void TMVAClassification()
{
TMVA::Tools::Instance();
std::cout << "==> Start TMVAClassification" << std::endl;
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"AnalysisType=Classification" );
factory->AddVariable("LifeTime", 'F');
factory->AddVariable("FlightDistance", 'F');
factory->AddVariable("pt", 'F');
TString fname = "../tau_data/training.root";
TFile *input = TFile::Open( fname );
TTree *tree = (TTree*)input->Get("data");
factory->AddTree(tree, "Signal", 1., "signal == 1", "Training");
factory->AddTree(tree, "Signal", 1., "signal == 1", "Test");
factory->AddTree(tree, "Background", 1., "signal == 0", "Training");
factory->AddTree(tree, "Background", 1., "signal == 0", "Test");
// gradient boosting training
factory->BookMethod(TMVA::Types::kBDT, "GBDT",
"NTrees=40:BoostType=Grad:Shrinkage=0.01:MaxDepth=7:UseNvars=6:nCuts=20:MinNodeSize=10");
factory->TrainAllMethods();
input->Close();
outputFile->Close();
delete factory;
}
void regressphi() {
TMVA::Tools::Instance();
std::cout << "==> Start TMVAClassification" << std::endl;
// 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( "mva", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
factory->AddVariable( "npv" , 'F' );
factory->AddVariable( "u" , 'F' );
factory->AddVariable( "uphi" , 'F' );
factory->AddVariable( "chsumet/sumet" , 'F' );
factory->AddVariable( "tku" , 'F' );
factory->AddVariable( "tkuphi" , 'F' );
factory->AddVariable( "nopusumet/sumet" , 'F' );
factory->AddVariable( "nopuu" , 'F' );
factory->AddVariable( "nopuuphi" , 'F' );
factory->AddVariable( "pusumet/sumet" , 'F' );
factory->AddVariable( "pumet" , 'F' );
factory->AddVariable( "pumetphi" , 'F' );
factory->AddVariable( "pucsumet/sumet" , 'F' );
factory->AddVariable( "pucu" , 'F' );
factory->AddVariable( "pucuphi" , 'F' );
factory->AddVariable( "jspt_1" , 'F' );
factory->AddVariable( "jseta_1" , 'F' );
factory->AddVariable( "jsphi_1" , 'F' );
factory->AddVariable( "jspt_2" , 'F' );
factory->AddVariable( "jseta_2" , 'F' );
factory->AddVariable( "jsphi_2" , 'F' );
factory->AddVariable( "nalljet" , 'I' );
factory->AddVariable( "njet" , 'I' );
factory->AddTarget( "rphi_z-uphi+ 2.*TMath::Pi()*(rphi_z-uphi < -TMath::Pi()) - 2.*TMath::Pi()*(rphi_z-uphi > TMath::Pi()) " );
TString lName = "../Jets/r11-dimu_nochs_v2.root"; TFile *lInput = TFile::Open(lName);
TTree *lRegress = (TTree*)lInput ->Get("Flat");
Double_t lRWeight = 1.0;
factory->AddRegressionTree( lRegress , lRWeight );
TCut lCut = "nbtag == 0"; //Cut to remove real MET
//(rpt_z < 40 || (rpt_z > 40 && rpt_z+u1 < 40)) && nbtag == 0 "; ==> stronger cut to remove Real MET
factory->PrepareTrainingAndTestTree( lCut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Block:NormMode=NumEvents:!V" );
// Boosted Decision Trees
factory->BookMethod( TMVA::Types::kBDT, "RecoilPhiRegress_data_clean2_njet",
"!H:!V:VarTransform=None:nEventsMin=200:NTrees=100:BoostType=Grad:Shrinkage=0.1:MaxDepth=100:NNodesMax=100000:UseYesNoLeaf=F:nCuts=2000");//MaxDepth=100
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 REG::Loop() {
if (fChain == 0) return;
Long64_t nentries = fChain->GetEntriesFast();
Long64_t nbytes = 0, nb = 0;
TMVA::Tools::Instance();
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
TString outfileName( "TMVAReg.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
factory->AddVariable( "l1Pt", "Variable 1", "units", 'F' );
factory->AddVariable( "l1Eta", "Variable 2", "units", 'F' );
factory->AddVariable( "l1Phi", "Variable 1", "units", 'F' );
// factory->AddVariable( "RhoL1", "Variable 2", "units", 'F' );
factory->AddTarget( "ratio" );
factory->AddRegressionTree(fChain, 1.0 );
TCut mycut = "";
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=10000:nTest_Regression=0:SplitMode=Block:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=100:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
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;
}
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");
}
////////////////////////////////////////////////////////////////////////////////
/// Main ///
////////////////////////////////////////////////////////////////////////////////
void TrainRegressionFJ(TString myMethodList="")
{
gROOT->SetBatch(1);
gROOT->LoadMacro("HelperFunctions.h" ); // make functions visible to TTreeFormula
if (!TString(gROOT->GetVersion()).Contains("5.34")) {
std::cout << "INCORRECT ROOT VERSION! Please use 5.34:" << std::endl;
std::cout << "source /uscmst1/prod/sw/cms/slc5_amd64_gcc462/lcg/root/5.34.02-cms/bin/thisroot.csh" << std::endl;
std::cout << "Return without doing anything." << std::endl;
return;
}
//TString curDynamicPath( gSystem->GetDynamicPath() );
//gSystem->SetDynamicPath( "../lib:" + curDynamicPath );
//TString curIncludePath(gSystem->GetIncludePath());
//gSystem->SetIncludePath( " -I../include " + curIncludePath );
// Load 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"] = 1;
Use["BDT1"] = 0;
Use["BDTG"] = 0;
Use["BDTG1"] = 0;
//--------------------------------------------------------------------------
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 = 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 ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVARegFJ.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 weights/
//
// 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( "TMVARegressionFJ", outputFile,
"!V:!Silent:!Color:!DrawProgressBar:Transformations=I:AnalysisType=Regression" );
// 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";
const std::vector<std::string> & inputExpressions = GetInputExpressionsFJReg();
const std::vector<std::string> & inputExpressionLabels = GetInputExpressionLabelsFJReg();
assert(inputExpressions.size() == inputExpressionLabels.size());
// 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' );
for (UInt_t iexpr=0; iexpr!=inputExpressions.size(); iexpr++){
Label label = MakeLabel(inputExpressionLabels.at(iexpr));
TString expr = inputExpressions.at(iexpr);
factory->AddVariable(expr, label.xlabel, label.unit, label.type);
}
// 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" );
factory->AddTarget( "fathFilterJets_genPt" );
// 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
TFile *input(0);
TString dirname = "skim_ZnnH_regression_fj/";
TString prefix = "skim_";
TString suffix = ".root";
TTree *regTrainTree(0), *regTestTree(0);
std::vector<std::string> processes;
processes.push_back("ZnnH110");
processes.push_back("ZnnH115");
processes.push_back("ZnnH120");
processes.push_back("ZnnH125");
processes.push_back("ZnnH130");
processes.push_back("ZnnH135");
processes.push_back("ZnnH140");
processes.push_back("ZnnH145");
processes.push_back("ZnnH150");
#ifdef USE_WH
processes.push_back("WlnH110");
processes.push_back("WlnH115");
processes.push_back("WlnH120");
processes.push_back("WlnH125");
processes.push_back("WlnH130");
processes.push_back("WlnH135");
processes.push_back("WlnH140");
processes.push_back("WlnH145");
processes.push_back("WlnH150");
#endif
std::vector<TFile *> files;
for (UInt_t i=0; i<processes.size(); i++){
std::string process = processes.at(i);
input = (TFile*) TFile::Open(dirname + prefix + process + suffix, "READ");
if (!input) {
std::cout << "ERROR: Could not open input file." << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
files.push_back(input);
// --- Register the regression tree
regTrainTree = (TTree*) input->Get("tree_train");
regTestTree = (TTree*) input->Get("tree_test");
// 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(regTrainTree, regWeight, TMVA::Types::kTraining);
factory->AddRegressionTree(regTestTree , regWeight, TMVA::Types::kTesting );
}
// Set individual event weights (the variables must exist in the original TTree)
//factory->SetWeightExpression( "var1", "Regression" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = "fathFilterJets_genPt>10 && fathFilterJets_pt>15 && abs(fathFilterJets_eta)<2.5"; // this is to avoid 3rd filter jet without gen match
//TCut mycut = "hJet_genPt[0] > 0. && hJet_genPt[1] > 0. && hJet_csv[0] > 0. && hJet_csv[1] > 0. && hJet_pt[0] > 20. && hJet_pt[1] > 20. && abs(hJet_eta[0])<2.5 && abs(hJet_eta[1])<2.5";
// Tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut, "V:nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents" );
// 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/MethodCuts.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:nEventsMin=30:NodePurityLimit=0.5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
//"!H:V:NTrees=60:nEventsMin=20:NodePurityLimit=0.5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30:DoBoostMonitor" );
if (Use["BDT1"])
factory->BookMethod( TMVA::Types::kBDT, "BDT1",
"!H:V:NTrees=100:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
if (Use["BDTG"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:V:NTrees=2000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.7:nCuts=200:MaxDepth=3:NNodesMax=15" );
if (Use["BDTG1"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG1",
"!H:V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:MaxDepth=3:NNodesMax=15" );
//--------------------------------------------------------------------------
// 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;
for (UInt_t i=0; i<files.size(); i++)
files.at(i)->Close();
delete outputFile;
delete factory;
// Launch the GUI for the root macros
//gROOT->SetMacroPath( "$ROOTSYS/tmva/macros/" );
//gROOT->Macro( "$ROOTSYS/tmva/macros/TMVAlogon.C" );
//gROOT->LoadMacro( "$ROOTSYS/tmva/macros/TMVAGui.C" );
//if (!gROOT->IsBatch()) TMVARegGui( 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"] = 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"] = 0;
// ---
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["MLPBNN"] = 0; // recommended ANN with BFGS training method and bayesian regulator
