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();
}
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 );
}
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
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
// ---
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDERSkNN"] = 0; // depreciated until further notice
Use["PDEFoam"] = 0;
// --
Use["KNN"] = 0;
// ---
Use["HMatrix"] = 0;
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0;
Use["LD"] = 0;
// ---
Use["FDA_GA"] = 0;
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
// ---
Use["MLP"] = 0; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["MLPBNN"] = 0; // recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // *** missing
Use["TMlpANN"] = 0;
// ---
Use["SVM"] = 0;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 0;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 0;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 0;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// read training and test data
factory->AddVariable("CScostheta",'F');
factory->AddVariable("ZRapidity",'F');
factory->AddVariable("REDmet",'F');
if (ReadDataFromAsciiIFormat) {
// load the signal and background event samples from ascii files
// format in file must be:
// var1/F:var2/F:var3/F:var4/F
// 0.04551 0.59923 0.32400 -0.19170
// ...
TString datFileS = "tmva_example_sig.dat";
TString datFileB = "tmva_example_bkg.dat";
factory->SetInputTrees( datFileS, datFileB );
}
else {
// load the signal and background event samples from ROOT trees
TString fname = "./tmva_class_example.root";
TString fname_Data7TeV_DoubleElectron2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_0.root";
TString fname_Data7TeV_MuEG2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_0.root";
TString fname_ZH125 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH125.root";
TString fname_SingleT_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_tW.root";
TString fname_SingleT_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_s.root";
TString fname_Data7TeV_DoubleMu2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_0.root";
TString fname_Data7TeV_DoubleElectron2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_0.root";
TString fname_ZH135 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH135.root";
TString fname_DYJetsToLL = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//DYJetsToLL.root";
TString fname_ZH115 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH115.root";
TString fname_SingleTbar_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_t.root";
TString fname_Data7TeV_DoubleElectron2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_1.root";
TString fname_Data7TeV_DoubleMu2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_1.root";
TString fname_Data7TeV_MuEG2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_1.root";
TString fname_TTJets = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//TTJets.root";
TString fname_SingleTbar_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_s.root";
TString fname_WJetsToLNu = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WJetsToLNu.root";
TString fname_Data7TeV_DoubleElectron2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_1.root";
TString fname_ZZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZZ.root";
TString fname_ZH150 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH150.root";
TString fname_Data7TeV_MuEG2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_1.root";
TString fname_WW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WW.root";
TString fname_ZH105 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH105.root";
TString fname_Data7TeV_DoubleMu2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_0.root";
TString fname_SingleTbar_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_tW.root";
TString fname_WZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WZ.root";
TString fname_Data7TeV_MuEG2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_0.root";
TString fname_Data7TeV_DoubleMu2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_1.root";
TString fname_ZH145 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH145.root";
TString fname_SingleT_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_t.root";
if (gSystem->AccessPathName( fname )) // file does not exist in local directory
gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *input_Data7TeV_DoubleElectron2011B_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_0 );
TFile *input_Data7TeV_MuEG2011B_0 = TFile::Open( fname_Data7TeV_MuEG2011B_0 );
TFile *input_ZH125 = TFile::Open( fname_ZH125 );
TFile *input_SingleT_tW = TFile::Open( fname_SingleT_tW );
TFile *input_SingleT_s = TFile::Open( fname_SingleT_s );
TFile *input_Data7TeV_DoubleMu2011B_0 = TFile::Open( fname_Data7TeV_DoubleMu2011B_0 );
TFile *input_Data7TeV_DoubleElectron2011A_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_0 );
TFile *input_ZH135 = TFile::Open( fname_ZH135 );
TFile *input_DYJetsToLL = TFile::Open( fname_DYJetsToLL );
TFile *input_ZH115 = TFile::Open( fname_ZH115 );
TFile *input_SingleTbar_t = TFile::Open( fname_SingleTbar_t );
TFile *input_Data7TeV_DoubleElectron2011B_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_1 );
TFile *input_Data7TeV_DoubleMu2011A_1 = TFile::Open( fname_Data7TeV_DoubleMu2011A_1 );
TFile *input_Data7TeV_MuEG2011A_1 = TFile::Open( fname_Data7TeV_MuEG2011A_1 );
TFile *input_TTJets = TFile::Open( fname_TTJets );
TFile *input_SingleTbar_s = TFile::Open( fname_SingleTbar_s );
TFile *input_WJetsToLNu = TFile::Open( fname_WJetsToLNu );
TFile *input_Data7TeV_DoubleElectron2011A_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_1 );
TFile *input_ZZ = TFile::Open( fname_ZZ );
TFile *input_ZH150 = TFile::Open( fname_ZH150 );
TFile *input_Data7TeV_MuEG2011B_1 = TFile::Open( fname_Data7TeV_MuEG2011B_1 );
TFile *input_WW = TFile::Open( fname_WW );
TFile *input_ZH105 = TFile::Open( fname_ZH105 );
TFile *input_Data7TeV_DoubleMu2011A_0 = TFile::Open( fname_Data7TeV_DoubleMu2011A_0 );
TFile *input_SingleTbar_tW = TFile::Open( fname_SingleTbar_tW );
TFile *input_WZ = TFile::Open( fname_WZ );
TFile *input_Data7TeV_MuEG2011A_0 = TFile::Open( fname_Data7TeV_MuEG2011A_0 );
TFile *input_Data7TeV_DoubleMu2011B_1 = TFile::Open( fname_Data7TeV_DoubleMu2011B_1 );
TFile *input_ZH145 = TFile::Open( fname_ZH145 );
TFile *input_SingleT_t = TFile::Open( fname_SingleT_t );
