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 process(const std::vector<std::string>& inputFiles, const std::string& name, const std::string& outputFile) {
TChain* signal = loadChain(inputFiles, "signal");
TChain* background = loadChain(inputFiles, "background");
TFile* output = TFile::Open(outputFile.c_str(), "recreate");
TMVA::Factory* factory = new TMVA::Factory(name.c_str(), output, "V");
factory->AddSignalTree(signal, 1.);
factory->AddBackgroundTree(background, 1.);
//{
//factory->AddVariable("lightJet1p2_Pt");
//factory->AddVariable("leptonic_B_Pt");
//factory->AddVariable("leptonic_Top_Pt");
//factory->AddVariable("leptonic_Top_M");
//factory->AddVariable("hadronic_B_Pt");
//factory->AddVariable("hadronic_W_M");
//factory->AddVariable("hadronic_Top_Pt");
//factory->AddVariable("hadronic_Top_M");
//factory->AddVariable("delta_R_tops");
//factory->AddVariable("delta_R_lightjets");
//factory->AddVariable("leptonic_B_CSV");
//factory->AddVariable("hadronic_B_CSV");
//}
// chi^2 style
{
factory->AddVariable("leptonic_Top_M");
factory->AddVariable("hadronic_W_M");
factory->AddVariable("hadronic_Top_M");
factory->AddVariable("ht_fraction");
}
factory->SetWeightExpression("weight");
factory->PrepareTrainingAndTestTree("", "", "V:VerboseLevel=Info:nTrain_Signal=100000:nTrain_Background=100000:nTest_Signal=100000:nTest_Background=100000");
factory->BookMethod(TMVA::Types::kBDT, "BDT", "V:BoostType=AdaBoost:nCuts=20:VarTransform=D");
factory->BookMethod(TMVA::Types::kMLP, "NN", "V:VarTransform=D");
//factory->BookMethod(TMVA::Types::kPDERS, "PDERS", "V");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
output->Close();
delete output;
delete signal;
delete background;
}
void test_train(TString signalName = "WW",
TString bkgName = "DY")
{
TFile *outFile = new TFile("myAnalysisFile.root","RECREATE");
TMVA::Factory *factory = new TMVA::Factory(signalName, outFile,"");
TString directory = "../rootFiles/SF/MediumIDTighterIP/";
//signalName = directory + signalName;
//defining WW signal
TFile *MySignalFile = new TFile("../rootFiles/SF/MediumIDTighterIP/WW.root","READ");
TTree* sigTree = (TTree*)MySignalFile->Get("nt");
factory->AddSignalTree(sigTree,1);
//defining DY background
TFile *MyBkgFile = new TFile("../rootFiles/SF/MediumIDTighterIP/DY.root","READ");
TTree* bkgTree = (TTree*)MyBkgFile->Get("nt");
factory->AddBackgroundTree(bkgTree,1);
factory->SetWeightExpression("baseW");
//************************************ FACTORY
factory->AddVariable("fullpmet");
factory->AddVariable("trkpmet");
factory->AddVariable("ratioMet");
factory->AddVariable("ptll");
factory->AddVariable("mth");
factory->AddVariable("jetpt1");
factory->AddVariable("ptWW");
factory->AddVariable("dphilljet");
factory->AddVariable("dphillmet");
factory->AddVariable("dphijet1met");
factory->AddVariable("nvtx");
factory->PrepareTrainingAndTestTree("",500,500,500,500);
cout<<"I've prepared trees"<<endl;
//factory->BookMethod(TMVA::Types::kFisher, "Fisher","");
factory->BookMethod(TMVA::Types::kBDT, "BDT","");
cout<<"I've booked method"<<endl;
factory->TrainAllMethods();
factory->TestAllMethods();
cout<<"I've tested all methods"<<endl;
factory->EvaluateAllMethods();
cout<<"I've evaluated all methods"<<endl;
}
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(char* trainFile, char* tree,
char* mycuts, char* mycutb, char* inputVars[], int size)
{
// this loads the library
TMVA::Tools::Instance();
// Create a new root output file.
TFile* outputFile = TFile::Open( "TMVA.root", "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
for (int ivar = 0; ivar < size; ++ivar) {
factory->AddVariable(inputVars[ivar], 'F');
}
// read training and test data
TFile *input = TFile::Open( trainFile);
TTree *signal = (TTree*)input->Get(tree);
TTree *background = (TTree*)input->Get(tree);
// global event weights per tree
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 );
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( TCut(mycuts), TCut(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:
// ---- 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" );
// ---- 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 << "==> TMVAClassification is done!" << std::endl;
delete factory;
}
void trainBDT(void)
{
// Open input file and get tree
TFile *infile = new TFile("l3bdt.root");
TTree *l3tree = (TTree*)infile->Get("l3tree");
if(l3tree == NULL){
cout << "Couldn't open \"l3bdt.root\"!" << endl;
return;
}
// Open output root file (for TMVA)
TFile *outfile = new TFile("l3BDT_out.root", "RECREATE");
TMVA::Factory *fac = new TMVA::Factory("L3",outfile,"");
// Specify input tree that contains both signal and background
TCut signalCut("is_good==1");
TCut backgroundCut("is_good==0");
fac->SetInputTrees(l3tree, signalCut, backgroundCut);
// Add variables
fac->AddVariable("Nstart_counter", 'I');
fac->AddVariable("Ntof", 'I');
fac->AddVariable("Nbcal_points", 'I');
fac->AddVariable("Nbcal_clusters", 'I');
fac->AddVariable("Ebcal_points", 'F');
fac->AddVariable("Ebcal_clusters", 'F');
fac->AddVariable("Nfcal_clusters", 'I');
fac->AddVariable("Efcal_clusters", 'F');
fac->AddVariable("Ntrack_candidates", 'I');
fac->AddVariable("Ptot_candidates", 'F');
TCut preSelectCut("");
fac->PrepareTrainingAndTestTree(preSelectCut,"");
fac->BookMethod(TMVA::Types::kBDT, "BDT", "");
fac->TrainAllMethods();
fac->TestAllMethods();
fac->EvaluateAllMethods();
delete fac;
outfile->Close();
delete outfile;
}
void trainBJetIdMVA(TString SELECTION)
{
// the training is done using a dedicated tree format
TFile *src = TFile::Open("bjetId_"+SELECTION+".root");
TTree *tr = (TTree*)src->Get("jets");
TFile *outf = new TFile("bjetId_"+SELECTION+"_MVA.root","RECREATE");
TCut signalCut = "abs(partonId) == 5";
TCut bkgCut = "abs(partonId) != 5";
TCut preselectionCut = "btagIdx<4 && etaIdx<4 && etaIdx>-1 && ptIdx<4";
int N = 100000;
cout<<"NUMBER OF TRAINING EVENTS = "<<N<<endl;
TMVA::Factory* factory = new TMVA::Factory("factory_"+SELECTION+"_",outf,"!V:!Silent:Color:DrawProgressBar:Transformations=I;G:AnalysisType=Classification" );
factory->SetInputTrees(tr,signalCut,bkgCut);
factory->AddVariable("btagIdx",'I');
factory->AddVariable("etaIdx" ,'I');
factory->AddVariable("btag" ,'F');
factory->AddVariable("eta" ,'F');
char name[1000];
sprintf(name,"nTrain_Signal=%d:nTrain_Background=%d:nTest_Signal=%d:nTest_Background=%d",N,N,N,N);
factory->PrepareTrainingAndTestTree(preselectionCut,name);
// specify the training methods
factory->BookMethod(TMVA::Types::kLikelihood,"Likelihood");
//factory->BookMethod(TMVA::Types::kBDT,"BDT_DEF");
//factory->BookMethod(TMVA::Types::kBDT,"BDT_ADA","NTrees=600:AdaBoostBeta=0.1:nCuts=35");
//factory->BookMethod(TMVA::Types::kBDT,"BDT_GRAD1","NTrees=600:nCuts=40:BoostType=Grad:Shrinkage=0.5");
factory->BookMethod(TMVA::Types::kBDT,"BDT_GRAD2","NTrees=600:nCuts=25:BoostType=Grad:Shrinkage=0.2");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
}
void TMVAtest(){
//gSystem->Load("../lib/slc5_amd64_gcc462/libTAMUWWMEPATNtuple.so");
gSystem->Load("libPhysics");
//gSystem->Load("EvtTreeForAlexx_h.so");
gSystem->Load("libTMVA.1");
gSystem->Load("AutoDict_vector_TLorentzVector__cxx.so");
TMVA::Tools::Instance();
TFile* outputFile = TFile::Open("TMVA1.root", "RECREATE");
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification",outputFile,"V=true:Color:DrawProgressBar");// ":Transformations=I;D;P;G,D" );
TFile* signal = TFile::Open("/uscms_data/d2/aperloff/Spring12ME7TeV/MEResults/microNtuples_oldStructure/microWW_EPDv01.root");
TFile* bkg = TFile::Open("/uscms_data/d2/aperloff/Spring12ME7TeV/MEResults/microNtuples_oldStructure/microWJets_EPDv01.root");
TTree* stree = (TTree*)signal->Get("METree");
TTree* btree = (TTree*)bkg->Get("METree");
factory->AddSignalTree(stree,1.0);
factory->AddBackgroundTree(btree,1.0);
factory->SetSignalWeightExpression("1.0");
factory->SetBackgroundWeightExpression("1.0");
factory->AddVariable("tEventProb[0]");
factory->AddVariable("tEventProb[1]");
factory->AddVariable("tEventProb[2]");
//factory->AddVariable("tEventProb0 := tEventProb[0]",'F');
//factory->AddVariable("tEventProb1 := tEventProb[1]",'F');
//factory->AddVariable("tEventProb2 := tEventProb[2]",'F');
TCut test("Entry$>-2 && jLV[1].Pt()>30");
TCut mycuts (test);
factory->PrepareTrainingAndTestTree(mycuts,mycuts,"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=None:V=true:VerboseLevel=DEBUG");
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
}
int main(int argc, char**argv){
if(argc != 2){
std::cerr << " >>>>> analysis.cpp::usage: " << argv[0] << " configFileName" << std::endl ;
return 1;
}
parseConfigFile (argv[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 TMVARegression.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
std::vector<std::string> UseMethodName;
UseMethodName = gConfigParser -> readStringListOption("Input::UseMethodName");
std::cout << " >>>>> Input::UseMethodName size = " << UseMethodName.size() << std::endl;
std::cout << " >>>>> >>>>> ";
for (unsigned int iCat = 0; iCat < UseMethodName.size(); iCat++){
std::cout << " " << UseMethodName.at(iCat) << ", ";
}
std::cout << std::endl;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
std::map<std::string,int> Use;
for(std::vector<std::string>::iterator it=UseMethodName.begin(); it!=UseMethodName.end(); ++it) Use[*it]=0;
std::string UseMethodFlag;
try{ UseMethodFlag = gConfigParser -> readStringOption("Input::UseMethodFlag");
std::cout<< UseMethodFlag<<std::endl;
std::vector<TString> mlist = gTools().SplitString( UseMethodFlag, '/' );
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 -1;
}
Use[regMethod] = 1;
std::cout << "regMethod= " << regMethod<< " 1 "<<std::endl;
}
}
catch (char * exception){
std::cerr << " exception = Use All method " << std::endl;
for(std::vector<std::string>::iterator it=UseMethodName.begin() ;it!=UseMethodName.end(); it++) Use[*it]=1;
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
std::string outputFileName = gConfigParser -> readStringOption("Output::outputFileName");
std::cout<<" Output Data File = "<<outputFileName<<std::endl;
TFile* outputFile = TFile::Open( outputFileName.c_str(), "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/
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
// Read training and test data (see TMVAClassification for reading ASCII files)
// load the signal and background event samples from ROOT trees
std::string inputFileList = gConfigParser -> readStringOption("Input::inputFileList");
std::string treeNameDATA = gConfigParser -> readStringOption("Input::treeNameDATA");
std::cout<<" Input Data List = "<<inputFileList<<std::endl;
TChain* treeDATA = new TChain(treeNameDATA.c_str());
FillChain(*treeDATA,inputFileList.c_str());
TMVA::Factory *factory = new TMVA::Factory( "TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
std::string RegionOfTraining = gConfigParser -> readStringOption("Input::RegionOfTraining");
std::cout<<" RegionOfTraining = "<<RegionOfTraining<<std::endl;
if(RegionOfTraining=="EB"){
factory->AddVariable( "ele1_scE/ele1_scERaw" , 'F');
factory->AddVariable( "ele1_eRegrInput_nPV" , 'F');
factory->AddVariable( "ele1_eRegrInput_r9" , 'F');
factory->AddVariable( "ele1_fbrem" , 'F');
factory->AddVariable( "ele1_eta" , 'F');
factory->AddVariable( "ele1_DphiIn" , 'F');
factory->AddVariable( "ele1_DetaIn" , 'F');
factory->AddVariable( "ele1_sigmaIetaIeta" , 'F');
factory->AddVariable( "ele1_eRegrInput_etaW" , 'F');
factory->AddVariable( "ele1_eRegrInput_phiW" , 'F');
factory->AddVariable( "ele1_eRegrInput_bCE_Over_sCE", 'F');
factory->AddVariable( "ele1_eRegrInput_sigietaieta_bC1" , 'F');
factory->AddVariable( "ele1_eRegrInput_sigiphiiphi_bC1" , 'F');
factory->AddVariable( "ele1_eRegrInput_sigietaiphi_bC1" , 'F');
factory->AddVariable( "ele1_eRegrInput_e3x3_Over_bCE" , 'F');
factory->AddVariable( "ele1_eRegrInput_Deta_bC_sC" , 'F');
factory->AddVariable( "ele1_eRegrInput_Dphi_bC_sC" , 'F');
factory->AddVariable( "ele1_eRegrInput_bEMax_Over_bCE" , 'F');
factory->AddVariable( "ele1_dxy_PV" , 'F');
factory->AddVariable( "ele1_dz_PV" , 'F');
factory->AddVariable( "ele1_sigmaP/ele1_tkP" , 'F');
factory->AddVariable( "ele1_eRegrInput_bCELow_Over_sCE", 'F');
factory->AddVariable( "ele1_eRegrInput_e3x3_Over_bCELow" , 'F');
factory->AddVariable( "ele1_eRegrInput_Deta_bCLow_sC" , 'F');
factory->AddVariable( "ele1_eRegrInput_Dphi_bCLow_sC" , 'F');
factory->AddVariable( "ele1_eRegrInput_seedbC_etacry" , 'F');
