1.0;
Double_t backgroundWeight_sig = 1.0;
factory->AddSignalTree ( ptree_sig, signalWeight_sig );
factory->AddBackgroundTree( ptree_sig, backgroundWeight_sig );
// Add Numubar sample
//Double_t signalWeight_bar = nmcFile/float(nbarFile);
Double_t backgroundWeight_bar = nmcFile/float(nbarFile);
//factory->AddSignalTree ( ptree_bar, signalWeight_bar );
factory->AddBackgroundTree( ptree_bar, backgroundWeight_bar );
// Add wall background
//Double_t signalWeight_bkg = nmcFile/float(nbkgFile);
Double_t backgroundWeight_bkg = nmcFile/float(nbkgFile);
//factory->AddSignalTree ( ptree_bkg, signalWeight_bkg );
factory->AddBackgroundTree( ptree_bkg, backgroundWeight_bkg );
// Add INGRID background
//Double_t signalWeight_bkg2 = nmcFile/float(nbkg2File);
Double_t backgroundWeight_bkg2 = nmcFile/float(nbkg2File);
//factory->AddSignalTree ( ptree_bkg2, signalWeight_bkg2 );
factory->AddBackgroundTree( ptree_bkg2, backgroundWeight_bkg2 );
//factory->SetSignalWeightExpression ("norm*totcrsne*2.8647e-13");
//factory->SetBackgroundWeightExpression( "norm*totcrsne*2.8647e-13" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "Ntrack==2 && abs(inttype)==16 && fileIndex==1 && pang<90 && mumucl>0.6 && opening>10 && coplanarity>90 && pmucl>0.2"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "Ntrack==2 && (abs(inttype)!=16 || fileIndex>1) && pang<90 && mumucl>0.6 && opening>10 && coplanarity>90 && pmucl>0.2"; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
/*if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );*/
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( )
{
// this loads the library
TMVA::Tools::Instance();
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object.
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// ---------- input variables
factory->AddVariable("iso12x12", 'F');
factory->AddVariable("iso4x4", 'F');
factory->AddVariable("isoLshaped", 'F');
factory->AddVariable("PUM0", 'F');
// ---------- spectators ----------------
factory->AddSpectator("pt", "F");
factory->AddSpectator("eta", "F");
factory->AddSpectator("phi", "F");
factory->AddSpectator("e", "F");
// read training and test data
TString fSig = "DrellYan_Zee.root";
TString fBkg = "MinBias.root";
TFile *fileSig = TFile::Open( fSig );
TFile *fileBkg = TFile::Open( fBkg );
TTree *signal = (TTree*)fileSig->Get("tree");
TTree *background = (TTree*)fileBkg->Get("tree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
TCut mycuts = "pt > 10";
TCut mycutb = "pt > 10";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// ---- Book MVA methods
// Boosted Decision Trees
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// ---- Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassificationElecTau(std::string ordering_ = "Pt", std::string bkg_ = "qqH115vsWZttQCD") {
TMVA::Tools::Instance();
TString outfileName( "TMVAElecTau"+ordering_+"Ord_"+bkg_+".root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationElecTau"+ordering_+"Ord_"+bkg_, outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
factory->AddVariable( "pt1", "pT-tag1", "GeV/c" , 'F' );
factory->AddVariable( "pt2", "pT-tag2", "GeV/c" , 'F' );
factory->AddVariable( "Deta","|y-tag1 - y-tag2|","" , 'F' );
//factory->AddVariable( "opposite:=abs(eta1*eta2)/eta1/eta2","sign1*sign2","" , 'F' );
//factory->AddVariable( "Dphi", "#Delta#phi" ,"" , 'F' );
factory->AddVariable( "Mjj", "M(tag1,tag2)", "GeV/c^{2}" , 'F' );
factory->AddSpectator( "eta1", "#eta_{tag1}" , 'F' );
factory->AddSpectator( "eta2", "#eta_{tag2}" , 'F' );
factory->SetWeightExpression( "sampleWeight" );
TString fSignalName = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleVBFH115-powheg-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameDYJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleZjets-alpgen-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameWJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleWJets-madgraph-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameQCD = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleQCD_Open_ElecTauStream.root";
TString fBackgroundNameTTbar = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleTTJets-madgraph-PUS1_Open_ElecTauStream.root";
TFile *fSignal(0);
TFile *fBackgroundDYJets(0);
TFile *fBackgroundWJets(0);
TFile *fBackgroundQCD(0);
TFile *fBackgroundTTbar(0);
fSignal = TFile::Open( fSignalName );
fBackgroundDYJets = TFile::Open( fBackgroundNameDYJets );
fBackgroundWJets = TFile::Open( fBackgroundNameWJets );
fBackgroundQCD = TFile::Open( fBackgroundNameQCD );
fBackgroundTTbar = TFile::Open( fBackgroundNameTTbar );
if(!fSignal || !fBackgroundDYJets || !fBackgroundWJets || !fBackgroundQCD || !fBackgroundTTbar) {
std::cout << "ERROR: could not open files" << std::endl;
exit(1);
}
TString tree = "outTree"+ordering_+"Ord";
TCut mycuts = "";
TCut mycutb = "";
TCut cutA = "pt1>0 && tightestHPSWP>0";
TCut cutB = "pt1>0 && combRelIsoLeg1<0.1";
TCut cutBl = "pt1>0 && combRelIsoLeg1<0.3";
TCut cutC = "pt1>0 && diTauCharge==0";
TCut cutD = "pt1>0 && MtLeg1<40";
// select events for training
TFile* dummy = new TFile("dummy.root","RECREATE");
TH1F* allEvents = new TH1F("allEvents","",1,-10,10);
float totalEvents, cutEvents;
// signal: all
TTree *signal = ((TTree*)(fSignal->Get(tree)))->CopyTree(cutA&&cutB&&cutC&&cutD);
cout << "Copied signal tree with full selection: " << ((TTree*)(fSignal->Get(tree)))->GetEntries() << " --> " << signal->GetEntries() << endl;
allEvents->Reset();
signal->Draw("eta1>>allEvents","sampleWeight");
cutEvents = allEvents->Integral();
Double_t signalWeight = 1.0;
cout << "Signal: expected yield " << cutEvents << " -- weight " << signalWeight << endl;
// Z+jets: all
TTree *backgroundDYJets = ((TTree*)(fBackgroundDYJets->Get(tree)))->CopyTree(cutA&&cutB&&cutC&&cutD);
cout << "Copied DYJets tree with full selection: " << ((TTree*)(fBackgroundDYJets->Get(tree)))->GetEntries() << " --> " << backgroundDYJets->GetEntries() << endl;
allEvents->Reset();
backgroundDYJets->Draw("eta1>>allEvents","sampleWeight");
cutEvents = allEvents->Integral();
Double_t backgroundDYJetsWeight = 1.0;
cout << "ZJets: expected yield " << cutEvents << " -- weight " << backgroundDYJetsWeight << endl;
// W+jets: iso+Mt
TTree *backgroundWJets = ((TTree*)(fBackgroundWJets->Get(tree)))->CopyTree(cutB&&cutD);
cout << "Copied WJets tree with iso+Mt selection: " << ((TTree*)(fBackgroundWJets->Get(tree)))->GetEntries() << " --> " << backgroundWJets->GetEntries() << endl;
allEvents->Reset();
backgroundWJets->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundWJets->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0)");
cutEvents = allEvents->Integral();
Double_t backgroundWJetsWeight = cutEvents / totalEvents;
cout << "WJets: expected yield " << cutEvents << " -- weight " << backgroundWJetsWeight << endl;
// QCD: Mt+loose iso
TTree *backgroundQCD = ((TTree*)(fBackgroundQCD->Get(tree)))->CopyTree(cutD&&cutBl);
cout << "Copied QCD tree with Mt selection: " << ((TTree*)(fBackgroundQCD->Get(tree)))->GetEntries() << " --> " << backgroundQCD->GetEntries() << endl;
allEvents->Reset();
backgroundQCD->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundQCD->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0 && combRelIsoLeg1<0.1)");
cutEvents = allEvents->Integral();
Double_t backgroundQCDWeight = cutEvents / totalEvents;
cout << "QCD: expected yield " << cutEvents << " -- weight " << backgroundQCDWeight << endl;
// TTbar: iso+Mt
TTree *backgroundTTbar = ((TTree*)(fBackgroundTTbar->Get(tree)))->CopyTree(cutB&&cutD);
cout << "Copied TTbar tree with iso+Mt selection: " << ((TTree*)(fBackgroundTTbar->Get(tree)))->GetEntries() << " --> " << backgroundTTbar->GetEntries() << endl;
allEvents->Reset();
backgroundTTbar->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundTTbar->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0)");
cutEvents = allEvents->Integral();
Double_t backgroundTTbarWeight = cutEvents / totalEvents;
cout << "TTbar: expected yield " << cutEvents << " -- weight " << backgroundTTbarWeight << endl;
delete allEvents;
factory->AddSignalTree ( signal, signalWeight );
//factory->AddBackgroundTree( backgroundDYJets, backgroundDYJetsWeight );
//factory->AddBackgroundTree( backgroundWJets, backgroundWJetsWeight );
factory->AddBackgroundTree( backgroundQCD, backgroundQCDWeight );
//factory->AddBackgroundTree( backgroundTTbar, backgroundTTbarWeight );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=1:nTest_Background=1:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=GA:EffSel:CutRangeMin[0]=25.:CutRangeMax[0]=999:CutRangeMin[1]=25.:CutRangeMax[1]=999.:CutRangeMin[2]=1.0:CutRangeMax[2]=9.:CutRangeMin[3]=100:CutRangeMax[3]=7000:VarProp=FSmart" );
/*
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=200:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
*/
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void ZTMVAClassification( TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 1; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 1; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 1; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
//factory->AddVariable( "maxpioneta", "maxpioneta", "", 'F' );
//factory->AddVariable( "minpioneta", "minpioneta", "", 'F' );
factory->AddVariable( "nTT", "nTT", "", 'F' );
// factory->AddVariable( "pidpimin", "pidpimin", "", 'F' );
// factory->AddVariable( "pidpimax", "pidpimax", "", 'F' );
factory->AddVariable( "normxpt", "normxpt", "", 'F' );
factory->AddVariable( "eta", "eta", "", 'F' );
//factory->AddVariable( "phi", "phi", "", 'F' );
// factory->AddVariable( "normptsum", "normptsum", "", 'F' );
//factory->AddVariable( "ptAsym", "ptAsym", "", 'F' );
//factory->AddVariable( "dphimax", "dphimax", "", 'F' );
//factory->AddVariable( "dphimin", "dphimin", "", 'F' );
//factory->AddVariable( "drmax", "drmax", "", 'F' );
// factory->AddVariable( "drmin", "drmin", "", 'F' );
// factory->AddVariable( "normpionp", "normpionp", "", 'F' );
factory->AddVariable( "normminpionpt", "normminpionpt", "", 'F' );
//factory->AddVariable( "normminpionp", "normminpionp", "", 'F' );
factory->AddVariable( "normmaxpionpt", "normmaxpionpt", "", 'F' );
// factory->AddVariable( "normptj", "normptj", "", 'F' );
//factory->AddVariable( "jmasspull", "jmasspull", "", 'F' );
//factory->AddVariable( "vchi2dof", "vchi2dof", "", 'F' );
// factory->AddVariable("maxchi2","maxchi2","", 'F');