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] = 0;
}
}
// 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: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( "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
factory->AddVariable("CScostheta",'F');
factory->AddVariable("ZRapidity",'F');
factory->AddVariable("REDmet",'F');
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
TString fname = "./tmva_class_example.root";
TString fname_Data7TeV_DoubleElectron2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_0.root";
TString fname_Data7TeV_MuEG2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_0.root";
TString fname_ZH125 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH125.root";
TString fname_SingleT_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_tW.root";
TString fname_SingleT_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_s.root";
TString fname_Data7TeV_DoubleMu2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_0.root";
TString fname_Data7TeV_DoubleElectron2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_0.root";
TString fname_ZH135 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH135.root";
TString fname_DYJetsToLL = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//DYJetsToLL.root";
TString fname_ZH115 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH115.root";
TString fname_SingleTbar_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_t.root";
TString fname_Data7TeV_DoubleElectron2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_1.root";
TString fname_Data7TeV_DoubleMu2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_1.root";
TString fname_Data7TeV_MuEG2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_1.root";
TString fname_TTJets = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//TTJets.root";
TString fname_SingleTbar_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_s.root";
TString fname_WJetsToLNu = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WJetsToLNu.root";
TString fname_Data7TeV_DoubleElectron2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_1.root";
TString fname_ZZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZZ.root";
TString fname_ZH150 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH150.root";
TString fname_Data7TeV_MuEG2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_1.root";
TString fname_WW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WW.root";
TString fname_ZH105 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH105.root";
TString fname_Data7TeV_DoubleMu2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_0.root";
TString fname_SingleTbar_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_tW.root";
TString fname_WZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WZ.root";
TString fname_Data7TeV_MuEG2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_0.root";
TString fname_Data7TeV_DoubleMu2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_1.root";
TString fname_ZH145 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH145.root";
TString fname_SingleT_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_t.root";
if (gSystem->AccessPathName( fname )) // file does not exist in local directory
gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *input_Data7TeV_DoubleElectron2011B_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_0 );
TFile *input_Data7TeV_MuEG2011B_0 = TFile::Open( fname_Data7TeV_MuEG2011B_0 );
TFile *input_ZH125 = TFile::Open( fname_ZH125 );
TFile *input_SingleT_tW = TFile::Open( fname_SingleT_tW );
TFile *input_SingleT_s = TFile::Open( fname_SingleT_s );
TFile *input_Data7TeV_DoubleMu2011B_0 = TFile::Open( fname_Data7TeV_DoubleMu2011B_0 );
TFile *input_Data7TeV_DoubleElectron2011A_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_0 );
TFile *input_ZH135 = TFile::Open( fname_ZH135 );
TFile *input_DYJetsToLL = TFile::Open( fname_DYJetsToLL );
TFile *input_ZH115 = TFile::Open( fname_ZH115 );
TFile *input_SingleTbar_t = TFile::Open( fname_SingleTbar_t );
TFile *input_Data7TeV_DoubleElectron2011B_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_1 );
TFile *input_Data7TeV_DoubleMu2011A_1 = TFile::Open( fname_Data7TeV_DoubleMu2011A_1 );
TFile *input_Data7TeV_MuEG2011A_1 = TFile::Open( fname_Data7TeV_MuEG2011A_1 );
TFile *input_TTJets = TFile::Open( fname_TTJets );
TFile *input_SingleTbar_s = TFile::Open( fname_SingleTbar_s );
TFile *input_WJetsToLNu = TFile::Open( fname_WJetsToLNu );
TFile *input_Data7TeV_DoubleElectron2011A_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_1 );
TFile *input_ZZ = TFile::Open( fname_ZZ );
TFile *input_ZH150 = TFile::Open( fname_ZH150 );
TFile *input_Data7TeV_MuEG2011B_1 = TFile::Open( fname_Data7TeV_MuEG2011B_1 );
TFile *input_WW = TFile::Open( fname_WW );
TFile *input_ZH105 = TFile::Open( fname_ZH105 );
TFile *input_Data7TeV_DoubleMu2011A_0 = TFile::Open( fname_Data7TeV_DoubleMu2011A_0 );
TFile *input_SingleTbar_tW = TFile::Open( fname_SingleTbar_tW );
TFile *input_WZ = TFile::Open( fname_WZ );
TFile *input_Data7TeV_MuEG2011A_0 = TFile::Open( fname_Data7TeV_MuEG2011A_0 );
TFile *input_Data7TeV_DoubleMu2011B_1 = TFile::Open( fname_Data7TeV_DoubleMu2011B_1 );
TFile *input_ZH145 = TFile::Open( fname_ZH145 );
TFile *input_SingleT_t = TFile::Open( fname_SingleT_t );
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_0 file: " << input_Data7TeV_DoubleElectron2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_0 file: " << input_Data7TeV_MuEG2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH125 file: " << input_ZH125->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_tW file: " << input_SingleT_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_s file: " << input_SingleT_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_0 file: " << input_Data7TeV_DoubleMu2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_0 file: " << input_Data7TeV_DoubleElectron2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH135 file: " << input_ZH135->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_DYJetsToLL file: " << input_DYJetsToLL->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH115 file: " << input_ZH115->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_t file: " << input_SingleTbar_t->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_1 file: " << input_Data7TeV_DoubleElectron2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_1 file: " << input_Data7TeV_DoubleMu2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_1 file: " << input_Data7TeV_MuEG2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_TTJets file: " << input_TTJets->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_s file: " << input_SingleTbar_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WJetsToLNu file: " << input_WJetsToLNu->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_1 file: " << input_Data7TeV_DoubleElectron2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZZ file: " << input_ZZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH150 file: " << input_ZH150->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_1 file: " << input_Data7TeV_MuEG2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WW file: " << input_WW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH105 file: " << input_ZH105->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_0 file: " << input_Data7TeV_DoubleMu2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_tW file: " << input_SingleTbar_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WZ file: " << input_WZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_0 file: " << input_Data7TeV_MuEG2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_1 file: " << input_Data7TeV_DoubleMu2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH145 file: " << input_ZH145->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_t file: " << input_SingleT_t->GetName() << std::endl;
TTree *signal_ZH145 = (TTree*)input_ZH145->Get("tmvatree");
TTree *background_ZZ = (TTree*)input_ZZ->Get("tmvatree");
// 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_ZH145, 1.0 );
factory->AddBackgroundTree( background_ZZ, 1.0 );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signal_ZH145TrainingTree, signal_ZH145TrainWeight, "Training" );
// factory->AddSignalTree( signal_ZH145TestTree, signal_ZH145TestWeight, "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("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
factory->SetSignalWeightExpression("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "(CUT>2)";
TCut mycutb = "(CUT>2)";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, "SplitMode=random:!V" );
// "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:Seed=0:EffSel:Steps=50:Cycles=3:PopSize=1000: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: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:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2: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:!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=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=1000:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6: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=1000: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
gROOT->ProcessLine(".q;");
}
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;
}
void mytmvaClass( 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\(\"P_myMethod\"\)
//--------------------------------
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
//
// --- 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 (Not of much 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)"
//Syntax --> "factory->AddVariable( "VarName", "UserDefinedLabel", "units", 'VarType' );" //Where VarType refers to float, int etc.