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_0 file: " << input_Data7TeV_DoubleElectron2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_0 file: " << input_Data7TeV_MuEG2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH125 file: " << input_ZH125->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_tW file: " << input_SingleT_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_s file: " << input_SingleT_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_0 file: " << input_Data7TeV_DoubleMu2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_0 file: " << input_Data7TeV_DoubleElectron2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH135 file: " << input_ZH135->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_DYJetsToLL file: " << input_DYJetsToLL->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH115 file: " << input_ZH115->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_t file: " << input_SingleTbar_t->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_1 file: " << input_Data7TeV_DoubleElectron2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_1 file: " << input_Data7TeV_DoubleMu2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_1 file: " << input_Data7TeV_MuEG2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_TTJets file: " << input_TTJets->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_s file: " << input_SingleTbar_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WJetsToLNu file: " << input_WJetsToLNu->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_1 file: " << input_Data7TeV_DoubleElectron2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZZ file: " << input_ZZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH150 file: " << input_ZH150->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_1 file: " << input_Data7TeV_MuEG2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WW file: " << input_WW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH105 file: " << input_ZH105->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_0 file: " << input_Data7TeV_DoubleMu2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_tW file: " << input_SingleTbar_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WZ file: " << input_WZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_0 file: " << input_Data7TeV_MuEG2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_1 file: " << input_Data7TeV_DoubleMu2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH145 file: " << input_ZH145->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_t file: " << input_SingleT_t->GetName() << std::endl;
TTree *signal_ZH145 = (TTree*)input_ZH145->Get("tmvatree");
TTree *background_ZZ = (TTree*)input_ZZ->Get("tmvatree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal_ZH145, 1.0 );
factory->AddBackgroundTree( background_ZZ, 1.0 );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signal_ZH145TrainingTree, signal_ZH145TrainWeight, "Training" );
// factory->AddSignalTree( signal_ZH145TestTree, signal_ZH145TestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
factory->SetBackgroundWeightExpression("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
factory->SetSignalWeightExpression("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "(CUT>2)";
TCut mycutb = "(CUT>2)";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, "SplitMode=random:!V" );
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:Seed=0:EffSel:Steps=50:Cycles=3:PopSize=1000:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=1000:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=1000:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
gROOT->ProcessLine(".q;");
}
int TMVAKaggleHiggs ( 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;
// --- 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
Use["NN"] = 1; // improved implementation of a NN
//
// --- 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 TMVAKaggleHiggs" << 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 1;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fname = "./training.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 *tree = (TTree*)input->Get("data");
// 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( "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' );
TString limit ("-900.0");
TString replacementValue ("0.0");
std::vector<std::string> vars = {"DER_mass_MMC","DER_mass_transverse_met_lep","DER_mass_vis","DER_pt_h","DER_deltaeta_jet_jet","DER_mass_jet_jet","DER_prodeta_jet_jet","DER_deltar_tau_lep","DER_pt_tot","DER_sum_pt","DER_pt_ratio_lep_tau","DER_met_phi_centrality","DER_lep_eta_centrality","PRI_tau_pt","PRI_tau_eta","PRI_tau_phi","PRI_lep_pt","PRI_lep_eta","PRI_lep_phi","PRI_met","PRI_met_phi","PRI_met_sumet","PRI_jet_num","PRI_jet_leading_pt","PRI_jet_leading_eta","PRI_jet_leading_phi","PRI_jet_subleading_pt","PRI_jet_subleading_eta","PRI_jet_subleading_phi","PRI_jet_all_pt"};
for (std::vector<std::string>::iterator it = vars.begin (), itEnd = vars.end (); it != itEnd; ++it)
{
std::string s = *it;
TString current;
current.Form ("%s:=(%s<%s?%s:%s)",s.c_str (), s.c_str (), limit.Data (), replacementValue.Data (), s.c_str ());
factory->AddVariable (current, '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' );
// global event weights per tree (see below for setting event-wise weights)
Double_t weight = 1.0;
// Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
// factory->AddBackgroundTree( background, backgroundWeight );
factory->AddTree(tree, "Signal", 1., "Label == 1");
factory->AddTree(tree, "Background", 1., "Label == 0");
// 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->SetSignalWeightExpression( "Weight" );
factory->SetBackgroundWeightExpression( "Weight" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "Label==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "Label==0"; // 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:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=5000:nTrain_Background=5000:nTest_Signal=5000:nTest_Background=5000: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
// improved neural network implementation
if (Use["NN"])
{
// TString layoutString ("Layout=TANH|(N+100)*2,LINEAR");
// TString layoutString ("Layout=SOFTSIGN|100,SOFTSIGN|50,SOFTSIGN|20,LINEAR");
// TString layoutString ("Layout=RELU|300,RELU|100,RELU|30,RELU|10,LINEAR");
// TString layoutString ("Layout=SOFTSIGN|50,SOFTSIGN|30,SOFTSIGN|20,SOFTSIGN|10,LINEAR");
// TString layoutString ("Layout=TANH|50,TANH|30,TANH|20,TANH|10,LINEAR");
// TString layoutString ("Layout=SOFTSIGN|50,SOFTSIGN|20,LINEAR");
TString layoutString ("Layout=SOFTSIGN|70,SOFTSIGN|30,LINEAR");
std::vector<TString> strategy;
strategy.push_back (TString ("LearningRate=1e-2,Momentum=0.9,Repetitions=1,ConvergenceSteps=70,BatchSize=120,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE,DropConfig=0.5+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True"));
strategy.push_back (TString ("LearningRate=1e-4,Momentum=0.5,Repetitions=1,ConvergenceSteps=70,BatchSize=80,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.1+0.1+0.1+0.1,DropRepetitions=1"));
strategy.push_back (TString ("LearningRate=1e-5,Momentum=0.3,Repetitions=1,ConvergenceSteps=70,BatchSize=60,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True"));
strategy.push_back (TString ("LearningRate=1e-6,Momentum=0.0,Repetitions=1,ConvergenceSteps=70,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True"));
// strategy.push_back (TString ("LearningRate=1e-6,Momentum=0.0,Repetitions=1,ConvergenceSteps=50,BatchSize=30,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True"));
TString trainingStrategyString ("TrainingStrategy=");
for (std::vector<TString>::const_iterator it = strategy.begin (), itEnd = strategy.end (); it != itEnd; ++it)
{
if (it != strategy.begin ())
trainingStrategyString += "|";
trainingStrategyString += *it;
}
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CROSSENTROPY");
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=G:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
factory->BookMethod( TMVA::Types::kNN, "NN", nnOptions ); // NN
}
// 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()) TMVA::TMVAGui( outfileName );
return 0;
}
void Reg(){
TMVA::Tools::Instance();
std::cout << "==> Start TMVARegression" << std::endl;
ifstream myfile;
myfile.open("99per.txt");
ostringstream xcS,xcH,xcP,xcC,xcN;
double xS,xH,xC,xN,xP;
if(myfile.is_open()){
while(!myfile.eof()){
myfile>>xS>>xH>>xC>>xN>>xP;
}
}
xcS<<xS;
xcH<<xH;
xcC<<xC;
xcN<<xN;
xcP<<xP;
//Output file