factory->AddVariable( "ele1_eRegrInput_seedbC_phicry" , 'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
// factory->AddTarget("ele1_scE/ele1_E_true" );
factory->AddTarget("ele1_tkP/ele1_E_true" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// 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( treeDATA, regWeight );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// factory->SetWeightExpression( "var1", "Regression" );
// TCut mycut = "ele1_isEB==1 && ele1_sigmaP/ele1_tkP<0.4 && ele1_fbrem>0 && abs(ele1_dxy_PV)<0.05 && abs(ele1_dz_PV)<0.05 && ele1_eRegrInput_etaW > 0.006 && ele1_eRegrInput_phiW<0.08 && ele1_eRegrInput_sigietaieta_bC1>0.006 && ele1_eRegrInput_sigiphiiphi_bC1>0.008 && abs(ele1_eRegrInput_Deta_bC_sC)<0.004 && abs(ele1_eRegrInput_Dphi_bC_sC)<0.04 && abs(ele1_eRegrInput_seedbC_etacry)<0.6 && abs(ele1_eRegrInput_seedbC_phicry)<0.6 && ele1_scE/ele1_scERaw<1.2 && (ele1_scE/ele1_E_true)<1.4 && (ele1_scE/ele1_E_true)>0.3"; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycut = "ele1_isEB==1 && ele1_sigmaP/ele1_tkP<0.4 && ele1_fbrem>0 && abs(ele1_dxy_PV)<0.05 && abs(ele1_dz_PV)<0.05 && ele1_eRegrInput_etaW > 0.006 && ele1_eRegrInput_phiW<0.08 && ele1_eRegrInput_sigietaieta_bC1>0.006 && ele1_eRegrInput_sigiphiiphi_bC1>0.008 && abs(ele1_eRegrInput_Deta_bC_sC)<0.004 && abs(ele1_eRegrInput_Dphi_bC_sC)<0.04 && abs(ele1_eRegrInput_seedbC_etacry)<0.6 && abs(ele1_eRegrInput_seedbC_phicry)<0.6 && ele1_scE/ele1_scERaw<1.2 && ele1_tkP/ele1_E_true<1.8 && ele1_tkP/ele1_E_true>0.2"; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=2500000:nTest_Regression=2500000:SplitMode=Random:NormMode=NumEvents:!V" );
TString Name = Form("weight_%s_%s_P_W",RegionOfTraining.c_str(),UseMethodFlag.c_str());
(TMVA::gConfig().GetIONames()).fWeightFileDir = Name;
}
if(RegionOfTraining=="EE"){
factory->AddVariable( "ele1_scE/ele1_scERaw" , 'F');
factory->AddVariable( "ele1_eRegrInput_nPV",'F');
factory->AddVariable( "ele1_eRegrInput_r9",'F');
factory->AddVariable( "ele1_fbrem",'F');
factory->AddVariable( "ele1_eta",'F');
factory->AddVariable( "ele1_DphiIn",'F');
factory->AddVariable( "ele1_DetaIn",'F');
factory->AddVariable( "ele1_sigmaIetaIeta",'F');
factory->AddVariable( "ele1_eRegrInput_etaW",'F');
factory->AddVariable( "ele1_eRegrInput_phiW",'F');
factory->AddVariable( "ele1_dxy_PV",'F');
factory->AddVariable( "ele1_dz_PV",'F');
factory->AddVariable( "ele1_sigmaP/ele1_tkP",'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
// factory->AddTarget("ele1_scE/ele1_E_true" );
factory->AddTarget("ele1_tkP/ele1_E_true" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// 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( treeDATA, regWeight );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// factory->SetWeightExpression( "var1", "Regression" );
// TCut mycut = "ele1_isEB==0 && ele1_sigmaP/ele1_tkP<0.4 && ele1_fbrem>0 && abs(ele1_dxy_PV)<0.05 && abs(ele1_dz_PV)<0.05 &&(ele1_scE/ele1_E_true)<1.4 && (ele1_scE/ele1_E_true)>0.3";
TCut mycut = "ele1_isEB==0 && ele1_sigmaP/ele1_tkP<0.4 && ele1_fbrem>0 && abs(ele1_dxy_PV)<0.05 && abs(ele1_dz_PV)<0.05 && (ele1_tkP/ele1_E_true)<1.6";
// for example: TCut mycut = "abs(var1)<0.5 &&
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=3000000:nTest_Regression=3000000:SplitMode=Random:NormMode=NumEvents:!V" );
TString Name = Form("weight_%s_%s_P_W",RegionOfTraining.c_str(),UseMethodFlag.c_str());
(TMVA::gConfig().GetIONames()).fWeightFileDir = Name;
}
// Apply additional cuts on the signal and background samples (can be different)
// // If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS", "!H:!V:Normthree=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=0.3: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=G,U,D" );
// 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" );
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=200:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=400:HiddenLayers=N+10:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15" );
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=N:NeuronType=tanh:NCycles=200:HiddenLayers=N+10:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15" );
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=G,N:NeuronType=tanh:NCycles=200:HiddenLayers=N+5:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:NCycles=250:HiddenLayers=N+5:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:TestRate=10");
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=N" );
// factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=N,G" );
// Boosted Decision Trees
if (Use["BDT"])
// factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=100:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=200:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:PruneMethod=CostComplexity:PruneStrength=30" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=300:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:PruneMethod=CostComplexity:PruneStrength=30" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=100:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:PruneMethod=CostComplexity:PruneStrength=30" );
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=100:nEventsMin=20:BoostType=AdaBoostR2:SeparationType=RegressionVariance:PruneMethod=CostComplexity:PruneStrength=30");
if (Use["BDTG"])
// factory->BookMethod( TMVA::Types::kBDT, "BDTG","!H:!V:NTrees=2000::BoostType=Grad:Shrinkage=0.1:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:MaxDepth=3:NNodesMax=15" );
factory->BookMethod( TMVA::Types::kBDT, "BDTG","!H:!V:NTrees=1000::BoostType=Grad:Shrinkage=0.1:UseBaggedGrad:GradBaggingFraction=0.5:MaxDepth=5:NNodesMax=25:PruneMethod=CostComplexity:PruneStrength=30");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVARegGui( outputFileName.c_str() );
return 0;
}
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 );
}
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;
}
//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 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 );
}
int main( int argc, char** argv )
{//main
std::string folder;
if (argc > 1) {
folder = argv[1];
}
else {
folder = "output_tmva/nunu/MET130/";
}
bool useQCD = true;
bool useOthers = false;
bool useOthersAsSignal = true;
//List of input signal files
std::vector<std::string> sigfiles;
//sigfiles.push_back("MC_VBF_HToZZTo4Nu_M-120");
sigfiles.push_back("MC_Powheg-Htoinv-mH125");
if (useOthersAsSignal) {
sigfiles.push_back("MC_TTJets");
//powheg samples
//sigfiles.push_back("MC_TT-v1");
//sigfiles.push_back("MC_TT-v2");
//
sigfiles.push_back("MC_T-tW");
sigfiles.push_back("MC_Tbar-tW");
sigfiles.push_back("MC_SingleT-s-powheg-tauola");
sigfiles.push_back("MC_SingleTBar-s-powheg-tauola");
sigfiles.push_back("MC_SingleT-t-powheg-tauola");
sigfiles.push_back("MC_SingleTBar-t-powheg-tauola");
sigfiles.push_back("MC_WW-pythia6-tauola");
sigfiles.push_back("MC_WZ-pythia6-tauola");
sigfiles.push_back("MC_ZZ-pythia6-tauola");
sigfiles.push_back("MC_W1JetsToLNu_enu");
sigfiles.push_back("MC_W2JetsToLNu_enu");
sigfiles.push_back("MC_W3JetsToLNu_enu");
sigfiles.push_back("MC_W4JetsToLNu_enu");
sigfiles.push_back("MC_WJetsToLNu-v1_enu");
sigfiles.push_back("MC_WJetsToLNu-v2_enu");
sigfiles.push_back("MC_W1JetsToLNu_munu");
sigfiles.push_back("MC_W2JetsToLNu_munu");
sigfiles.push_back("MC_W3JetsToLNu_munu");
sigfiles.push_back("MC_W4JetsToLNu_munu");
sigfiles.push_back("MC_WJetsToLNu-v1_munu");
sigfiles.push_back("MC_WJetsToLNu-v2_munu");
sigfiles.push_back("MC_W1JetsToLNu_taunu");
sigfiles.push_back("MC_W2JetsToLNu_taunu");
sigfiles.push_back("MC_W3JetsToLNu_taunu");
sigfiles.push_back("MC_W4JetsToLNu_taunu");
sigfiles.push_back("MC_WJetsToLNu-v1_taunu");
sigfiles.push_back("MC_WJetsToLNu-v2_taunu");
sigfiles.push_back("MC_DYJetsToLL");
sigfiles.push_back("MC_DY1JetsToLL");
sigfiles.push_back("MC_DY2JetsToLL");
sigfiles.push_back("MC_DY3JetsToLL");
sigfiles.push_back("MC_DY4JetsToLL");
sigfiles.push_back("MC_ZJetsToNuNu_100_HT_200");
sigfiles.push_back("MC_ZJetsToNuNu_200_HT_400");
sigfiles.push_back("MC_ZJetsToNuNu_400_HT_inf");
sigfiles.push_back("MC_ZJetsToNuNu_50_HT_100");
sigfiles.push_back("MC_GJets-HT-200To400-madgraph");
sigfiles.push_back("MC_GJets-HT-400ToInf-madgraph");
sigfiles.push_back("MC_WGamma");
sigfiles.push_back("MC_EWK-Z2j");
sigfiles.push_back("MC_EWK-Z2jiglep");
sigfiles.push_back("MC_EWK-W2jminus_enu");
sigfiles.push_back("MC_EWK-W2jplus_enu");
sigfiles.push_back("MC_EWK-W2jminus_munu");
sigfiles.push_back("MC_EWK-W2jplus_munu");
sigfiles.push_back("MC_EWK-W2jminus_taunu");
sigfiles.push_back("MC_EWK-W2jplus_taunu");
}
//List of input files
std::vector<std::string> bkgfiles;
if (useQCD){
bkgfiles.push_back("MC_QCD-Pt-30to50-pythia6");
bkgfiles.push_back("MC_QCD-Pt-50to80-pythia6");
bkgfiles.push_back("MC_QCD-Pt-80to120-pythia6");
bkgfiles.push_back("MC_QCD-Pt-120to170-pythia6");
bkgfiles.push_back("MC_QCD-Pt-170to300-pythia6");
bkgfiles.push_back("MC_QCD-Pt-300to470-pythia6");
bkgfiles.push_back("MC_QCD-Pt-470to600-pythia6");
bkgfiles.push_back("MC_QCD-Pt-600to800-pythia6");
bkgfiles.push_back("MC_QCD-Pt-800to1000-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1000to1400-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1400to1800-pythia6");
bkgfiles.push_back("MC_QCD-Pt-1800-pythia6");
}
if (useOthers) {
bkgfiles.push_back("MC_TTJets");
//powheg samples
//bkgfiles.push_back("MC_TT-v1");
//bkgfiles.push_back("MC_TT-v2");
//
bkgfiles.push_back("MC_T-tW");
bkgfiles.push_back("MC_Tbar-tW");
bkgfiles.push_back("MC_SingleT-s-powheg-tauola");
bkgfiles.push_back("MC_SingleTBar-s-powheg-tauola");
bkgfiles.push_back("MC_SingleT-t-powheg-tauola");
bkgfiles.push_back("MC_SingleTBar-t-powheg-tauola");
bkgfiles.push_back("MC_WW-pythia6-tauola");
bkgfiles.push_back("MC_WZ-pythia6-tauola");
bkgfiles.push_back("MC_ZZ-pythia6-tauola");
bkgfiles.push_back("MC_W1JetsToLNu_enu");
bkgfiles.push_back("MC_W2JetsToLNu_enu");
bkgfiles.push_back("MC_W3JetsToLNu_enu");
bkgfiles.push_back("MC_W4JetsToLNu_enu");
bkgfiles.push_back("MC_WJetsToLNu-v1_enu");
bkgfiles.push_back("MC_WJetsToLNu-v2_enu");
bkgfiles.push_back("MC_W1JetsToLNu_munu");
bkgfiles.push_back("MC_W2JetsToLNu_munu");
bkgfiles.push_back("MC_W3JetsToLNu_munu");
bkgfiles.push_back("MC_W4JetsToLNu_munu");
bkgfiles.push_back("MC_WJetsToLNu-v1_munu");
bkgfiles.push_back("MC_WJetsToLNu-v2_munu");
bkgfiles.push_back("MC_W1JetsToLNu_taunu");
bkgfiles.push_back("MC_W2JetsToLNu_taunu");
bkgfiles.push_back("MC_W3JetsToLNu_taunu");
bkgfiles.push_back("MC_W4JetsToLNu_taunu");
bkgfiles.push_back("MC_WJetsToLNu-v1_taunu");
bkgfiles.push_back("MC_WJetsToLNu-v2_taunu");
bkgfiles.push_back("MC_DYJetsToLL");
bkgfiles.push_back("MC_DY1JetsToLL");
bkgfiles.push_back("MC_DY2JetsToLL");
bkgfiles.push_back("MC_DY3JetsToLL");
bkgfiles.push_back("MC_DY4JetsToLL");
bkgfiles.push_back("MC_ZJetsToNuNu_100_HT_200");
bkgfiles.push_back("MC_ZJetsToNuNu_200_HT_400");
bkgfiles.push_back("MC_ZJetsToNuNu_400_HT_inf");
bkgfiles.push_back("MC_ZJetsToNuNu_50_HT_100");
bkgfiles.push_back("MC_GJets-HT-200To400-madgraph");
bkgfiles.push_back("MC_GJets-HT-400ToInf-madgraph");
bkgfiles.push_back("MC_WGamma");
bkgfiles.push_back("MC_EWK-Z2j");
bkgfiles.push_back("MC_EWK-Z2jiglep");
bkgfiles.push_back("MC_EWK-W2jminus_enu");
bkgfiles.push_back("MC_EWK-W2jplus_enu");
bkgfiles.push_back("MC_EWK-W2jminus_munu");
bkgfiles.push_back("MC_EWK-W2jplus_munu");
bkgfiles.push_back("MC_EWK-W2jminus_taunu");
bkgfiles.push_back("MC_EWK-W2jplus_taunu");
}
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TFile *output_tmva = TFile::Open((folder+"/TMVA_QCDrej.root").c_str(),"RECREATE");
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", output_tmva,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
//fill the variables with event weight from the trees
//const unsigned nVars = 4;
factory->AddSpectator("jet1_pt","Jet 1 p_{T}", "GeV", 'F');
factory->AddSpectator("jet2_pt","Jet 2 p_{T}", "GeV", 'F');
factory->AddSpectator("jet1_eta","Jet 1 #eta", "", 'F');
factory->AddVariable("jet2_eta","Jet 2 #eta", "", 'F');// **
factory->AddSpectator("jet1_phi","Jet 1 #phi", "", 'F');
factory->AddSpectator("jet2_phi","Jet 2 #phi", "", 'F');
factory->AddSpectator("dijet_M","M_{jj}", " GeV", 'F');
factory->AddSpectator("dijet_deta","#Delta#eta_{jj}", "", 'F');
factory->AddSpectator("dijet_sumeta","#eta_{j1}+#eta_{j2}", "", 'F');
factory->AddSpectator("dijet_dphi","#Delta#phi_{jj}", "", 'F');
factory->AddSpectator("met","MET", "GeV", 'F');// **