// factory->AddVariable("normr","normr","", 'F');
// factory->AddVariable("normq","normq","", 'F');
//factory->AddVariable("normminm","normminm","", 'F');
factory->AddVariable("logipmax","logipmax","", 'F');
factory->AddVariable("logipmin","logipmin","", 'F');
factory->AddVariable("logfd","logfd",'F');
factory->AddVariable("logvd","logvd",'F');
//factory->AddVariable("pointAngle","pointingAngle",'F');
factory->AddVariable("logvpi","",'F');
//factory->AddVariable("logmaxprob","",'F');
//factory->AddVariable("logminprob","",'F');
factory->AddSpectator( "mReFit", "mReFit", "", 'D' );
// factory->AddSpectator( "Qdecay", "Qdecay", "",'F' );
// factory->AddSpectator( "m23", "m23", "",'F' );
// TFile * input_Background = new TFile("../back.root");
TFile * input_Signal = new TFile("../cmx12.root");
TFile * input_Background = new TFile("../background12.root");
std::cout << "--- TMVAClassification : Using input file for signal : " << input_Signal->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input file for backgound : " << input_Background->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)input_Signal->Get("psiCand");
TTree *background = (TTree*)input_Background->Get("psiCand");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "QDecay < 300&&fdchi2 > 300"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "QDecay < 300&&fdchi2> 300"; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"]){
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
//factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=Norm:NCycles=600:HiddenLayers=N+5:TestRate=5" );
// factory->BookMethod( TMVA::Types::kMLP, "MLPCE", "H:!V:NeuronType=sigmoid:VarTransform=Norm:NCycles=600:HiddenLayers=N+5:TestRate=5:EstimatorType=CE" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=sigmoid:VarTransform=Norm:NCycles=600:HiddenLayers=9:TestRate=5:EstimatorType=CE" );
// factory->BookMethod( TMVA::Types::kMLP, "MLPCE83", "H:!V:NeuronType=tanh:VarTransform=Norm:NCycles=600:HiddenLayers=8,3:TestRate=5:EstimatorType=CE" );
}
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) { // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTGI",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5:SeparationType=GiniIndexWithLaplace" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG6",
// "!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG2",
// "!H:!V:NTrees=800:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
factory->BookMethod( TMVA::Types::kBDT, "BDTG3",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG4",
// "!H:!V:NTrees=1200:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG5",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=5" );
}
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
//factory->AddVariable( "myvar1 := var1+var2", 'F' );
//factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
factory->AddVariable( "Lambdab_ETA", "Lambdab_ETA", "", 'F' );
factory->AddVariable( "Lambdab_P", "Lambdab_P", "", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "Lambdab_PT", "Lambdab_PT", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fname_signal = "/exp/LHCb/amhis/LeptonU/tuples/montecarlo/spring16/mc-15154001-leptonU.root";
TString fname_background = "/exp/LHCb/amhis/LeptonU/tuples/data/LeptonU-total-electrons-11122015.root";
TFile *input_signal = TFile::Open( fname_signal );
TFile *input_background = TFile::Open( fname_background );
std::cout << "--- TMVAClassification : Using input file for signal: " << input_signal->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input file for background: " << input_background->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)input_signal->Get("Tuple_Bu2LLK_eeLine2/DecayTree");
TTree *background = (TTree*)input_background->Get("TupleFromData_Bu2LLK_eeLine2/DecayTree");
std::cout << signal << std::endl;
std::cout << background << std::endl;
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4], weight;
//
// // Signal
// for (UInt_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2.0) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// // Background (has event weights)
// background->SetBranchAddress( "weight", &weight );
// for (UInt_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight*weight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight*weight );
// }
// --- end ------------------------------------------------------------
//
// --- end of tree registration
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// factory->SetBackgroundWeightExpression( "weight" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
TCut mycut = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Signal=3000:nTrain_Background=3000:nTrain_Signal=3000:nTrain_Background=3000:SplitMode=random:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch())
gROOT->ProcessLine(TString::Format("TMVAGui(\"%s\")", outfileName.Data()));
}
void TMVAClassificationHwwNtuple( TString myMethodList = "" )
{
// This loads the library
TMVA::Tools::Instance();
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
cout<<regMethod<<" is on"<<endl;
}
}
// -------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// For one variable
//TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
// "!V:!Silent:Color:DrawProgressBar:Transformations=I:AnalysisType=Classification" );
// For Multiple Variables
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
//factory->AddVariable( "pt1", "LeadLepton pt", "", 'F' );
//factory->AddVariable( "pt2", "TailLepton pt", "", 'F' );
factory->AddVariable( "pfmet", "MissingEt", "", 'F' );
factory->AddVariable( "mpmet", "Minimum Proj. Met", "", 'F' );
factory->AddVariable( "dphill", "DeltPhiOfLepLep", "", 'F' );
//factory->AddVariable( "mll", "DiLepton Mass", "", 'F' );
factory->AddVariable( "ptll", "DiLepton pt", "", 'F' );
//
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
//factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
//factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
//
//factory->AddSpectator( "mWW", "Higgs Mass", "", 'F' );
factory->AddSpectator( "pt1", "LeadLepton pt", "", 'F' );
factory->AddSpectator( "pt2", "TailLepton pt", "", 'F' );
factory->AddSpectator( "pfmet", "MissingEt", "", 'F' );
factory->AddSpectator( "mpmet", "Minimum Proj. Met", "", 'F' );
factory->AddSpectator( "dphill", "DeltPhiOfLepLep", "", 'F' );
factory->AddSpectator( "mll", "DiLepton Mass", "", 'F' );
factory->AddSpectator( "ptll", "DiLepton pt", "", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
//TString fname = "./tmva_class_example.root";
//TString fname = "/afs/cern.ch/work/s/salee/private/HWWwidth/HWW/GGVvAnalyzer/MkNtuple/Hw1Int8TeV/MkNtuple.root";
//TString fname = "/terranova_0/HWWwidth/HWW/GGVvAnalyzer/MkNtuple/Hw1Int8TeV/MkNtuple.root";
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// exit(-1);
//gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
//TFile *input = TFile::Open( fname );
//TFile *SB_OnPeak = TFile::Open("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntOnPeak_8TeV.root");
//TTree *SB_OnPeak_Tree = (TTree*)SB_OnPeak->Get("latino");
TChain *S_Chain = new TChain("latino");
TChain *C_Chain = new TChain("latino");
TChain *SCI_Chain = new TChain("latino");
TChain *qqWW_Chain = new TChain("latino");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigOnPeak_8TeV.root");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigShoulder_8TeV.root");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigTail_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntOnPeak_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntShoulder_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntTail_8TeV.root");
C_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw25_CotHead_8TeV.root");
C_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw25_CotTail_8TeV.root");
qqWW_Chain->Add("/afs/cern.ch/user/m/maiko/work/public/Tree/tree_skim_wwmin/nominals/latino_000_WWJets2LMad.root");
// --- Register the training and test trees
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( S_Chain );
factory->AddBackgroundTree( qqWW_Chain );
factory->AddBackgroundTree( C_Chain );
// Classification training and test data in ROOT tree format with signal and background events being located in the same tree
//factory->SetInputTrees(SCI_Chain, GenOffCut, GenOnCut);
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
factory->SetWeightExpression ("2.1*puW*baseW*effW*triggW*19.468");
//factory->SetSignalWeightExpression ("2.1*puW*baseW*effW*triggW*19.468");
//factory->SetBackgroundWeightExpression("puW*baseW*effW*triggW*19.468");
//factory->PrepareTrainingAndTestTree( ChanCommOff,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=None:!V" );
//"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V";
factory->PrepareTrainingAndTestTree( ChanCommOff0J,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=None:!V" );
// ---- Book MVA methods
//
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
//"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// -----------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// -----------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char* argv[]){
// Configurable parameters
// int max_events; // Maximum number of events to process
//string filelist; // The file containing a list of files to use as input
//string input_prefix; // A prefix that will be added to the path of each input file
string folder;
string output_name; // Name of the ouput ROOT File
string output_folder; // Folder to write the output in
string paramfile;
string paramfile2;
string classname;
bool twotag;
bool onetag;
po::options_description config("Configuration");
po::variables_map vm;
po::notify(vm);
config.add_options()
("folder", po::value<string>(&folder)->default_value("output/Paper_2012/"))
// ("input_prefix", po::value<string>(&input_prefix)->default_value(""))
("output_name", po::value<string>(&output_name)->default_value("test_tmva.root"))
("output_folder", po::value<string>(&output_folder)->default_value(""))
("paramfile", po::value<string>(¶mfile)->default_value("./scripts/Paper_params_2012.dat"))
("paramfile2", po::value<string>(¶mfile2)->default_value("./scripts/TMVAinputshad.dat"))
("classname", po::value<string>(&classname)->default_value("HhhMVA"))
("twotag", po::value<bool>(&twotag)->default_value(true))
("onetag", po::value<bool>(&onetag)->default_value(false))
;
po::store(po::command_line_parser(argc, argv).