Float_t nhiggsJetSubjets;
Float_t njets;
Float_t deltaPhiWH;
Float_t jetPt[11];
Float_t jetEta[11];
Float_t jetPhi[11];
Float_t jetE[11];
Float_t higgsJetSubjetEta[3];
Float_t higgsJetSubjetPhi[3];
Float_t higgsJetSubjetPt[3];
Float_t higgsJetSubjetE[3];
Float_t Wphi;
Float_t fatjetPt[15];
Float_t fatjetEta[15];
Float_t fatjetPhi[15];
Float_t fatjetE[15];
Float_t DeltaPhiWH;
TLorentzVector fatjet(0,0,0,0);
TLorentzVector subjet1(0,0,0,0);
TLorentzVector subjet2(0,0,0,0);
TLorentzVector subjet3(0,0,0,0);
TLorentzVector akt[15];
fatjet.SetPtEtaPhiE(fatjetPt[0],fatjetEta[0],fatjetPhi[0], fatjetE[0]);
// deltaPhiWH = std::fabs(Wphi-fatjetPhi[0]);
// if(deltaPhiWH>TMath::Pi()){ std::fabs(deltaPhiWH = 2*TMath::Pi()-deltaPhiWH);}
factory->AddVariable( "deltaPhiWH", "deltaPhiWH", "", 'F' );
factory->AddVariable( "jetPt.array[0]", "jetPt.array[0]", "", 'F' );
factory->AddVariable( "fatjetPt[0].array[0]", "fatjetPt.array[0]", "", 'F' );
//factory->AddVariable( "DeltaR[3][13]", "DeltaR[3][13]", "", 'F' );
// factory->AddSpectator( "nhiggsJetSubjets", "nhiggsJetSubjets", "", 'F');
// factory->AddSpectator( "njets", "", "njets", 'I');
// factory->AddSpectator( "jetPt[0]", "jetPt[0]", "", 'F');
// factory->AddSpectator( "jetPt[1]", "jetPt[1]", "", 'F');
// factory->AddSpectator( "jetPt[2]", "jetPt[2]", "", 'F');
// factory->AddSpectator( "jetPt[3]", "jetPt[3]", "", 'F');
// factory->AddSpectator( "jetPt[4]", "jetPt[4]", "", 'F');
// factory->AddSpectator( "jetPt[5]", "jetPt[5]", "", 'F');
// factory->AddSpectator( "jetPt[6]", "jetPt[6]", "", 'F');
// factory->AddSpectator( "jetPt[7]", "jetPt[7]", "", 'F');
// factory->AddSpectator( "jetPt[8]", "jetPt[8]", "", 'F');
// factory->AddSpectator( "jetPt[9]", "jetPt[9]", "", 'F');
// factory->AddSpectator( "jetPt[10]", "jetPt[10]", "", 'F');
// factory->AddSpectator( "jetEta[0]", "jetEta[0]", "", 'F');
// factory->AddSpectator( "jetEta[1]", "jetEta[1]", "", 'F');
// factory->AddSpectator( "jetEta[2]", "jetEta[2]", "", 'F');
// factory->AddSpectator( "jetEta[3]", "jetEta[3]", "", 'F');
// factory->AddSpectator( "jetEta[4]", "jetEta[4]", "", 'F');
// factory->AddSpectator( "jetEta[5]", "jetEta[5]", "", 'F');
// factory->AddSpectator( "jetEta[6]", "jetEta[6]", "", 'F');
// factory->AddSpectator( "jetEta[7]", "jetEta[7]", "", 'F');
// factory->AddSpectator( "jetEta[8]", "jetEta[8]", "", 'F');
// factory->AddSpectator( "jetEta[9]", "jetEta[9]", "", 'F');
// factory->AddSpectator( "jetEta[10]", "jetEta[10]", "", 'F');
// factory->AddSpectator( "jetPhi[0]", "jetPhi[0]", "", 'F');
// factory->AddSpectator( "jetPhi[1]", "jetPhi[1]", "", 'F');
// factory->AddSpectator( "jetPhi[2]", "jetPhi[2]", "", 'F');
// factory->AddSpectator( "jetPhi[3]", "jetPhi[3]", "", 'F');
// factory->AddSpectator( "jetPhi[4]", "jetPhi[4]", "", 'F');
// factory->AddSpectator( "jetPhi[5]", "jetPhi[5]", "", 'F');
// factory->AddSpectator( "jetPhi[6]", "jetPhi[6]", "", 'F');
// factory->AddSpectator( "jetPhi[7]", "jetPhi[7]", "", 'F');
// factory->AddSpectator( "jetPhi[8]", "jetPhi[8]", "", 'F');
// factory->AddSpectator( "jetPhi[9]", "jetPhi[9]", "", 'F');
// factory->AddSpectator( "jetPhi[10]", "jetPhi[10]", "", 'F');
// factory->AddSpectator("jetE[0]", "jetE[0]", "", 'F');
// factory->AddSpectator("jetE[1]", "jetE[1]", "", 'F');
// factory->AddSpectator("jetE[2]", "jetE[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[0]","higgsJetSubjetEta[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[1]","higgsJetSubjetEta[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[2]","higgsJetSubjetEta[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[0]","higgsJetSubjetPhi[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[1]","higgsJetSubjetPhi[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[2]","higgsJetSubjetPhi[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[0]","higgsJetSubjetPt[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[1]","higgsJetSubjetPt[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[2]","higgsJetSubjetPt[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[0]","higgsJetSubjetE[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[1]","higgsJetSubjetE[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[2]","higgsJetSubjetE[2]", "", 'F');
// factory->AddSpectator("Wphi", "Wphi", "" , 'F');
// factory->AddVariable("fatjetPt[0]", "fatjetPt[0]", "", 'F');
// factory->AddSpectator("fatjetPhi[0]", "fatjetPhi[0]", "", 'F');
// factory->AddSpectator("fatjetEta[0]", "fatjetEta[0]", "", 'F');
// factory->AddSpectator("fatjetE[0]", "fatjetE[0]", "", 'F');
// //if(std::fabs(Wphi-fatjetPhi[0])<TMath::Pi()){
// factory->AddVariable("abs(Wphi-fatjetPhi[0])", "DeltaPhiWH", "", 'F');
// //}
// if ((abs(Wphi-fatjetPhi[0])>TMath::Pi())){
// factory->AddVariable("(abs(DeltaPhiWH = 2*(TMath::Pi())-DeltaPhiWH))", "DeltaPhiWH", "", 'F');
// }
// Here, we add the lepton flag as a spectator so we can cut (further down) on lep == 0 for muons only or lep == 1 for electrons only.
//factory->AddSpectator( "lepType[0]", "lepType[0]", "units", '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( "spec1 := var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// --- Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fsig_name_WH = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/mc11_7TeV.128034.HerwigppPowHeg_Boosted_WH125lnubb.merge.NTUP_HSG5WH.Output_PreCuts-Original.root";
TString fback_name_TT = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/TT_NewBranch2.output_MERGE_PreCuts-Original.root";
TString fback_name_Wbb = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/mc11_7TeV.128861.SherpaWbb2J_lnu_Wpt100GeV_PreCuts-Original.root";
TFile *sig_input_WH = TFile::Open( fsig_name_WH );
TFile *back_input_TT = TFile::Open( fback_name_TT );
TFile *back_input_Wbb = TFile::Open( fback_name_Wbb);
// --- Register the training and test trees
TTree *signal_WH = (TTree*)sig_input_WH->Get("OutputTree");
TTree *background_TT = (TTree*)back_input_TT->Get("OutputTree");
TTree * background_Wbb = (TTree*)back_input_Wbb->Get("OutputTree");
// --- global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight_WH = 1;
Double_t backgroundWeight_TT = 1;
Double_t backgroundWeight_Wbb= 1;
// --- Here can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal_WH, signalWeight_WH );
factory->AddBackgroundTree( background_TT, backgroundWeight_TT );
factory->AddBackgroundTree( background_Wbb, backgroundWeight_Wbb);
Float_t nhiggsJetSubjets;
Float_t njets;
Float_t deltaPhiWH;
Float_t jetPt[11];
Float_t jetEta[11];
Float_t jetPhi[11];
Float_t jetE[11];
Float_t higgsJetSubjetEta[3];
Float_t higgsJetSubjetPhi[3];
Float_t higgsJetSubjetPt[3];
Float_t higgsJetSubjetE[3];
Float_t Wphi;
Float_t fatjetPt[15];
Float_t fatjetEta[15];
Float_t fatjetPhi[15];
Float_t fatjetE[15];
TLorentzVector fatjet(0,0,0,0);
TLorentzVector subjet1(0,0,0,0);
TLorentzVector subjet2(0,0,0,0);
TLorentzVector subjet3(0,0,0,0);
TLorentzVector akt[15];
fatjet.SetPtEtaPhiE(fatjetPt[0],fatjetEta[0],fatjetPhi[0], fatjetE[0]);
deltaPhiWH = std::fabs(Wphi-fatjetPhi[0]);
if(deltaPhiWH>TMath::Pi()){ std::fabs(deltaPhiWH = 2*TMath::Pi()-deltaPhiWH);}
float deltaEta[3][11];
float deltaPhi[3][11];
float DeltaR[3][13];
for(int j = 0; j<nhiggsJetSubjets; j++){
for(int i = 0; i<njets; i++){
deltaEta[j][i] = std::fabs(higgsJetSubjetEta[j]-jetEta[i]);
deltaPhi[j][i] = std::fabs(higgsJetSubjetPhi[j]-jetPhi[i]);
DeltaR[j][i] = std::sqrt(deltaEta[j][i]*deltaEta[j][i]+deltaPhi[j][i]*deltaPhi[j][i]);
}
}
for (int i=0; i < njets; i++) {
akt[i].SetPtEtaPhiE(jetPt[i],jetEta[i],jetPhi[i], jetE[i]);
}
subjet1.SetPtEtaPhiE(higgsJetSubjetPt[0],higgsJetSubjetEta[0],higgsJetSubjetPhi[0], higgsJetSubjetE[0]);
subjet2.SetPtEtaPhiE(higgsJetSubjetPt[1],higgsJetSubjetEta[1],higgsJetSubjetPhi[1], higgsJetSubjetE[1]);
FatHiggs = subjet1 + subjet2;
if (nhiggsJetSubjets>2){
subjet3.SetPtEtaPhiE(higgsJetSubjetPt[2],higgsJetSubjetEta[2],higgsJetSubjetPhi[2], higgsJetSubjetE[2]);
}
// To give different trees for training and testing, do:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("wei
// --- Apply additional cuts on the signal and background samples (can be different)
// PLEASE NOTE: If no cuts are required, do NOT leave any spaces between quotation marks, otherwise an error will occur.