factory->AddSpectator("met_phi","MET #phi", "", 'F');
factory->AddVariable("met_significance","MET significance", "", 'F');// **
factory->AddSpectator("sumet","#Sum E_{T}", "GeV", 'F');
factory->AddSpectator("ht","H_{T}", "GeV", 'F');
factory->AddVariable("mht","MH_{T}", "GeV", 'F');// **
factory->AddSpectator("sqrt_ht","#sqrt{H_{T}}", "GeV^{0.5}", 'F');
factory->AddSpectator("unclustered_et","Unclustered E_{T}", "GeV", 'F');
factory->AddSpectator("unclustered_phi","Unclustered #phi", "GeV", 'F');
factory->AddSpectator("jet1met_dphi","#Delta#phi(MET,jet1)", "", 'F');
factory->AddVariable("jet2met_dphi","#Delta#phi(MET,jet2)", "", 'F');// **
factory->AddVariable("jetmet_mindphi","minimum #Delta#phi(MET,jet)", "", 'F');// **
factory->AddVariable("jetunclet_mindphi","minimum #Delta#phi(unclustered,jet)", "", 'F');// **
factory->AddVariable("metunclet_dphi","#Delta#phi(MET,unclustered)", "", 'F');// **
factory->AddVariable("dijetmet_scalarSum_pt", "p_{T}^{jet1}+p_{T}^{jet2}+MET", "GeV", 'F');// **
factory->AddSpectator("dijetmet_vectorialSum_pt","p_{T}(#vec{j1}+#vec{j2}+#vec{MET})", "GeV", 'F');
factory->AddVariable("dijetmet_ptfraction","p_{T}^{dijet}/(p_{T}^{dijet}+MET)", "", 'F');// **
//factory->AddVariable("jet1met_scalarprod := (jet1_pt*cos(jet1_phi)*met_x+jet1_pt*sin(jet1_phi)*met_y)/met", "#vec{p_{T}^{jet1}}.#vec{MET}/MET", "GeV" , 'F');
//factory->AddVariable("jet2met_scalarprod := (jet2_pt*cos(jet2_phi)*met_x+jet2_pt*sin(jet2_phi)*met_y)/met", "#vec{p_{T}^{jet2}}.#vec{MET}/MET", "GeV" , 'F');
factory->AddVariable("jet1met_scalarprod", "#vec{p_{T}^{jet1}}.#vec{MET}/MET", "GeV" , 'F');// **
factory->AddVariable("jet2met_scalarprod", "#vec{p_{T}^{jet2}}.#vec{MET}/MET", "GeV" , 'F');// **
factory->AddVariable("jet1met_scalarprod_frac := jet1met_scalarprod/met", "#vec{p_{T}^{jet1}}.#vec{MET}/MET^{2}", "" , 'F');// **
factory->AddVariable("jet2met_scalarprod_frac := jet2met_scalarprod/met", "#vec{p_{T}^{jet2}}.#vec{MET}/MET^{2}", "" , 'F');// **
factory->AddSpectator("n_jets_cjv_30","CJV jets (30 GeV)", "" , 'I');
factory->AddSpectator("n_jets_cjv_20EB_30EE","CJV jets (|#eta|<2.4 and 20 GeV, or 30 GeV)", "" , 'I');
//test with only VBF variables used in cut-based analysis
//factory->AddVariable("dijet_M","M_{jj}", " GeV", 'F');
//factory->AddVariable("dijet_deta","#Delta#eta_{jj}", "", 'F');
//factory->AddVariable("dijet_dphi","#Delta#phi_{jj}", "", 'F');
//factory->AddVariable("met","MET", "GeV", 'F');
//factory->AddVariable("n_jets_cjv_30","CJV jets (30 GeV)", "" , 'I');
//get input files
//signal
//TFile *signalfile = TFile::Open((folder+"/"+"MC_VBF_HToZZTo4Nu_M-120.root").c_str());
//TTree *signal = (TTree*)signalfile->Get("TmvaInputTree");
//Double_t signalWeight = 1.0;
//factory->AddSignalTree(signal,signalWeight);
//Set individual event weights (the variables must exist in the original TTree)
//factory->SetSignalWeightExpression("total_weight");
//background
std::map<std::string, TFile *> tfiles;
for (unsigned i = 0; i < bkgfiles.size(); ++i) {
std::string filename = (bkgfiles[i]+".root");
TFile * tmp = new TFile((folder+"/"+filename).c_str());
if (!tmp) {
std::cerr << "Warning, file " << filename << " could not be opened." << std::endl;
} else {
tfiles[bkgfiles[i]] = tmp;
}
}
TTree *background[bkgfiles.size()];
//signal
std::map<std::string, TFile *> sfiles;
for (unsigned i = 0; i < sigfiles.size(); ++i) {
std::string filename = (sigfiles[i]+".root");
TFile * tmp = new TFile((folder+"/"+filename).c_str());
if (!tmp) {
std::cerr << "Warning, file " << filename << " could not be opened." << std::endl;
} else {
sfiles[sigfiles[i]] = tmp;
}
}
TTree *signal[sigfiles.size()];
for (unsigned i = 0; i < bkgfiles.size(); ++i) {
std::string f = bkgfiles[i];
if (tfiles[f]){
background[i] = (TTree*)tfiles[f]->Get("TmvaInputTree");
//if (f.find("QCD-Pt")!=f.npos){
//}
Double_t backgroundWeight = 1.0;
factory->AddBackgroundTree(background[i],backgroundWeight);
factory->SetBackgroundWeightExpression("total_weight");
}//if file exist
else {
std::cout << " Cannot find background file " << f << std::endl;
}
}//loop on files
for (unsigned i = 0; i < sigfiles.size(); ++i) {
std::string f = sigfiles[i];
if (sfiles[f]){
signal[i] = (TTree*)sfiles[f]->Get("TmvaInputTree");
//if (f.find("QCD-Pt")!=f.npos){
//}
Double_t signalWeight = 1.0;
factory->AddSignalTree(signal[i],signalWeight);
factory->SetSignalWeightExpression("total_weight");
}//if file exist
else {
std::cout << " Cannot find signal file " << f << std::endl;
}
}//loop on files
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";//dijet_deta>3.8 && dijet_M > 1100 && met > 100 && met_significance>5";
TCut mycutb = "";//dijet_deta>3.8 && dijet_M > 1100 && met > 100 && met_significance>5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Likelihood ("naive Bayes estimator")
//factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
//"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Linear discriminant (same as Fisher discriminant)
//factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
//factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=60:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
// Boosted Decision Trees
// Gradient Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDTG",
//"!H:!V:NTrees=1000:MinNodeSize=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:nCuts=20:MaxDepth=2" );
// Adaptive Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDT1000",
// "!H:!V:NTrees=1000:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=1000:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.2:SeparationType=GiniIndex:nCuts=20" );
// Bagging
//factory->BookMethod( TMVA::Types::kBDT, "BDTB",
// "!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
// Decorrelation + Adaptive Boost
//factory->BookMethod( TMVA::Types::kBDT, "BDTD",
// "!H:!V:NTrees=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
// Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
//factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
// "!H:!V:NTrees=50:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
output_tmva->Close();
std::cout << "==> Wrote root file: " << output_tmva->GetName() << std::endl
<< "==> TMVAClassification is done!" << std::endl
<< std::endl
<< "==> To view the results, launch the GUI: \"root -l ./TMVAGui.C\"" << std::endl
<< std::endl;
// Clean up
delete factory;
return 0;
}//main
////////////////////////////////////////////////////////////////////////////////
/// 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 eventsToTrain = "0", const TString & region = "barrel", const TString index = "", TString myMethodList = "BDT")
{
std::cout << "running classification for " << region << " for " << myMethodList << std::endl;
if( region != "barrel" && region != "endcaps" ) {
std::cout << "Error, region can only be barrel or endcaps. Selected region was: " << region << std::endl;
exit(1);
}
if( index != "" && index != "0" && index != "1" && index != "2" ) {
std::cout << "Error, index can only be \"\", \"0\", \"1\" or \"2\". Selected index was: " << index << std::endl;
exit(1);
}
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
std::exit(2);
}
Use[regMethod] = 1;
}
}
// Input and output file names
TString fnameTrainS = "BsMC12_barrel_preselection";
TString fnameTrainB = "Barrel_preselection";
TString fnameTestS = "BsMC12_barrel_preselection";
TString fnameTestB = "Barrel_preselection";
TString outputFileName = "TMVA_barrel";
TString weightDirName = "barrel";
if( region == "endcaps" ) {
fnameTrainS = "BsMC12_endcaps_preselection";
fnameTrainB = "Endcaps_preselection";
fnameTestS = "BsMC12_endcaps_preselection";
fnameTestB = "Endcaps_preselection";
outputFileName = "TMVA_endcaps";
weightDirName = "endcaps";
}
if( index != "" ) {
fnameTrainS += "_"+index;
fnameTrainB += "_"+index;
TString indexTest = "";
// The test index is the train index +1 (2+1 -> 0)
if( index == "0" ) indexTest = "1";
else if( index == "1" ) indexTest = "2";
else if( index == "2" ) indexTest = "0";
fnameTestS += "_"+indexTest;
fnameTestB += "_"+indexTest;
outputFileName += "_"+index;
weightDirName += index;
}
fnameTrainS = rootDir + fnameTrainS + ".root";
fnameTrainB = rootDir + fnameTrainB + ".root";
fnameTestS = rootDir + fnameTestS + ".root";
fnameTestB = rootDir + fnameTestB + ".root";
outputFileName = rootDir + outputFileName + ".root";
weightDirName = weightsDir + weightDirName + "Weights";
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName(outputFileName);
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// (TMVA::gConfig().GetIONames()).fWeightFileDir = outputFileName;
(TMVA::gConfig().GetIONames()).fWeightFileDir = weightDirName;
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
bool useNewMuonID = false;
factory->AddVariable( "fls3d", "fls3d", "", 'F' );
factory->AddVariable( "alpha", "alpha", "", 'F' );
factory->AddVariable( "pvips", "pvips", "", 'F' );
factory->AddVariable( "iso", "iso", "", 'F' );
factory->AddVariable( "m1iso", "m1iso", "", 'F' );
factory->AddVariable( "m2iso", "m2iso", "", 'F' );
factory->AddVariable( "chi2dof", "chi2/dof", "", 'F' );
if( region == "barrel" ) {
factory->AddVariable( "eta", "eta", "", 'F' );
factory->AddVariable( "maxdoca", "maxdoca", "cm", 'F' );
}
else {
factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
factory->AddVariable( "pvip", "pvip", "cm", 'F' );
}
factory->AddVariable( "docatrk", "docatrk", "cm", 'F' );
// factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
// factory->AddVariable( "closetrk", "closetrk", "", 'I' );
// factory->AddVariable( "y", "y", "", 'F' );
// factory->AddVariable( "l3d", "l3d", "cm", 'F' );
// factory->AddVariable( "cosAlphaXY", "cosAlphaXY", "", 'F' );
// factory->AddVariable( "mu1_dxy", "mu1_dxy", "cm", 'F' );
// factory->AddVariable( "mu2_dxy", "mu2_dxy", "cm", 'F' );
if( useNewMuonID ) {
// New Muon-id
factory->AddVariable( "mu1_MVAMuonID", "mu1_MVAMuonID", "", 'F');
factory->AddVariable( "mu2_MVAMuonID", "mu2_MVAMuonID", "", 'F');
}
// Extra variables
// factory->AddVariable( "mu1_pt", "mu1_pt", "GeV/c", 'F' );
// factory->AddVariable( "mu2_pt", "mu2_pt", "GeV/c", 'F' );
// factory->AddVariable( "pvw8", "pvw8", "", 'F' );
// factory->AddVariable( "cosAlpha3D", "cosAlpha3D", "", 'F' );
// factory->AddVariable( "countTksOfPV", "countTksOfPV", "", 'I' );
// factory->AddVariable( "ctauErrPV", "ctauErrPV", "", 'F' );
// factory->AddVariable( "ctauPV", "ctauPV", "", 'F' );
// factory->AddVariable( "dcaxy", "dcaxy", "", 'F' );
// factory->AddVariable( "mu1_glbTrackProb", "mu1_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu1_nChi2", "mu1_nChi2", "", 'F' );
// factory->AddVariable( "mu1_nMuSegs", "mu1_nMuSegs", "", 'F' );
// factory->AddVariable( "mu1_nMuSegsCln", "mu1_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu1_nPixHits", "mu1_nPixHits", "", 'F' );
// factory->AddVariable( "mu1_nTrHits", "mu1_nTrHits", "", 'F' );
// factory->AddVariable( "mu1_segComp", "mu1_segComp", "", 'F' );
// factory->AddVariable( "mu1_trkEHitsOut", "mu1_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu1_trkVHits", "mu1_trkVHits", "", 'F' );
// factory->AddVariable( "mu1_validFrac", "mu1_validFrac", "", 'F' );
// factory->AddVariable( "mu1_chi2LocMom", "mu1_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu1_chi2LocPos", "mu1_chi2LocPos", "", 'F' );
// factory->AddVariable( "mu2_glbTrackProb", "mu2_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu2_nChi2", "mu2_nChi2", "", 'F' );
// factory->AddVariable( "mu2_nMuSegs", "mu2_nMuSegs", "", 'F' );
// factory->AddVariable( "mu2_nMuSegsCln", "mu2_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu2_nPixHits", "mu2_nPixHits", "", 'F' );
// factory->AddVariable( "mu2_nTrHits", "mu2_nTrHits", "", 'F' );
// factory->AddVariable( "mu2_segComp", "mu2_segComp", "", 'F' );
// factory->AddVariable( "mu2_trkEHitsOut", "mu2_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu2_trkVHits", "mu2_trkVHits", "", 'F' );
// factory->AddVariable( "mu2_validFrac", "mu2_validFrac", "", 'F' );
// factory->AddVariable( "mu2_chi2LocMom", "mu2_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu2_chi2LocPos", "mu2_chi2LocPos", "", 'F' );
// factory->AddVariable( "l3d := ctauPV*pt/mass", "l3d", "cm", 'F' );
// factory->AddVariable( "l3dSig := ctauPV/ctauErrPV", "l3dSig", "", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := mass*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := mass*3", "Spectator 2", "units", 'F' );