TString outfileName( "Ex1out_FullW_def.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
//Declaring the factory
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
//Declaring Input Varibles
factory->AddVariable( "Sieie",'F');
factory->AddVariable( "ToE", 'F' );
factory->AddVariable( "isoC",'F' );
factory->AddVariable( "isoN",'F' );
factory->AddVariable( "isoP",'F' );
TString fname = "../../CutTMVATrees_Barrel.root";
input = TFile::Open( fname );
// --- Register the regression tree
TTree *signal = (TTree*)input->Get("t_S");
TTree *background = (TTree*)input->Get("t_B");
//Just Some more settings
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddSignalTree( signal, signalWeight );
factory->AddBackgroundTree( background , backgroundWeight );
TCut mycuts ="";
TCut mycutb ="";
// factory->PrepareTrainingAndTestTree(mycuts,mycutb,"nTrain_Signal=9000:nTrain_Background=9000:nTest_Signal=10000:nTest_Background=10000");
factory->SetBackgroundWeightExpression("weightPT*weightXS");
factory->SetSignalWeightExpression("weightPT*weightXS");
TString methodName = "Cuts_FullsampleW_def";
TString methodOptions ="!H:!V:FitMethod=GA:EffMethod=EffSEl";
methodOptions +=":VarProp[0]=FMin:VarProp[1]=FMin:VarProp[2]=FMin:VarProp[3]=FMin:VarProp[4]=FMin";
methodOptions +=":CutRangeMax[0]="+xcS.str();
methodOptions +=":CutRangeMax[1]="+xcH.str();
methodOptions +=":CutRangeMax[2]="+xcC.str();
methodOptions +=":CutRangeMax[3]="+xcN.str();
methodOptions +=":CutRangeMax[4]="+xcP.str();
//************
factory->BookMethod(TMVA::Types::kCuts,methodName,methodOptions);
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
}
//void TMVAClassification( TString myMethodList = "" )
void tmvaClassifier( TString myMethodList = "", TString inputDir="~/work/ewkzp2j_5311/ll/", bool minimalTrain=false, bool useQG=false)
{
gSystem->ExpandPathName(inputDir);
TString pf("base_weights");
if(!minimalTrain){
if(useQG) pf="full_weights";
else pf="weights";
}
TMVA::gConfig().GetIONames().fWeightFileDir = inputDir + pf;
// 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"] = 1; // 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"] = 1;
Use["FisherCat"] = 0;//added by loic
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"] = 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;
// 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" );
// 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";
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
// std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
// --- Register the training and test trees
TChain *signal = new TChain("ewkzp2j");
TChain *background = new TChain("ewkzp2j");
TSystemDirectory dir(inputDir,inputDir);
TList *files = dir.GetListOfFiles();
if (files) {
TSystemFile *file;
TString fname;
TIter next(files);
while ((file=(TSystemFile*)next())) {
fname = file->GetName();
if(!fname.EndsWith("_summary.root")) continue;
if(fname.Contains("Data")) continue;
if(!fname.Contains("DY")) continue;
bool isSignal(false);
if(fname.Contains("JJ")) { signal->Add(fname); isSignal=true; }
else if(fname.Contains("50toInf") && fname.Contains("DY")) background->Add(fname);
cout << fname << " added as " << (isSignal ? "signal" : "background") << endl;
}
}else{
cout << "[Error] no files found in " << inputDir << endl;
}
cout << "Signal has " << signal->GetEntries() << " raw events" << endl
<< "Background has " << background->GetEntries() << " raw events"<< endl;
// global event weights per tree
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// event-per-event weights per tree
factory->SetBackgroundWeightExpression( "weight/cnorm" );
factory->SetSignalWeightExpression( "weight/cnorm" );
//define variables for the training
if(minimalTrain)
{
factory->AddVariable( "mjj", "M_{jj}" "GeV", 'F' );
factory->AddVariable( "detajj", "#Delta#eta_{jj}", "", 'F' );
factory->AddVariable( "spt", "#Delta_{rel}", "GeV", 'F' );
}
else
{
factory->AddVariable( "mjj", "M_{jj}" "GeV", 'F' );
factory->AddVariable( "detajj", "#Delta#eta_{jj}", "", 'F' );
factory->AddVariable( "setajj", "#Sigma#eta_{j}", "", 'F' );
factory->AddVariable( "eta1", "#eta(1)", "", 'F' );
factory->AddVariable( "eta2", "#eta(2)", "", 'F' );
factory->AddVariable( "pt1", "p_{T}(1)", "GeV", 'F' );
factory->AddVariable( "pt2", "p_{T}(2)", "GeV", 'F' );
factory->AddVariable( "spt", "#Delta_{rel}", "GeV", 'F' );
if(useQG) factory->AddVariable( "qg1", "q/g(1)", "", 'F' );
if(useQG) factory->AddVariable( "qg2", "q/g(2)", "", 'F' );
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- 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" );
if (Use["FisherCat"]){
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
TMVA::MethodCategory* mcategory = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcategory->AddMethod( "mjj<250", "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat1", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=250&&mjj<350" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0000", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=350&&mjj<450" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0350", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=450&&mjj<550" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0450", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=550&&mjj<750" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0550", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=750&&mjj<1000", "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0750", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=1000" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat1000", "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=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=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: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:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=25:PruneMethod=CostComplexity:PruneStrength=25.0:VarTransform=Decorrelate");
//"!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
// 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;
std::cout << " ==> Weights are stored in " << TMVA::gConfig().GetIONames().fWeightFileDir << std::endl;
delete factory;
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char* argv[]){
// Configurable parameters
// int max_events; // Maximum number of events to process
//string filelist; // The file containing a list of files to use as input
//string input_prefix; // A prefix that will be added to the path of each input file
string folder;
string output_name; // Name of the ouput ROOT File
string output_folder; // Folder to write the output in
string paramfile;
string paramfile2;
string classname;
bool twotag;
bool onetag;
po::options_description config("Configuration");
po::variables_map vm;
po::notify(vm);
config.add_options()
("folder", po::value<string>(&folder)->default_value("output/Paper_2012/"))
// ("input_prefix", po::value<string>(&input_prefix)->default_value(""))
("output_name", po::value<string>(&output_name)->default_value("test_tmva.root"))
("output_folder", po::value<string>(&output_folder)->default_value(""))
("paramfile", po::value<string>(¶mfile)->default_value("./scripts/Paper_params_2012.dat"))
("paramfile2", po::value<string>(¶mfile2)->default_value("./scripts/TMVAinputshad.dat"))
("classname", po::value<string>(&classname)->default_value("HhhMVA"))
("twotag", po::value<bool>(&twotag)->default_value(true))
("onetag", po::value<bool>(&onetag)->default_value(false))
;
po::store(po::command_line_parser(argc, argv).