TCut mycuts = "deltaPhiWH>-800"; //Signal Tree Cuts
TCut mycutb = "deltaPhiWH>-800"; //Background Tree Cuts
//cout << "DeltaPhiWH: " << deltaPhiWH << endl;
// 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:!V:NormMode=NumEvents");
// ---- 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[1]=0:CutRangeMax[1]=450:VarProp[1]=FMax:EffSel:Steps=60:Cycles=3:PopSize=2000: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=0.0333: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" );
// 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: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" );
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=350:nEventsMin=100:MaxDepth=3:BoostType=Grad:Shrinkage=0.05:UseBaggedGrad:GradBaggingFraction=0.51:nCuts=65:PruneStrength=2:PruneMethod=ExpectedError:NNodesMax=7" );
//"!H:!V:NTrees=350:nEventsMin=100:MaxDepth=3:BoostType=Grad:Shrinkage=0.05:UseBaggedGrad:GradBaggingFraction=0.55:nCuts=50:PruneStrength=2:PruneMethod=ExpectedError:NNodesMax=10" ); //nCuts=20 && no pruning originally
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"NTrees=550:nEventsMin=110:MaxDepth=5.5:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=10:PruneStrength=6:PruneMethod=ExpectedError");
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=950:nEventsMin=20:MaxDepth=10:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=300:nEventsMin=20:MaxDepth=10:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=10:PruneStrength=6:PruneMethod=ExpectedError: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" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("SigEffAt001","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 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 );
}
//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 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 classifyBDT(TString inputVariables = "trainingVars.txt",
TString signalName = "/mnt/hscratch/dabercro/skims2/BDT_Signal.root",
TString backName = "/mnt/hscratch/dabercro/skims2/BDT_Background.root") {
TMVA::Tools::Instance();
std::cout << "==> Start TMVAClassification" << std::endl;
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA/TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;N" );
// A very simple MVA (feel free to uncomment and comment what you like) => as a rule of thumb 10-20 variables is where people start to get worried about total number
ifstream configFile;
configFile.open(inputVariables.Data());
TString tempFormula;
configFile >> tempFormula; // Is the name of the BDT
while(!configFile.eof()){
configFile >> tempFormula;
if(tempFormula != ""){
factory->AddVariable(tempFormula,'F');
}
}
TString lVars;
// TCut lCut = "jet1qg2<2.&&jet1pt>250.&&jet1pullAngle>-5.";// < 10 && jet1mass_m2 > 60 && jet1mass_m2 < 120";
// TCut lCut = "passZ > 3 && fjet1pt > 250 && fjet1MassPruned < 120 && fatjetid < 2";
TCut lCut = "abs(fjet1PartonId)!=24&&abs(fjet1PartonId)!=23";
// std::string lEventCut = "event % 2 == 1";
// lCut += lEventCut.c_str();
// TCut lSCut = "passT > 0 && fjet1pt > 250 && fjet1MassPruned < 120 && abs(fjet1PartonId) == 24&& fatjetid < 2";
TCut lSCut = "abs(fjet1PartonId)==24||abs(fjet1PartonId)==23";
// lSCut += lEventCut.c_str();
TCut cleanCut = "fjet1QGtagSub2 > -10 && fjet1PullAngle > -4 && abs(fjet1pt/fjet1MassTrimmed)<200 && abs(fjet1pt/fjet1MassPruned)<200";
TFile *lSAInput = TFile::Open(signalName);
TTree *lSASignal = (TTree*)lSAInput ->Get("DMSTree");
TFile *lSBInput = TFile::Open(backName);
TTree *lSBSignal = (TTree*)lSBInput ->Get("DMSTree");
Double_t lSWeight = 1.0;
Double_t lBWeight = 1.0;
gROOT->cd( outfileName+TString(":/") );
factory->AddSignalTree ( lSASignal, lSWeight );
gROOT->cd( outfileName+TString(":/") );
factory->AddBackgroundTree( lSBSignal, lBWeight );
factory->SetWeightExpression("weight");
std::stringstream pSignal,pBackground;
pSignal << "nTrain_Signal="<< lSASignal->GetEntries() << ":nTrain_Background=" << lSBSignal->GetEntries();
// factory->PrepareTrainingAndTestTree( lSCut, lCut,(pSignal.str()+":SplitMode=Block:NormMode=NumEvents:!V").c_str() );
factory->PrepareTrainingAndTestTree(lSCut&&cleanCut,lCut&&cleanCut,"nTrain_Signal=0:nTrain_Background=0:SplitMode=Alternate:NormMode=NumEvents:!V");
std::string lName = "alpha_VBF";
TString lBDTDef = "!H:!V:NTrees=400:BoostType=Grad:Shrinkage=0.1:UseBaggedGrad=F:nCuts=2000:NNodesMax=10000:MaxDepth=5:UseYesNoLeaf=F:nEventsMin=200";
// TString lBDTDef = "!H:!V:NTrees=400:BoostType=Grad:Shrinkage=0.1:UseBaggedGrad=F:nCuts=2000:MaxDepth=5:UseYesNoLeaf=F:MinNodeSize=0.086:NegWeightTreatment=IgnoreNegWeightsInTraining";
factory->BookMethod(TMVA::Types::kBDT,"BDT_simple_alpha",lBDTDef);
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 );
//TString lBDTDef = "!H:!V:NTrees=100:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad=F:nCuts=2000:NNodesMax=10000:MaxDepth=3:SeparationType=GiniIndex";
}
/**********************************************************************************
* Project : TMVA - a ROOT-integrated toolkit for multivariate data analysis *
* Package : TMVA *
* Root Macro: TMVAClassification *
* *
* This macro provides examples for the training and testing of the *
* TMVA classifiers. *
* *
* As input data is used a toy-MC sample consisting of four Gaussian-distributed *
* and linearly correlated input variables. *
* *
* The methods to be used can be switched on and off by means of booleans, or *
* via the prompt command, for example: *
* *
* root -l ./TMVAClassification.C\(\"Fisher,Likelihood\"\) *
* *
* (note that the backslashes are mandatory) *
* If no method given, a default set of classifiers is used. *
* *
* The output file "TMVA.root" can be analysed with the use of dedicated *
* macros (simply say: root -l <macro.C>), which can be conveniently *
* invoked through a GUI that will appear at the end of the run of this macro. *
* Launch the GUI via the command: *
* *
* root -l ./TMVAGui.C *
* *
**********************************************************************************/
void TMVAClassification( TString myMethodList = "")
{
TTree *signal = (TTree *)gDirectory->Get("VertexG");
if (! signal) { std::cout << "No signal TTree" << std::endl; return;}
TTree *background = (TTree *)gDirectory->Get("VertexB");
if (! background) { std::cout << "No background TTree" << std::endl; return;}
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// 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
Use["myBDTD"] = 1; // mine
//
// --- 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 (size_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";
// load the signal and background event samples from ROOT trees
std::cout << " starts ... " << std::endl;
// global event weights per tree (see below for setting event-wise weights)
// Float_t w;
double signalWeight = 1.0;
double backgroundWeight = 1.0;
std::cout << " signalWeight = " << signalWeight << " backWeight = " << backgroundWeight << std::endl;
factory->AddSignalTree( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
TString separator(":");
TString Vnames(vnames);
TObjArray *array = Vnames.Tokenize(separator);
std::vector<std::string> inputVars;
TIter next(array);
TObjString *objs;
while ((objs = (TObjString *) next())) {
// std::cout << objs->GetString() << std::endl;
TString name(objs->GetString());
if (name == "BEMC") continue;
if (name == "noBEMC") continue;
factory->AddVariable(name, 'F');
}
// 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");
// commented JB : 04/26 ??