factory->AddSpectator( "mass", "mass", "GeV/c^{2}", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
if (gSystem->AccessPathName( fnameTrainS )) { // file does not exist in local directory
std::cout << "Did not access " << fnameTrainS << " exiting." << std::endl;
std::exit(4);
}
//gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *inputTrainS = TFile::Open( fnameTrainS );
TFile *inputTrainB = TFile::Open( fnameTrainB );
TFile *inputTestS = TFile::Open( fnameTestS );
TFile *inputTestB = TFile::Open( fnameTestB );
// --- Register the training and test trees
TTree *signalTrainTree = (TTree*)inputTrainS->Get("probe_tree");
TTree *backgroundTrainTree = (TTree*)inputTrainB->Get("probe_tree");
TTree *signalTestTree = (TTree*)inputTestS->Get("probe_tree");
TTree *backgroundTestTree = (TTree*)inputTestB->Get("probe_tree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalTrainWeight = 1.0;
Double_t backgroundTrainWeight = 1.0;
Double_t signalTestWeight = 1.0;
Double_t backgroundTestWeight = 1.0;
// Decide if using the split and mixing or the full trees
if( fnameTrainS == fnameTestS ) {
if( fnameTrainB != fnameTestB ) {
std::cout << "This macro cannot handle cases where the same signal sample is used for training and testing, but different background samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << std::endl;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signalTrainTree, signalTrainWeight );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight );
}
else {
if( fnameTrainB == fnameTestB ) {
std::cout << "This macro cannot handle cases where the same background sample is used for training and testing, but different signal samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << " for training and" << std::endl;
std::cout << "--- input file: " << inputTestS->GetName() << std::endl;
std::cout << "--- and file: " << inputTestB->GetName() << " for testing." << std::endl;
// To give different trees for training and testing, do as follows:
factory->AddSignalTree( signalTrainTree, signalTrainWeight, "Training" );
factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight, "Training" );
factory->AddBackgroundTree( backgroundTestTree, backgroundTestWeight, "Test" );
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal="+eventsToTrain+":nTrain_Background="+eventsToTrain+":SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=3000:nTrain_Background=3000:nTest_Signal=3000:nTest_Background=3000:SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+8:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=800:nEventsMin=50:MaxDepth=2:BoostType=AdaBoost:AdaBoostBeta=1:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:NNodesMax=5" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
std::cout << "Training all methods" << std::endl;
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
std::cout << "Testing all methods" << std::endl;
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
std::cout << "Evaluating all methods" << std::endl;
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void 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";
}
void TMVAMulticlass(){
TString outfileName = "TMVAMulticlass.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=multiclass" );
factory->AddVariable( "var0", 'F' );
factory->AddVariable( "var1", 'F' );
TFile *input(0);
TString fname = "./data.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find data.root in the local directory
std::cout << "--- TMVAMulticlass : Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
else {
gROOT->LoadMacro( "./createData.C");
create_multiclassdata(20000);
cout << " created data.root for tests of the multiclass features"<<endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
TTree *tree = (TTree*)input->Get("TreeR");
gROOT->cd( outfileName+TString(":/") );
factory->AddTree ( tree, "Signal1", 1. , "cls==0" );
factory->AddTree ( tree, "Signal2", 1. , "cls==1" );
factory->AddTree ( tree, "Background", 1., "cls==2" );
factory->PrepareTrainingAndTestTree( "", "SplitMode=Random:NormMode=NumEvents:!V" );
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::kMLP, "MLP", "!H:!V:NeuronType=tanh:VarTransform=N:NCycles=100:HiddenLayers=N+5,3:TestRate=5"); // testing vartransforms
factory->BookMethod( TMVA::Types::kMLP, "MLP2", "!H:!V:NeuronType=tanh:NCycles=100:HiddenLayers=N+5,3:TestRate=5");
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x0*x1:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName MVAconfigFileName" << std::endl ;
return 1;
}
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
double LUMI = gConfigParser -> readDoubleOption("Options::Lumi");
std::vector<std::string> SignalName;
SignalName = gConfigParser -> readStringListOption("Options::SignalName");
for (int iSignalSample=0; iSignalSample<SignalName.size(); iSignalSample++) {
std::cout << " Signal[" << iSignalSample << "] = " << SignalName.at(iSignalSample) << std::endl;
}
std::string nameWeight = "1";
try {
nameWeight = gConfigParser -> readStringOption("Options::nameWeight");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::nameWeight " << nameWeight << std::endl;
TTree *treeJetLepVect[200];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++) {
xsection[iSample] = atof(xsectionName[iSample]);
}
for (int iSample=0; iSample<numberOfSamples; iSample++) {
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
TFile* f = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) f->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
double XSection;
XSection = xsection[iSample];
Normalization[iSample] = XSection * LUMI / 1000.;
}
//==== cut
std::string CutFile = gConfigParser -> readStringOption("Selections::CutFile");
std::vector<std::string> vCut;
std::cout << " nCuts = " << ReadFileCut(CutFile, vCut) << std::endl;
std::string Cut;
if (vCut.size() != 0) {
Cut = vCut.at(0);
}
else {
Cut = "1";
}
//==== HiggsMass
std::string HiggsMass = gConfigParser -> readStringOption("Options::HiggsMass");
//==== list of methods
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
TString myMethodList;
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
if (iMVA == 0) myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
else myMethodList = Form ("%s,%s",myMethodList.Data(),vectorMyMethodList.at(iMVA).c_str());
}
//==== output
TString outfileName = gConfigParser -> readStringOption("Output::outFileName");
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 1;
Use["BDTG"] = 1;
Use["FDA_GA"] = 0;
Use["PDEFoam"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return 0;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "AnalysisType=multiclass:!V:!Silent:!V:Transformations=I;D" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=multiclass" );
factory->AddVariable( "jetpt1" , 'F');
factory->AddVariable( "jetpt2" , 'F');
factory->AddVariable( "mjj" , 'F');
factory->AddVariable( "detajj" , 'F');
factory->AddVariable( "dphilljetjet" , 'F');
factory->AddVariable( "pt1" , 'F');
factory->AddVariable( "pt2" , 'F');
factory->AddVariable( "mll" , 'F');
factory->AddVariable( "dphill" , 'F');
factory->AddVariable( "mth" , 'F');
factory->AddVariable( "dphillmet" , 'F');
factory->AddVariable( "mpmet" , 'F');
factory->AddSpectator( "channel" , 'F');
for (int iSample=0; iSample<numberOfSamples; iSample++) {
int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
if (numEnt != 0) {
if (iSample == 0) factory->AddTree( treeJetLepVect[iSample], "Signal", Normalization[iSample] );
else if (iSample == 1) factory->AddTree( treeJetLepVect[iSample], "Background", Normalization[iSample] );
else factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] , nameWeight.c_str());
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]));
}
}
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
//
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// // factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
std::cerr << " AAAAAAAAAAAAAAAAAAAAAAAAAAAAA " << std::endl;
TCut mycuts = Cut.c_str();
// factory->SetWeightExpression( nameWeight.c_str() );
// factory->SetBackgroundWeightExpression( nameWeight.c_str() );
// factory->SetSignalWeightExpression ( nameWeight.c_str() );
std::cerr << " BBBBBBBBBBBBBBBBBBBBBBBBBBBBB " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts ,"SplitMode=Random:NormMode=None:!V");
// factory->PrepareTrainingAndTestTree( "" ,"SplitMode=Random:NormMode=None:!V");
std::cerr << " CCCCCCCCCCCCCCCCCCCCCCCCCCCCC " << std::endl;
// gradient boosted decision trees
// if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
// neural network
if (Use["MLP"]) factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:NCycles=1000:HiddenLayers=N+5,5:TestRate=5:EstimatorType=MSE");
// functional discriminant with GA minimizer
if (Use["FDA_GA"]) factory->BookMethod( TMVA::Types::kFDA, "FDA_GA", "H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
// PDE-Foam approach
if (Use["PDEFoam"]) factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam", "!H:!V:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
//==== Optimize parameters in MVA methods
// factory->OptimizeAllMethods();
// factory->OptimizeAllMethods("ROCIntegral","Scan");
//==== Train MVAs using the set of training events ====
factory->TrainAllMethods();
//==== Evaluate all MVAs using the set of test events ====
factory->TestAllMethods();
//==== Evaluate and compare performance of all configured MVAs ====
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAnalysis is done!" << std::endl;
delete factory;
//==== change position of weights file
std::string toDo;
toDo = "rm -r Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
toDo = "mv weights Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "" )
{
// TString curDynamicPath( gSystem->GetDynamicPath() );
// gSystem->SetDynamicPath( "/usr/local/bin/root/bin:" + curDynamicPath );
// TString curIncludePath(gSystem->GetIncludePath());
// gSystem->SetIncludePath( " -I /usr/local/bin/root/include " + curIncludePath );
// // load TMVA shared library created in local release: for MAC OSX
// if (TString(gSystem->GetBuildArch()).Contains("macosx") ) gSystem->Load( "libTMVA.so" );
// gSystem->Load( "libTMVA" );
// TMVA::Tools::Instance();
// // welcome the user
// TMVA::gTools().TMVAWelcomeMessage();
// TMVAGlob::SetTMVAStyle();
// // this loads the library
// TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 1;
// Use["Likelihood"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable("deltaEta := deta", 'F');
factory->AddVariable("deltaPhi := dphi", 'F');
factory->AddVariable("sigmaIetaIeta := sieie", 'F');
factory->AddVariable("HoverE := hoe", 'F');
factory->AddVariable("trackIso := trackiso", 'F');
factory->AddVariable("ecalIso := ecaliso", 'F');
factory->AddVariable("hcalIso := hcaliso", 'F');
//factory->AddVariable("nMissingHits := misshits", 'I');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "et", 'F' );
factory->AddSpectator( "eta", 'F' );
factory->AddSpectator( "phi", 'F' );
// read training and test data
TFile *input = TFile::Open( "SigElectrons.root" );
TFile *inputB = TFile::Open( "BkgElectrons.root" );
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree *signal = (TTree*)input->Get("ntuple");
TTree *background = (TTree*)inputB->Get("ntuple");
factory->AddSignalTree ( signal, 1.0 );
factory->AddBackgroundTree( background, 1.0 );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
//factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/correlations.C");
gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/variables.C");
}
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
bool batchMode(false);
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "var1", 'F' );
factory->AddVariable( "var2", 'F' );
factory->AddVariable( "var3", 'F' );
factory->AddVariable( "var4", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "eta" );
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname( "" );
if (UseOffsetMethod) fname = "../execs/data/toy_sigbkg_categ_offset.root";
else fname = "../execs/data/toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
/// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
/// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Fisher discriminant
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Categorised classifier
TMVA::MethodCategory* mcat = 0;
// the variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// the Fisher