options(config).allow_unregistered().run(), vm);
po::notify(vm);
std::cout << "-------------------------------------" << std::endl;
std::cout << "Train MVA" << std::endl;
std::cout << "-------------------------------------" << std::endl; string param_fmt = "%-25s %-40s\n";
std::vector<string> bckglist;
bckglist.push_back("TTJetsFullLept");
bckglist.push_back("TTJetsSemiLept");
bckglist.push_back("TTJetsHadronicExt");
// bckglist.push_back("WWJetsTo2L2Nu");
// bckglist.push_back("WZJetsTo2L2Q");
// bckglist.push_back("WZJetsTo3LNu");
// bckglist.push_back("ZZJetsTo2L2Nu");
// bckglist.push_back("ZZJetsTo2L2Q");
// bckglist.push_back("ZZJetsTo4L");
// bckglist.push_back("DYJetsToTauTauSoup");
// bckglist.push_back("DYJetsToLLSoup");
// bckglist.push_back("DYJetsToTauTau");
// bckglist.push_back("DYJetsToLL");
// bckglist.push_back("T-tW");
// bckglist.push_back("Tbar-tW");
std::vector<string> signallist;
signallist.push_back("GluGluToHTohhTo2Tau2B_mH-300");
sample_names_.reserve(bckglist.size()+signallist.size());
sample_names_.insert(sample_names_.end(),bckglist.begin(),bckglist.end());
sample_names_.insert(sample_names_.end(),signallist.begin(),signallist.end());
std::vector<TFile*> BackgroundSamples;
for(unsigned int iter=0;iter<bckglist.size();++iter){
BackgroundSamples.push_back(TFile::Open((folder+bckglist.at(iter)+"_mt_2012.root").c_str()));
}
std::vector<TFile*> SignalSamples;
for(unsigned int sigIter=0;sigIter<signallist.size();++sigIter){
SignalSamples.push_back(TFile::Open((folder+signallist.at(sigIter)+"_mt_2012.root").c_str()));
}
std::vector<TTree*> backgroundTrees;
for(unsigned int iter2=0;iter2<BackgroundSamples.size();++iter2){
backgroundTrees.push_back(dynamic_cast<TTree*>(BackgroundSamples.at(iter2)->Get("ntuple")));
}
std::vector<TTree*> signalTrees;
for(unsigned int sigIter2=0;sigIter2<SignalSamples.size();++sigIter2){
signalTrees.push_back(dynamic_cast<TTree*>(SignalSamples.at(sigIter2)->Get("ntuple")));
}
TFile *outfile = new TFile((output_folder+output_name).c_str(),"RECREATE");
TMVA::Factory *factory = new TMVA::Factory(classname,outfile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
std::vector<std::string> vars;
std::ifstream parafile(paramfile2.c_str());
std::cout<<paramfile2.c_str()<<std::endl;
string line;
while(getline(parafile,line)){
vars.push_back(line);
}
parafile.close();
std::cout<<(vars.at(0)).c_str()<<std::endl;
std::vector<float> var2;
for(unsigned int variter=0;variter<vars.size();++variter){
var2.push_back(::atof((vars.at(variter)).c_str()));
}
for(unsigned int variter=0;variter<vars.size();++variter){
factory->AddVariable((vars.at(variter)).c_str(),(vars.at(variter)).c_str(),"",'F');
}
factory->AddSpectator("mt_1","mt_1","",'F');
factory->AddSpectator("n_prebjets","n_prebjets","",'I');
factory->AddSpectator("prebjetbcsv_1","prebjetbcsv_1","",'F');
factory->AddSpectator("prebjetbcsv_2","prebjetbcsv_2","",'F');
double weightval_=0;
ParseParamFile(paramfile);
for(unsigned int bckgit=0;bckgit<backgroundTrees.size();++bckgit){
auto it = sample_info_.find(bckglist.at(bckgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs = it->second.second;
weightval_=(double) xs/evt;
std::cout<<weightval_<<std::endl;
}
factory->AddBackgroundTree(backgroundTrees.at(bckgit),weightval_);
}
for(unsigned int sgit=0;sgit<signalTrees.size();++sgit){
auto it = sample_info_.find(signallist.at(sgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs=it->second.second;
weightval_=(Double_t) xs/evt;
}
std::cout<<weightval_<<std::endl;
factory->AddSignalTree(signalTrees.at(sgit),weightval_);
}
factory->SetBackgroundWeightExpression("wt");
factory->SetSignalWeightExpression("wt");
TCut mycutb, mycuts;
if(twotag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
}
else if(onetag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
}
else{
mycutb="n_prebjets>1&&mt_1<30";
mycuts="n_prebjets>1&&mt_1<30";
}
//TCut mycutb="";
//TCut mycuts="";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,"SplitMode=Random:!V");
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outfile->Close();
delete factory;
return 0;
}
int main(int argc, char * argv[])
{
//Processing input options
int c;
std::string outFname;
outFname = std::string("QualityNaF.root");
// Open input files, get the trees
TChain *mc = InputFileReader("FileListNtuples_ext.txt","parametri_geo");
// Preparing options for the TMVA::Factory
std::string options(
"!V:"
"!Silent:"
"Color:"
"DrawProgressBar:"
"Transformations=I;D;P;G,D:"
"AnalysisType=Classification"
);
//Creating the factory
TFile * ldFile = new TFile(outFname.c_str(),"RECREATE");
TMVA::Factory * factory = new TMVA::Factory("QualityNaF", ldFile, options.c_str());
//Preparing variables
//general
/*factory->AddVariable("Chisquare", 'F');
factory->AddVariable("Layernonusati", 'I');
factory->AddVariable("NTofUsed", 'I');
factory->AddVariable("diffR", 'F');
factory->AddVariable("TOF_Up_Down", 'F');*/
//Tof
//factory->AddVariable("TOFchisq_s", 'F');
//factory->AddVariable("TOFchisq_t", 'F');
//RICH
factory->AddVariable("Richtotused", 'F');
factory->AddVariable("RichPhEl", 'F');
factory->AddVariable("RICHprob", 'F');
factory->AddVariable("RICHcollovertotal");
factory->AddVariable("RICHLipBetaConsistency");
factory->AddVariable("RICHTOFBetaConsistency");
factory->AddVariable("RICHChargeConsistency");
factory->AddVariable("RICHPmts");
factory->AddVariable("RICHgetExpected");
factory->AddVariable("tot_hyp_p_uncorr");
factory->AddVariable("Bad_ClusteringRICH");
factory->AddVariable("NSecondariesRICHrich");
//factory->AddVariable("HitHValldir");
//factory->AddVariable("HitHVallrefl");
//factory->AddVariable("HVBranchCheck:= (HitHValldir - HitHVoutdir) - (HitHVallrefl - HitHVoutrefl)");
factory->AddVariable("HitHVoutdir");
factory->AddVariable("HitHVoutrefl");
//Spectator Variables
factory->AddSpectator("R", 'F');
factory->AddSpectator("BetaRICH_new", 'F');
//Preselection cuts
std::string PreSelection = "qL1>0&&(joinCutmask&187)==187&&qL1<1.75&&R>0";
std::string ChargeCut = "qUtof>0.8&&qUtof<1.3&&qLtof>0.8&&qLtof<1.3";
std::string VelocityCut = /*"Beta<0.8";*/"((joinCutmask>>11))==1024&&BetaRICH_new>0&&BetaRICH_new<0.975";
std::string signalCut = /*"(R/Beta)*(1-Beta^2)^0.5>1.65&&GenMass>1&&GenMass<2";*/"(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5>0.5&&(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5<1.5";
std::string bkgndCut = /*"(R/Beta)*(1-Beta^2)^0.5>1.65&&GenMass>0&&GenMass<1";*/"(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5>3";
factory->AddTree(mc,"Signal" ,1,(PreSelection +"&&"+ ChargeCut + "&&" + VelocityCut + "&&"+ signalCut).c_str());
factory->AddTree(mc,"Background",1,(PreSelection +"&&"+ ChargeCut + "&&" + VelocityCut + "&&"+ bkgndCut).c_str());
// Preparing
std::string preselection = "";
std::string inputparams(
"SplitMode=Random:"
"NormMode=NumEvents:"
"!V"
);
factory->PrepareTrainingAndTestTree(preselection.c_str(),inputparams.c_str());
// Training
std::string trainparams ="!H:!V:MaxDepth=3";
factory->BookMethod(TMVA::Types::kBDT, "BDT", trainparams.c_str());
trainparams ="!H:!V";
factory->BookMethod(TMVA::Types::kLikelihood, "Likelihood", trainparams.c_str());
trainparams ="!H:!V:VarTransform=Decorrelate";
//factory->BookMethod(TMVA::Types::kLikelihood, "LikelihoodD", trainparams.c_str());
trainparams ="!H:!V";
//factory->BookMethod(TMVA::Types::kCuts, "Cuts", trainparams.c_str());
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
}
void WWTMVAClassification( TString myMethodList = "", double mH=400., int njets, TString chan="el" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
// ---
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDERSkNN"] = 0; // depreciated until further notice
Use["PDEFoam"] = 0;
// --
Use["KNN"] = 0;
// ---
Use["HMatrix"] = 0;
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0;
Use["LD"] = 1;
// ---
Use["FDA_GA"] = 0;
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
// ---
Use["MLP"] = 0; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["CFMlpANN"] = 0; // *** missing
Use["TMlpANN"] = 0;
// ---
Use["SVM"] = 0;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 0;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 0;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
///////TString outfileName( "TMVA.root" );
char outfileName[192];
sprintf(outfileName,"TMVA_%3.0f_nJ%i_%s.root",mH,njets,chan.Data());