//factory->dSetBackgroundWeightExpression("weight");
// 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( mycuts,mycutb,"NSigTrain=9000:NBkgTrain=50000:NSigTest=9000:NBkgTest=50000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb, "nTrain_Signal=4900:nTrain_Background=49000:nTest_Signal=4900:nTest_Background=49000:SplitMode=Random:!V"); // for KFVertex
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,"nTrain_Signal=20000:nTrain_Background=40000:nTest_Signal=20000:nTest_Background=40000:SplitMode=Random:!V"); // for PPV
// ---- 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: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=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["myBDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTDTEST",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6: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
// TMVA::IMethod* category = factory->BookMethod( TMVA::Types::kCategory,"Category","" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
#if 0
factory->OptimizeAllMethods("SigEffAt001", "Scan");
factory->OptimizeAllMethods("ROCIntegral", "GA");
#endif
// --------------------------------------------------------------------------------------------------
// ---- 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;
}
void test2(){
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
TString outfileName( "trainingBDT_tZq.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "BDT_trainning_tzq", outputFile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
TFile *input_sig = TFile::Open( "../TreeReader/outputroot/histofile_tZq.root" );
TFile *input_wz = TFile::Open( "../TreeReader/outputroot/histofile_WZ.root" );
TTree *signal = (TTree*)input_sig->Get("Ttree_tZq");
TTree *background = (TTree*)input_wz->Get("Ttree_WZ");
factory->AddSignalTree ( signal, 1.);
factory->AddBackgroundTree( background, 1.);
std::vector<TString > varList;
varList.push_back("tree_cosThetaStar");;
varList.push_back("tree_topMass");
varList.push_back("tree_totMass");
varList.push_back("tree_deltaPhilb");
varList.push_back("tree_deltaRlb");
varList.push_back("tree_deltaRTopZ");
varList.push_back("tree_asym");
varList.push_back("tree_Zpt");
varList.push_back("tree_ZEta");
varList.push_back("tree_topPt");
varList.push_back("tree_topEta");
varList.push_back("tree_NJets");
varList.push_back("tree_NBJets");
varList.push_back("tree_deltaRZl");
varList.push_back("tree_deltaPhiZmet");
varList.push_back("tree_btagDiscri");
varList.push_back("tree_totPt");
varList.push_back("tree_totEta");
varList.push_back("tree_leptWPt");
varList.push_back("tree_leptWEta");
varList.push_back("tree_leadJetPt");
varList.push_back("tree_leadJetEta");
varList.push_back("tree_deltaRZleptW");
varList.push_back("tree_deltaPhiZleptW");
varList.push_back("tree_met" );
varList.push_back("tree_mTW" );
for(unsigned int i=0; i< varList.size() ; i++) factory->AddVariable( varList[i].Data(), 'F');
factory->SetSignalWeightExpression ("tree_EvtWeight");
factory->SetBackgroundWeightExpression("tree_EvtWeight");
// 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";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
//factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// 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( std::string selectionName, std::string charge, 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"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
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;
// ---
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"] = 0;
// ---
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"] = 0;
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" );
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( "MET" , "ME_{T}", "GeV", 'F');
//factory->AddVariable( "TMath::Max(pT1,pT2)" , "Lead Lepton p_{T}", "GeV", 'F');
factory->AddVariable( "HT" , "H_{T}", "GeV", 'F');
//factory->AddVariable( "M3" , "M_{3}", "GeV", 'F');
factory->AddVariable( "TMath::Min(pT1,pT2)" , "Sublead Lepton p_{T}", "GeV", 'F');
//factory->AddVariable( "NbJ" , "N B Jets", "", 'I');
//factory->AddVariable( "NbJmed" , "N B Jets (medium)", "", 'I');
//factory->AddVariable( "NJ" , "N Jets", "", '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( "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";
//TString fname = "opt_ttW_Apr10_Iso005_NoZVeto_jet20.root";
TString fname = "opt_ttW_Nov20_muDetIso0p05_elDetIso0p05_jet20_withZveto_optimization.root";
//TString fname = "opt_ttW_" + selectionName + ".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* opt_tree = (TTree*)input->Get("tree_opt");
TFile* signalFile = TFile::Open("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/TTbarW_Yields.root");
TTree *signal = (TTree*)signalFile->Get("SigEvents");
TChain* background = new TChain("SigEvents");
background->Add("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/TTJets_Yields.root");
background->Add("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/WZTo3LNu_Yields.root");
//TTree *background = (TTree*)opt_tree->CopyTree("SName==\"TTJets\" || SName==\"DYJets\" || SName==\"WZTo3LNu\"");
//TTree *background = (TTree*)opt_tree->CopyTree("SName==\"DYJets\"");
// 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->SetSignalWeightExpression("eventWeight");
factory->SetBackgroundWeightExpression("1./SLumi");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts;
TCut mycutb;
if( charge == "plus" ) {
mycuts = "Charge==1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = "Charge==1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else if( charge == "minus" ) {
mycuts = "Charge==-1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = "Charge==-1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else if( charge == "all" ) {
mycuts = " SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = " SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else {
std::cout << "only 'plus' and 'minus' and 'all' are allowed for charge." <<std::endl;
return;
}
//if( btagMed_presel_ ) {
// mycuts += "NbJmed>0"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
// mycutb += "NbJmed>0"; // 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"]) {
std::string bookConditions;
bookConditions = "H:!V:FitMethod=MC";
bookConditions += ":VarProp[0]=FMax"; //HT
bookConditions += ":VarProp[1]=FMax"; //pt2
bookConditions += ":EffSel:SampleSize=500000000";
//bookConditions += ":EffSel:SampleSize=50000";
factory->BookMethod( TMVA::Types::kCuts, "Cuts", bookConditions.c_str() );
//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();
if (Use["Cuts"]) {
for( unsigned iEff=1; iEff<11; ++iEff ) {
TMVA::IMethod* method = (TMVA::IMethod*)factory->GetMethod("Cuts");
TMVA::MethodCuts* cuts = dynamic_cast<TMVA::MethodCuts*>(method);
std::string optcutsdir = "optcuts_" + selectionName + "_" + charge;
std::string mkdir_command = "mkdir -p " + optcutsdir;
system(mkdir_command.c_str());
char cutsFileName[500];
sprintf( cutsFileName, "%s/cuts_Seff%d.txt", optcutsdir.c_str(), 10*iEff );
ofstream ofs(cutsFileName);
std::vector<Double_t> cutsMin, cutsMax;
cuts->GetCuts((float)iEff*0.10, cutsMin, cutsMax);
bool found_pT1 = false;
bool found_pT2 = false;
bool found_NJ = false;
bool found_NbJ = false;
bool found_NbJmed = false;
for( unsigned iCut=0; iCut<cutsMin.size(); ++iCut) {
TString varName = factory->DefaultDataSetInfo().GetVariableInfo(iCut).GetInternalName();
if( varName=="TMath_Min_pT1,pT2_") {
ofs << "pT1 " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
ofs << "pT2 " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
found_pT1 = true;
found_pT2 = true;
} else {
ofs << varName << " " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
}
if( varName=="pT1" ) found_pT1 = true;
if( varName=="pT2" ) found_pT2 = true;
if( varName=="NJ" ) found_NJ = true;
if( varName=="NbJ" ) found_NbJ = true;
if( varName=="NbJmed" ) found_NbJmed = true;
}
// preselection cuts (if not optimized):
if( !found_pT1 ) ofs << "pT1 20. 100000." << std::endl;
if( !found_pT2 ) ofs << "pT2 20. 100000." << std::endl;
if( !found_NJ ) ofs << "NJ 3 100000." << std::endl;
if( !found_NbJ ) ofs << "NbJ 1 100000." << std::endl;
if( !found_NbJmed && btagMed_presel_ ) ofs << "NbJmed 1 100000." << std::endl;
if( charge=="plus" )
ofs << "Charge 1 10" << std::endl;
else if( charge=="minus" )
ofs << "Charge -10 0" << std::endl;
ofs.close();
} // for eff
} // if cuts
// --------------------------------------------------------------
// 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 TMVAtest1()