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kFisher,"Category_Fisher_1","!H:!V:Fisher");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher,"Category_Fisher_2","!H:!V:Fisher");
// the Likelihood
TMVA::MethodBase* liCat = factory->BookMethod( TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVA_stop( TString signal_name = "T2tt", int train_region = 1, float x_parameter = 0.25)
{
// 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 TMVA_stop.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVA_stop.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)
//-----------------------------------------------------
// define event selection (store in TCut sel)
//-----------------------------------------------------
TCut njets4("mini_njets>=4");
TCut met100("mini_met>=100");
TCut mt120("mini_mt>=120");
TCut nb1("mini_nb>=1");
TCut isotrk("mini_passisotrk==1");
TCut lep_pt30("mini_nlep>=1 && mini_lep1pt>30.0");
TCut sig("mini_sig==1");
TCut sel0 = njets4 + met100 + mt120 + nb1 + isotrk + lep_pt30 + sig;
cout << "Using selection : " << sel0.GetTitle() << endl;
cout << "Doing signal point : " << train_region << endl;
//-----------------------------------------------------
// choose which variables to include in MVA training
//-----------------------------------------------------
std::map<std::string,int> mvaVar;
mvaVar[ "met" ] = 1;
mvaVar[ "lep1pt" ] = 0;
mvaVar[ "mt2w" ] = 1;
mvaVar[ "htratiom" ] = 1;
mvaVar[ "chi2" ] = 1;
mvaVar[ "dphimjmin" ] = 1;
mvaVar[ "pt_b" ] = 0;
mvaVar[ "nb" ] = 0;
mvaVar[ "pt_J1" ] = 0;
mvaVar[ "pt_J2" ] = 0;
mvaVar[ "rand" ] = 0;
mvaVar[ "mt" ] = 0;
mvaVar[ "mt2bl" ] = 0;
mvaVar[ "mt2b" ] = 0;
mvaVar[ "lep1eta" ] = 0;
mvaVar[ "thrjetlm" ] = 0;
mvaVar[ "apljetlm" ] = 0;
mvaVar[ "sphjetlm" ] = 0;
mvaVar[ "cirjetlm" ] = 0;
mvaVar[ "chi2min" ] = 0;
mvaVar[ "chi2min_mt2b" ] = 0;
mvaVar[ "chi2min_mt2bl" ] = 0;
mvaVar[ "chi2min_mt2w" ] = 0;
mvaVar[ "mt2bmin" ] = 0;
mvaVar[ "mt2blmin" ] = 0;
mvaVar[ "mt2wmin_chi2" ] = 0;
mvaVar[ "mt2bmin_chi2" ] = 0;
mvaVar[ "mt2blmin_chi2" ] = 0;
mvaVar[ "mt2wmin_chi2prob" ] = 0;
mvaVar[ "mt2bmin_chi2prob" ] = 0;
mvaVar[ "mt2blmin_chi2prob" ] = 0;
mvaVar[ "htratiol" ] = 0;
mvaVar[ "dphimj1" ] = 0;
mvaVar[ "dphimj2" ] = 0;
mvaVar[ "metsig" ] = 0;
//---------------------------------
//choose bkg samples to include
//---------------------------------
cout << "Background trees: " << endl;
int n_backgrounds = 8;
TString backgrounds[] = {"ttdl_powheg", "ttsl_powheg", "w1to4jets", "tW_lep", "triboson", "diboson", "ttV", "DY1to4Jtot" };
TString bkgPath = "/nfs-3/userdata/stop/Train/V00-02-18__V00-03-00_4jetsMET100_bkg/";
TChain* chBackground = new TChain("t");
for (int i = 0; i < n_backgrounds; i++) {
TString backgroundChain = bkgPath + "/" + backgrounds[i] + ".root";
cout << " " << backgroundChain << endl;
chBackground ->Add(backgroundChain );
}
//---------------------------------
//choose signal sample to include
//---------------------------------
cout << "Signal trees: " << endl;
TString s_train_region = "";
s_train_region += train_region;
TString s_x_parameter = "";
s_x_parameter = Form("%.2f",x_parameter);
TString signalPath = "/nfs-3/userdata/stop/Train/";
TString signalVersion = "V00-02-18__V00-03-00_4jetsMET100_";
TChain *chSignal = new TChain("t");
TString base_name = signalPath + "/" + signalVersion + signal_name + "/" + signal_name + "_" + s_train_region;
if (signal_name == "T2bw") base_name = base_name + "_" + s_x_parameter;
TString signalChain = base_name + ".root" ;
cout << " " << signalChain << endl;
chSignal->Add(signalChain);
//-----------------------------------------------------
// choose backgrounds to include for multiple outputs
//-----------------------------------------------------
// bool doMultipleOutputs = false;
// TChain *chww = new TChain("Events");
// chww->Add(Form("%s/WWTo2L2Nu_PU_testFinal_baby.root",babyPath));
// chww->Add(Form("%s/GluGluToWWTo4L_PU_testFinal_baby.root",babyPath));
// TChain *chwjets = new TChain("Events");
// chwjets->Add(Form("%s/WJetsToLNu_PU_testFinal_baby.root",babyPath));
// TChain *chtt = new TChain("Events");
// chtt->Add(Form("%s/TTJets_PU_testFinal_baby.root",babyPath));
// std::map<std::string,int> includeBkg;
// includeBkg["ww"] = 1;
// includeBkg["wjets"] = 0;
// includeBkg["tt"] = 0;
//---------------------------------------------------------------
// 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["BDT1"] = 0; // 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;
//
// --- multi-output MVA's
Use["multi_BDTG"] = 0;
Use["multi_MLP"] = 0;
Use["multi_FDA_GA"] = 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_" + signal_name + "_" + s_train_region;
if (signal_name == "T2bw") outfileName = outfileName +"_" + s_x_parameter;
outfileName += ".root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TString classification_name = "classification_" + signal_name + "_" + s_train_region;
if (signal_name == "T2bw") classification_name = classification_name +"_" + s_x_parameter;
/*
TString multioutfileName( "TMVA_HWW_multi.root" );
TFile* multioutputFile;
if( doMultipleOutputs )
multioutputFile = TFile::Open( multioutfileName, "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( classification_name, outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
/*
TMVA::Factory *multifactory;
if( doMultipleOutputs )
multifactory= new TMVA::Factory( "TMVAMulticlass", multioutputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=multiclass" );
*/
// 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' );
//--------------------------------------------------------
// choose which variables to include in training
//--------------------------------------------------------
if( mvaVar[ "met" ] == 1 ) factory->AddVariable( "mini_met" , "E_{T}^{miss}" , "GeV", 'F' );
if( mvaVar[ "mt" ] == 1 ) factory->AddVariable( "mini_mt" , "M_{T}" , "GeV", 'F' );
if( mvaVar[ "mt2w" ] == 1 ) factory->AddVariable( "mini_mt2w" , "MT2W" , "GeV", 'F' );
if( mvaVar[ "mt2bl" ] == 1 ) factory->AddVariable( "mini_mt2bl" , "MT2bl" , "GeV", 'F' );
if( mvaVar[ "mt2b" ] == 1 ) factory->AddVariable( "mini_mt2b" , "MT2b" , "GeV", 'F' );
if( mvaVar[ "chi2" ] == 1 ) factory->AddVariable( "mini_chi2" , "chi2" , "" , 'F' );
if( mvaVar[ "lep1pt" ] == 1 ) factory->AddVariable( "mini_lep1pt" , "lepton pt" , "" , 'F' );
if( mvaVar[ "lep1eta" ] == 1 ) factory->AddVariable( "mini_lep1eta" , "lepton eta" , "" , 'F' );
if( mvaVar[ "thrjetlm" ] == 1 ) factory->AddVariable( "mini_thrjetlm" , "thrust" , "" , 'F' );
if( mvaVar[ "apljetlm" ] == 1 ) factory->AddVariable( "mini_apljetlm" , "aplanarity" , "" , 'F' );
if( mvaVar[ "sphjetlm" ] == 1 ) factory->AddVariable( "mini_sphjetlm" , "sphericity" , "" , 'F' );
if( mvaVar[ "cirjetlm" ] == 1 ) factory->AddVariable( "mini_cirjetlm" , "circularity" , "" , 'F' );
if( mvaVar[ "chi2min" ] == 1 ) factory->AddVariable( "mini_min(chi2min,100)" , "#chi^{2}_{min}" , "" , 'F' );
if( mvaVar[ "chi2minprob" ] == 1 ) factory->AddVariable( "mini_chi2minprob" , "Prob(#chi^{2}_{min})" , "" , 'F' );
if( mvaVar[ "chi2min_mt2b" ] == 1 ) factory->AddVariable( "mini_chi2min_mt2b" , "MT2b(#chi^{2}_{min})" , "" , 'F' );
if( mvaVar[ "chi2min_mt2bl" ] == 1 ) factory->AddVariable( "mini_chi2min_mt2bl" , "MT2bl(#chi^{2}_{min})" , "" , 'F' );
if( mvaVar[ "chi2min_mt2w" ] == 1 ) factory->AddVariable( "mini_chi2min_mt2w" , "MT2W(#chi^{2}_{min})" , "" , 'F' );
if( mvaVar[ "mt2bmin" ] == 1 ) factory->AddVariable( "mini_mt2bmin" , "MT2b_{min}" , "" , 'F' );
if( mvaVar[ "mt2blmin" ] == 1 ) factory->AddVariable( "mini_mt2blmin" , "MT2bl_{min}" , "" , 'F' );
if( mvaVar[ "mt2wmin" ] == 1 ) factory->AddVariable( "mini_mt2wmin" , "MT2W_{min}" , "" , 'F' );
if( mvaVar[ "mt2bmin_chi2" ] == 1 ) factory->AddVariable( "min(mt2bmin_chi2,100)" , "#chi^{2}(MT2b_{min})" , "" , 'F' );
if( mvaVar[ "mt2blmin_chi2" ] == 1 ) factory->AddVariable( "min(mt2blmin_chi2,100)" , "#chi^{2}(MT2bl_{min})" , "" , 'F' );
if( mvaVar[ "mt2wmin_chi2" ] == 1 ) factory->AddVariable( "min(mt2wmin_chi2,100)" , "#chi^{2}(MT2W_{min})" , "" , 'F' );
if( mvaVar[ "mt2bmin_chi2prob" ] == 1 ) factory->AddVariable( "mt2bmin_chi2prob" , "Prob(#chi^{2}(MT2b_{min}))" , "" , 'F' );
if( mvaVar[ "mt2blmin_chi2prob" ] == 1 ) factory->AddVariable( "mt2blmin_chi2prob" , "Prob(#chi^{2}(MT2bl_{min}))" , "" , 'F' );
if( mvaVar[ "mt2wmin_chi2prob" ] == 1 ) factory->AddVariable( "mt2wmin_chi2prob" , "Prob(#chi^{2}(MT2W_{min}))" , "" , 'F' );
if( mvaVar[ "htratiol" ] == 1 ) factory->AddVariable( "mini_htssl/(mini_htosl+mini_htssl)" , "H_{T}^{SSL}/H_{T}" , "" , 'F' );
if( mvaVar[ "htratiom" ] == 1 ) factory->AddVariable( "mini_htssm/(mini_htosm+mini_htssm)" , "H_{T}^{SSM}/H_{T}" , "" , 'F' );
if( mvaVar[ "dphimj1" ] == 1 ) factory->AddVariable( "mini_dphimj1" , "#Delta#phi(j1,E_{T}^{miss})", "" , 'F' );
if( mvaVar[ "dphimj2" ] == 1 ) factory->AddVariable( "mini_dphimj2" , "#Delta#phi(j2,E_{T}^{miss})", "" , 'F' );
if( mvaVar[ "dphimjmin" ] == 1 ) factory->AddVariable( "mini_dphimjmin" , "min(#Delta#phi(j_{1,2},E_{T}^{miss}))", "" , 'F' );
if( mvaVar[ "rand" ] == 1 ) factory->AddVariable( "mini_rand" , "random(0,1)" , "" , 'F' );
if( mvaVar[ "metsig" ] == 1 ) factory->AddVariable( "met/sqrt(htosl+htssl)" , "E_{T}^{miss}/#sqrt{H_{T}}" , "#sqrt{GeV}" , 'F' )
;
if( mvaVar[ "pt_b" ] == 1 ) factory->AddVariable( "mini_pt_b" , "P_T(b) GeV" , 'F' );
if( mvaVar[ "nb" ] == 1 ) factory->AddVariable( "mini_nb" , "P_T(b) GeV" , 'F' );
if( mvaVar[ "pt_J1" ] == 1 ) factory->AddVariable( "pt_J1" , "P_T(J1) GeV" , 'F' );
if( mvaVar[ "pt_J2" ] == 1 ) factory->AddVariable( "pt_J2" , "P_T(J2) GeV" , 'F' );
/*
if( doMultipleOutputs ){
if (mvaVar["lephard_pt"]) multifactory->AddVariable( "lephard_pt", "1st lepton pt", "GeV", 'F' );
if (mvaVar["lepsoft_pt"]) multifactory->AddVariable( "lepsoft_pt", "2nd lepton pt", "GeV", 'F' );
if (mvaVar["dil_dphi"]) multifactory->AddVariable( "dil_dphi", "dphi(ll)", "", 'F' );
if (mvaVar["dil_mass"]) multifactory->AddVariable( "dil_mass", "M(ll)", "GeV", 'F' );
if (mvaVar["event_type"]) multifactory->AddVariable( "event_type", "Dil Flavor Type", "", 'F' );
if (mvaVar["met_projpt"]) multifactory->AddVariable( "met_projpt", "Proj. MET", "GeV", 'F' );
if (mvaVar["met_pt"]) multifactory->AddVariable( "met_pt", "MET", "GeV", 'F' );
if (mvaVar["mt_lephardmet"]) multifactory->AddVariable( "mt_lephardmet", "MT(lep1,MET)", "GeV", 'F' );
if (mvaVar["mt_lepsoftmet"]) multifactory->AddVariable( "mt_lepsoftmet", "MT(lep2,MET)", "GeV", 'F' );
if (mvaVar["mthiggs"]) multifactory->AddVariable( "mthiggs", "MT(Higgs)", "GeV", 'F' );
if (mvaVar["dphi_lephardmet"]) multifactory->AddVariable( "dphi_lephardmet", "dphi(lep1,MET)", "GeV", 'F' );
if (mvaVar["dphi_lepsoftmet"]) multifactory->AddVariable( "dphi_lepsoftmet", "dphi(lep2,MET)", "GeV", 'F' );
if (mvaVar["lepsoft_fbrem"]) multifactory->AddVariable( "lepsoft_fbrem", "2nd lepton f_{brem}", "", 'F' );
if (mvaVar["lepsoft_eOverPIn"]) multifactory->AddVariable( "lepsoft_eOverPIn", "2nd lepton E/p", "", 'F' );
if (mvaVar["lepsoft_qdphi"]) multifactory->AddVariable( "lepsoft_q * lepsoft_dPhiIn", "2nd lepton q#times#Delta#phi", "", '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' );
// TTree* signalTrainingTree = (TTree*) chSignalTrain;
// TTree* signalTestTree = (TTree*) chSignalTest;
//
// TTree* bkgTrainingTree = (TTree*) chBkgTrain;
// TTree* bkgTestTree = (TTree*) chBkgTest;
// std::cout << "--- TMVAClassification : Using bkg input files: -------------------" << std::endl;
//
// TObjArray *listOfBkgFiles = chbackground->GetListOfFiles();
// TIter bkgFileIter(listOfBkgFiles);
// TChainElement* currentBkgFile = 0;
//
// while((currentBkgFile = (TChainElement*)bkgFileIter.Next())) {
// std::cout << currentBkgFile->GetTitle() << std::endl;
// }
//
// std::cout << "--- TMVAClassification : Using sig input files: -------------------" << std::endl;
//
// TObjArray *listOfSigFiles = chsignal->GetListOfFiles();
// TIter sigFileIter(listOfSigFiles);
// TChainElement* currentSigFile = 0;
//
// while((currentSigFile = (TChainElement*)sigFileIter.Next())) {
// std::cout << currentSigFile->GetTitle() << std::endl;
// }
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
// factory->AddSignalTree ( chSignal, signalWeight );
// factory->AddBackgroundTree( chBackground, backgroundWeight );
factory->AddTree(chSignal, "Signal", signalWeight, sel0+"mini_rand < 0.5", "train");
factory->AddTree(chSignal, "Signal", signalWeight, sel0+"mini_rand >= 0.5", "test");
factory->AddTree(chBackground, "Background", backgroundWeight, sel0+"mini_rand < 0.5", "train");