options(config).allow_unregistered().run(), vm);
po::notify(vm);
std::cout << "-------------------------------------" << std::endl;
std::cout << "Train MVA" << std::endl;
std::cout << "-------------------------------------" << std::endl; string param_fmt = "%-25s %-40s\n";
std::vector<string> bckglist;
bckglist.push_back("TTJetsFullLept");
bckglist.push_back("TTJetsSemiLept");
bckglist.push_back("TTJetsHadronicExt");
// bckglist.push_back("WWJetsTo2L2Nu");
// bckglist.push_back("WZJetsTo2L2Q");
// bckglist.push_back("WZJetsTo3LNu");
// bckglist.push_back("ZZJetsTo2L2Nu");
// bckglist.push_back("ZZJetsTo2L2Q");
// bckglist.push_back("ZZJetsTo4L");
// bckglist.push_back("DYJetsToTauTauSoup");
// bckglist.push_back("DYJetsToLLSoup");
// bckglist.push_back("DYJetsToTauTau");
// bckglist.push_back("DYJetsToLL");
// bckglist.push_back("T-tW");
// bckglist.push_back("Tbar-tW");
std::vector<string> signallist;
signallist.push_back("GluGluToHTohhTo2Tau2B_mH-300");
sample_names_.reserve(bckglist.size()+signallist.size());
sample_names_.insert(sample_names_.end(),bckglist.begin(),bckglist.end());
sample_names_.insert(sample_names_.end(),signallist.begin(),signallist.end());
std::vector<TFile*> BackgroundSamples;
for(unsigned int iter=0;iter<bckglist.size();++iter){
BackgroundSamples.push_back(TFile::Open((folder+bckglist.at(iter)+"_mt_2012.root").c_str()));
}
std::vector<TFile*> SignalSamples;
for(unsigned int sigIter=0;sigIter<signallist.size();++sigIter){
SignalSamples.push_back(TFile::Open((folder+signallist.at(sigIter)+"_mt_2012.root").c_str()));
}
std::vector<TTree*> backgroundTrees;
for(unsigned int iter2=0;iter2<BackgroundSamples.size();++iter2){
backgroundTrees.push_back(dynamic_cast<TTree*>(BackgroundSamples.at(iter2)->Get("ntuple")));
}
std::vector<TTree*> signalTrees;
for(unsigned int sigIter2=0;sigIter2<SignalSamples.size();++sigIter2){
signalTrees.push_back(dynamic_cast<TTree*>(SignalSamples.at(sigIter2)->Get("ntuple")));
}
TFile *outfile = new TFile((output_folder+output_name).c_str(),"RECREATE");
TMVA::Factory *factory = new TMVA::Factory(classname,outfile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
std::vector<std::string> vars;
std::ifstream parafile(paramfile2.c_str());
std::cout<<paramfile2.c_str()<<std::endl;
string line;
while(getline(parafile,line)){
vars.push_back(line);
}
parafile.close();
std::cout<<(vars.at(0)).c_str()<<std::endl;
std::vector<float> var2;
for(unsigned int variter=0;variter<vars.size();++variter){
var2.push_back(::atof((vars.at(variter)).c_str()));
}
for(unsigned int variter=0;variter<vars.size();++variter){
factory->AddVariable((vars.at(variter)).c_str(),(vars.at(variter)).c_str(),"",'F');
}
factory->AddSpectator("mt_1","mt_1","",'F');
factory->AddSpectator("n_prebjets","n_prebjets","",'I');
factory->AddSpectator("prebjetbcsv_1","prebjetbcsv_1","",'F');
factory->AddSpectator("prebjetbcsv_2","prebjetbcsv_2","",'F');
double weightval_=0;
ParseParamFile(paramfile);
for(unsigned int bckgit=0;bckgit<backgroundTrees.size();++bckgit){
auto it = sample_info_.find(bckglist.at(bckgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs = it->second.second;
weightval_=(double) xs/evt;
std::cout<<weightval_<<std::endl;
}
factory->AddBackgroundTree(backgroundTrees.at(bckgit),weightval_);
}
for(unsigned int sgit=0;sgit<signalTrees.size();++sgit){
auto it = sample_info_.find(signallist.at(sgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs=it->second.second;
weightval_=(Double_t) xs/evt;
}
std::cout<<weightval_<<std::endl;
factory->AddSignalTree(signalTrees.at(sgit),weightval_);
}
factory->SetBackgroundWeightExpression("wt");
factory->SetSignalWeightExpression("wt");
TCut mycutb, mycuts;
if(twotag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
}
else if(onetag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
}
else{
mycutb="n_prebjets>1&&mt_1<30";
mycuts="n_prebjets>1&&mt_1<30";
}
//TCut mycutb="";
//TCut mycuts="";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,"SplitMode=Random:!V");
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outfile->Close();
delete factory;
return 0;
}
void test2(){
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
TString outfileName( "trainingBDT_tZq.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "BDT_trainning_tzq", outputFile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
TFile *input_sig = TFile::Open( "../TreeReader/outputroot/histofile_tZq.root" );
TFile *input_wz = TFile::Open( "../TreeReader/outputroot/histofile_WZ.root" );
TTree *signal = (TTree*)input_sig->Get("Ttree_tZq");
TTree *background = (TTree*)input_wz->Get("Ttree_WZ");
factory->AddSignalTree ( signal, 1.);
factory->AddBackgroundTree( background, 1.);
std::vector<TString > varList;
varList.push_back("tree_cosThetaStar");;
varList.push_back("tree_topMass");
varList.push_back("tree_totMass");
varList.push_back("tree_deltaPhilb");
varList.push_back("tree_deltaRlb");
varList.push_back("tree_deltaRTopZ");
varList.push_back("tree_asym");
varList.push_back("tree_Zpt");
varList.push_back("tree_ZEta");
varList.push_back("tree_topPt");
varList.push_back("tree_topEta");
varList.push_back("tree_NJets");
varList.push_back("tree_NBJets");
varList.push_back("tree_deltaRZl");
varList.push_back("tree_deltaPhiZmet");
varList.push_back("tree_btagDiscri");
varList.push_back("tree_totPt");
varList.push_back("tree_totEta");
varList.push_back("tree_leptWPt");
varList.push_back("tree_leptWEta");
varList.push_back("tree_leadJetPt");
varList.push_back("tree_leadJetEta");
varList.push_back("tree_deltaRZleptW");