{
// ---------------------------------------------------------------
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 TrainName = "TMVA";
TString outfileName( TrainName+".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( TrainName, 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 ("ptphoton", 'F');
// factory->AddVariable ("etaphoton", 'F');
factory->AddVariable ("ptmuon", 'F');
// factory->AddVariable ("etamuon", 'F');
factory->AddVariable ("ptjet", 'F');
// factory->AddVariable ("etajet", 'F');
// factory->AddVariable ("masstop", 'F');
// factory->AddVariable ("mtw", 'F');
factory->AddVariable ("deltaRphotonjet", 'F');
factory->AddVariable ("deltaRphotonmuon", 'F');
// factory->AddVariable ("ht", 'F');
// factory->AddVariable ("photonmuonmass", 'F');
factory->AddVariable ("costopphoton", 'F');
// factory->AddVariable ("topphotonmass", 'F');
//factory->AddVariable ("pttop", 'F');
//factory->AddVariable ("etatop", 'F');
factory->AddVariable ("jetmultiplicity", 'F');
// factory->AddVariable ("bjetmultiplicity", 'F');
factory->AddVariable ("deltaphiphotonmet", 'F');
factory->AddVariable ("cvsdiscriminant", 'F');
// factory->AddVariable ("leptoncharge", 'F');
//Load the signal and background event samples from ROOT trees
// TFile *inputSTrain(0);
// TFile *inputBTrain(0);
TString sigFileTrain = "SIGNALtGu.root";
TString bkgFileTrain = "WPHJET.root";
TString ttbarFileTrain1 ="TTBAR1.root";
TString ttbarFileTrain2 ="TTBAR2.root";
TString ttbarFileTrain3 ="TTBAR3.root";
TString TTGFileTrain ="TTG.root";
TString WWFileTrain ="WW.root";
TString WZFileTrain ="WZ.root";
TString ZZFileTrain ="ZZ.root";
TString ZGAMMAFileTrain ="ZGAMMA.root";
// TString bkgFileTrain = "TTG.root";
TFile *inputSTrain = TFile::Open( sigFileTrain );
if (!inputSTrain) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
TFile *inputBTrain = TFile::Open( bkgFileTrain );
TFile *inputBttbar1 = TFile::Open( ttbarFileTrain1);
TFile *inputBttbar2 = TFile::Open( ttbarFileTrain2);
TFile *inputBttbar3 = TFile::Open( ttbarFileTrain3);
TFile *inputTTG= TFile::Open(TTGFileTrain );
TFile *inputWW= TFile::Open(WWFileTrain );
TFile *inputWZ= TFile::Open(WZFileTrain );
TFile *inputZZ= TFile::Open(ZZFileTrain );
TFile *inputZGAMMA= TFile::Open( ZGAMMAFileTrain);
if (!inputBTrain) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAnalysis : Accessing Signal Train: " << sigFileTrain << std::endl;
std::cout << "--- TMVAnalysis : Accessing Background Train: " << bkgFileTrain << std::endl;
TTree *signalTrain = (TTree*)inputSTrain->FindObjectAny("atq");
TTree *backgroundTrain = (TTree*)inputBTrain->FindObjectAny("atq");
TTree *ttbarbackground1 = (TTree*)inputBttbar1->FindObjectAny("atq");
TTree *ttbarbackground2 = (TTree*)inputBttbar2->FindObjectAny("atq");
TTree *ttbarbackground3 = (TTree*)inputBttbar3->FindObjectAny("atq");
TTree *TTGbackground = (TTree*)inputTTG->FindObjectAny("atq");
TTree *WWbackground = (TTree*)inputWW->FindObjectAny("atq");
TTree *WZbackground = (TTree*)inputWZ->FindObjectAny("atq");
TTree *ZZbackground = (TTree*)inputZZ->FindObjectAny("atq");
TTree *ZGAMMAbackground = (TTree*)inputZGAMMA->FindObjectAny("atq");
// TTree *signalTrain = (TTree*)inputSTrain->FindObjectAny("insidetopmass");
// TTree *backgroundTrain = (TTree*)inputBTrain->FindObjectAny("insidetopmass");
// factory->AddSignalTree( signalTrain, 1);
//cout<<"reza1";
// factory->AddBackgroundTree( backgroundTrain, 1, );
//cout<<"reza2";
factory->SetInputTrees(signalTrain,backgroundTrain,1,1);
factory->AddBackgroundTree( ttbarbackground1, 1.1);
factory->AddBackgroundTree( ttbarbackground2, 1.1);
// factory->AddBackgroundTree( ttbarbackground3, 0.3);
factory->AddBackgroundTree( TTGbackground, 1);
factory->AddBackgroundTree( WWbackground, 1);
factory->AddBackgroundTree(WZbackground , 1);
factory->AddBackgroundTree(ZZbackground , 1);
factory->AddBackgroundTree(ZGAMMAbackground , 1);
// Set xs-weight
// factory->SetSignalWeightExpression ("weight");
//factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = "";
// TCut mycutb = "";
Int_t nSignalTrain = signalTrain->GetEntries();
Int_t nBackTrain = backgroundTrain->GetEntries();
factory->PrepareTrainingAndTestTree( "","", "nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:SplitSeed=88!V" );
//factory->PrepareTrainingAndTestTree( "", "",
// "nTrain_Signal=100:nTrain_Background=100:nTest_Signal=100:nTest_Background=100:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
//":NSigTrain=:NBkgTrain=:NSigTest=:NBkgTest=:SplitMode=Alternate:!V" );
//":nTrain_Signal=10000:nTest_Signal=2260:nTrain_Background=100000:nTest_Background=100000:SplitMode=Alternate:!V" );
// ":nTrain_Signal=nSignalTrain:nTrain_Background=nBackTrain:!V");
//":nTrain_Signal=nSignalTrain:nTest_Signal=nSignalTest:nTrain_Background=nBackTrain:nTest_Background=nBackTest:SplitMode=Block:!V");
//":SplitMode=Alternate:!V");
//":nTrain_Signal=:nTest_Signal=:nTrain_Background=:nTest_Background=:SplitMode=Block:!V");
//":SplitMode=Alternate:!V" );
// ---- Book MVA methods
// factory->BookMethod( TMVA::Types::kBDT, "BDT",
// "!H:!V:NTrees=300:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=-1:NNodesMax=5:UseNvars=4:PruneStrength=5:PruneMethod=CostComplexity:MaxDepth=4" );
//factory->BookMethod( TMVA::Types::kBDT, "BDT",
// "!H:!V:NTrees=400:BoostType=AdaBoost:AdaBoostBeta=0.5:MaxDepth=3:SeparationType=GiniIndex:PruneMethod=NoPruning" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:AdaBoostBeta=0.8:MaxDepth=3:SeparationType=GiniIndex:PruneMethod=NoPruning" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5");
// factory->BookMethod(TMVA::Types::kFisher, "Fisher", "H:!V:Fisher");
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
// factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001" );
// 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" );
// 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 );
}
int main( int argc, char* argv[] ) {
std::cout << std::endl << std::endl;
std::cout << "------------------------------------------------------" << std::endl;
std::cout << "| |" << std::endl;
std::cout << "| |" << std::endl;
std::cout << "| Running runZGAnalysis |" << std::endl;
std::cout << "| |" << std::endl;
std::cout << "| |" << std::endl;
std::cout << "------------------------------------------------------" << std::endl;
std::cout << std::endl << std::endl;
if( argc<2 ) {
std::cout << "USAGE: ./runZGAnalysis [configFileName] [data/MC]" << std::endl;
std::cout << "Exiting." << std::endl;
exit(11);
}
std::string configFileName(argv[1]);
ZGConfig cfg(configFileName);
bool onlyData = false;
bool onlyMC = false;
bool onlySignal = false;
bool noSignals = false;
if( argc > 2 ) {
std::string dataMC(argv[2]);
if( dataMC=="data" ) onlyData = true;
else if( dataMC=="MC" || dataMC=="mc" ) onlyMC = true;
else if( dataMC=="mcbg" || dataMC=="mcBG" || dataMC=="MCBG" || dataMC=="mc_bg" || dataMC=="MC_BG" ) {
onlyMC = true;
noSignals = true;
} else if( dataMC=="signal" ) onlySignal = true;
else {
std::cout << "-> You passed a second argument that isn't 'data', nor 'MC', nor 'signal', so I don't know what to do about it." << std::endl;
}
} else {
std::cout << "-> Will run on both data and MC." << std::endl;
}
if( onlyMC ) {
std::cout << "-> Will run only on MC." << std::endl;
if( noSignals ) {
std::cout << "-> Will skip signal." << std::endl;
}
}
if( onlyData ) {
std::cout << "-> Will run only on data." << std::endl;
}
std::string outputdir = cfg.getEventYieldDir();
system(Form("mkdir -p %s", outputdir.c_str()));
std::string outfileName(Form("%s/trees_tmp.root", outputdir.c_str()));
TFile* outfile = TFile::Open(outfileName.c_str(), "update");
outfile->cd();
if( !onlyData && !onlySignal ) { // run on MC
std::string samplesFileName = "../samples/samples_" + cfg.mcSamples() + ".dat";
std::cout << std::endl << std::endl;
std::cout << "-> Loading samples from file: " << samplesFileName << std::endl;
std::vector<ZGSample> fSamples = ZGSample::loadSamples(samplesFileName);
//std::vector<ZGSample> fSamples = ZGSample::loadSamples(samplesFileName, 100, 999);
if( fSamples.size()==0 ) {
std::cout << "There must be an error: samples is empty!" << std::endl;
exit(120);
}
//addTreeToFile( outfile, "zg", fSamples, cfg);
addTreeToFile( outfile, "zg", fSamples, cfg, 851, 852 );
addTreeToFile( outfile, "dy", fSamples, cfg, 700, 710 );
//addTreeToFile( outfile, "top", fSamples, cfg, 300, 499 ); // irrelevant
std::cout << "-> Done looping on MC samples." << std::endl;
} // if MC samples