factory->AddTree(chBackground, "Background", backgroundWeight, sel0+"mini_rand >= 0.5", "test");
// To give different trees for training and testing, do as follows:
//factory->AddSignalTree( signalTrainingTree, signalWeight, "Training" );
//factory->AddSignalTree( signalTestTree, signalWeight, "Test" );
//factory->AddBackgroundTree( bkgTrainingTree, backgroundWeight, "Training" );
//factory->AddBackgroundTree( bkgTestTree, backgroundWeight, "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)
factory->SetSignalWeightExpression ("mini_weight");
factory->SetBackgroundWeightExpression("mini_weight");
/*
if( doMultipleOutputs ){
multifactory->AddTree(signal,"Signal");
multifactory->SetSignalWeightExpression ("event_scale1fb");
multifactory->SetBackgroundWeightExpression("event_scale1fb");
multifactory->SetWeightExpression("event_scale1fb");
if( includeBkg["ww"] ){
TTree* ww = (TTree*) chww;
multifactory->AddTree(ww,"WW");
cout << "Added WW to multi-MVA" << endl;
}
if( includeBkg["wjets"] ){
TTree* wjets = (TTree*) chwjets;
multifactory->AddTree(wjets,"WJets");
cout << "Added W+jets to multi-MVA" << endl;
}
if( includeBkg["tt"] ){
TTree* tt = (TTree*) chtt;
multifactory->AddTree(tt,"tt");
cout << "Added ttbar multi-MVA" << endl;
}
}
*/
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = sel0; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = sel0; // 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" );
//Use random splitting
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=100000:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
factory->PrepareTrainingAndTestTree( "", "",
"nTrain_Signal=0:nTrain_Background=0:NormMode=None:!V" );
// if( doMultipleOutputs ){
// multifactory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// }
//Use alternate splitting
//(this is preferable since its easier to track which events were used for training, but the job crashes! need to fix this...)
//factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Alternate: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=0.0333: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" );
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:VarTransform=N:NCycles=1000:HiddenLayers=N+N:TestRate=5:!UseRegulator:LearningRate=0.2:DecayRate=0.001:BPMode=batch:BatchSize=500");
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["BDT1"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT1",
"!H:!V:NTrees=200:nEventsMin=300:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=4: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" );
// if( doMultipleOutputs ){
// if (Use["multi_BDTG"]) // gradient boosted decision trees
// multifactory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
// if (Use["multi_MLP"]) // neural network
// multifactory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:NCycles=1000:HiddenLayers=N+5,5:TestRate=5:EstimatorType=MSE");
// if (Use["multi_FDA_GA"]) // functional discriminant with GA minimizer
// multifactory->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" );
// }
// 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();
// if( doMultipleOutputs ){
// // Train nulti-MVAs using the set of training events
// multifactory->TrainAllMethods();
// // ---- Evaluate all multi-MVAs using the set of test events
// multifactory->TestAllMethods();
// // ----- Evaluate and compare performance of all configured multi-MVAs
// multifactory->EvaluateAllMethods();
// }
// --------------------------------------------------------------
// Save the output
outputFile->Close();
//if( doMultipleOutputs ) multioutputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
//TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
//gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
//gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 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 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 BJetRegression( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVARegression.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 1;
Use["KNN"] = 1;
//
// --- Linear Discriminant Analysis
Use["LD"] = 1;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 1;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0;
Use["BDTG"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TString outfileName( "TMVAReg_CSVJ1.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// std::string inputVariables[] = {"CSVJ1PtUncorr", "CSVJ1Pt", "CSVJ1Et", "CSVJ1Mt", "CSVJ1ptLeadTrk",
// "CSVJ1Vtx3dL", "CSVJ1Vtx3deL", "CSVJ1vtxMass", "CSVJ1VtxPt",
// "CSVJ1SoftLeptPtRel", "CSVJ1SoftLeptPt",
// "CSVJ1SoftLeptdR" , "CSVJ1Ntot"};
std::string inputVariables[] = {"jetPtUncorr", "jetPt", "jetEt", "jetMt", "jetptLeadTrk",
"jetVtx3dL", "jetVtx3deL", "jetvtxMass", "jetVtxPt",
"jetSoftLeptPtRel", "jetSoftLeptPt",
"jetSoftLeptdR" , "jetNtot", "jetJECUnc"}; //
for(int ivar = 0; ivar < 14; ivar++){
factory->AddVariable( inputVariables[ivar], inputVariables[ivar], "units", 'F' );
}
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
// factory->AddTarget( "matchGenJet1Pt" );
factory->AddTarget( "matchGenJetPt" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// Read training and test data (see TMVAClassification for reading ASCII files)
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = "/scratch/zmao/regression/allSample_both_isobTag.root";
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_reg_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
// --- Register the regression tree
TTree *regTree = (TTree*)input->Get("eventTree");
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddRegressionTree( regTree, regWeight );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// factory->SetWeightExpression( "triggerEff", "Regression" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = ""; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=40:NEventsMax=60:VarTransform=None" );
// And the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:MultiTargetRegression=F:TargetSelection=Mpv:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Compress=T:Kernel=None:Nmin=10:VarTransform=None" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// Linear discriminant
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD",
"!H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=MC:SampleSize=100000:Sigma=0.1:VarTransform=D" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options) .. the formula of this example is good for parabolas
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:PopSize=100:Cycles=3:Steps=30:Trim=True:SaveBestGen=1:VarTransform=Norm" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
// Neural network (MLP)
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=20000:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDT"])
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=100:MinNodeSize=1.0%:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
if (Use["BDTG"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=2000::BoostType=Grad:Shrinkage=0.1:UseBaggedBoost:BaggedSampleFraction=0.7:nCuts=200:MaxDepth=3:NNodesMax=15" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVARegGui( outfileName );
}
void mvaDonut(TString Type = "Dl", int iChannel = 1, TString Sample = "Sig") {
TString Channels[] = {"D0","Ds0","Dp","Dsp"};
TString fname = "mva"; if(Sample=="Dss") fname += Sample;
fname += Type; fname += Channels[iChannel-1];
TString outfileName = fname; outfileName += ".root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
int isDss = 0;
if(Sample=="Dss") isDss=1;
TMVA::Factory *factory = new TMVA::Factory( fname, outputFile,
Form("!V:!Silent:%sColor", gROOT->IsBatch()?"!":"") );
TChain c("ntp1");
c.Add("~/releases/ntuplePID50/workdir/AWG82/ntuples/small/Add_R24MVA_RunAll.root");
TString sigCuts[] = {"(MCType==1||MCType==3||MCType==5)", "(MCType==2||MCType==4||MCType==6)",
"(MCType==7||MCType==9||MCType==11)", "(MCType==8||MCType==10||MCType==12)",
"MCType>12"};
TString bkgCuts[2][2] = {{"MCType>6", "(MCType>0&&MCType<7||MCType>12)"},
{"MCType>0&&MCType<13","MCType>0&&MCType<13"}};
TString sigStr = "candLepTru==1&&"; if(isDss) sigStr += "pmisspi0"; else sigStr += "candPMiss";
sigStr += ">0.2&&candType=="; sigStr += iChannel; sigStr += "&&";
if(isDss) sigStr += sigCuts[4]; else sigStr += sigCuts[iChannel-1];
TString bkgStr = "candType=="; bkgStr += iChannel; bkgStr += "&&";
if(isDss) bkgStr += "pmisspi0"; else bkgStr += "candPMiss";
bkgStr += ">0.2&&";
if(Type=="Dl") bkgStr += bkgCuts[isDss][(iChannel-1)/2];
else bkgStr += "MCType==0";
TCut sigCut = "1", bkgCut = "1", mycuts = "", mycutb = "";
sigCut += sigStr; bkgCut += bkgStr;
// --- Base ---
// int nSig = 9, nDpi0 = 10;
// TString sigVari[] = {"candEExtra","candMES","candDmass","candDeltam","candTagChargedMult","candBTagDeltam",
// "candBTagDmass","candDeltaE","candCosT"};
// TString Dpi0Vari[] = {"mpi0","candDmass","dmpi0","eextrapi0","ppi0","e1pi0","candCosT","candDeltam",
// "candMES","candDeltaE"};
// --- NoDmNoMp0 ---
// int nSig = 8, nDpi0 = 9;
// TString sigVari[] = {"candEExtra","candMES","candDmass","candDeltam","candTagChargedMult",
// "candBTagDmass","candDeltaE","candCosT"};
// TString Dpi0Vari[] = {"candDmass","dmpi0","eextrapi0","ppi0","e1pi0","candCosT","candDeltam",
// "candMES","candDeltaE"};
// sigCuts[4] = "MCType>12&&mpi0>.125&&mpi0<.145";
// --- NoMes ---
// int nSig = 8, nDpi0 = 9;
// TString sigVari[] = {"candEExtra","candDmass","candDeltam","candTagChargedMult","candBTagDeltam",
// "candBTagDmass","candDeltaE","candCosT"};
// TString Dpi0Vari[] = {"mpi0","candDmass","dmpi0","eextrapi0","ppi0","e1pi0","candCosT","candDeltam",
// "candDeltaE"};
// --- NoMulYesDm ---
int nSig = 8, nDpi0 = 11;
TString sigVari[] = {"candEExtra","candMES","candDmass","candDeltam","candBTagDeltam",
"candBTagDmass","candDeltaE","candCosT"};
TString Dpi0Vari[] = {"mpi0","candDmass","dmpi0","eextrapi0","ppi0","e1pi0","candCosT","candDeltam",
"candMES","candDeltaE","candBTagDeltam"};
factory->SetInputTrees(&c, sigCut, bkgCut);
if(isDss==0){
for(int vari = 0; vari < nSig; vari++){
if(sigVari[vari]=="candDeltam" && iChannel%2==1) continue;
char variChar = 'F';
if(sigVari[vari]=="candTagChargedMult") variChar = 'I';
factory->AddVariable(sigVari[vari], variChar);
}
} else {
for(int vari = 0; vari < nDpi0; vari++){
if(Dpi0Vari[vari]=="candDeltam" && iChannel%2==1) continue;
factory->AddVariable(Dpi0Vari[vari], 'F');
}
}
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"NSigTest=100:NBkgTest=100:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=500:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=2.5" );
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
gROOT->ProcessLine(".q");
}
//void TMVAClassification( TString myMethodList = "" )
void Example_Eric( 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"] =0;
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;
// ---
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"] = 1; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["CFMlpANN"] =0; // *** missing
Use["TMlpANN"] =0;
// ---
Use["SVM"] =1;
// ---
Use["BDT"] =1;
Use["BDTD"] =0;
Use["BDTG"] =0;
Use["BDTB"] =0;
// ---
Use["RuleFit"] =1;
// ---
Use["Plugin"] =0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = 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_Eric2.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( "Mqq := Mqq", 'F' );
factory->AddVariable( "Pt_qq := Pt_qq", 'F' );
factory->AddVariable( "Eta_qq := Eta_qq", 'F' );
factory->AddVariable( "Charge_qq := Charge_qq", 'F' );
factory->AddVariable( "DPhi_ll := DPhi_ll", 'F' );
factory->AddVariable( "DPt_ll := DPt_ll", 'F' );
//factory->AddVariable( "MinDPhi_lMET := MinDPhi_lMET", 'F' );
//factory->AddVariable( "Aplanarity := aplanarity", 'F' );
//factory->AddVariable( "chargeEta := chargeEta", 'F' );
//factory->AddVariable( "MET := Met", 'F' );
//factory->AddVariable( "MtauJet := MtauJet", 'F' );
//factory->AddVariable( "HT := Ht", 'F' );
//factory->AddVariable( "Chi2 := kinFitChi2", 'F' );
//factory->AddVariable( "DeltaPhiTauMET := DeltaPhiTauMet", 'F' );
//factory->AddVariable( "Mt := Mt", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// read training and test data
if (ReadDataFromAsciiIFormat) {
// load the signal and background event samples from ascii files
// format in file must be:
// var1/F:var2/F:var3/F:var4/F
// 0.04551 0.59923 0.32400 -0.19170
// ...
