Float_t hhMVA::GetBDTValue(Float_t mTT, Float_t ptTT, Float_t mBB, Float_t ptBB,
Float_t mHH, Float_t ptHH, Float_t mt2,
Float_t dRbb, Float_t dRtt, Float_t dRhh) {
if (!fTMVAReader) {
cout << "TMVA reader not initialized properly" << endl;
return -999;
}
fMVAVar_mTT =mTT;
fMVAVar_ptTT =ptTT;
fMVAVar_mBB1 =mBB;
fMVAVar_ptBB1 =ptBB;
fMVAVar_mHH =mHH;
fMVAVar_ptHH =ptHH;
fMVAVar_mt2 =mt2;
fMVAVar_dRbb =dRbb;
fMVAVar_dRtt =dRtt;
fMVAVar_dRhh =dRhh;
TMVA::Reader *reader = 0;
reader = fTMVAReader;
return reader->EvaluateMVA("BDT method");
}
int reader_wrapper::bookReader( TString xml_file_name) {
m_reader = new TMVA::Reader("!Color:Silent");
for (auto var : m_spectators) {
m_reader->AddSpectator(var.formula, &var.value);
}
for (auto& var : m_variables) {
m_reader->AddVariable(var.formula, &var.value);
}
m_reader->BookMVA( m_methodName, xml_file_name );
return 0;
}
void TMVAPredict()
{
std::ofstream outfile ("baseline_c.csv");
outfile << "id,prediction\n";
TMVA::Tools::Instance();
std::cout << "==> Start TMVAPredict" << std::endl;
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
string variables_name[3] = {"LifeTime",
"FlightDistance",
"pt"}
Float_t variables[3];
for (int i=0; i < 3; i++){
reader->AddVariable(variables_name[i].c_str(), &variables[i]);
variables[i] = 0.0;
}
TString dir = "weights/";
TString prefix = "TMVAClassification";
TString method_name = "GBDT";
TString weightfile = dir + prefix + TString("_") + method_name + TString(".weights.xml");
reader->BookMVA( method_name, weightfile );
TFile *input(0);
input = TFile::Open("../tau_data/test.root");
TTree* tree = (TTree*)input->Get("data");
Int_t ids;
Float_t prediction;
tree->SetBranchAddress("id", &ids);
for (int i=0; i < 3; i++){
tree->SetBranchAddress(variables_name[i].c_str(), &variables[i]);
}
for (Long64_t ievt=0; ievt < tree->GetEntries(); ievt++) {
tree->GetEntry(ievt);
prediction = reader->EvaluateMVA(method_name);
outfile << ids << "," << (prediction + 1.) / 2. << "\n";
}
outfile.close();
input->Close();
delete reader;
}
int reader_wrapper::GetEntry(Long64_t e) {
/// don't care about spectators here
for (auto b: m_branches) {
b->GetEntry(e);
}
for (auto& v : m_variables) {
v.value = v.ttreeformula->EvalInstance();
}
m_response = m_reader->EvaluateMVA(m_methodName.Data());
m_responseBranch->Fill();
return 0;
}
void makeclassification() {
Float_t *vars = new Float_t[10];
//initialize TMVA Reader (example here is diphoton mva from higgs->gamma gamma mva analysis)
TMVA::Reader* tmva = new TMVA::Reader();
tmva->AddVariable("masserrsmeared/mass", &vars[0]);
tmva->AddVariable("masserrsmearedwrongvtx/mass", &vars[1]);
tmva->AddVariable("vtxprob", &vars[2]);
tmva->AddVariable("ph1.pt/mass", &vars[3]);
tmva->AddVariable("ph2.pt/mass", &vars[4]);
tmva->AddVariable("ph1.eta", &vars[5]);
tmva->AddVariable("ph2.eta", &vars[6]);
tmva->AddVariable("TMath::Cos(ph1.phi-ph2.phi)" , &vars[7]);
tmva->AddVariable("ph1.idmva", &vars[8]);
tmva->AddVariable("ph2.idmva", &vars[9]);
tmva->BookMVA("BDTG","/afs/cern.ch/user/b/bendavid/cmspublic/diphotonmvaApr1/HggBambu_SMDipho_Jan16_BDTG.weights.xml");
//tmva->BookMVA("BDTG","/scratch/bendavid/root/HggBambu_SMDipho_Jan16_BDTG.weights.xml");
TMVA::MethodBDT *bdt = dynamic_cast<TMVA::MethodBDT*>(tmva->FindMVA("BDTG"));
//enable root i/o for objects with reflex dictionaries in standalone root mode
ROOT::Cintex::Cintex::Enable();
//open output root file
TFile *fout = new TFile("gbrtest.root","RECREATE");
//create GBRForest from tmva object
GBRForest *gbr = new GBRForest(bdt);
//write to file
fout->WriteObject(gbr,"gbrtest");
fout->Close();
}
int main(){
TMVA::Tools::Instance();
std::cout<<"Hello world"<<std::endl;
TFile* OutputFile = TFile::Open("Outputfile.root","RECREATE");
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", OutputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
std::vector<VMVariable*> Variables;
MVariable* Var3= new MVariable("var3",F,none);
MVariable* Var4 = new MVariable("var4",F,none);
Variables.push_back(Var3);
Variables.push_back(Var4);
MVariable* Var1 = new MVariable("var1",F,none);
MVariable* Var2 = new MVariable("var2",F,none);
MultiVariable* MyVar1 = new MultiVariable("Var1+Var2",sum);
MyVar1->AddVariable(Var1);
MyVar1->AddVariable(Var2);
Variables.push_back(MyVar1);
MultiVariable* MyVar2 = new MultiVariable("Minus",subtract);
MyVar2->AddVariable(Var1);
MyVar2->AddVariable(Var2);
Variables.push_back(MyVar2);
std::string InputName= "./tmva_class_exampleD.root";
TFile *input = TFile::Open("./tmva_class_exampleD.root" );
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background=(TTree*)input->Get("TreeB");
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
for(auto v:Variables){
factory->AddVariable(v->GetFactoryName(),v->GetType());
}
factory->SetBackgroundWeightExpression( "weight" );
TCut mycuts = "";
TCut mycutb = "";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
std::vector<MClassifier*> Classifiers;
Classifiers.push_back(new MClassifier(TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20"));
for(auto C:Classifiers){