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
char classifierName[192];
sprintf(classifierName,"TMVAClassification_%3.0f_nJ%i_%s",mH,njets,chan.Data());
TMVA::Factory *factory = new TMVA::Factory( classifierName, outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
//TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
// "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// leptonic W
factory->AddVariable("WWpt := ptlvjj", 'F');
factory->AddVariable("WWy := ylvjj", 'F');
//factory->AddVariable("Wpt := W_pt", 'F');
//factory->AddVariable("MET := event_met_pfmet", 'F');
if (chan = "mu"){
factory->AddVariable("LepCharge := W_muon_charge", 'F');
}
else if (chan = "el"){
factory->AddVariable("LepCharge := W_electron_charge", 'F');
}
else{
std::cout << "Invalid channel!" << std::endl;
return;
}
// factory->AddVariable("J1QGL := JetPFCor_QGLikelihood[0]", 'F');
// factory->AddVariable("J2QGL := JetPFCor_QGLikelihood[1]", 'F');
factory->AddVariable("costheta1 := ang_ha", 'F');
factory->AddVariable("costheta2 := ang_hb", 'F');
factory->AddVariable("costhetaS := ang_hs", 'F');
factory->AddVariable("Phi := ang_phi", 'F');
factory->AddVariable("Phi2 := ang_phib", 'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator("run := event_runNo", "I");
factory->AddSpectator("lumi := event_lumi", "I");
factory->AddSpectator("event := event_evtNo", "I");
factory->AddSpectator("mjj := Mass2j_PFCor", "F");
factory->AddSpectator("mlvjj := MassV2j_PFCor", "F");
factory->AddSpectator("masslvjj := masslvjj", "F");
//factory->AddSpectator("ggdevt := ggdevt", "F");
//factory->AddSpectator("fit_mlvjj := fit_mlvjj", "F");
// read training and test data
char signalOutputName[192];
sprintf(signalOutputName,"/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_%s_HWWMH%3.0f_CMSSW428.root",chan.Data(),mH);
TFile *input1 = TFile::Open( signalOutputName );
//TFile *input1 = TFile::Open( "/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_mu_HWWMH400_CMSSW428.root");
char backgroundOutputName[192];
sprintf(backgroundOutputName,"/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_%s_WpJ_CMSSW428.root",chan.Data());
TFile *input2 = TFile::Open( backgroundOutputName );
std::cout << "--- TMVAClassification : Using input file: " << input1->GetName() << std::endl;
TTree *signal = (TTree*)input1->Get("WJet");
TTree *background = (TTree*)input2->Get("WJet");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
// TCut mycuts = "abs(eta)>1.5"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
// TCut mycutb = "abs(eta)>1.5"; // for example: TCut mycutb = "abs(var1)<0.5";
char * mass4bodycut = "";
if(njets==2) {
if(chan.Contains("mu")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>176 && fit_mlvjj<262)"; // 2j170mu =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>179 && fit_mlvjj<256)"; // 2j180mu
if(mH==190.) mass4bodycut = "(fit_mlvjj>186 && fit_mlvjj<214)"; // 2j190mu
if(mH==200.) mass4bodycut = "(fit_mlvjj>191 && fit_mlvjj<226)"; // 2j200mu
if(mH==250.) mass4bodycut = "(fit_mlvjj>226 && fit_mlvjj<287)"; // 2j250mu
if(mH==300.) mass4bodycut = "(fit_mlvjj>265 && fit_mlvjj<347)"; // 2j300mu
if(mH==350.) mass4bodycut = "(fit_mlvjj>308 && fit_mlvjj<401)"; // 2j350mu
if(mH==400.) mass4bodycut = "(fit_mlvjj>346 && fit_mlvjj<457)"; // 2j400mu
if(mH==450.) mass4bodycut = "(fit_mlvjj>381 && fit_mlvjj<512)"; // 2j450mu
if(mH==500.) mass4bodycut = "(fit_mlvjj>415 && fit_mlvjj<568)"; // 2j500mu
if(mH==550.) mass4bodycut = "(fit_mlvjj>440 && fit_mlvjj<617)"; // 2j550mu
if(mH==600.) mass4bodycut = "(fit_mlvjj>462 && fit_mlvjj<663)"; // 2j600mu
}
if(chan.Contains("el")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>176 && fit_mlvjj<262)"; // 2j170el =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>179 && fit_mlvjj<256)"; // 2j180el
if(mH==190.) mass4bodycut = "(fit_mlvjj>186 && fit_mlvjj<214)"; // 2j190el
if(mH==200.) mass4bodycut = "(fit_mlvjj>191 && fit_mlvjj<226)"; // 2j200el
if(mH==250.) mass4bodycut = "(fit_mlvjj>226 && fit_mlvjj<287)"; // 2j250el
if(mH==300.) mass4bodycut = "(fit_mlvjj>265 && fit_mlvjj<347)"; // 2j300el
if(mH==350.) mass4bodycut = "(fit_mlvjj>308 && fit_mlvjj<401)"; // 2j350el
if(mH==400.) mass4bodycut = "(fit_mlvjj>346 && fit_mlvjj<457)"; // 2j400el
if(mH==450.) mass4bodycut = "(fit_mlvjj>381 && fit_mlvjj<512)"; // 2j450el
if(mH==500.) mass4bodycut = "(fit_mlvjj>415 && fit_mlvjj<568)"; // 2j500el
if(mH==550.) mass4bodycut = "(fit_mlvjj>440 && fit_mlvjj<617)"; // 2j550el
if(mH==600.) mass4bodycut = "(fit_mlvjj>462 && fit_mlvjj<663)"; // 2j600el
}
}
if(njets==3) {
if(chan.Contains("mu")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>150 && fit_mlvjj<271)"; // 3j170mu =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>175 && fit_mlvjj<284)"; // 3j180mu
if(mH==190.) mass4bodycut = "(fit_mlvjj>185 && fit_mlvjj<290)"; // 3j190mu
if(mH==200.) mass4bodycut = "(fit_mlvjj>188 && fit_mlvjj<293)"; // 3j200mu
if(mH==250.) mass4bodycut = "(fit_mlvjj>216 && fit_mlvjj<300)"; // 3j250mu
if(mH==300.) mass4bodycut = "(fit_mlvjj>241 && fit_mlvjj<355)"; // 3j300mu
if(mH==350.) mass4bodycut = "(fit_mlvjj>269 && fit_mlvjj<407)"; // 3j350mu
if(mH==400.) mass4bodycut = "(fit_mlvjj>300 && fit_mlvjj<465)"; // 3j400mu
if(mH==450.) mass4bodycut = "(fit_mlvjj>332 && fit_mlvjj<518)"; // 3j450mu
if(mH==500.) mass4bodycut = "(fit_mlvjj>362 && fit_mlvjj<569)"; // 3j500mu
if(mH==550.) mass4bodycut = "(fit_mlvjj>398 && fit_mlvjj<616)"; // 3j550mu
if(mH==600.) mass4bodycut = "(fit_mlvjj>419 && fit_mlvjj<660)"; // 3j600mu
}
if(chan.Contains("el")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>150 && fit_mlvjj<271)"; // 3j170el =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>175 && fit_mlvjj<284)"; // 3j180el
if(mH==190.) mass4bodycut = "(fit_mlvjj>185 && fit_mlvjj<290)"; // 3j190el
if(mH==200.) mass4bodycut = "(fit_mlvjj>188 && fit_mlvjj<293)"; // 3j200el
if(mH==250.) mass4bodycut = "(fit_mlvjj>216 && fit_mlvjj<300)"; // 3j250el
if(mH==300.) mass4bodycut = "(fit_mlvjj>241 && fit_mlvjj<355)"; // 3j300el
if(mH==350.) mass4bodycut = "(fit_mlvjj>269 && fit_mlvjj<407)"; // 3j350el
if(mH==400.) mass4bodycut = "(fit_mlvjj>300 && fit_mlvjj<465)"; // 3j400el
if(mH==450.) mass4bodycut = "(fit_mlvjj>332 && fit_mlvjj<518)"; // 3j450el
if(mH==500.) mass4bodycut = "(fit_mlvjj>362 && fit_mlvjj<569)"; // 3j500el
if(mH==550.) mass4bodycut = "(fit_mlvjj>398 && fit_mlvjj<616)"; // 3j550el
if(mH==600.) mass4bodycut = "(fit_mlvjj>419 && fit_mlvjj<660)"; // 3j600el
}
}
char mycutschar[1000];
sprintf(mycutschar,"ggdevt == %i &&(Mass2j_PFCor>65 && Mass2j_PFCor<95) && %s", njets, mass4bodycut);
TCut mycuts (mycutschar);
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycuts,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+5:TestRate=10:EpochMonitoring" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+5:TestRate=10:TrainingMethod=BFGS:!EpochMonitoring" );
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString eventsToTrain = "0", const TString & region = "barrel", const TString index = "", TString myMethodList = "BDT")
{
std::cout << "running classification for " << region << " for " << myMethodList << std::endl;
if( region != "barrel" && region != "endcaps" ) {
std::cout << "Error, region can only be barrel or endcaps. Selected region was: " << region << std::endl;
exit(1);
}
if( index != "" && index != "0" && index != "1" && index != "2" ) {
std::cout << "Error, index can only be \"\", \"0\", \"1\" or \"2\". Selected index was: " << index << std::endl;
exit(1);
}
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
std::exit(2);
}
Use[regMethod] = 1;
}
}
// Input and output file names
TString fnameTrainS = "BsMC12_barrel_preselection";
TString fnameTrainB = "Barrel_preselection";
TString fnameTestS = "BsMC12_barrel_preselection";
TString fnameTestB = "Barrel_preselection";
TString outputFileName = "TMVA_barrel";
TString weightDirName = "barrel";
if( region == "endcaps" ) {
fnameTrainS = "BsMC12_endcaps_preselection";
fnameTrainB = "Endcaps_preselection";
fnameTestS = "BsMC12_endcaps_preselection";
fnameTestB = "Endcaps_preselection";
outputFileName = "TMVA_endcaps";
weightDirName = "endcaps";
}
if( index != "" ) {
fnameTrainS += "_"+index;
fnameTrainB += "_"+index;
TString indexTest = "";
// The test index is the train index +1 (2+1 -> 0)
if( index == "0" ) indexTest = "1";
else if( index == "1" ) indexTest = "2";