// load signal samples, if any
if( cfg.mcSamples()!="" && cfg.additionalStuff()!="noSignals" && !noSignals && !onlyData ) {
std::string samplesFileName = "../samples/samples_" + cfg.mcSamples() + ".dat";
std::cout << std::endl << std::endl;
std::cout << "-> Loading signal samples from file: " << samplesFileName << std::endl;
std::vector<ZGSample> fSamples = ZGSample::loadSamples(samplesFileName, 1000); // only signal (id>=1000)
if( fSamples.size()==0 ) {
std::cout << "No signal samples found, skipping." << std::endl;
} else {
for( unsigned i=0; i<fSamples.size(); ++i )
addTreeToFile( outfile, fSamples[i], cfg );
} // if samples != 0
} // if mc samples
if( !(cfg.dummyAnalysis()) && cfg.dataSamples()!="" && !onlyMC && !onlySignal ) {
std::string samplesFile_data = "../samples/samples_" + cfg.dataSamples() + ".dat";
std::cout << std::endl << std::endl;
std::cout << "-> Loading data from file: " << samplesFile_data << std::endl;
std::vector<ZGSample> samples_data = ZGSample::loadSamples(samplesFile_data);
if( samples_data.size()==0 ) {
std::cout << "There must be an error: samples_data is empty!" << std::endl;
exit(1209);
}
addTreeToFile( outfile, "data" , samples_data, cfg );
std::cout << "-> Done looping on data." << std::endl;
}
outfile->Close();
std::string finalFileName = outputdir + "/trees.root";
system( Form("cp %s %s", outfileName.c_str(), finalFileName.c_str()) );
std::cout << "-> Wrote trees to file: " << finalFileName << std::endl;
return 0;
}
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 );
}
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 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 );
}
// Analysis_Lifetime::Setup()
Analysis::RetType Analysis_Lifetime::Setup(ArgList& analyzeArgs, DataSetList* datasetlist,
TopologyList* PFLin, DataFileList* DFLin, int debugIn)
{
// Get Keywords
FileName outfileName( analyzeArgs.GetStringKey("out") );
std::string setname = analyzeArgs.GetStringKey("name");
bool sortSets = (!analyzeArgs.hasKey("nosort"));
windowSize_ = analyzeArgs.getKeyInt("window", -1);
averageonly_ = analyzeArgs.hasKey("averageonly");
cumulative_ = analyzeArgs.hasKey("cumulative");
deltaAvg_ = analyzeArgs.hasKey("delta");
cut_ = analyzeArgs.getKeyDouble("cut", 0.5);
fuzzCut_ = analyzeArgs.getKeyInt("fuzz", -1);
if (fuzzCut_ < 1) fuzzCut_ = -1;
normalizeCurves_ = !analyzeArgs.hasKey("rawcurve");
if (analyzeArgs.hasKey("greater"))
Compare_ = Compare_GreaterThan;
else if (analyzeArgs.hasKey("less"))
Compare_ = Compare_LessThan;
else
Compare_ = Compare_GreaterThan;
// Select datasets from remaining args
if (inputDsets_.AddSetsFromArgs( analyzeArgs.RemainingArgs(), *datasetlist )) {
mprinterr("Error: lifetime: Could not add data sets.\n");
return Analysis::ERR;
}
// Sort data sets
if (sortSets) inputDsets_.SortArray1D();
// Create output datasets
DataFile* outfile = 0;
DataFile* maxfile = 0;
DataFile* avgfile = 0;
if (setname.empty())
setname = datasetlist->GenerateDefaultName( "lifetime" );
if ( windowSize_ != -1) {
outfile = DFLin->AddDataFile(outfileName, analyzeArgs);
if (!averageonly_ && outfile != 0) {
maxfile = DFLin->AddDataFile(outfileName.DirPrefix() + "max." +
outfileName.Base(), analyzeArgs);
avgfile = DFLin->AddDataFile(outfileName.DirPrefix() + "avg." +
outfileName.Base(), analyzeArgs);
}
int didx = 0;
for (Array1D::const_iterator set = inputDsets_.begin(); set != inputDsets_.end(); ++set)
{
MetaData md(setname, didx);
md.SetLegend( (*set)->Meta().Legend() );
DataSet_1D* outSet = (DataSet_1D*)datasetlist->AddSet( DataSet::FLOAT, md );
if (CheckDsetError(outSet, "output", (*set)->legend()))
return Analysis::ERR;
outputDsets_.push_back( outSet );
if (outfile != 0) outfile->AddDataSet( outSet );
if (!averageonly_) {
// MAX
md.SetAspect("max");
outSet = (DataSet_1D*)datasetlist->AddSet(DataSet::INTEGER, md);
if (CheckDsetError(outSet, "lifetime max", (*set)->legend()))
return Analysis::ERR;
maxDsets_.push_back( outSet );
if (maxfile != 0) maxfile->AddDataSet( outSet );
// AVG
md.SetAspect("avg");
outSet = (DataSet_1D*)datasetlist->AddSet(DataSet::FLOAT, md);
if (CheckDsetError(outSet, "lifetime avg", (*set)->legend()))
return Analysis::ERR;
avgDsets_.push_back( outSet );
if (avgfile != 0) avgfile->AddDataSet( outSet );
}
++didx;
}
// Set step to window size.
std::string fileArgs = "xstep " + integerToString( windowSize_ );
if (outfile != 0) outfile->ProcessArgs( fileArgs );
if (maxfile != 0) maxfile->ProcessArgs( fileArgs );
if (avgfile != 0) avgfile->ProcessArgs( fileArgs );
}
// Lifetime curves
DataFile* crvfile = 0;
if (!averageonly_) {
if (!outfileName.empty()) {
crvfile = DFLin->AddDataFile(outfileName.DirPrefix() + "crv." +
outfileName.Base(), analyzeArgs);
}
MetaData md(setname, "curve");
for (int didx = 0; didx != (int)inputDsets_.size(); didx++)
{
md.SetIdx(didx);
DataSet_1D* outSet = (DataSet_1D*)datasetlist->AddSet(DataSet::DOUBLE, md);
if (CheckDsetError(outSet, "lifetime curve", inputDsets_[didx]->legend()))
return Analysis::ERR;
curveSets_.push_back( outSet );
if (crvfile != 0) crvfile->AddDataSet( outSet );
}
}
// Non-window output file
if (!averageonly_ && windowSize_ == -1) {
standalone_ = DFLin->AddCpptrajFile( outfileName, "Lifetimes", DataFileList::TEXT, true );
if (standalone_ == 0) return Analysis::ERR;
} else
standalone_ = 0;
if (!averageonly_)
mprintf(" LIFETIME: Calculating average lifetime using a cutoff of %f", cut_);
else
mprintf(" LIFETIME: Calculating only averages");
mprintf(" of data in %i sets\n", inputDsets_.size());
if (!sortSets) mprintf("\tInput data sets will not be sorted.\n");
if (debugIn > 0)
for (Array1D::const_iterator set = inputDsets_.begin(); set != inputDsets_.end(); ++set)
mprintf("\t%s\n", (*set)->legend());
if (Compare_ == Compare_GreaterThan)
mprintf("\tValues greater than %f are considered present.\n", cut_);
else
mprintf("\tValues less than %f are considered present.\n", cut_);
if (windowSize_ != -1) {
mprintf("\tAverage of data over windows will be saved to sets named %s\n",
setname.c_str());
mprintf("\tWindow size for averaging: %i\n", windowSize_);
if (cumulative_)
mprintf("\tCumulative averages will be saved.\n");
if (deltaAvg_)
mprintf("\tChange of average from previous average will be saved.\n");
}
if (outfile != 0) {
mprintf("\tOutfile: %s", outfile->DataFilename().full());
if (!averageonly_ && outfile != 0)
mprintf(", %s, %s", maxfile->DataFilename().base(), avgfile->DataFilename().base());
mprintf("\n");
}
if (!averageonly_) {
if (crvfile != 0)
mprintf("\tLifetime curves output: %s\n", crvfile->DataFilename().base());
if (normalizeCurves_)
mprintf("\tLifetime curves will be normalized.\n");
else
mprintf("\tLifetime curves will not be normalized.\n");
}
if (fuzzCut_ != -1)
mprintf("\tFuzz value of %i frames will be used.\n", fuzzCut_);
return Analysis::OK;
}
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"] = 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"] = 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"] = 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"] = 0; // 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;
}
}
// --------------------------------------------------------------------------------------------------
// --- 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( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable( "pho_ecalClusterIsoR4", "pho_ecalClusterIsoR4", "units", 'F' );
factory->AddVariable( "pho_hcalRechitIsoR4", "pho_hcalRechitIsoR4", "units", 'F' );
factory->AddVariable( "pho_trackIsoR4PtCut20", "pho_trackIsoR4PtCut20", "units", 'F' );
factory->AddVariable( "phoHoverE", "phoHoverE", "units", 'F' );
factory->AddVariable( "phoSigmaIEtaIEta_2012", "phoSigmaIEtaIEta_2012", "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
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
// TString fname = "./tmva_class_example.root";
TString fname = "/net/hisrv0001/home/juliusbl/alex/cut/cutTree.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 *signal = (TTree*)input->Get("cutT");
TTree *background = (TTree*)input->Get("cutT");
// 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 = "subid==0"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "subid==1"; // 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["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()));
// efficiencies( TString fin = "TMVA.root", Int_t type = 2, Bool_t useTMVAStyle = kTRUE );
}
void testBDT(){
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
/*