if(!(C->AddMethodToFactory(factory))){
std::cout<<"Booking classifier failed"<<std::endl;
return 1;
}
}
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
OutputFile->Close();
delete factory;
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
for(auto v: Variables){
reader->AddVariable(v->GetFactoryName(),v->GetReaderAddress());
}
for(auto C:Classifiers){
if(!(C->AddMethodToReader(reader,"./weights/","TMVAClassification"))){
std::cout<<"Failed adding classifer to reader"<<std::endl;
return 1;
}
}
TFile* Input = TFile::Open("./tmva_class_exampleD.root");
TTree* TreeToEvaluate= (TTree*)Input->Get("TreeS");
TFile* AppliedFile = new TFile("AppliedFile.root","RECREATE");
TTree* AppliedTree=TreeToEvaluate->CloneTree(0);
for(auto C:Classifiers){
if(!(C->MakeBranch(AppliedTree)))return 1;
}
for(auto Var:Variables){
if(!(Var->SetBA(TreeToEvaluate))){
std::cout<<"Problem Setting Branch addresses"<<std::endl;
return 1;
}
}
Long64_t N=TreeToEvaluate->GetEntries();
LoopTimer LT(0.05);
int vetoedeventcounter=0;
double StartEntry=0.0;
double LastEntry=0.0;
Long64_t iStart=0;
Long64_t iEnd=N;
for(Long64_t i=iStart;i<iEnd;++i){
LT.DeclareLoopStart(iEnd-iStart);
TreeToEvaluate->GetEntry(i);
bool useevent=true;
for(auto Var:Variables){
useevent=Var->DoOperation();
}
if(!useevent){
vetoedeventcounter++;
continue;
}
for(auto C:Classifiers){
if(!(C->Apply(reader)))return 1;
}
AppliedTree->Fill();
}
AppliedTree->Write();
AppliedFile->Close();
std::cout<<"Got here"<<std::endl;
// Compare Applied file from here with applied file from TMVA tests.
TFile* ReadAppliedFile = TFile::Open("AppliedFile.root");
TTree* AppliedTreeRead=(TTree*)ReadAppliedFile->Get("TreeS");
if(!AppliedTreeRead)std::cout<<"NUll pointer to tree"<<std::endl;
double BDTResponse; AppliedTreeRead->SetBranchAddress("BDT_response",&BDTResponse);
TFile* ReadTMVATestFile = TFile::Open("/home/tw/root-v5-34/tmva/test/TreeFile.root");
if(!ReadTMVATestFile)std::cout<<"File open faild"<<std::endl;
TTree* TMVATestTree=(TTree*)ReadTMVATestFile->Get("AppliedTree");
if(!TMVATestTree)std::cout<<"NUll pointer to tree"<<std::endl;
double TestBDTResponse; TMVATestTree->SetBranchAddress("BDT_response",&TestBDTResponse);
Long64_t ATRN=AppliedTreeRead->GetEntries();
Long64_t TTTN=TMVATestTree->GetEntries();
std::cout<<"Entries in my tree= "<<ATRN<<std::endl;
std::cout<<"Entries in TMVA tree= "<<TTTN<<std::endl;
if(ATRN!=TTTN)std::cout<<"SOMETHING WRONG EVENTS NOT EQUAL"<<std::endl;
std::vector<double> ATRValues;
std::vector<double> TTTValues;
for(int i=0;i<ATRN;++i){
TMVATestTree->GetEntry(i);
AppliedTreeRead->GetEntry(i);
ATRValues.push_back(BDTResponse);
TTTValues.push_back(TestBDTResponse);
// std::cout<<" MYTree = "<<BDTResponse<<" TMVATREE= "<<TestBDTResponse<<std::endl;
}
std::sort(ATRValues.begin(),ATRValues.end());
std::sort(TTTValues.begin(),TTTValues.end());
for(int i=0;i<TTTN;++i){
std::cout<<" MY Value= "<<ATRValues.at(i)<<" TTT Value = "<<TTTValues.at(i)<<std::endl;
}
}
void TMVARegressionApplication( TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 1;
Use["KNN"] = 1;
//
// --- Linear Discriminant Analysis
Use["LD"] = 1;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 1;
Use["DNN_CPU"] = 0;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0;
Use["BDTG"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegressionApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t var1, var2;
reader->AddVariable( "var1", &var1 );
reader->AddVariable( "var2", &var2 );
// Spectator variables declared in the training have to be added to the reader, too
Float_t spec1,spec2;
reader->AddSpectator( "spec1:=var1*2", &spec1 );
reader->AddSpectator( "spec2:=var1*3", &spec2 );
// --- Book the MVA methods
TString dir = "dataset/weights/";
TString prefix = "TMVARegression";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = it->first + " method";
TString weightfile = dir + prefix + "_" + TString(it->first) + ".weights.xml";
reader->BookMVA( methodName, weightfile );
}
}
// Book output histograms
TH1* hists[100];
Int_t nhists = -1;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
TH1* h = new TH1F( it->first.c_str(), TString(it->first) + " method", 100, -100, 600 );
if (it->second) hists[++nhists] = h;
}
nhists++;
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fname = "./tmva_reg_example.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
else {
TFile::SetCacheFileDir(".");
input = TFile::Open("http://root.cern.ch/files/tmva_reg_example.root", "CACHEREAD"); // if not: download from ROOT server
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVARegressionApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
TTree* theTree = (TTree*)input->Get("TreeR");
std::cout << "--- Select signal sample" << std::endl;
theTree->SetBranchAddress( "var1", &var1 );
theTree->SetBranchAddress( "var2", &var2 );
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) {
std::cout << "--- ... Processing event: " << ievt << std::endl;
}
theTree->GetEntry(ievt);
// Retrieve the MVA target values (regression outputs) and fill into histograms