varList.push_back("tree_deltaPhiZleptW");
varList.push_back("tree_met" );
varList.push_back("tree_mTW" );
for(unsigned int i=0; i< varList.size() ; i++) factory->AddVariable( varList[i].Data(), 'F');
factory->SetSignalWeightExpression ("tree_EvtWeight");
factory->SetBackgroundWeightExpression("tree_EvtWeight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
//factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "", int isMC=1, int useSvtx=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();
// to get access to the GUI and all tmva macros
TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
//gROOT->ProcessLine(".L /Users/kjung/root5-34-23/tmva/test/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"] = 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"] = 1; // 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;
string svtxExt = "noSvtx";
if(useSvtx) svtxExt = "withSvtx";
if(!isMC) outfileName = "TMVA_trained_data.root";
else outfileName = Form("TMVA_trained_cJet_medDCuts_BvC_%s.root",svtxExt.c_str());
cout << "fn: "<< outfileName << endl;
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
outputFile->cd();
// 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' );
if(useSvtx) factory->AddVariable("svtxptFrac","svtx pt fraction","units",'F');
//factory->AddVariable( "djetR", "Closest Meson to Jet dr", "", 'F' );
factory->AddVariable( "nIP","number of IP trks","units",'I');
if(useSvtx) factory->AddVariable( "svtxm", "svtx mass", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxmEnergyFrac","svtxmEnergyFrac","units",'F');
if(useSvtx) factory->AddVariable( "svtxpt", "svtx pt", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxmcorr", "corrected svtx mass", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxdl", "svtx displacement", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxdls", "svtx displacement significance", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxntrk", "svtx ntracks", "units", 'F');
if(useSvtx) factory->AddVariable( "sv2Trkdl", "2trk svtx close2PV dl", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxTrkSumChi2", "svtx trk sum chi2", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxTrkNetCharge", "svtx trk net chg", "units", 'F');
if(useSvtx) factory->AddVariable( "svtxNtrkInCone", "svtx ntrk in cone", "units", 'F');
//factory->AddVariable( "jteta", "Jet eta", "units", 'F' );
factory->AddVariable( "closestDMass","Closest DMass", "units", 'F' );
factory->AddVariable( "closestDType","Closest Type","units",'F');
factory->AddVariable( "closestDPt","Closest DpT", "units", 'F' );
/*factory->AddVariable( "chargedMax","chargedMax","units",'F');
factory->AddVariable( "chargedSum","chargedSum","units",'F');
factory->AddVariable( "neutralMax","neutralMax","units",'F');
factory->AddVariable( "neutralSum","neutralSum","units",'F');
factory->AddVariable( "photonMax","photonMax","units",'F');
factory->AddVariable( "photonSum","photonSum","units",'F');
factory->AddVariable( "eSum","eSum","units",'F');
factory->AddVariable( "muSum","muSum","units",'F');*/
for(int i=0; i<3; i++){
//factory->AddVariable( Form("ipProb0_%d",i),Form("prob0 IP part %d",i),"units",'F');
//factory->AddVariable( Form("ipPt_%d",i),Form("IP pt part %d",i),"units",'F');
factory->AddVariable( Form("trackIP2dSig_%d",i),Form("IP trk 2d sig part %d",i),"units",'F');
factory->AddVariable( Form("trackIP3dSig_%d",i),Form("IP trk 3d sig part %d",i),"units",'F');
factory->AddVariable( Form("trackIP2d_%d",i),Form("IP trk 2d part %d",i),"units",'F');
factory->AddVariable( Form("trackIP3d_%d",i),Form("IP trk 3d part %d",i),"units",'F');
}
for(int i=0; i<1; i++){
//factory->AddVariable( Form("trackPtRel_%d",i),Form("pt rel part %d",i),"units",'F');
//factory->AddVariable( Form("trackPPar_%d",i),Form("track ppar part %d",i),"units",'F');
//factory->AddVariable( Form("trackPParRatio_%d",i),Form("track ppar part %d",i),"units",'F');
factory->AddVariable( Form("trackJetDist_%d",i),Form("dist to jet part %d",i),"units",'F');
factory->AddVariable( Form("trackDecayLenVal_%d",i),Form("trk decay len part %d",i),"units",'F');
//factory->AddVariable( Form("trackDeltaR_%d",i),Form("trk dr to jet part %d",i),"units",'F');
//factory->AddVariable( Form("trackPtRatio_%d",i),Form("trk pt ratio part %d",i),"units",'F');
}
//factory->AddVariable( "trackSip2dSigAboveCharm","trackSip2dSigAboveCharm","units",'F');
//factory->AddVariable( "trackSip3dSigAboveCharm","trackSip3dSigAboveCharm","units",'F');
//factory->AddVariable( "trackSip2dValAboveCharm","trackSip2dValAboveCharm","units",'F');
//factory->AddVariable( "trackSip3dValAboveCharm","trackSip3dValAboveCharm","units",'F');
//factory->AddVariable( "svJetDeltaR","svJetDeltaR","units",'F');
factory->AddVariable( "trackSumJetDeltaR","trackSumJetDeltaR","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' );
if(isMC) factory->AddSpectator( "refpt", "ref pT", "units", 'F' );
factory->AddSpectator( "rawpt", "raw pT", "units", 'F' );
//factory->AddSpectator( "dCandPt", "D-Meson pT", "units" , 'F' );
if(isMC) factory->AddSpectator( "refparton_flavorForB", "jet flavor", "units" , 'F' );
//factory->AddSpectator( "evtSelection", "event selection", "units" , 'F' );
//factory->AddSpectator( "vz", "z-vertex", "units" , 'F' );
//if(isMC) factory->AddSpectator( "subid", "subid", "units" , 'F' );
//factory->AddSpectator( "pthat", "pthat", "units" , 'F' );
//factory->AddSpectator( "run", "run", "units" , 'I' );
//factory->AddSpectator( "bin", "centrality", "units" , 'I' );