else if( index == "2" ) indexTest = "0";
fnameTestS += "_"+indexTest;
fnameTestB += "_"+indexTest;
outputFileName += "_"+index;
weightDirName += index;
}
fnameTrainS = rootDir + fnameTrainS + ".root";
fnameTrainB = rootDir + fnameTrainB + ".root";
fnameTestS = rootDir + fnameTestS + ".root";
fnameTestB = rootDir + fnameTestB + ".root";
outputFileName = rootDir + outputFileName + ".root";
weightDirName = weightsDir + weightDirName + "Weights";
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName(outputFileName);
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// (TMVA::gConfig().GetIONames()).fWeightFileDir = outputFileName;
(TMVA::gConfig().GetIONames()).fWeightFileDir = weightDirName;
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
bool useNewMuonID = false;
factory->AddVariable( "fls3d", "fls3d", "", 'F' );
factory->AddVariable( "alpha", "alpha", "", 'F' );
factory->AddVariable( "pvips", "pvips", "", 'F' );
factory->AddVariable( "iso", "iso", "", 'F' );
factory->AddVariable( "m1iso", "m1iso", "", 'F' );
factory->AddVariable( "m2iso", "m2iso", "", 'F' );
factory->AddVariable( "chi2dof", "chi2/dof", "", 'F' );
if( region == "barrel" ) {
factory->AddVariable( "eta", "eta", "", 'F' );
factory->AddVariable( "maxdoca", "maxdoca", "cm", 'F' );
}
else {
factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
factory->AddVariable( "pvip", "pvip", "cm", 'F' );
}
factory->AddVariable( "docatrk", "docatrk", "cm", 'F' );
// factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
// factory->AddVariable( "closetrk", "closetrk", "", 'I' );
// factory->AddVariable( "y", "y", "", 'F' );
// factory->AddVariable( "l3d", "l3d", "cm", 'F' );
// factory->AddVariable( "cosAlphaXY", "cosAlphaXY", "", 'F' );
// factory->AddVariable( "mu1_dxy", "mu1_dxy", "cm", 'F' );
// factory->AddVariable( "mu2_dxy", "mu2_dxy", "cm", 'F' );
if( useNewMuonID ) {
// New Muon-id
factory->AddVariable( "mu1_MVAMuonID", "mu1_MVAMuonID", "", 'F');
factory->AddVariable( "mu2_MVAMuonID", "mu2_MVAMuonID", "", 'F');
}
// Extra variables
// factory->AddVariable( "mu1_pt", "mu1_pt", "GeV/c", 'F' );
// factory->AddVariable( "mu2_pt", "mu2_pt", "GeV/c", 'F' );
// factory->AddVariable( "pvw8", "pvw8", "", 'F' );
// factory->AddVariable( "cosAlpha3D", "cosAlpha3D", "", 'F' );
// factory->AddVariable( "countTksOfPV", "countTksOfPV", "", 'I' );
// factory->AddVariable( "ctauErrPV", "ctauErrPV", "", 'F' );
// factory->AddVariable( "ctauPV", "ctauPV", "", 'F' );
// factory->AddVariable( "dcaxy", "dcaxy", "", 'F' );
// factory->AddVariable( "mu1_glbTrackProb", "mu1_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu1_nChi2", "mu1_nChi2", "", 'F' );
// factory->AddVariable( "mu1_nMuSegs", "mu1_nMuSegs", "", 'F' );
// factory->AddVariable( "mu1_nMuSegsCln", "mu1_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu1_nPixHits", "mu1_nPixHits", "", 'F' );
// factory->AddVariable( "mu1_nTrHits", "mu1_nTrHits", "", 'F' );
// factory->AddVariable( "mu1_segComp", "mu1_segComp", "", 'F' );
// factory->AddVariable( "mu1_trkEHitsOut", "mu1_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu1_trkVHits", "mu1_trkVHits", "", 'F' );
// factory->AddVariable( "mu1_validFrac", "mu1_validFrac", "", 'F' );
// factory->AddVariable( "mu1_chi2LocMom", "mu1_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu1_chi2LocPos", "mu1_chi2LocPos", "", 'F' );
// factory->AddVariable( "mu2_glbTrackProb", "mu2_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu2_nChi2", "mu2_nChi2", "", 'F' );
// factory->AddVariable( "mu2_nMuSegs", "mu2_nMuSegs", "", 'F' );
// factory->AddVariable( "mu2_nMuSegsCln", "mu2_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu2_nPixHits", "mu2_nPixHits", "", 'F' );
// factory->AddVariable( "mu2_nTrHits", "mu2_nTrHits", "", 'F' );
// factory->AddVariable( "mu2_segComp", "mu2_segComp", "", 'F' );
// factory->AddVariable( "mu2_trkEHitsOut", "mu2_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu2_trkVHits", "mu2_trkVHits", "", 'F' );
// factory->AddVariable( "mu2_validFrac", "mu2_validFrac", "", 'F' );
// factory->AddVariable( "mu2_chi2LocMom", "mu2_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu2_chi2LocPos", "mu2_chi2LocPos", "", 'F' );
// factory->AddVariable( "l3d := ctauPV*pt/mass", "l3d", "cm", 'F' );
// factory->AddVariable( "l3dSig := ctauPV/ctauErrPV", "l3dSig", "", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := mass*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := mass*3", "Spectator 2", "units", 'F' );
factory->AddSpectator( "mass", "mass", "GeV/c^{2}", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
if (gSystem->AccessPathName( fnameTrainS )) { // file does not exist in local directory
std::cout << "Did not access " << fnameTrainS << " exiting." << std::endl;
std::exit(4);
}
//gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *inputTrainS = TFile::Open( fnameTrainS );
TFile *inputTrainB = TFile::Open( fnameTrainB );
TFile *inputTestS = TFile::Open( fnameTestS );
TFile *inputTestB = TFile::Open( fnameTestB );
// --- Register the training and test trees
TTree *signalTrainTree = (TTree*)inputTrainS->Get("probe_tree");
TTree *backgroundTrainTree = (TTree*)inputTrainB->Get("probe_tree");
TTree *signalTestTree = (TTree*)inputTestS->Get("probe_tree");
TTree *backgroundTestTree = (TTree*)inputTestB->Get("probe_tree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalTrainWeight = 1.0;
Double_t backgroundTrainWeight = 1.0;
Double_t signalTestWeight = 1.0;
Double_t backgroundTestWeight = 1.0;
// Decide if using the split and mixing or the full trees
if( fnameTrainS == fnameTestS ) {
if( fnameTrainB != fnameTestB ) {
std::cout << "This macro cannot handle cases where the same signal sample is used for training and testing, but different background samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << std::endl;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signalTrainTree, signalTrainWeight );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight );
}
else {
if( fnameTrainB == fnameTestB ) {
std::cout << "This macro cannot handle cases where the same background sample is used for training and testing, but different signal samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << " for training and" << std::endl;
std::cout << "--- input file: " << inputTestS->GetName() << std::endl;
std::cout << "--- and file: " << inputTestB->GetName() << " for testing." << std::endl;
// To give different trees for training and testing, do as follows:
factory->AddSignalTree( signalTrainTree, signalTrainWeight, "Training" );
factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight, "Training" );
factory->AddBackgroundTree( backgroundTestTree, backgroundTestWeight, "Test" );
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal="+eventsToTrain+":nTrain_Background="+eventsToTrain+":SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=3000:nTrain_Background=3000:nTest_Signal=3000:nTest_Background=3000:SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+8:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=800:nEventsMin=50:MaxDepth=2:BoostType=AdaBoost:AdaBoostBeta=1:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:NNodesMax=5" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
std::cout << "Training all methods" << std::endl;
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
std::cout << "Testing all methods" << std::endl;
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
std::cout << "Evaluating all methods" << std::endl;
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVATrainer(){
// This loads the library
TMVA::Tools::Instance();
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName = "TMVATrainingResults_fat_BBvsGSP.root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVATrainer", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable("TagVarCSV_vertexCategory","TagVarCSV_vertexCategory","units",'F');