// NOTE: EvaluateRegression(..) returns a vector for multi-target regression
for (Int_t ih=0; ih<nhists; ih++) {
TString title = hists[ih]->GetTitle();
Float_t val = (reader->EvaluateRegression( title ))[0];
hists[ih]->Fill( val );
}
}
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// --- Write histograms
TFile *target = new TFile( "TMVARegApp.root","RECREATE" );
for (Int_t ih=0; ih<nhists; ih++) hists[ih]->Write();
target->Close();
std::cout << "--- Created root file: \"" << target->GetName()
<< "\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVARegressionApplication is done!" << std::endl << std::endl;
}
void TMVAClassificationApplication_tW(TString signal = "data")
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t jetpt;
Float_t jeteta;
Float_t jetphi;
Float_t metpt;
Float_t metpro;
Float_t lep0pt;
Float_t lep1pt;
Float_t lep0eta;
Float_t lep1eta;
Float_t lep0phi;
Float_t lep1phi;
Float_t ptsys;
Float_t ht;
Float_t oblateness;
Float_t sphericity;
Float_t aplanarity;
Float_t njetw;
Float_t sqrts;
Float_t deltarleps;
Float_t deltaphileps;
Float_t deltaetaleps;
Float_t philepmetclose;
Float_t philepmetfar;
Float_t rlepmetclose;
Float_t rlepmetfar;
Float_t philepjetclose;
Float_t philepjetfar;
Float_t rlepjetclose;
Float_t rlepjetfar;
Float_t phijetmet;
Float_t rjetmet;
Float_t mll;
Float_t htnomet;
Float_t ptsysnomet;
Float_t metphi;
Float_t metminusptsysnomet;
reader->AddVariable ("jetpt", &jetpt);
reader->AddVariable ("jeteta", &jeteta);
reader->AddVariable ("jetphi", &jetphi);
reader->AddVariable ("metpt", &metpt);
reader->AddVariable ("metpro",&metpro);
reader->AddVariable ("lep0pt",&lep0pt);
reader->AddVariable ("lep1pt",&lep1pt);
reader->AddVariable ("lep0eta",&lep0eta);
reader->AddVariable ("lep1eta",&lep1eta);
reader->AddVariable ("lep0phi",&lep0phi);
reader->AddVariable ("lep1phi",&lep1phi);
reader->AddVariable ("ptsys",&ptsys);
reader->AddVariable ("ht",&ht);
reader->AddVariable ("oblateness", &oblateness);
reader->AddVariable ("sphericity", &sphericity);
reader->AddVariable ("aplanarity", &aplanarity);
reader->AddVariable ("njetw", &njetw);
reader->AddVariable ("sqrts", &sqrts);
reader->AddVariable ("deltarleps", &deltarleps);
reader->AddVariable ("deltaphileps", &deltaphileps);
reader->AddVariable ("deltaetaleps", &deltaetaleps);
reader->AddVariable ("philepmetclose", &philepmetclose);
reader->AddVariable ("philepmetfar", &philepmetfar);
reader->AddVariable ("rlepmetclose", &rlepmetclose);
reader->AddVariable ("rlepmetfar", &rlepmetfar);
reader->AddVariable ("philepjetclose", &philepjetclose);
reader->AddVariable ("philepjetfar", &philepjetfar);
reader->AddVariable ("rlepjetclose", &rlepjetclose);
reader->AddVariable ("rlepjetfar", &rlepjetfar);
reader->AddVariable ("phijetmet", &phijetmet);
reader->AddVariable ("rjetmet", &rjetmet);
reader->AddVariable ("mll", &mll);
reader->AddVariable ("htnomet", &htnomet);
reader->AddVariable ("ptsysnomet", &ptsysnomet);
reader->AddVariable ("metphi", &metphi);
reader->AddVariable ("metminusptsysnomet", &metminusptsysnomet);
// *************************************************
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "test_tw_00";
TString name = "BDT_"+prefix;
std::cout<<"********* name = "<<name<<std::endl;
//
// book the MVA methods
//
reader->BookMVA( "BDT method", dir + prefix + "_BDT.weights.xml" );
// book output histograms
Int_t nbin = 100;
histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -1.0, 1.0 );
// book example histogram for probability (the other methods are done similarly)
probHistBDT = new TH1F( "Probability_MVA_BDT", "Probability_MVA_BDT", nbin, -1, 1);
rarityHistBDT = new TH1F( "Rarity_MVA_BDT", "Rarity_MVA_BDT", nbin, -1, 1);
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString folder = "rootfiles/";
if(signal == "data") { TString fname = folder+"tmva_test_0_data.root"; }
if(signal == "tw"){ TString fname = folder+"tmva_test_0_twdr.root"; }
if(signal == "ww"){ TString fname = folder+"tmva_test_0_ww.root"; }
if(signal == "qcd"){ TString fname = folder+"tmva_test_0_qcd_mu.root"; }
if(signal == "wz"){ TString fname = folder+"tmva_test_0_wz.root"; }
if(signal == "zz"){ TString fname = folder+"tmva_test_0_zz.root"; }
if(signal == "st"){ TString fname = folder+"tmva_test_0_st.root"; }
if(signal == "tt"){ TString fname = folder+"tmva_test_0_tt.root"; }
if(signal == "wjets"){ TString fname = folder+"tmva_test_0_wjets.root"; }
if(signal == "zjets"){ TString fname = folder+"tmva_test_0_zjets.root"; }
if(signal == "di"){TString fname = folder + "tmva_test_0_di.root";}
input = TFile::Open( fname,"UPDATE");
if (!input) {
cout << "ERROR: could not open data file: " << fname << endl;
exit(1);
}
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
input->cd();
TTree* theTree = (TTree*)input->Get("myTree");
cout << "--- Select signal sample" << endl;
double userjetpt;
double userjeteta;
double userjetphi;
double usermetpt;
double usermetpro;
double userlep0pt;
double userlep1pt;
double userlep0eta;
double userlep1eta;
double userlep0phi;
double userlep1phi;
double userptsys;
double userht;
double useroblateness;