factory->AddSpectator( "jtpt", "Jet pT", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fname;
if(!isMC) fname = "/Users/kjung/charmJets/pPb/input/DMesonCJet_pPbData_ppReco_akPu3PF_convertToJetTree_withLHCbVars_medDCuts.root";
else fname = "/Users/kjung/charmJets/pPb/input/DMesonCJet_QCDJetOnly_pPbMC_ppReco_akPu3PF_convertToJetTree_medDCuts.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, *background;
if(useSvtx){
signal = (TTree*)input->Get("jets");
background = (TTree*)input->Get("jets");
}
else{
signal = (TTree*)input->Get("jetsNoSvtx");
background = (TTree*)input->Get("jetsNoSvtx");
}
TTree *signal_2 = (TTree*)input->Get("dMesons");
TTree *background_2 = (TTree*)input->Get("dMesons");
signal->AddFriend(signal_2);
background->AddFriend(background_2);
// 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
const int nvars = 35; //67;
const int nvarsWithInt = 2;
double weight;
std::vector<double> vars(nvars);
double treevars[nvars-nvarsWithInt];
int treevars2[nvarsWithInt];
//std::string variables[nvars] = {"djetR","closestDPt","svtxm","svtxdl","jtpt","refpt","rawpt","refparton_flavorForB","svtxdls","trackIP2dSig_0","trackIP3dSig_0","trackIP2d_0","trackIP3d_0","ipProb0_0","trackPtRel_0","trackPPar_0","trackPParRatio_0","trackJetDist_0","trackDecayLenVal_0","trackDeltaR_0","trackPtRatio_0","ipPt_0","trackIP2dSig_1","trackIP3dSig_1","trackIP2d_1","trackIP3d_1","ipProb0_1","trackPtRel_1","trackPPar_1","trackPParRatio_1","trackJetDist_1","trackDecayLenVal_1","trackDeltaR_1","trackPtRatio_1","ipPt_1","trackIP2dSig_2","trackIP3dSig_2","trackIP2d_2","trackIP3d_2","ipProb0_2","trackPtRel_2","trackPPar_2","trackPParRatio_2","trackJetDist_2","trackDecayLenVal_2","trackDeltaR_2","trackPtRatio_2","ipPt_2","trackIP2dSig_3","trackIP3dSig_3","trackIP2d_3","trackIP3d_3","ipProb0_3","trackPtRel_3","trackPPar_3","trackPParRatio_3","trackJetDist_3","trackDecayLenVal_3","trackDeltaR_3","trackPtRatio_3","ipPt_3","trackSip2dValAboveCharm","trackSip3dValAboveCharm","svJetDeltaR","trackSumJetDeltaR","nIP","svtxntrk"};
std::string variables[nvars] = {"jtpt","refpt","rawpt","refparton_flavorForB","svtxptFrac","svtxmEnergyFrac","svtxpt","svtxm",
"svtxdl","svtxdls","svtxTrkSumChi2","svtxTrkNetCharge","sv2Trkdl", "closestDMass","closestDType","closestDPt","trackIP2dSig_0","trackIP2dSig_1",
"trackIP2dSig_2","trackIP3dSig_0","trackIP3dSig_1","trackIP3dSig_2","trackIP2d_0","trackIP2d_1",
"trackIP2d_2","trackIP3d_0","trackIP3d_1","trackIP3d_2","trackJetDist_0","trackDecayLenVal_0","svJetDeltaR",
"trackSumJetDeltaR","svtxNtrkInCone","svtxntrk","nIP"};
//std::string variables[nvars] = {"jtpt","refpt","rawpt","refparton_flavorForB","svtxptFrac","svtxdl","svtxdls","closestDPt","closestDType","closestDMass","svtxm","svtxmcorr","svJetDeltaR","trackSumJetDeltaR","svtxpt","sv2Trkdl","svtxTrkSumChi2","svtxTrkNetCharge","svtxNtrkInCone","svtxntrk"};
signal->SetBranchAddress("weight", &weight);
for (UInt_t ivar=0; ivar<nvars-nvarsWithInt; ivar++) signal->SetBranchAddress( variables[ivar].c_str(), &(treevars[ivar]) );
for (UInt_t ivar=nvars-nvarsWithInt; ivar<nvars; ivar++) signal->SetBranchAddress( variables[ivar].c_str(), &(treevars2[ivar]) );
for (UInt_t i=0; i<signal->GetEntries(); i++) {
signal->GetEntry(i);
for (UInt_t ivar=0; ivar<nvars-nvarsWithInt; ivar++) vars[ivar] = treevars[ivar];
for (UInt_t ivar=nvars-nvarsWithInt; ivar<nvars; ivar++) vars[ivar] = treevars2[ivar];
// add training and test events; here: first half is training, second is testing
// note that the weight can also be event-wise
//for(int ij=0; ij<nvars; ij++) cout << ij << " " << vars[ij] << endl;
if(isMC && (abs(vars[3])==4)) {
if (i%2==0) factory->AddSignalTrainingEvent( vars, weight );
else factory->AddSignalTestEvent ( vars, weight );
}
}
//
// // Background (has event weights)
background->SetBranchAddress( "weight", &weight );
for (UInt_t ivar=0; ivar<nvars-nvarsWithInt; ivar++) background->SetBranchAddress( variables[ivar].c_str(), &(treevars[ivar]) );
for (UInt_t ivar=nvars-nvarsWithInt; ivar<nvars; ivar++) background->SetBranchAddress( variables[ivar].c_str(), &(treevars2[ivar]) );
for (UInt_t i=0; i<background->GetEntries(); i++) {
background->GetEntry(i);
for (UInt_t ivar=0; ivar<nvars-nvarsWithInt; ivar++) vars[ivar] = treevars[ivar];
for (UInt_t ivar=nvars-nvarsWithInt; ivar<nvars; ivar++) vars[ivar] = treevars2[ivar];
// add training and test events; here: first half is training, second is testing
// note that the weight can also be event-wise
if(isMC && (abs(vars[3])==5)) {
if (i%2==0) factory->AddBackgroundTrainingEvent( vars, weight );
else factory->AddBackgroundTestEvent ( vars, 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->SetSignalWeightExpression("weight");
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
//
// 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=850:MinNodeSize=2%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.05:UseBaggedBoost:GradBaggingFraction=0.9:SeparationType=GiniIndex:nCuts=500: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()) 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 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");
gROOT->ProcessLine(".L BDT.C");
gROOT->ProcessLine(".L BDTControlPlots.C");
gROOT->ProcessLine(".L BDT_Reg.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
//
// Turn on-off the MVA to run
//
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 1;
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"] = 0; // uses Adaptive Boost
Use["BDTG"] = 1; // 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.