factory->AddVariable("TagVarCSV_jetNTracks","TagVarCSV_jetNTracks","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_0","TagVarCSV_trackSip2dSig_0","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_1","TagVarCSV_trackSip2dSig_1","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_2","TagVarCSV_trackSip2dSig_2","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_3","TagVarCSV_trackSip2dSig_3","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_0","TagVarCSV_trackSip3dSig_0","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_1","TagVarCSV_trackSip3dSig_1","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_2","TagVarCSV_trackSip3dSig_2","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_3","TagVarCSV_trackSip3dSig_3","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_0","TagVarCSV_trackPtRel_0","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_1","TagVarCSV_trackPtRel_1","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_2","TagVarCSV_trackPtRel_2","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_3","TagVarCSV_trackPtRel_3","units",'F');
factory->AddVariable("TagVarCSV_trackSip2dSigAboveCharm","TagVarCSV_trackSip2dSigAboveCharm","units",'F');
//factory->AddVariable("TagVarCSV_trackSip3dSigAboveCharm","TagVarCSV_trackSip3dSigAboveCharm","units",'F');
//factory->AddVariable("TagVarCSV_trackSumJetEtRatio","TagVarCSV_trackSumJetEtRatio","units",'F');
//factory->AddVariable("TagVarCSV_trackSumJetDeltaR","TagVarCSV_trackSumJetDeltaR","units",'F');
factory->AddVariable("TagVarCSV_jetNTracksEtaRel","TagVarCSV_jetNTracksEtaRel","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_0","TagVarCSV_trackEtaRel_0","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_1","TagVarCSV_trackEtaRel_1","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_2","TagVarCSV_trackEtaRel_2","units",'F');
factory->AddVariable("TagVarCSV_jetNSecondaryVertices","TagVarCSV_jetNSecondaryVertices","units",'F');
factory->AddVariable("TagVarCSV_vertexMass","TagVarCSV_vertexMass","units",'F');
factory->AddVariable("TagVarCSV_vertexNTracks","TagVarCSV_vertexNTracks","units",'F');
factory->AddVariable("TagVarCSV_vertexEnergyRatio","TagVarCSV_vertexEnergyRatio","units",'F');
factory->AddVariable("TagVarCSV_vertexJetDeltaR","TagVarCSV_vertexJetDeltaR","units",'F');
factory->AddVariable("TagVarCSV_flightDistance2dSig","TagVarCSV_flightDistance2dSig","units",'F');
//factory->AddVariable("TagVarCSV_flightDistance3dSig","TagVarCSV_flightDistance3dSig","units",'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator("Jet_pt","Jet_pt","units",'F');
factory->AddSpectator("Jet_eta","Jet_eta","units",'F');
factory->AddSpectator("Jet_phi","Jet_phi","units",'F');
factory->AddSpectator("Jet_mass","Jet_mass","units",'F');
factory->AddSpectator("Jet_massGroomed","Jet_massGroomed","units",'F');
factory->AddSpectator("Jet_flavour","Jet_flavour","units",'F');
factory->AddSpectator("Jet_nbHadrons","Jet_nbHadrons","units",'F');
factory->AddSpectator("Jet_JP","Jet_JP","units",'F');
factory->AddSpectator("Jet_JBP","Jet_JBP","units",'F');
factory->AddSpectator("Jet_CSV","Jet_CSV","units",'F');
factory->AddSpectator("Jet_CSVIVF","Jet_CSVIVF","units",'F');
factory->AddSpectator("Jet_tau1","Jet_tau1","units",'F');
factory->AddSpectator("Jet_tau2","Jet_tau2","units",'F');
factory->AddSpectator("SubJet1_CSVIVF","SubJet1_CSVIVF","units",'F');
factory->AddSpectator("SubJet2_CSVIVF","SubJet2_CSVIVF","units",'F');
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fnameSig = "RadionToHH_4b_M-800_TuneZ2star_8TeV-Madgraph_pythia6_JetTaggingVariables_training.root";
TString fnameBkg = "QCD_Pt-300to470_TuneZ2star_8TeV_pythia6_JetTaggingVariables_training.root";
TFile *inputSig = TFile::Open( fnameSig );
TFile *inputBkg = TFile::Open( fnameBkg );
std::cout << "--- TMVAClassification : Using input files: " << inputSig->GetName() << std::endl
<< inputBkg->GetName() << std::endl;
// --- Register the training and test trees
TTree *sigTree = (TTree*)inputSig->Get("tagVars/ttree");
TTree *bkgTree = (TTree*)inputBkg->Get("tagVars/ttree");
// // global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// factory->SetInputTrees( tree,signalCut,backgroundCut );
factory->AddSignalTree ( sigTree, signalWeight );
factory->AddBackgroundTree( bkgTree, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut signalCut = "Jet_massGroomed>80 && Jet_massGroomed<150";
TCut backgroundCut = "abs(Jet_flavour)==5 && Jet_nbHadrons>1 && Jet_massGroomed>80 && Jet_massGroomed<150";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree( signalCut, backgroundCut,
"nTrain_Signal=22000:nTest_Signal=20000:nTrain_Background=22000:nTest_Background=2730:SplitMode=Random:!V" );
// Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG_T1000D3_fat_BBvsGSP",
"!H:!V:NTrees=1000:MaxDepth=3:MinNodeSize=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG_T1000D5_fat_BBvsGSP",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20" );
// // Adaptive Boost
// factory->BookMethod( TMVA::Types::kBDT, "BDT",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
// // Bagging
// factory->BookMethod( TMVA::Types::kBDT, "BDTB",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
// // Decorrelation + Adaptive Boost
// factory->BookMethod( TMVA::Types::kBDT, "BDTD",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName MVAconfigFileName" << std::endl ;
return 1;
}
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
double LUMI = gConfigParser -> readDoubleOption("Options::Lumi");
std::vector<std::string> SignalName;
SignalName = gConfigParser -> readStringListOption("Options::SignalName");
for (int iSignalSample=0; iSignalSample<SignalName.size(); iSignalSample++) {
std::cout << " Signal[" << iSignalSample << "] = " << SignalName.at(iSignalSample) << std::endl;
}
std::string nameWeight = "1";
try {
nameWeight = gConfigParser -> readStringOption("Options::nameWeight");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::nameWeight " << nameWeight << std::endl;
TTree *treeJetLepVect[200];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++) {
xsection[iSample] = atof(xsectionName[iSample]);
}
for (int iSample=0; iSample<numberOfSamples; iSample++) {
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
TFile* f = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) f->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
double XSection;
XSection = xsection[iSample];
Normalization[iSample] = XSection * LUMI / 1000.;
}
//==== cut
std::string CutFile = gConfigParser -> readStringOption("Selections::CutFile");
std::vector<std::string> vCut;
std::cout << " nCuts = " << ReadFileCut(CutFile, vCut) << std::endl;
std::string Cut;
if (vCut.size() != 0) {
Cut = vCut.at(0);
}
else {
Cut = "1";
}
//==== HiggsMass
std::string HiggsMass = gConfigParser -> readStringOption("Options::HiggsMass");
//==== list of methods
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
TString myMethodList;
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
if (iMVA == 0) myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
else myMethodList = Form ("%s,%s",myMethodList.Data(),vectorMyMethodList.at(iMVA).c_str());
}
//==== output
TString outfileName = gConfigParser -> readStringOption("Output::outFileName");
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 1;
Use["BDTG"] = 1;
Use["FDA_GA"] = 0;
Use["PDEFoam"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return 0;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "AnalysisType=multiclass:!V:!Silent:!V:Transformations=I;D" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=multiclass" );
factory->AddVariable( "jetpt1" , 'F');
factory->AddVariable( "jetpt2" , 'F');
factory->AddVariable( "mjj" , 'F');
factory->AddVariable( "detajj" , 'F');
factory->AddVariable( "dphilljetjet" , 'F');
factory->AddVariable( "pt1" , 'F');
factory->AddVariable( "pt2" , 'F');
factory->AddVariable( "mll" , 'F');
factory->AddVariable( "dphill" , 'F');
factory->AddVariable( "mth" , 'F');
factory->AddVariable( "dphillmet" , 'F');
factory->AddVariable( "mpmet" , 'F');
factory->AddSpectator( "channel" , 'F');
for (int iSample=0; iSample<numberOfSamples; iSample++) {
int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
if (numEnt != 0) {
if (iSample == 0) factory->AddTree( treeJetLepVect[iSample], "Signal", Normalization[iSample] );
else if (iSample == 1) factory->AddTree( treeJetLepVect[iSample], "Background", Normalization[iSample] );
else factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] , nameWeight.c_str());
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]));
}
}
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
//
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// // factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
std::cerr << " AAAAAAAAAAAAAAAAAAAAAAAAAAAAA " << std::endl;
TCut mycuts = Cut.c_str();