double usersphericity;
double useraplanarity;
double usernjetw;
double usersqrts;
double userdeltarleps;
double userdeltaphileps;
double userdeltaetaleps;
double userphilepmetclose;
double userphilepmetfar;
double userrlepmetclose;
double userrlepmetfar;
double userphilepjetclose;
double userphilepjetfar;
double userrlepjetclose;
double userrlepjetfar;
double userphijetmet;
double userrjetmet;
double userweight;
double userweightnopu;
double usermll;
double userhtnomet;
double userptsysnomet;
double usermetphi;
double usermetminusptsysnomet;
theTree->SetBranchAddress ("savetheweight", &userweight);
theTree->SetBranchAddress ("weightnopu", &userweightnopu);
theTree->SetBranchAddress ("jetpt", &userjetpt);
theTree->SetBranchAddress ("jeteta", &userjeteta);
theTree->SetBranchAddress ("jetphi", &userjetphi);
theTree->SetBranchAddress ("metpt", &usermetpt);
theTree->SetBranchAddress ("metpro",&usermetpro);
theTree->SetBranchAddress ("lep0pt",&userlep0pt);
theTree->SetBranchAddress ("lep1pt",&userlep1pt);
theTree->SetBranchAddress ("lep0eta",&userlep0eta);
theTree->SetBranchAddress ("lep1eta",&userlep1eta);
theTree->SetBranchAddress ("lep0phi",&userlep0phi);
theTree->SetBranchAddress ("lep1phi",&userlep1phi);
theTree->SetBranchAddress ("ptsys",&userptsys);
theTree->SetBranchAddress ("ht",&userht);
theTree->SetBranchAddress ("oblateness", &useroblateness);
theTree->SetBranchAddress ("sphericity", &usersphericity);
theTree->SetBranchAddress ("aplanarity", &useraplanarity);
theTree->SetBranchAddress ("njetw", &usernjetw);
theTree->SetBranchAddress ("sqrts", &usersqrts);
theTree->SetBranchAddress ("deltarleps", &userdeltarleps);
theTree->SetBranchAddress ("deltaphileps", &userdeltaphileps);
theTree->SetBranchAddress ("deltaetaleps", &userdeltaetaleps);
theTree->SetBranchAddress ("philepmetclose", &userphilepmetclose);
theTree->SetBranchAddress ("philepmetfar", &userphilepmetfar);
theTree->SetBranchAddress ("rlepmetclose", &userrlepmetclose);
theTree->SetBranchAddress ("rlepmetfar", &userrlepmetfar);
theTree->SetBranchAddress ("philepjetclose", &userphilepjetclose);
theTree->SetBranchAddress ("philepjetfar", &userphilepjetfar);
theTree->SetBranchAddress ("rlepjetclose", &userrlepjetclose);
theTree->SetBranchAddress ("rlepjetfar", &userrlepjetfar);
theTree->SetBranchAddress ("phijetmet", &userphijetmet);
theTree->SetBranchAddress ("rjetmet", &userrjetmet);
theTree->SetBranchAddress ("mll", &usermll);
theTree->SetBranchAddress ("htnomet", &userhtnomet);
theTree->SetBranchAddress ("ptsysnomet", &userptsysnomet);
theTree->SetBranchAddress ("metphi", &usermetphi);
theTree->SetBranchAddress ("metminusptsysnomet", &usermetminusptsysnomet);
Double_t tBDT;
TTree* BDTTree = new TTree(name,"");
BDTTree->Branch("BDT",&tBDT,"BDT/D");
double tweight = 1;
std::cout<<" ... opening file : "<<fname<<std::endl;
cout << "--- Processing: " << theTree->GetEntries() << " events" << endl;
TH1F *hBDT = new TH1F("hBDT","",100,-1.0,1.0);
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) cout << "--- ... Processing event: " << ievt << endl;
theTree->GetEntry(ievt);
tweight = userweight;
jetpt = userjetpt;
jeteta = userjeteta;
jetphi = userjetphi;
metpt = usermetpt;
metpro = usermetpro;
lep0pt = userlep0pt;
lep1pt = userlep1pt;
lep0eta = userlep0eta;
lep1eta = userlep1eta;
lep0phi = userlep0phi;
lep1phi = userlep1phi;
ptsys = userptsys;
ht = userht;
oblateness = useroblateness;
sphericity = usersphericity;
aplanarity = useraplanarity;
njetw = usernjetw;
sqrts = usersqrts;
deltarleps = userdeltarleps;
deltaphileps = userdeltaphileps;
deltaetaleps = userdeltaetaleps;
philepmetclose = userphilepmetclose;
philepmetfar = userphilepmetfar;
rlepmetclose = userrlepmetclose;
rlepmetfar = userrlepmetfar;
philepjetclose = userphilepjetclose;
philepjetfar = userphilepjetfar;
rlepjetclose = userrlepjetclose;
rlepjetfar = userrlepjetfar;
phijetmet = userphijetmet;
rjetmet = userrjetmet;
mll = usermll;
htnomet = userhtnomet;
ptsysnomet = userptsysnomet;
metphi = usermetphi;
metminusptsysnomet = usermetminusptsysnomet;
double bdt = reader->EvaluateMVA("BDT method");
tBDT = bdt;
BDTTree->Fill();
if (signal == "data") tweight = 1;
hBDT->Fill(bdt,tweight);
double bdt_ = reader->EvaluateMVA("BDT method");
histBdt ->Fill(bdt_);
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
input->cd();
hBDT->Write();
BDTTree->Write();
input->Close();
// --- Write histograms
TFile *target = new TFile( "TMVApp.root","RECREATE" );
histBdt ->Write();
std::cout << "--- Created root file: \"TMVApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void apply(std::string iName="train/OutputTmp.root") {
TMVA::Tools::Instance();
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
float lPt = 0; reader->AddVariable("pt" , &lPt);
//float lEta = 0; reader->AddVariable("eta" , &lEta);
//float lDR = 0; reader->AddVariable("dR" , &lDR);
//float lPtc = 0; reader->AddVariable("ptc" , &lPtc);
// float lPtdR = 0; reader->AddVariable("ptdR" , &lPtdR);
//float lPuppi = 0; reader->AddVariable("puppi" , &lPuppi);
float lPtODR = 0; reader->AddVariable("ptodR" , &lPtODR);