string outFileName = "TMVA_" + sSelection[mode-1] + ".root";
TString outfileName( outFileName.c_str());
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' );
*/
//Not order matter for the CutRange declarations
if(mode==1){
//SRZjets inside Z use mT2, pTll, mjj, dR_ll, mEff, mWWT
factory->AddVariable( "mT2", 'F');
factory->AddVariable( "pTll", 'F');
factory->AddVariable( "mjj", 'F');
factory->AddVariable( "dR_ll", 'F');
factory->AddVariable( "mEff", 'F');
factory->AddVariable( "mWWT", 'F');
factory->AddVariable( "mctPerp", 'F');
factory->AddVariable( "metrel", 'F');
factory->AddVariable( "met/mEff", 'F');
factory->AddVariable( "mT2jj", 'F');
factory->AddVariable( "sphericity", 'F');
factory->AddVariable( "sphericityTrans", 'F');
factory->AddVariable( "abs(llAcoplanarity+3.1415)", 'F');
factory->AddVariable( "abs(jjAcoplanarity+3.1415)", 'F');
factory->AddVariable( "mTl[0]", 'F');
factory->AddVariable( "mTl[1]", 'F');
//factory->AddVariable( "mctPara", 'F'); //issue with var content NAN
}
else if(mode==2){
factory->AddVariable( "mT2", 'F');
factory->AddVariable( "pTll", 'F');
factory->AddVariable( "mjj", 'F');
factory->AddVariable( "dR_ll", 'F');
factory->AddVariable( "mEff", 'F');
factory->AddVariable( "mWWT", 'F');
factory->AddVariable( "mctPerp", 'F');
factory->AddVariable( "metrel", 'F');
factory->AddVariable( "met/mEff", 'F');
factory->AddVariable( "mT2jj", 'F');
factory->AddVariable( "sphericity", 'F');
factory->AddVariable( "sphericityTrans", 'F');
factory->AddVariable( "abs(llAcoplanarity+3.1415)", 'F');
factory->AddVariable( "abs(jjAcoplanarity+3.1415)", 'F');
factory->AddVariable( "mTl[0]", 'F');
factory->AddVariable( "mTl[1]", 'F');
}
else if(mode==3){
factory->AddVariable( "mT2", 'F');
factory->AddVariable( "pTll", 'F');
factory->AddVariable( "mjj", 'F');
factory->AddVariable( "dR_ll", 'F');
factory->AddVariable( "mEff", 'F');
factory->AddVariable( "mWWT", 'F');
factory->AddVariable( "mctPerp", 'F');
factory->AddVariable( "metrel", 'F');
factory->AddVariable( "met/mEff", 'F');
factory->AddVariable( "mT2jj", 'F');
factory->AddVariable( "sphericity", 'F');
factory->AddVariable( "sphericityTrans", 'F');
factory->AddVariable( "abs(llAcoplanarity+3.1415)", 'F');
factory->AddVariable( "abs(jjAcoplanarity+3.1415)", 'F');
factory->AddVariable( "mTl[0]", 'F');
factory->AddVariable( "mTl[1]", 'F');
}
else if(mode==4){
factory->AddVariable( "mT2", 'F');
factory->AddVariable( "pTll", 'F');
factory->AddVariable( "dR_ll", 'F');
factory->AddVariable( "mWWT", 'F');
factory->AddVariable( "metrel", 'F');
factory->AddVariable( "mTl[0]", 'F');
factory->AddVariable( "mTl[1]", '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_bkg = string(getenv("HISTOANA")) + "/SusyAna/" + ver +
"toyNt_Bkg_Zjets_SherpaAlpgen_WZ_ZZ_PowHeg_WW_PowHeg_TopMCNLO_" + toySkim + "_rlep.root";
if(toySkim == "DIL_optimSRSS")
fname_bkg = string(getenv("HISTOANA")) + "/SusyAna/" + ver +
"toyNt_Bkg_Zjets_SherpaAlpgen_WZ_ZZ_PowHeg_WW_PowHeg_TopMCNLO_FAKE_" + toySkim + ".root";
std::cout << "Bkg file: " << fname_bkg << std::endl;
TFile* fBkg = TFile::Open( fname_bkg.Data() );
TString fname_sig;
fname_sig = string(getenv("HISTOANA")) + "/SusyAna/" + ver + "ToyNtOutputs/";
if(mode==1) fname_sig += "164339_" + toySkim + ".root"; //wA_noslep_300_50
else if(mode==2) fname_sig += "164326_" + toySkim + ".root"; //wA_noslep_150_0
else if(mode==3) fname_sig += "157955_" + toySkim + ".root"; //wA_slep_142_107
//else if(mode==4) fname_sig += "176559_" + toySkim + ".root"; //wC_slep_117_47
else if(mode==4) fname_sig += "144907_" + toySkim + ".root"; //wC_slep_150_50
std::cout << "Signal file: " << fname_sig << std::endl;
TFile* fSig = TFile::Open( fname_sig.Data() );
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
std::cout << "--- TMVAClassification : Using input Bkg file: " << fBkg->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input Sig file: " << fSig->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)fSig->Get("ToyNt");
TTree *background = (TTree*)fBkg->Get("ToyNt");
// 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( "w" );
factory->SetSignalWeightExpression( "w");
// Apply additional cuts on the signal and background samples (can be different)
// for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycuts = "";
if(mode==1){ //Optimisation inside Z peak
mycuts = "(llType==0 || llType==1) && abs(mll-91.2)<10 && nCJets>=2 \
&& j_pt[0]>20 && j_isC20[0] && Alt$(j_pt[1],0) && Alt$(j_isC20[1],0)";
/* \&& mEff>250 && met/mEff>0.3"; */
}
else if(mode==2){
mycuts = "(llType==0 || llType==1) && abs(mll-91.2)<10 && nCJets>=2 \
&& j_pt[0]>20 && j_isC20[0] && Alt$(j_pt[1],0) && Alt$(j_isC20[1],0) \
&& mT2jj>60";
}
else if(mode==3){
mycuts = "llType==1 && nBJets==0 &&nFJets==0 ";
}
else if(mode==4){
mycuts = "llType==2";
}
/*
//Optimation close to diagonal
TCut mycuts = "(llType==0 || llType==1) && mll<50 && nCJets>=2 \
&& j_pt[0]>20 && j_isC20[0] && Alt$(j_pt[1],0) && Alt$(j_isC20[1],0)";
*/
// for example: TCut mycutb = "abs(var1)<0.5";
TCut mycutb = mycuts;
// 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" );
if(mode==1)
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=4000:nTrain_Background=100000:SplitMode=Random:NormMode=NumEvents:!V" );
else if(mode==2)
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=4000:nTrain_Background=100000:SplitMode=Random:NormMode=NumEvents:!V" );
else if(mode==3)
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=1000:nTrain_Background=100000:SplitMode=Random:NormMode=NumEvents:!V" );
else if(mode==4)
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=1000:nTrain_Background=100000: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:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=1000:CutRangeMin[2]=0:CutRangeMax[2]=2000:CutRangeMin[3]=0:CutRangeMax[3]=5:CutRangeMin[4]=0:CutRangeMax[4]=3000:CutRangeMin[5]=0:CutRangeMax[5]=2000: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"]){
if(mode==1)
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"!H:V:FitMethod=GA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=1000:CutRangeMin[2]=0:CutRangeMax[2]=2000:CutRangeMin[3]=0:CutRangeMax[3]=5:CutRangeMin[4]=0:CutRangeMax[4]=3000:CutRangeMin[5]=0:CutRangeMax[5]=2000:VarProp=FSmart:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
else if(mode==2)
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"!H:V:FitMethod=GA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=3000:CutRangeMin[2]=0:CutRangeMax[2]=3000:CutRangeMin[3]=0:CutRangeMax[3]=1000:CutRangeMin[4]=0:CutRangeMax[4]=1000:CutRangeMin[5]=0:CutRangeMax[5]=3000:VarProp=FSmart:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
else if(mode==3)
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"!H:V:FitMethod=GA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=2000:CutRangeMin[2]=0:CutRangeMax[2]=1000:CutRangeMin[3]=0:CutRangeMax[3]=5:VarProp=FSmart:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
}
if (Use["CutsSA"]){
if(mode==1)
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=1000:CutRangeMin[2]=0:CutRangeMax[2]=2000:CutRangeMin[3]=0:CutRangeMax[3]=5:CutRangeMin[4]=0:CutRangeMax[4]=3000:CutRangeMin[5]=0:CutRangeMax[5]=2000:VarProp=FSmart:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
else if(mode==2)