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "testBDT", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// global event weights per tree (see below for setting event-wise weights)
//Double_t signalWeight = 0.003582;
//Double_t backgroundWeight = 0.0269;
Double_t signalWeight = 1;
Double_t backgroundWeight = 1;
TFile *input_sig = TFile::Open( "signal_exclusif.root" );
TFile *input_wz = TFile::Open( "bruit_w_z.root" );
TTree *signal = (TTree*)input_sig->Get("tree");
TTree *background = (TTree*)input_wz->Get("tree");
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
factory->AddVariable("PT_z" , 'F');
factory->AddVariable("ASYM" , 'F');
factory->AddVariable("PHI_lw_b", 'F');
factory->AddVariable("M_top", 'F');
*/
TString outfileName( "bdtTMVA_FCNC_tZ.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "doBDT_FCNC_tZ", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// global event weights per tree (see below for setting event-wise weights)
//Double_t signalWeight = 0.003582;
//Double_t backgroundWeight = 0.0269;
Double_t signalWeight = 1;
Double_t backgroundWeight = 1;
TFile *input_sig = TFile::Open( "proof.root" );
TFile *input_wz = TFile::Open( "proof.root" );
TTree *signal = (TTree*)input_sig->Get("Ttree_FCNCkut");
TTree *background_WZ = (TTree*)input_wz->Get("Ttree_WZ");
/*TTree *background_ZZ = (TTree*)input_wz->Get("Ttree_ZZ");
TTree *background_WW = (TTree*)input_wz->Get("Ttree_WW");
TTree *background_TTbar = (TTree*)input_wz->Get("Ttree_TTbar");
TTree *background_Zjets = (TTree*)input_wz->Get("Ttree_Zjets");
TTree *background_Wjets = (TTree*)input_wz->Get("Ttree_Wjets");
TTree *background_TtW = (TTree*)input_wz->Get("Ttree_TtW");
TTree *background_TbartW = (TTree*)input_wz->Get("Ttree_TbartW");*/
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background_WZ, backgroundWeight );
/*factory->AddBackgroundTree( background_ZZ, backgroundWeight );
factory->AddBackgroundTree( background_WW, backgroundWeight );
factory->AddBackgroundTree( background_TTbar, backgroundWeight );
factory->AddBackgroundTree( background_Zjets, backgroundWeight );
factory->AddBackgroundTree( background_Wjets, backgroundWeight );
factory->AddBackgroundTree( background_TtW, backgroundWeight );
factory->AddBackgroundTree( background_TbartW, backgroundWeight );*/
factory->AddVariable("tree_topMass", 'F');
factory->AddVariable("tree_deltaPhilb", 'F');
factory->AddVariable("tree_asym", 'F');
factory->AddVariable("tree_Zpt", 'F');
// to set weights. The variable must exist in the tree
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// 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";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// 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 fname = "./tmva_class_example.root")
{
// 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 tmva_dir(TString(gRootDir) + "/tmva");
if(gSystem->Getenv("TMVASYS"))
tmva_dir = TString(gSystem->Getenv("TMVASYS"));
gROOT->SetMacroPath(tmva_dir + "/test/:" + gROOT->GetMacroPath() );
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["KNN"] = 1; // k-nearest neighbour method
// ---------------------------------------------------------------
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" );
// 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: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( "pt_eH", 'D' );
factory->AddVariable( "max(pt_jet_eH,pt_eH)", 'D' );
factory->AddVariable( "njets", '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( "spec1 := var1*2", "Spectator 1", "units", 'F' );
/// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TFile *input(0);
if (gSystem->AccessPathName( fname )){ // file does not exist in local directory
gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
fname = "./tmva_class_example.root";
}else{
input= TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file " << fname << std::endl;
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
// --- Register the training and test trees
TTree *inputTree = (TTree*)input->Get("FakeTreeSig");
TTree *background = (TTree*)input->Get("FakeTreeBG");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// cuts for signal and background
//~ TCut signalCut = "selected==1 && id_iso_eleH==1";
//~ TCut backgroundCut = "selected==1 && id_iso_eleH==0";
//~
//~ std::cout << " THe signal cut is " << signalCut.GetTitle() << " bg cut is " << backgroundCut.GetTitle() << std::endl;
Int_t num_pass = inputTree->GetEntries();
Int_t num_fail = background->GetEntries();
std::cout << num_pass << " " << num_fail << std::endl;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( inputTree, 1.0 );
factory->AddBackgroundTree( background, 1.0 );
factory->SetWeightExpression( "weight" );
//factory->SetInputTrees( inputTree, signalCut, backgroundCut );
// 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");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "selected==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "selected==1"; // 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" );
std::stringstream indexes;
indexes.str("");
indexes << "nTrain_Signal=" << num_pass << ":nTrain_Background=" << num_fail << ":SplitMode=Random:NormMode=None:!V";
std::string input_opt=indexes.str();
std::cout << "Options are " << input_opt << std::endl;
factory->PrepareTrainingAndTestTree( mycuts, mycutb, input_opt);
//"nTrain_Signal="+num_pass+":nTrain_Background="+num_fail+":SplitMode=Random:NormMode=None:!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
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=50:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// 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 );
}
TString autoencoder (std::string inputFileName)
{
std::string tmstr (now ());
TString tmstmp (tmstr.c_str ());
std::cout << "==> Start Autoencoder " << std::endl;
std::cout << "-------------------- open input file ---------------- " << std::endl;
TString fname = pathToData + TString (inputFileName.c_str ()) + TString (".root");
TFile *input = TFile::Open( fname );
std::cout << "-------------------- get tree ---------------- " << std::endl;
TTree *tree = (TTree*)input->Get("data");
TString outfileName( "TMVAAutoEnc__" );
outfileName += TString (inputFileName.c_str ()) + TString ("__") + 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( "TMVAAutoencoder", outputFile,
"AnalysisType=Regression:Color:DrawProgressBar" );
std::cout << "-------------------- add variables ---------------- " << std::endl;
for (auto varname : variableNames+additionalVariableNames)
{
factory->AddVariable (varname.c_str (), 'F');
factory->AddTarget (varname.c_str (), 'F');
}
std::cout << "-------------------- add tree ---------------- " << std::endl;
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
factory->AddRegressionTree (tree, regWeight);
std::cout << "-------------------- prepare ---------------- " << std::endl;
TCut mycut = ""; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents:!V" );
/* // This would set individual event weights (the variables defined in the */
/* // expression need to exist in the original TTree) */
/* factory->SetWeightExpression( "var1", "Regression" ); */
if (true)
{
TString layoutString ("Layout=TANH|100,TANH|20,TANH|40,LINEAR");
TString training0 ("LearningRate=1e-5,Momentum=0.5,Repetitions=1,ConvergenceSteps=500,BatchSize=50,TestRepetitions=7,WeightDecay=0.01,Regularization=NONE,DropConfig=0.5+0.5+0.5+0.5,DropRepetitions=2");
TString training1 ("LearningRate=1e-5,Momentum=0.9,Repetitions=1,ConvergenceSteps=500,BatchSize=30,TestRepetitions=7,WeightDecay=0.01,Regularization=L2,DropConfig=0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.3,Repetitions=1,ConvergenceSteps=10,BatchSize=40,TestRepetitions=7,WeightDecay=0.1,Regularization=L2");
TString training3 ("LearningRate=1e-5,Momentum=0.1,Repetitions=1,ConvergenceSteps=10,BatchSize=10,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 ; //+ "|" + training3;
// TString trainingStrategyString ("TrainingStrategy=LearningRate=1e-1,Momentum=0.3,Repetitions=3,ConvergenceSteps=20,BatchSize=30,TestRepetitions=7,WeightDecay=0.0,L1=false,DropFraction=0.0,DropRepetitions=5");
TString nnOptions ("!H:V:ErrorStrategy=SUMOFSQUARES:VarTransform=N:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
factory->BookMethod( TMVA::Types::kNN, TString("NN_")+tmstmp, nnOptions ); // NN
}
// --------------------------------------------------------------------------------------------------
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
// TMVA::TMVARegGui (outfileName);
delete factory;
return TString("NN_")+tmstmp;
}