//float lPtODRS = 0; reader->AddVariable("ptodRS" , &lPtODRS);
float lPtODRSO = 0; reader->AddVariable("ptodRSO" , &lPtODRSO);
//float lDRLV = 0; reader->AddVariable("dR_lv" , &lDRLV);
//float lPtcLV = 0; reader->AddVariable("ptc_lv" , &lPtcLV);
//float lPtdRLV = 0; reader->AddVariable("ptdR_lv" , &lPtdRLV);
//float lPuppiLV = 0; reader->AddVariable("puppi_lv" , &lPuppiLV);
float lPtODRLV = 0; reader->AddVariable("ptodR_lv" , &lPtODRLV);
//float lPtODRSLV = 0; reader->AddVariable("ptodRS_lv" , &lPtODRSLV);
float lPtODRSOLV = 0; reader->AddVariable("ptodRSO_lv" , &lPtODRSOLV);
//float lDRPU = 0; reader->AddVariable("dR_pu" , &lDRPU);
//float lPtcPU = 0; reader->AddVariable("pt_pu" , &lPtcPU);
//float lPtdRPU = 0; reader->AddVariable("ptdR_pu" , &lPtdRPU);
//float lPuppiPU = 0; reader->AddVariable("puppi_pu" , &lPuppiPU);
//float lPtODRPU = 0; reader->AddVariable("ptodR_pu" , &lPtODRPU);
//float lPtODRSPU = 0; reader->AddVariable("ptodRS_pu" , &lPtODRSPU);
//float lPtODRSOPU = 0; reader->AddVariable("ptodRSO_pu" , &lPtODRSOPU);
std::string lJetName = "BDT";
reader->BookMVA(lJetName .c_str(),(std::string("weights/TMVAClassificationCategory_PUDisc_v1")+std::string(".weights.xml")).c_str());
TFile *lFile = new TFile(iName.c_str());
TTree *lTree = (TTree*) lFile->Get("tree");
lTree->SetBranchAddress("pt" , &lPt);
//lTree->SetBranchAddress("eta" , &lEta);
//lTree->SetBranchAddress("dR" , &lDR);
//lTree->SetBranchAddress("ptc" , &lPtc);
//lTree->SetBranchAddress("ptdR" , &lPtdR);
//lTree->SetBranchAddress("puppi" , &lPuppi);
lTree->SetBranchAddress("ptodR" , &lPtODR);
//lTree->SetBranchAddress("ptodRS" , &lPtODRS);
lTree->SetBranchAddress("ptodRSO" , &lPtODRSO);
//lTree->SetBranchAddress("dR_lv" , &lDRLV);
// lTree->SetBranchAddress("ptc_lv" , &lPtcLV);
//lTree->SetBranchAddress("ptdR_lv" , &lPtdRLV);
//lTree->SetBranchAddress("puppi_lv" , &lPuppiLV);
lTree->SetBranchAddress("ptodR_lv" , &lPtODRLV);
//lTree->SetBranchAddress("ptodRS_lv" , &lPtODRSLV);
lTree->SetBranchAddress("ptodRSO_lv" , &lPtODRSOLV);
//lTree->SetBranchAddress("dR_pu" , &lDRPU);
//lTree->SetBranchAddress("pt_pu" , &lPtcPU);
//lTree->SetBranchAddress("ptdR_pu" , &lPtdRPU);
//lTree->SetBranchAddress("puppi_pu" , &lPuppiPU);
//lTree->SetBranchAddress("ptodR_pu" , &lPtODRPU);
//lTree->SetBranchAddress("ptodRS_pu" , &lPtODRSPU);
//lTree->SetBranchAddress("ptodRSO_pu" , &lPtODRSOPU);
int lNEvents = lTree->GetEntries();
TFile *lOFile = new TFile("Output.root","RECREATE");
TTree *lOTree = lTree->CloneTree(0);
float lMVA = 0; lOTree->Branch("bdt" ,&lMVA ,"lMVA/F");
for (Long64_t i0=0; i0<lNEvents;i0++) {
if (i0 % 10000 == 0) std::cout << "--- ... Processing event: " << double(i0)/double(lNEvents) << std::endl;
lTree->GetEntry(i0);
lMVA = float(reader->EvaluateMVA(lJetName.c_str()));
lOTree->Fill();
}
lOTree->Write();
lOFile->Close();
delete reader;
}
void TMVAReader(){
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
TMVA::Tools::Instance(); // loads libraries
//######################################
// Fat jet variables
//######################################
float Jet_pt;
float Jet_eta;
float Jet_phi;
float Jet_mass;
float Jet_massGroomed;
float Jet_flavour;
float Jet_nbHadrons;
float Jet_JP;
float Jet_JBP;
float Jet_CSV;
float Jet_CSVIVF;
float Jet_tau1;
float Jet_tau2;
// CSV TaggingVariables
// per jet
float TagVarCSV_jetNTracks; // tracks associated to jet
float TagVarCSV_jetNTracksEtaRel; // tracks associated to jet for which trackEtaRel is calculated
float TagVarCSV_trackSumJetEtRatio; // ratio of track sum transverse energy over jet energy
float TagVarCSV_trackSumJetDeltaR; // pseudoangular distance between jet axis and track fourvector sum
float TagVarCSV_trackSip2dValAboveCharm; // track 2D signed impact parameter of first track lifting mass above charm
float TagVarCSV_trackSip2dSigAboveCharm; // track 2D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV_trackSip3dValAboveCharm; // track 3D signed impact parameter of first track lifting mass above charm
float TagVarCSV_trackSip3dSigAboveCharm; // track 3D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV_vertexCategory; // category of secondary vertex (Reco, Pseudo, No)
float TagVarCSV_jetNSecondaryVertices; // number of reconstructed possible secondary vertices in jet
float TagVarCSV_vertexMass; // mass of track sum at secondary vertex
float TagVarCSV_vertexNTracks; // number of tracks at secondary vertex
float TagVarCSV_vertexEnergyRatio; // ratio of energy at secondary vertex over total energy
float TagVarCSV_vertexJetDeltaR; // pseudoangular distance between jet axis and secondary vertex direction
float TagVarCSV_flightDistance2dVal; // transverse distance between primary and secondary vertex
float TagVarCSV_flightDistance2dSig; // transverse distance significance between primary and secondary vertex
float TagVarCSV_flightDistance3dVal; // distance between primary and secondary vertex
float TagVarCSV_flightDistance3dSig; // distance significance between primary and secondary vertex
// per jet per track