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=3000:CutRangeMin[2]=0:CutRangeMax[2]=3000:CutRangeMin[3]=0:CutRangeMax[3]=1000:CutRangeMin[4]=0:CutRangeMax[4]=1000:CutRangeMin[5]=0:CutRangeMax[5]=3000:VarProp=FSmart:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
else if(mode==3)
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:CutRangeMin[0]=0:CutRangeMax[0]=1000:CutRangeMin[1]=0:CutRangeMax[1]=2000:CutRangeMin[2]=0:CutRangeMax[2]=1000:CutRangeMin[3]=0:CutRangeMax[3]=5:VarProp=FSmart: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=500:HiddenLayers=N+1: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:IgnoreNegWeightsInTraining=True" ); // 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 [MY DEFAULT]
if (Use["BDTG"]){ // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=300:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=10:NNodesMax=5:IgnoreNegWeightsInTraining=True" );
}
if (Use["BDT"]){ // Adaptive Boost
if(mode<3){
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:V:NTrees=100:nEventsMin=2000:MaxDepth=4:UseRandomisedTrees=True:UseNVars=4:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:PruneStrength=-1:IgnoreNegWeightsInTraining=True" );
}
else if(mode==3){
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:V:NTrees=50:nEventsMin=2000:MaxDepth=4:UseRandomisedTrees=True:UseNVars=4:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:PruneStrength=-1:IgnoreNegWeightsInTraining=True" );
}
}
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 );
}
std::pair<TString,TString> TMVAClassification (
TString infilename,
AnalysisType analysisType = AnalysisType::DIRECT,
TString additionalRootFileName = "")
{
TMVA::Tools::Instance();
std::string tmstr (now ());
TString tmstmp (tmstr.c_str ());
std::cout << "==> Start TMVAClassification" << std::endl;
std::cout << "-------------------- open input file ---------------- " << std::endl;
TString fname = infilename; //pathToData + infilename + TString (".root");
if (analysisType != AnalysisType::TRANSFORMED)
fname = pathToData + infilename + TString (".root");
std::cout << "open file " << std::endl << fname.Data () << std::endl;
std::cout << "-------------------- get tree ---------------- " << std::endl;
TString treeName = "data";
if (analysisType == AnalysisType::TRANSFORMED)
treeName = "transformed";
std::cout << "-------------------- create tchain with treeName ---------------- " << std::endl;
std::cout << treeName << std::endl;
TChain* tree = new TChain (treeName);
std::cout << "add file" << std::endl;
std::cout << fname << std::endl;
tree->Add (fname);
TChain* treeFriend (NULL);
if (additionalRootFileName.Length () > 0)
{
std::cout << "-------------------- add additional input file ---------------- " << std::endl;
std::cout << additionalRootFileName << std::endl;
treeFriend = new TChain (treeName);
treeFriend->Add (additionalRootFileName);
tree->AddFriend (treeFriend,"p");
}
// tree->Draw ("mass:prediction");
// return std::make_pair(TString("hallo"),TString ("nix"));
TString outfileName;
if (analysisType == AnalysisType::BACKGROUND)
{
outfileName = TString ("BACK_" + infilename) + tmstmp + TString (".root");
}
else
outfileName += TString ( "TMVA__" ) + tmstmp + TString (".root");
std::cout << "-------------------- open output file ---------------- " << std::endl;
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
std::cout << "-------------------- prepare factory ---------------- " << std::endl;
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"AnalysisType=Classification:Transformations=I:!V" );
std::cout << "-------------------- add variables ---------------- " << std::endl;
for (auto varname : variableNames)
{
factory->AddVariable (varname.c_str (), 'F');
}
for (auto varname : spectatorNames)
{
factory->AddSpectator (varname.c_str (), 'F');
}
std::cout << "-------------------- add trees ---------------- " << std::endl;
TCut signalCut ("signal==1");
TCut backgroundCut ("signal==0");
if (analysisType == AnalysisType::TRANSFORMED)
{
signalCut = "(signal_original==1 && signal_in==0)";
backgroundCut = "(signal_original==0 && signal_in==0)";
}
if (analysisType == AnalysisType::BACKGROUND)
{
signalCut = TString("(signal==0) * (prediction > 0.7)");
backgroundCut = TString("(signal==0) * (prediction < 0.4)");
}
//tree->Draw ("prediction",signalCut);
//return std::make_pair(TString("hallo"),TString ("nix"));
factory->AddTree(tree, "Signal", 1.0, baseCut + signalCut, "TrainingTesting");
factory->AddTree(tree, "Background", 1.0, baseCut + backgroundCut, "TrainingTesting");
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
/* // Set individual event weights (the variables must exist in the original TTree) */
if (analysisType == AnalysisType::BACKGROUND)
{
factory->SetSignalWeightExpression ("prediction");
factory->SetBackgroundWeightExpression ("1");
}
std::cout << "-------------------- prepare ---------------- " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
TString methodName ("");
if (analysisType == AnalysisType::BACKGROUND)
methodName = TString ("TONBKG_") + tmstmp;
if (false)
{
// gradient boosting training
methodName += TString("GBDT");
factory->BookMethod(TMVA::Types::kBDT, methodName,
"NTrees=40:BoostType=Grad:Shrinkage=0.01:MaxDepth=7:UseNvars=6:nCuts=20:MinNodeSize=10");
}
if (false)
{
methodName += TString("Likelihood");
factory->BookMethod( TMVA::Types::kLikelihood, methodName,
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
}
if (false)
{
TString layoutString ("Layout=TANH|100,LINEAR");
TString training0 ("LearningRate=1e-1,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-2,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-2,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-3,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNgauss");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (false)
{
TString layoutString ("Layout=TANH|200,TANH|70,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2;
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CROSSENTROPY");
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=N:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName = TString("NNnormalized");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (true)
{
TString layoutString ("Layout=TANH|100,TANH|50,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=100,BatchSize=20,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=30,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:!V:ErrorStrategy=CROSSENTROPY:VarTransform=P+G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNPG");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
factory->TrainAllMethods();
// return std::make_pair(TString("hallo"),TString ("nix"));
factory->TestAllMethods();
factory->EvaluateAllMethods();
//input->Close();
outputFile->Close();
// TMVA::TMVAGui (outfileName);
delete factory;
delete tree;
switch (analysisType)
{
case AnalysisType::BACKGROUND:
std::cout << "DONE BACKGROUND" << std::endl;
break;
case AnalysisType::DIRECT:
std::cout << "DONE DIRECT" << std::endl;
break;
case AnalysisType::TRANSFORMED:
std::cout << "DONE TRANSFORMED" << std::endl;
break;
};
std::cout << "classification, return : " << outfileName << " , " << methodName << std::endl;
return std::make_pair (outfileName, methodName);
}