// factory->SetWeightExpression( nameWeight.c_str() );
// factory->SetBackgroundWeightExpression( nameWeight.c_str() );
// factory->SetSignalWeightExpression ( nameWeight.c_str() );
std::cerr << " BBBBBBBBBBBBBBBBBBBBBBBBBBBBB " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts ,"SplitMode=Random:NormMode=None:!V");
// factory->PrepareTrainingAndTestTree( "" ,"SplitMode=Random:NormMode=None:!V");
std::cerr << " CCCCCCCCCCCCCCCCCCCCCCCCCCCCC " << std::endl;
// gradient boosted decision trees
// if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
// neural network
if (Use["MLP"]) factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:NCycles=1000:HiddenLayers=N+5,5:TestRate=5:EstimatorType=MSE");
// functional discriminant with GA minimizer
if (Use["FDA_GA"]) factory->BookMethod( TMVA::Types::kFDA, "FDA_GA", "H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
// PDE-Foam approach
if (Use["PDEFoam"]) factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam", "!H:!V:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
//==== Optimize parameters in MVA methods
// factory->OptimizeAllMethods();
// factory->OptimizeAllMethods("ROCIntegral","Scan");
//==== Train MVAs using the set of training events ====
factory->TrainAllMethods();
//==== Evaluate all MVAs using the set of test events ====
factory->TestAllMethods();
//==== Evaluate and compare performance of all configured MVAs ====
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAnalysis is done!" << std::endl;
delete factory;
//==== change position of weights file
std::string toDo;
toDo = "rm -r Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
toDo = "mv weights Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 1;
Use["CutsGA"] = 1;
Use["CutsSA"] = 1;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 1; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 1;
Use["LikelihoodMIX"] = 1;
// ---
Use["PDERS"] = 1;
Use["PDERSD"] = 1;
Use["PDERSPCA"] = 1;
Use["PDERSkNN"] = 1; // depreciated until further notice
Use["PDEFoam"] = 1;
// --
Use["KNN"] = 1;
// ---
Use["HMatrix"] = 1;
Use["Fisher"] = 1;
Use["FisherG"] = 1;
Use["BoostedFisher"] = 1;
Use["LD"] = 1;
// ---
Use["FDA_GA"] = 1;
Use["FDA_SA"] = 1;
Use["FDA_MC"] = 1;
Use["FDA_MT"] = 1;
Use["FDA_GAMT"] = 1;
Use["FDA_MCMT"] = 1;
// ---
Use["MLP"] = 1; // this is the recommended ANN
Use["MLPBFGS"] = 1; // recommended ANN with optional training method
Use["CFMlpANN"] = 1; // *** missing
Use["TMlpANN"] = 1;
// ---
Use["SVM"] = 1;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 1;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 1;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "myvar1 := var1+var2", 'F' );
factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
factory->AddVariable( "var3", "Variable 3", "units", 'F' );
factory->AddVariable( "var4", "Variable 4", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// read training and test data
if (ReadDataFromAsciiIFormat) {
// load the signal and background event samples from ascii files
// format in file must be:
// var1/F:var2/F:var3/F:var4/F
// 0.04551 0.59923 0.32400 -0.19170
// ...
TString datFileS = "tmva_example_sig.dat";
TString datFileB = "tmva_example_bkg.dat";
factory->SetInputTrees( datFileS, datFileB );
}
else {
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = "../macros/tmva_example.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
else {
input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS" );
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethodsForClassification();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
bool batchMode(false);
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "var1", 'F' );
factory->AddVariable( "var2", 'F' );
factory->AddVariable( "var3", 'F' );
factory->AddVariable( "var4", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "eta" );
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname( "" );
if (UseOffsetMethod) fname = "../execs/data/toy_sigbkg_categ_offset.root";
else fname = "../execs/data/toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
/// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
/// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Fisher discriminant
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Categorised classifier
TMVA::MethodCategory* mcat = 0;
// the variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// the Fisher
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kFisher,"Category_Fisher_1","!H:!V:Fisher");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher,"Category_Fisher_2","!H:!V:Fisher");
// the Likelihood
TMVA::MethodBase* liCat = factory->BookMethod( TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void trainMVACat()
{
char name[1000];
float XSEC[6] = {3.67e+5,2.94e+4,6.524e+03,1.064e+03,121.5,2.542e+01};
float NORM[6];
TCut preselectionCut = "ht>400 && jetPt[5]>40 && (triggerBit[0] || triggerBit[2]) && nBJets>1 && nLeptons==0";
TFile *bkgSrc[6];
bkgSrc[0] = TFile::Open("flatTree_QCD_HT300to500.root");
bkgSrc[1] = TFile::Open("flatTree_QCD_HT500to700.root");
bkgSrc[2] = TFile::Open("flatTree_QCD_HT700to1000.root");
bkgSrc[3] = TFile::Open("flatTree_QCD_HT1000to1500.root");
bkgSrc[4] = TFile::Open("flatTree_QCD_HT1500to2000.root");
bkgSrc[5] = TFile::Open("flatTree_QCD_HT2000toInf.root");
TFile *sigSrc = TFile::Open("flatTree_ttHJetTobb_M125.root");
//TFile *sigSrc = TFile::Open("flatTree_TT.root");
TTree *sigTree = (TTree*)sigSrc->Get("hadtop/events");
TTree *bkgTree[6];
TFile *outf = new TFile("mva_Cat_QCD.root","RECREATE");
TMVA::Factory* factory = new TMVA::Factory("factory_mva_Cat_QCD_",outf,"!V:!Silent:Color:DrawProgressBar:Transformations=I;G:AnalysisType=Classification");
factory->AddSignalTree(sigTree);
for(int k=0;k<6;k++) {
NORM[k] = ((TH1F*)bkgSrc[k]->Get("hadtop/pileup"))->GetEntries();
bkgTree[k] = (TTree*)bkgSrc[k]->Get("hadtop/events");
factory->AddBackgroundTree(bkgTree[k],XSEC[k]/NORM[k]);
}
//int N_SIG(sigTree->GetEntries(preselectionCut));
//int N_BKG0(bkgTree[0]->GetEntries(preselectionCut));
//int N_BKG1(bkgTree[1]->GetEntries(preselectionCut));
//int N_BKG2(bkgTree[2]->GetEntries(preselectionCut));
//int N_BKG3(bkgTree[3]->GetEntries(preselectionCut));
//float N_BKG_EFF = N_BKG0*XSEC[0]/NORM[0]+N_BKG1*XSEC[1]/NORM[1]+N_BKG2*XSEC[2]/NORM[2]+N_BKG3*XSEC[3]/NORM[3];
//int N = TMath::Min((float)N_SIG,N_BKG_EFF);
//cout<<N_SIG<<" "<<N_BKG_EFF<<endl;
const int NVAR = 21;
TString VAR[NVAR] = {
"nJets",
//"nBJets",
"ht",
"jetPt[0]","jetPt[1]","jetPt[2]","jetPt[3]","jetPt[4]","jetPt[5]",
"mbbMin","dRbbMin",
//"dRbbAve","mbbAve",
//"btagAve","btagMax","btagMin",
//"qglAve","qglMin","qglMedian",
"sphericity","aplanarity","foxWolfram[0]","foxWolfram[1]","foxWolfram[2]","foxWolfram[3]",
"mTop[0]","ptTTbar","mTTbar","dRbbTop","chi2"
};
char TYPE[NVAR] = {
'I',
//'I',
'F',
'F','F','F','F','F','F',
'F','F',
//'F','F',
//'F','F','F',
//'F','F','F',
'F','F','F','F','F','F',
'F','F','F','F','F'
};
for(int i=0;i<NVAR;i++) {
factory->AddVariable(VAR[i],TYPE[i]);
}
factory->AddSpectator("status",'I');
factory->AddSpectator("nBJets",'I');
sprintf(name,"nTrain_Signal=%d:nTrain_Background=%d:nTest_Signal=%d:nTest_Background=%d",-1,-1,-1,-1);
factory->PrepareTrainingAndTestTree(preselectionCut,name);
TMVA::IMethod* BDT_Category = factory->BookMethod( TMVA::Types::kCategory,"BDT_Category");
TMVA::MethodCategory* mcategory_BDT = dynamic_cast<TMVA::MethodCategory*>(BDT_Category);
mcategory_BDT->AddMethod("status == 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kBDT,
"BDT_Cat1",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status == 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kBDT,
"BDT_Cat2",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status < 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kBDT,
"BDT_Cat3",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status < 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kBDT,
"BDT_Cat4",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
TMVA::IMethod* Fisher_Category = factory->BookMethod( TMVA::Types::kCategory,"Fisher_Category");
TMVA::MethodCategory* mcategory_Fisher = dynamic_cast<TMVA::MethodCategory*>(Fisher_Category);
mcategory_Fisher->AddMethod("status == 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kFisher,
"Fisher_Cat1","H:!V:Fisher");
mcategory_Fisher->AddMethod("status == 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kFisher,