float TagVarCSV_trackSip2dSig_0; // highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip2dSig_1; // second highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip2dSig_2; // third highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip2dSig_3; // fourth highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip2dSig_4; // fifth highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip2dSig_5; // sixth highest track 2D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_0; // highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_1; // second highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_2; // third highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_3; // fourth highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_4; // fifth highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackSip3dSig_5; // sixth highest track 3D signed IP of tracks belonging to a given jet
float TagVarCSV_trackPtRel_0; // highest track transverse momentum, relative to the jet axis
float TagVarCSV_trackPtRel_1; // second highest track transverse momentum, relative to the jet axis
float TagVarCSV_trackPtRel_2; // third highest track transverse momentum, relative to the jet axis
float TagVarCSV_trackPtRel_3; // fourth highest track transverse momentum, relative to the jet axis
float TagVarCSV_trackPtRel_4; // fifth highest track transverse momentum, relative to the jet axis
float TagVarCSV_trackPtRel_5; // sixth highest track transverse momentum, relative to the jet axis
// per jet per etaRel track
float TagVarCSV_trackEtaRel_0; // lowest track eta relative to jet axis
float TagVarCSV_trackEtaRel_1; // second lowest track eta relative to jet axis
float TagVarCSV_trackEtaRel_2; // third lowest track eta relative to jet axis
//######################################
// Subjet1 variables
//######################################
float SubJet1_pt;
float SubJet1_eta;
float SubJet1_phi;
float SubJet1_mass;
float SubJet1_flavour;
float SubJet1_nbHadrons;
float SubJet1_JP;
float SubJet1_JBP;
float SubJet1_CSV;
float SubJet1_CSVIVF;
// CSV TaggingVariables
// per jet
float TagVarCSV1_jetNTracks; // tracks associated to jet
float TagVarCSV1_jetNTracksEtaRel; // tracks associated to jet for which trackEtaRel is calculated
float TagVarCSV1_trackSumJetEtRatio; // ratio of track sum transverse energy over jet energy
float TagVarCSV1_trackSumJetDeltaR; // pseudoangular distance between jet axis and track fourvector sum
float TagVarCSV1_trackSip2dValAboveCharm; // track 2D signed impact parameter of first track lifting mass above charm
float TagVarCSV1_trackSip2dSigAboveCharm; // track 2D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV1_trackSip3dValAboveCharm; // track 3D signed impact parameter of first track lifting mass above charm
float TagVarCSV1_trackSip3dSigAboveCharm; // track 3D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV1_vertexCategory; // category of secondary vertex (Reco, Pseudo, No)
float TagVarCSV1_jetNSecondaryVertices; // number of reconstructed possible secondary vertices in jet
float TagVarCSV1_vertexMass; // mass of track sum at secondary vertex
float TagVarCSV1_vertexNTracks; // number of tracks at secondary vertex
float TagVarCSV1_vertexEnergyRatio; // ratio of energy at secondary vertex over total energy
float TagVarCSV1_vertexJetDeltaR; // pseudoangular distance between jet axis and secondary vertex direction
float TagVarCSV1_flightDistance2dVal; // transverse distance between primary and secondary vertex
float TagVarCSV1_flightDistance2dSig; // transverse distance significance between primary and secondary vertex
float TagVarCSV1_flightDistance3dVal; // distance between primary and secondary vertex
float TagVarCSV1_flightDistance3dSig; // distance significance between primary and secondary vertex
// per jet per etaRel track
float TagVarCSV1_trackEtaRel_0; // lowest track eta relative to jet axis
float TagVarCSV1_trackEtaRel_1; // second lowest track eta relative to jet axis
float TagVarCSV1_trackEtaRel_2; // third lowest track eta relative to jet axis
//######################################
// Subjet2 variables
//######################################
float SubJet2_pt;
float SubJet2_eta;
float SubJet2_phi;
float SubJet2_mass;
float SubJet2_flavour;
float SubJet2_nbHadrons;
float SubJet2_JP;
float SubJet2_JBP;
float SubJet2_CSV;
float SubJet2_CSVIVF;
// CSV TaggingVariables
// per jet
float TagVarCSV2_jetNTracks; // tracks associated to jet
float TagVarCSV2_jetNTracksEtaRel; // tracks associated to jet for which trackEtaRel is calculated
float TagVarCSV2_trackSumJetEtRatio; // ratio of track sum transverse energy over jet energy
float TagVarCSV2_trackSumJetDeltaR; // pseudoangular distance between jet axis and track fourvector sum
float TagVarCSV2_trackSip2dValAboveCharm; // track 2D signed impact parameter of first track lifting mass above charm
float TagVarCSV2_trackSip2dSigAboveCharm; // track 2D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV2_trackSip3dValAboveCharm; // track 3D signed impact parameter of first track lifting mass above charm