TString datFileS = "tmva_example_sig.dat";
TString datFileB = "tmva_example_bkg.dat";
factory->SetInputTrees( datFileS, datFileB );
}
else {
//TFile* f0 = new TFile("/opt/sbg/data/data1/cms/lebihan/clean_january_2012_2/CMSSW_4_2_8_patch7/src/MiniTreeAnalysis/NTupleAnalysis/macros/TopTauJets/TMVA_sig_newLumi.root");
//TFile* f1 = new TFile("/opt/sbg/data/data1/cms/lebihan/clean_january_2012_2/CMSSW_4_2_8_patch7/src/MiniTreeAnalysis/NTupleAnalysis/macros/TopTauJets/TMVA_bkg_newLumi.root");
TFile* f0 = TFile::Open("/opt/sbg/data/data1/cms/echabert/ttbarMET/ProdAlexMars13/CMSSW_5_3_2_patch4/src/NTuple/NTupleAnalysis/macros/TTbarMET/backup_outputProof10-04-13_16-00-57/proof_ttW.root");
TFile* f1 = TFile::Open("/opt/sbg/data/data1/cms/echabert/ttbarMET/ProdAlexMars13/CMSSW_5_3_2_patch4/src/NTuple/NTupleAnalysis/macros/TTbarMET/backup_outputProof10-04-13_16-00-57/proof_tt-dilepton.root");
TTree *signal = (TTree*)f0->Get("theTree2");
TTree *background = (TTree*)f1->Get("theTree2");
cout<<"trees: "<<signal<<" "<<background<<endl;
//Double_t backgroundWeight = 1.0;
//Double_t signalWeight = 1.0;
Double_t signalWeight = 0.30*20/185338;
Double_t backgroundWeight = 222.*0.1*20/9982625;
// ====== 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 );
// factory->AddSignalTree ( signal );
//factory->AddBackgroundTree( background );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
//factory->SetBackgroundWeightExpression("weight_BTAG");
//factory->SetSignalWeightExpression("weight*weight_BTAG");
// Apply additional cuts on the signal and background samples (can be different)
// TCut mycuts = "MHt >=0 && MMTauJet >=0 && MM3 >= 0"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
// TCut mycutb = "MHt >=0 && MMTauJet >=0 && MM3 >= 0"; // for example: TCut mycutb = "abs(var1)<0.5";
//TCut mycuts = "Met>=20 "; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
//TCut mycutb = "Met>=20 "; // for example: TCut mycutb = "abs(var1)<0.5";
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=3000:nTrain_Background=5000:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS" );
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethodsForClassification();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(){
TMVA::Tools::Instance();
std::cout<<"Hello world"<<std::endl;
TFile* OutputFile = TFile::Open("Outputfile.root","RECREATE");
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", OutputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
std::vector<VMVariable*> Variables;
MVariable* Var3= new MVariable("var3",F,none);
MVariable* Var4 = new MVariable("var4",F,none);
Variables.push_back(Var3);
Variables.push_back(Var4);
MVariable* Var1 = new MVariable("var1",F,none);
MVariable* Var2 = new MVariable("var2",F,none);
MultiVariable* MyVar1 = new MultiVariable("Var1+Var2",sum);
MyVar1->AddVariable(Var1);
MyVar1->AddVariable(Var2);
Variables.push_back(MyVar1);
MultiVariable* MyVar2 = new MultiVariable("Minus",subtract);
MyVar2->AddVariable(Var1);
MyVar2->AddVariable(Var2);
Variables.push_back(MyVar2);
std::string InputName= "./tmva_class_exampleD.root";
TFile *input = TFile::Open("./tmva_class_exampleD.root" );
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background=(TTree*)input->Get("TreeB");
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
for(auto v:Variables){
factory->AddVariable(v->GetFactoryName(),v->GetType());
}
factory->SetBackgroundWeightExpression( "weight" );
TCut mycuts = "";
TCut mycutb = "";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
std::vector<MClassifier*> Classifiers;
Classifiers.push_back(new MClassifier(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"));
for(auto C:Classifiers){
if(!(C->AddMethodToFactory(factory))){
std::cout<<"Booking classifier failed"<<std::endl;
return 1;
}
}
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
OutputFile->Close();
delete factory;
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
for(auto v: Variables){
reader->AddVariable(v->GetFactoryName(),v->GetReaderAddress());
}
for(auto C:Classifiers){
if(!(C->AddMethodToReader(reader,"./weights/","TMVAClassification"))){
std::cout<<"Failed adding classifer to reader"<<std::endl;
return 1;
}
}
TFile* Input = TFile::Open("./tmva_class_exampleD.root");
TTree* TreeToEvaluate= (TTree*)Input->Get("TreeS");
TFile* AppliedFile = new TFile("AppliedFile.root","RECREATE");
TTree* AppliedTree=TreeToEvaluate->CloneTree(0);
for(auto C:Classifiers){
if(!(C->MakeBranch(AppliedTree)))return 1;
}
for(auto Var:Variables){
if(!(Var->SetBA(TreeToEvaluate))){
std::cout<<"Problem Setting Branch addresses"<<std::endl;
return 1;
}
}
Long64_t N=TreeToEvaluate->GetEntries();
LoopTimer LT(0.05);
int vetoedeventcounter=0;
double StartEntry=0.0;
double LastEntry=0.0;
Long64_t iStart=0;
Long64_t iEnd=N;
for(Long64_t i=iStart;i<iEnd;++i){
LT.DeclareLoopStart(iEnd-iStart);
TreeToEvaluate->GetEntry(i);
bool useevent=true;
for(auto Var:Variables){
useevent=Var->DoOperation();
}
if(!useevent){
vetoedeventcounter++;
continue;
}
for(auto C:Classifiers){
if(!(C->Apply(reader)))return 1;
}
AppliedTree->Fill();
}
AppliedTree->Write();
AppliedFile->Close();
std::cout<<"Got here"<<std::endl;
// Compare Applied file from here with applied file from TMVA tests.
TFile* ReadAppliedFile = TFile::Open("AppliedFile.root");
TTree* AppliedTreeRead=(TTree*)ReadAppliedFile->Get("TreeS");
if(!AppliedTreeRead)std::cout<<"NUll pointer to tree"<<std::endl;
double BDTResponse; AppliedTreeRead->SetBranchAddress("BDT_response",&BDTResponse);
TFile* ReadTMVATestFile = TFile::Open("/home/tw/root-v5-34/tmva/test/TreeFile.root");
if(!ReadTMVATestFile)std::cout<<"File open faild"<<std::endl;
TTree* TMVATestTree=(TTree*)ReadTMVATestFile->Get("AppliedTree");
if(!TMVATestTree)std::cout<<"NUll pointer to tree"<<std::endl;
double TestBDTResponse; TMVATestTree->SetBranchAddress("BDT_response",&TestBDTResponse);
Long64_t ATRN=AppliedTreeRead->GetEntries();
Long64_t TTTN=TMVATestTree->GetEntries();
std::cout<<"Entries in my tree= "<<ATRN<<std::endl;
std::cout<<"Entries in TMVA tree= "<<TTTN<<std::endl;
if(ATRN!=TTTN)std::cout<<"SOMETHING WRONG EVENTS NOT EQUAL"<<std::endl;
std::vector<double> ATRValues;
std::vector<double> TTTValues;
for(int i=0;i<ATRN;++i){
TMVATestTree->GetEntry(i);
AppliedTreeRead->GetEntry(i);
ATRValues.push_back(BDTResponse);
TTTValues.push_back(TestBDTResponse);
// std::cout<<" MYTree = "<<BDTResponse<<" TMVATREE= "<<TestBDTResponse<<std::endl;
}
std::sort(ATRValues.begin(),ATRValues.end());
std::sort(TTTValues.begin(),TTTValues.end());
for(int i=0;i<TTTN;++i){
std::cout<<" MY Value= "<<ATRValues.at(i)<<" TTT Value = "<<TTTValues.at(i)<<std::endl;
}
}
//------------------------------------------------------------------------------
// MVATrain
//------------------------------------------------------------------------------
void MVATrain(TString signal)
{
TFile* outputfile = TFile::Open(trainingdir + signal + ".root", "recreate");
// Factory
//----------------------------------------------------------------------------
TMVA::Factory* factory = new TMVA::Factory(signal, outputfile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
// Get the trees
//----------------------------------------------------------------------------
_mctree.clear();
AddProcess("signal", signal);
AddProcess("background", "HZJ_HToWW_M125");
AddProcess("background", "ggZH_HToWW_M125");
// AddProcess("background", "14_HZ");
// AddProcess("background", "10_HWW");
// AddProcess("background", "06_WW");
// AddProcess("background", "02_WZTo3LNu");
// AddProcess("background", "03_ZZ");
// AddProcess("background", "11_Wg");
// AddProcess("background", "07_ZJets");
// AddProcess("background", "09_TTV");
// AddProcess("background", "05_ST");
// AddProcess("background", "00_Fakes");
Double_t weight = 1.0;
factory->AddSignalTree(_signaltree, weight);
for (UInt_t i=0; i<_mctree.size(); i++) factory->AddBackgroundTree(_mctree[i], weight);
factory->SetWeightExpression("eventW");
// Add variables
//----------------------------------------------------------------------------
// Be careful with the order: it must be respected at the reading step
// factory->AddVariable("<var1>+<var2>", "pretty title", "unit", 'F');
// factory->AddVariable("channel", "", "", 'F');
factory->AddVariable("metPfType1", "", "", 'F');
factory->AddVariable("m2l", "", "", 'F');
// factory->AddVariable("njet", "", "", 'F');
// factory->AddVariable("nbjet20cmvav2l", "", "", 'F');
factory->AddVariable("lep1pt", "", "", 'F');
factory->AddVariable("lep2pt", "", "", 'F');
// factory->AddVariable("jet1pt", "", "", 'F');
factory->AddVariable("jet2pt", "", "", 'F');
factory->AddVariable("mtw1", "", "", 'F');
factory->AddVariable("dphill", "", "", 'F');
factory->AddVariable("dphilep1jet1", "", "", 'F');
// factory->AddVariable("dphilep1jet2", "", "", 'F');
// factory->AddVariable("dphilmet1", "", "", 'F');
// factory->AddVariable("dphilep2jet1", "", "", 'F');
// factory->AddVariable("dphilep2jet2", "", "", 'F');
// factory->AddVariable("dphilmet2", "", "", 'F');
// factory->AddVariable("dphijj", "", "", 'F');
// factory->AddVariable("dphijet1met", "", "", 'F');
// factory->AddVariable("dphijet2met", "", "", 'F');
factory->AddVariable("dphillmet", "", "", 'F');
// Preselection cuts and preparation
//----------------------------------------------------------------------------
factory->PrepareTrainingAndTestTree("", ":nTrain_Signal=0:nTest_Signal=0:nTrain_Background=0:nTest_Background=0:SplitMode=Alternate:MixMode=Random:!V");
// Book MVA
//----------------------------------------------------------------------------
factory->BookMethod(TMVA::Types::kMLP, "MLP",
"H:!V:NeuronType=sigmoid:VarTransform=N:NCycles=600:HiddenLayers=25,10:TestRate=5:!UseRegulator");
// Train, test and evaluate MVA
//----------------------------------------------------------------------------
factory->TrainAllMethods(); // Train using the set of training events
factory->TestAllMethods(); // Evaluate using the set of test events
factory->EvaluateAllMethods(); // Evaluate and compare performance
// Save the output
//----------------------------------------------------------------------------
outputfile->Close();
delete factory;
}
void TMVAClassification( TString myMethodList = "" , TString myModel = "")
{
// 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;
// --- Cut optimisation
Use["Cuts"] = 1;
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"] = 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;
// ---------------------------------------------------------------
// Default model to be trained + tested
std::map<std::string,int> Model;
// --- Cut optimisation
Model[ "MM" ] = 0; // Mass mechanism
Model[ "RHC_L" ] = 0; // Right Handed Current
Model[ "RHC_E" ] = 0; // Right Handed Current
Model[ "M1" ] = 0; // Majoron
Model[ "M2" ] = 0; // Majoron
Model[ "M3" ] = 0; // Majoron
Model[ "M7" ] = 0; // Majoron
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;
}
}
if(myModel != "") {
std::string regModel(myModel);
if( Model.find(regModel) == Model.end() ){