"Fisher_Cat2","H:!V:Fisher");
mcategory_Fisher->AddMethod("status < 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kFisher,
"Fisher_Cat3","H:!V:Fisher");
mcategory_Fisher->AddMethod("status < 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kFisher,
"Fisher_Cat4","H:!V:Fisher");
// specify the training methods
//factory->BookMethod(TMVA::Types::kFisher,"Fisher");
//factory->BookMethod(TMVA::Types::kBDT,"BDT_GRAD_2000","NTrees=2000:BoostType=Grad:Shrinkage=0.1");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outf->Close();
}
void Classification()
{
TMVA::Tools::Instance();
TMVA::PyMethodBase::PyInitialize();
TString outfileName("TMVA.root");
TFile *outputFile = TFile::Open(outfileName, "RECREATE");
TMVA::Factory *factory = new TMVA::Factory("TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
factory->AddVariable("myvar1 := var1+var2", 'F');
factory->AddVariable("myvar2 := var1-var2", "Expression 2", "", 'F');
factory->AddVariable("var3", "Variable 3", "units", 'F');
factory->AddVariable("var4", "Variable 4", "units", 'F');
factory->AddSpectator("spec1 := var1*2", "Spectator 1", "units", 'F');
factory->AddSpectator("spec2 := var1*3", "Spectator 2", "units", 'F');
TString fname = "./tmva_class_example.root";
if (gSystem->AccessPathName(fname)) // file does not exist in local directory
gSystem->Exec("curl -O http://root.cern.ch/files/tmva_class_example.root");
TFile *input = TFile::Open(fname);
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
// --- Register the training and test trees
TTree *tsignal = (TTree *)input->Get("TreeS");
TTree *tbackground = (TTree *)input->Get("TreeB");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree(tsignal, signalWeight);
factory->AddBackgroundTree(tbackground, backgroundWeight);
// Set individual event weights (the variables must exist in the original TTree)
factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree(mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=NumEvents:!V");
///////////////////
//Booking //
///////////////////
// Boosted Decision Trees
//PyMVA methods
factory->BookMethod(TMVA::Types::kPyRandomForest, "PyRandomForest",
"!V:NEstimators=150:Criterion=gini:MaxFeatures=auto:MaxDepth=3:MinSamplesLeaf=1:MinWeightFractionLeaf=0:Bootstrap=kTRUE");
factory->BookMethod(TMVA::Types::kPyAdaBoost, "PyAdaBoost",
"!V:BaseEstimator=None:NEstimators=100:LearningRate=1:Algorithm=SAMME.R:RandomState=None");
factory->BookMethod(TMVA::Types::kPyGTB, "PyGTB",
"!V:NEstimators=150:Loss=deviance:LearningRate=0.1:Subsample=1:MaxDepth=6:MaxFeatures='auto'");
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
}
std::pair<TString,TString> TMVAClassification (
TString infilename,
AnalysisType analysisType = AnalysisType::DIRECT,
TString additionalRootFileName = "")
{
TMVA::Tools::Instance();
std::string tmstr (now ());
TString tmstmp (tmstr.c_str ());
std::cout << "==> Start TMVAClassification" << std::endl;
std::cout << "-------------------- open input file ---------------- " << std::endl;
TString fname = infilename; //pathToData + infilename + TString (".root");
if (analysisType != AnalysisType::TRANSFORMED)
fname = pathToData + infilename + TString (".root");
std::cout << "open file " << std::endl << fname.Data () << std::endl;
std::cout << "-------------------- get tree ---------------- " << std::endl;
TString treeName = "data";
if (analysisType == AnalysisType::TRANSFORMED)
treeName = "transformed";
std::cout << "-------------------- create tchain with treeName ---------------- " << std::endl;
std::cout << treeName << std::endl;
TChain* tree = new TChain (treeName);
std::cout << "add file" << std::endl;
std::cout << fname << std::endl;
tree->Add (fname);
TChain* treeFriend (NULL);
if (additionalRootFileName.Length () > 0)
{
std::cout << "-------------------- add additional input file ---------------- " << std::endl;
std::cout << additionalRootFileName << std::endl;
treeFriend = new TChain (treeName);
treeFriend->Add (additionalRootFileName);
tree->AddFriend (treeFriend,"p");
}
// tree->Draw ("mass:prediction");
// return std::make_pair(TString("hallo"),TString ("nix"));
TString outfileName;
if (analysisType == AnalysisType::BACKGROUND)
{
outfileName = TString ("BACK_" + infilename) + tmstmp + TString (".root");
}
else
outfileName += TString ( "TMVA__" ) + tmstmp + TString (".root");
std::cout << "-------------------- open output file ---------------- " << std::endl;
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
std::cout << "-------------------- prepare factory ---------------- " << std::endl;
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"AnalysisType=Classification:Transformations=I:!V" );
std::cout << "-------------------- add variables ---------------- " << std::endl;
for (auto varname : variableNames)
{
factory->AddVariable (varname.c_str (), 'F');
}
for (auto varname : spectatorNames)
{
factory->AddSpectator (varname.c_str (), 'F');
}
std::cout << "-------------------- add trees ---------------- " << std::endl;
TCut signalCut ("signal==1");
TCut backgroundCut ("signal==0");
if (analysisType == AnalysisType::TRANSFORMED)
{
signalCut = "(signal_original==1 && signal_in==0)";
backgroundCut = "(signal_original==0 && signal_in==0)";
}
if (analysisType == AnalysisType::BACKGROUND)
{
signalCut = TString("(signal==0) * (prediction > 0.7)");
backgroundCut = TString("(signal==0) * (prediction < 0.4)");
}
//tree->Draw ("prediction",signalCut);
//return std::make_pair(TString("hallo"),TString ("nix"));
factory->AddTree(tree, "Signal", 1.0, baseCut + signalCut, "TrainingTesting");
factory->AddTree(tree, "Background", 1.0, baseCut + backgroundCut, "TrainingTesting");
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
/* // Set individual event weights (the variables must exist in the original TTree) */
if (analysisType == AnalysisType::BACKGROUND)
{
factory->SetSignalWeightExpression ("prediction");
factory->SetBackgroundWeightExpression ("1");
}
std::cout << "-------------------- prepare ---------------- " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
TString methodName ("");
if (analysisType == AnalysisType::BACKGROUND)
methodName = TString ("TONBKG_") + tmstmp;
if (false)
{
// gradient boosting training
methodName += TString("GBDT");
factory->BookMethod(TMVA::Types::kBDT, methodName,
"NTrees=40:BoostType=Grad:Shrinkage=0.01:MaxDepth=7:UseNvars=6:nCuts=20:MinNodeSize=10");
}
if (false)
{
methodName += TString("Likelihood");
factory->BookMethod( TMVA::Types::kLikelihood, methodName,
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
}
if (false)
{
TString layoutString ("Layout=TANH|100,LINEAR");
TString training0 ("LearningRate=1e-1,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-2,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-2,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-3,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNgauss");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (false)
{
TString layoutString ("Layout=TANH|200,TANH|70,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2;
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CROSSENTROPY");
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=N:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName = TString("NNnormalized");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (true)
{
TString layoutString ("Layout=TANH|100,TANH|50,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=100,BatchSize=20,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=30,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:!V:ErrorStrategy=CROSSENTROPY:VarTransform=P+G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNPG");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
factory->TrainAllMethods();
// return std::make_pair(TString("hallo"),TString ("nix"));
factory->TestAllMethods();
factory->EvaluateAllMethods();
//input->Close();
outputFile->Close();
// TMVA::TMVAGui (outfileName);
delete factory;
delete tree;
switch (analysisType)
{
case AnalysisType::BACKGROUND:
std::cout << "DONE BACKGROUND" << std::endl;
break;
case AnalysisType::DIRECT:
std::cout << "DONE DIRECT" << std::endl;
break;
case AnalysisType::TRANSFORMED:
std::cout << "DONE TRANSFORMED" << std::endl;
break;
};
std::cout << "classification, return : " << outfileName << " , " << methodName << std::endl;
return std::make_pair (outfileName, methodName);
}