float TagVarCSV2_trackSip3dSigAboveCharm; // track 3D signed impact parameter significance of first track lifting mass above charm
float TagVarCSV2_vertexCategory; // category of secondary vertex (Reco, Pseudo, No)
float TagVarCSV2_jetNSecondaryVertices; // number of reconstructed possible secondary vertices in jet
float TagVarCSV2_vertexMass; // mass of track sum at secondary vertex
float TagVarCSV2_vertexNTracks; // number of tracks at secondary vertex
float TagVarCSV2_vertexEnergyRatio; // ratio of energy at secondary vertex over total energy
float TagVarCSV2_vertexJetDeltaR; // pseudoangular distance between jet axis and secondary vertex direction
float TagVarCSV2_flightDistance2dVal; // transverse distance between primary and secondary vertex
float TagVarCSV2_flightDistance2dSig; // transverse distance significance between primary and secondary vertex
float TagVarCSV2_flightDistance3dVal; // distance between primary and secondary vertex
float TagVarCSV2_flightDistance3dSig; // distance significance between primary and secondary vertex
// per jet per etaRel track
float TagVarCSV2_trackEtaRel_0; // lowest track eta relative to jet axis
float TagVarCSV2_trackEtaRel_1; // second lowest track eta relative to jet axis
float TagVarCSV2_trackEtaRel_2; // third lowest track eta relative to jet axis
TMVA::Reader *reader = new TMVA::Reader( "!Color" );
reader->AddVariable("TagVarCSV_vertexCategory",&TagVarCSV_vertexCategory);
reader->AddVariable("TagVarCSV_jetNTracks",&TagVarCSV_jetNTracks);
//reader->AddVariable("TagVarCSV_trackSip2dSig_0",&TagVarCSV_trackSip2dSig_0);
//reader->AddVariable("TagVarCSV_trackSip2dSig_1",&TagVarCSV_trackSip2dSig_1);
//reader->AddVariable("TagVarCSV_trackSip2dSig_2",&TagVarCSV_trackSip2dSig_2);
//reader->AddVariable("TagVarCSV_trackSip2dSig_3",&TagVarCSV_trackSip2dSig_3);
reader->AddVariable("TagVarCSV_trackSip3dSig_0",&TagVarCSV_trackSip3dSig_0);
reader->AddVariable("TagVarCSV_trackSip3dSig_1",&TagVarCSV_trackSip3dSig_1);
reader->AddVariable("TagVarCSV_trackSip3dSig_2",&TagVarCSV_trackSip3dSig_2);
reader->AddVariable("TagVarCSV_trackSip3dSig_3",&TagVarCSV_trackSip3dSig_3);
//reader->AddVariable("TagVarCSV_trackPtRel_0",&TagVarCSV_trackPtRel_0);
//reader->AddVariable("TagVarCSV_trackPtRel_1",&TagVarCSV_trackPtRel_1);
//reader->AddVariable("TagVarCSV_trackPtRel_2",&TagVarCSV_trackPtRel_2);
//reader->AddVariable("TagVarCSV_trackPtRel_3",&TagVarCSV_trackPtRel_3);
reader->AddVariable("TagVarCSV_trackSip2dSigAboveCharm",&TagVarCSV_trackSip2dSigAboveCharm);
//reader->AddVariable("TagVarCSV_trackSip3dSigAboveCharm",&TagVarCSV_trackSip3dSigAboveCharm);
//reader->AddVariable("TagVarCSV_trackSumJetEtRatio",&TagVarCSV_trackSumJetEtRatio);
//reader->AddVariable("TagVarCSV_trackSumJetDeltaR",&TagVarCSV_trackSumJetDeltaR);
reader->AddVariable("TagVarCSV_jetNTracksEtaRel",&TagVarCSV_jetNTracksEtaRel);
reader->AddVariable("TagVarCSV_trackEtaRel_0",&TagVarCSV_trackEtaRel_0);
reader->AddVariable("TagVarCSV_trackEtaRel_1",&TagVarCSV_trackEtaRel_1);
reader->AddVariable("TagVarCSV_trackEtaRel_2",&TagVarCSV_trackEtaRel_2);
reader->AddVariable("TagVarCSV_jetNSecondaryVertices",&TagVarCSV_jetNSecondaryVertices);
reader->AddVariable("TagVarCSV_vertexMass",&TagVarCSV_vertexMass);
reader->AddVariable("TagVarCSV_vertexNTracks",&TagVarCSV_vertexNTracks);
reader->AddVariable("TagVarCSV_vertexEnergyRatio",&TagVarCSV_vertexEnergyRatio);
reader->AddVariable("TagVarCSV_vertexJetDeltaR",&TagVarCSV_vertexJetDeltaR);
reader->AddVariable("TagVarCSV_flightDistance2dSig",&TagVarCSV_flightDistance2dSig);
//reader->AddVariable("TagVarCSV_flightDistance3dSig",&TagVarCSV_flightDistance3dSig);
reader->AddSpectator("Jet_pt", &Jet_pt);
reader->AddSpectator("Jet_eta", &Jet_eta);
reader->AddSpectator("Jet_phi", &Jet_phi);
reader->AddSpectator("Jet_mass", &Jet_mass);
reader->AddSpectator("Jet_massGroomed", &Jet_massGroomed);
reader->AddSpectator("Jet_flavour", &Jet_flavour);
reader->AddSpectator("Jet_nbHadrons", &Jet_nbHadrons);
reader->AddSpectator("Jet_JP", &Jet_JP);
reader->AddSpectator("Jet_JBP", &Jet_JBP);
reader->AddSpectator("Jet_CSV", &Jet_CSV);
reader->AddSpectator("Jet_CSVIVF", &Jet_CSVIVF);
reader->AddSpectator("Jet_tau1", &Jet_tau1);
reader->AddSpectator("Jet_tau2", &Jet_tau2);
reader->AddSpectator("SubJet1_CSVIVF", &SubJet1_CSVIVF);
reader->AddSpectator("SubJet2_CSVIVF", &SubJet2_CSVIVF);
reader->BookMVA( "BDTG_T1000D3_fat_BBvsQCD method", "weights/TMVATrainer_BDTG_T1000D3_fat_BBvsQCD.weights.xml" );
// histograms
TH1F* hBDTGDiscSig = new TH1F("hBDTGDiscSig","",1000,-5,5);
TH1F* hBDTGDiscBkg = new TH1F("hBDTGDiscBkg","",1000,-5,5);
TH1F* hFatCSVIVFDiscSig = new TH1F("hFatCSVIVFDiscSig","",1000,-5,5);
TH1F* hFatCSVIVFDiscBkg = new TH1F("hFatCSVIVFDiscBkg","",1000,-5,5);
TH1F* hSubCSVIVFDiscSig = new TH1F("hSubCSVIVFDiscSig","",1000,-5,5);
TH1F* hSubCSVIVFDiscBkg = new TH1F("hSubCSVIVFDiscBkg","",1000,-5,5);
hBDTGDiscSig->GetXaxis()->SetTitle("BDTG Discriminant");
hBDTGDiscBkg->GetXaxis()->SetTitle("BDTG Discriminant");
hFatCSVIVFDiscSig->GetXaxis()->SetTitle("CSV Discriminant");
hFatCSVIVFDiscBkg->GetXaxis()->SetTitle("CSV Discriminant");