std::cout << "Model \"" << myModel << "\" not known in under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Model.begin(); it != Model.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Model[regModel] = 1;
} else {
std::cout << "No signal model as been specified. You must choose one among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Model.begin(); it != Model.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName;
outfileName.Form( "TMVA_%s.root", myModel.Data() );
//TString outfileDir( "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_FINAL_TECHNOTE_20150921/TMVA/" );
TString outfileDir( "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_UPDATE_TECHNOTE_20160429/TMVA/" );
TFile* outputFile = TFile::Open( outfileDir + 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
TString weightBaseName;
weightBaseName.Form("TMVAClassification_%s", myModel.Data());
TMVA::Factory *factory = new TMVA::Factory( weightBaseName , 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( "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( "min_el_en" , 'F' );
factory->AddVariable( "max_el_en" , 'F' );
factory->AddVariable( "el_en_asym := (max_el_en-min_el_en)/(min_el_en+max_el_en)" , 'F' );
factory->AddVariable( "el_en_sum := min_el_en+max_el_en" , 'F' );
factory->AddVariable( "cos_theta" , 'F' );
factory->AddVariable( "prob_int" , 'F' );
factory->AddVariable( "min_el_track_len" , 'F' );
factory->AddVariable( "max_el_track_len" , 'F' );
//factory->AddVariable( "min_el_curv := min_el_track_r*min_el_sign" , 'F' );
//factory->AddVariable( "max_el_curv := max_el_track_r*max_el_sign" , 'F' );
//factory->AddVariable( "max_vertex_s" , 'F' );
//factory->AddVariable( "max_vertex_z" , 'F' );
//factory->AddVariable( "min_vertex_s" , 'F' );
//factory->AddVariable( "min_vertex_z" , '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 fdir = "/sps/nemo/scratch/remoto/nemo3/plot/plot_FINAL_TECHNOTE_20150921/";
TString fdir = "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_UPDATE_TECHNOTE_20160429/";
TString fname = "TwoElectronIntTree.root";
TFile *input = TFile::Open( fdir + fname , "READ");
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree * sig_tree = 0;
Double_t sig_weight = 1.;
if ( Model[ "MM" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m1_tree" ) ;
if ( Model[ "RHC_L" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m2_tree" ) ;
if ( Model[ "RHC_E" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m18_tree" ) ;
if ( Model[ "M1" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m5_tree" ) ;
if ( Model[ "M2" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m15_tree" ) ;
if ( Model[ "M3" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m6_tree" ) ;
if ( Model[ "M7" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m7_tree" ) ;
factory->AddSignalTree( sig_tree , sig_weight );
//Double_t Cd116_2b0n_m1_weight = 1.;
//TTree * Cd116_2b0n_m1_tree = (TTree*) input->Get("Cd116_2b0n_m1_tree" ) ;
//factory->AddSignalTree( Cd116_2b0n_m1_tree , Cd116_2b0n_m1_weight );
TTree * Cd116_Tl208_tree = (TTree*) input->Get("Cd116_Tl208_tree" ) ; Double_t Cd116_Tl208_weight = 6.52838 ; if( Cd116_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Tl208_tree , Cd116_Tl208_weight ); };
TTree * Cd116_Ac228_tree = (TTree*) input->Get("Cd116_Ac228_tree" ) ; Double_t Cd116_Ac228_weight = 7.62351 ; if( Cd116_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Ac228_tree , Cd116_Ac228_weight ); };
TTree * Cd116_Bi212_tree = (TTree*) input->Get("Cd116_Bi212_tree" ) ; Double_t Cd116_Bi212_weight = 3.00708 ; if( Cd116_Bi212_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Bi212_tree , Cd116_Bi212_weight ); };
TTree * Cd116_Bi214_tree = (TTree*) input->Get("Cd116_Bi214_tree" ) ; Double_t Cd116_Bi214_weight = 18.1504 ; if( Cd116_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Bi214_tree , Cd116_Bi214_weight ); };
TTree * Cd116_Pb214_tree = (TTree*) input->Get("Cd116_Pb214_VT_tree" ) ; Double_t Cd116_Pb214_weight = 0.186417 ; if( Cd116_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Pb214_tree , Cd116_Pb214_weight ); };
TTree * Mylar_Bi214_tree = (TTree*) input->Get("Mylar_Bi214_tree" ) ; Double_t Mylar_Bi214_weight = 11.1346 ; if( Mylar_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Mylar_Bi214_tree , Mylar_Bi214_weight ); };
TTree * Mylar_Pb214_tree = (TTree*) input->Get("Mylar_Pb214_tree" ) ; Double_t Mylar_Pb214_weight = 0.496238 ; if( Mylar_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Mylar_Pb214_tree , Mylar_Pb214_weight ); };
TTree * Cd116_K40_tree = (TTree*) input->Get("Cd116_K40_tree" ) ; Double_t Cd116_K40_weight = 8.9841+25.8272 ; if( Cd116_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_K40_tree , Cd116_K40_weight ); };
TTree * Cd116_Pa234m_tree = (TTree*) input->Get("Cd116_Pa234m_tree" ) ; Double_t Cd116_Pa234m_weight = 27.9307+72.4667 ; if( Cd116_Pa234m_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Pa234m_tree , Cd116_Pa234m_weight ); };
TTree * SFoil_Bi210_tree = (TTree*) input->Get("SFoil_Bi210_tree" ) ; Double_t SFoil_Bi210_weight = 0+23.2438 ; if( SFoil_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Bi210_tree , SFoil_Bi210_weight ); };
TTree * SWire_Bi210_tree = (TTree*) input->Get("SWire_Bi210_tree" ) ; Double_t SWire_Bi210_weight = 0.136147+0.624187 ; if( SWire_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Bi210_tree , SWire_Bi210_weight ); };
TTree * SScin_Bi210_tree = (TTree*) input->Get("SScin_Bi210_tree" ) ; Double_t SScin_Bi210_weight = 1.75641 ; if( SScin_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Bi210_tree , SScin_Bi210_weight ); };
TTree * SScin_Bi214_tree = (TTree*) input->Get("SScin_Bi214_tree" ) ; Double_t SScin_Bi214_weight = 0.0510754 ; if( SScin_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Bi214_tree , SScin_Bi214_weight ); };
TTree * SScin_Pb214_tree = (TTree*) input->Get("SScin_Pb214_tree" ) ; Double_t SScin_Pb214_weight = 0 ; if( SScin_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Pb214_tree , SScin_Pb214_weight ); };
TTree * SWire_Tl208_tree = (TTree*) input->Get("SWire_Tl208_tree" ) ; Double_t SWire_Tl208_weight = 0.217623+1.07641 ; if( SWire_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Tl208_tree , SWire_Tl208_weight ); };
TTree * SWire_Bi214_P1_tree = (TTree*) input->Get("SWire_Bi214_tree" ) ; Double_t SWire_Bi214_weight = 21.4188+17.8236 ; if( SWire_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Bi214_tree , SWire_Bi214_weight ); };
TTree * SFoil_Bi214_tree = (TTree*) input->Get("SFoil_Bi214_tree" ) ; Double_t SFoil_Bi214_weight = 5.83533+2.80427 ; if( SFoil_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Bi214_tree , SFoil_Bi214_weight ); };
TTree * SWire_Pb214_tree = (TTree*) input->Get("SWire_Pb214_tree" ) ; Double_t SWire_Pb214_weight = 0.458486+0.649167 ; if( SWire_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Pb214_tree , SWire_Pb214_weight ); };
TTree * SFoil_Pb214_tree = (TTree*) input->Get("SFoil_Pb214_tree" ) ; Double_t SFoil_Pb214_weight = 0.218761+0.195287 ; if( SFoil_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Pb214_tree , SFoil_Pb214_weight ); };
TTree * FeShield_Bi214_tree = (TTree*) input->Get("FeShield_Bi214_tree" ) ; Double_t FeShield_Bi214_weight = 50.7021 ; if( FeShield_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Bi214_tree , FeShield_Bi214_weight ); };
TTree * FeShield_Tl208_tree = (TTree*) input->Get("FeShield_Tl208_tree" ) ; Double_t FeShield_Tl208_weight = 0.859465 ; if( FeShield_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Tl208_tree , FeShield_Tl208_weight ); };
TTree * FeShield_Ac228_tree = (TTree*) input->Get("FeShield_Ac228_tree" ) ; Double_t FeShield_Ac228_weight = 0.126868 ; if( FeShield_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Ac228_tree , FeShield_Ac228_weight ); };
TTree * CuTower_Co60_tree = (TTree*) input->Get("CuTower_Co60_tree" ) ; Double_t CuTower_Co60_weight = 3.9407 ; if( CuTower_Co60_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( CuTower_Co60_tree , CuTower_Co60_weight ); };
TTree * Air_Bi214_P1_tree = (TTree*) input->Get("Air_Bi214_tree" ) ; Double_t Air_Bi214_P1_weight = 4.19744 ; if( Air_Bi214_P1_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Air_Bi214_P1_tree , Air_Bi214_P1_weight ); };
TTree * Air_Tl208_P1_tree = (TTree*) input->Get("Air_Tl208_tree" ) ; Double_t Air_Tl208_P1_weight = 0 ; if( Air_Tl208_P1_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Air_Tl208_P1_tree , Air_Tl208_P1_weight ); };
TTree * PMT_Bi214_tree = (TTree*) input->Get("PMT_Bi214_tree" ) ; Double_t PMT_Bi214_weight = 27.9661 ; if( PMT_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Bi214_tree , PMT_Bi214_weight ); };
TTree * PMT_Tl208_tree = (TTree*) input->Get("PMT_Tl208_tree" ) ; Double_t PMT_Tl208_weight = 22.923 ; if( PMT_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Tl208_tree , PMT_Tl208_weight ); };
TTree * PMT_Ac228_tree = (TTree*) input->Get("PMT_Ac228_tree" ) ; Double_t PMT_Ac228_weight = 3.60712 ; if( PMT_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Ac228_tree , PMT_Ac228_weight ); };
TTree * PMT_K40_tree = (TTree*) input->Get("PMT_K40_tree" ) ; Double_t PMT_K40_weight = 16.813 ; if( PMT_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_K40_tree , PMT_K40_weight ); };
TTree * ScintInn_K40_tree = (TTree*) input->Get("ScintInn_K40_tree" ) ; Double_t ScintInn_K40_weight = 0.333988 ; if( ScintInn_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintInn_K40_tree , ScintInn_K40_weight ); };
TTree * ScintOut_K40_tree = (TTree*) input->Get("ScintOut_K40_tree" ) ; Double_t ScintOut_K40_weight = 0.601178 ; if( ScintOut_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintOut_K40_tree , ScintOut_K40_weight ); };
TTree * ScintPet_K40_tree = (TTree*) input->Get("ScintPet_K40_tree" ) ; Double_t ScintPet_K40_weight = 1.00195 ; if( ScintPet_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintPet_K40_tree , ScintPet_K40_weight ); };
TTree * MuMetal_Pa234m_tree = (TTree*) input->Get("MuMetal_Pa234m_tree" ) ; Double_t MuMetal_Pa234m_weight = 0.739038 ; if( MuMetal_Pa234m_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( MuMetal_Pa234m_tree , MuMetal_Pa234m_weight ); };
TTree * Cd116_2b2n_m14_tree = (TTree*) input->Get("Cd116_2b2n_m14_tree" ) ; Double_t Cd116_2b2n_m14_weight = 4977.55 ; if( Cd116_2b2n_m14_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_2b2n_m14_tree , Cd116_2b2n_m14_weight ); };
// --- 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)
// Apply cut on charge
//TCut mycuts = "min_el_sign < 0 && max_el_sign < 0.";
//TCut mycutb = "min_el_sign < 0 && max_el_sign < 0.";
// Apply cut on vertex
//TCut mycuts = "((max_vertex_x - min_vertex_x)**2 + (max_vertex_y - min_vertex_y)**2 <= 4**2)&&((max_vertex_z-min_vertex_z)**2<8**2)";
//TCut mycutb = "((max_vertex_x - min_vertex_x)**2 + (max_vertex_y - min_vertex_y)**2 <= 4**2)&&((max_vertex_z-min_vertex_z)**2<8**2)";
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=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=-1" );
// 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( outfileDir + outfileName );
}