hSubCSVIVFDiscSig->GetXaxis()->SetTitle("CSV Discriminant");
hSubCSVIVFDiscBkg->GetXaxis()->SetTitle("CSV Discriminant");
// background input tree
TString infilenameBkg="QCD_Pt-300to470_TuneZ2star_8TeV_pythia6_JetTaggingVariables_evaluation.root";
TFile inBkg(infilenameBkg);
TTree* intree = (TTree*)inBkg.Get("tagVars/ttree");
// set the branches to point to address of the variables declared above
//######################################
// Fat jet variables
//######################################
intree->SetBranchAddress("Jet_pt" ,&Jet_pt );
intree->SetBranchAddress("Jet_eta" ,&Jet_eta );
intree->SetBranchAddress("Jet_phi" ,&Jet_phi );
intree->SetBranchAddress("Jet_mass" ,&Jet_mass );
intree->SetBranchAddress("Jet_massGroomed" ,&Jet_massGroomed );
intree->SetBranchAddress("Jet_flavour" ,&Jet_flavour );
intree->SetBranchAddress("Jet_nbHadrons" ,&Jet_nbHadrons );
intree->SetBranchAddress("Jet_JP" ,&Jet_JP );
intree->SetBranchAddress("Jet_JBP" ,&Jet_JBP );
intree->SetBranchAddress("Jet_CSV" ,&Jet_CSV );
intree->SetBranchAddress("Jet_CSVIVF" ,&Jet_CSVIVF );
intree->SetBranchAddress("Jet_tau1" ,&Jet_tau1 );
intree->SetBranchAddress("Jet_tau2" ,&Jet_tau2 );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV_jetNTracks" ,&TagVarCSV_jetNTracks );
intree->SetBranchAddress("TagVarCSV_jetNTracksEtaRel" ,&TagVarCSV_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV_trackSumJetEtRatio" ,&TagVarCSV_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV_trackSumJetDeltaR" ,&TagVarCSV_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV_trackSip2dValAboveCharm" ,&TagVarCSV_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip2dSigAboveCharm" ,&TagVarCSV_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip3dValAboveCharm" ,&TagVarCSV_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip3dSigAboveCharm" ,&TagVarCSV_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV_vertexCategory" ,&TagVarCSV_vertexCategory );
intree->SetBranchAddress("TagVarCSV_jetNSecondaryVertices" ,&TagVarCSV_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV_vertexMass" ,&TagVarCSV_vertexMass );
intree->SetBranchAddress("TagVarCSV_vertexNTracks" ,&TagVarCSV_vertexNTracks );
intree->SetBranchAddress("TagVarCSV_vertexEnergyRatio" ,&TagVarCSV_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV_vertexJetDeltaR" ,&TagVarCSV_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV_flightDistance2dVal" ,&TagVarCSV_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV_flightDistance2dSig" ,&TagVarCSV_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV_flightDistance3dVal" ,&TagVarCSV_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV_flightDistance3dSig" ,&TagVarCSV_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_0" ,&TagVarCSV_trackSip2dSig_0 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_1" ,&TagVarCSV_trackSip2dSig_1 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_2" ,&TagVarCSV_trackSip2dSig_2 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_3" ,&TagVarCSV_trackSip2dSig_3 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_4" ,&TagVarCSV_trackSip2dSig_4 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_5" ,&TagVarCSV_trackSip2dSig_5 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_0" ,&TagVarCSV_trackSip3dSig_0 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_1" ,&TagVarCSV_trackSip3dSig_1 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_2" ,&TagVarCSV_trackSip3dSig_2 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_3" ,&TagVarCSV_trackSip3dSig_3 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_4" ,&TagVarCSV_trackSip3dSig_4 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_5" ,&TagVarCSV_trackSip3dSig_5 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_0" ,&TagVarCSV_trackPtRel_0 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_1" ,&TagVarCSV_trackPtRel_1 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_2" ,&TagVarCSV_trackPtRel_2 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_3" ,&TagVarCSV_trackPtRel_3 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_4" ,&TagVarCSV_trackPtRel_4 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_5" ,&TagVarCSV_trackPtRel_5 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_0" ,&TagVarCSV_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_1" ,&TagVarCSV_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_2" ,&TagVarCSV_trackEtaRel_2 );
//######################################
// Subjet1 variables
//######################################
intree->SetBranchAddress("SubJet1_pt" ,&SubJet1_pt );
intree->SetBranchAddress("SubJet1_eta" ,&SubJet1_eta );
intree->SetBranchAddress("SubJet1_phi" ,&SubJet1_phi );
intree->SetBranchAddress("SubJet1_mass" ,&SubJet1_mass );
intree->SetBranchAddress("SubJet1_flavour" ,&SubJet1_flavour );
intree->SetBranchAddress("SubJet1_nbHadrons" ,&SubJet1_nbHadrons );
intree->SetBranchAddress("SubJet1_JP" ,&SubJet1_JP );
intree->SetBranchAddress("SubJet1_JBP" ,&SubJet1_JBP );
intree->SetBranchAddress("SubJet1_CSV" ,&SubJet1_CSV );
intree->SetBranchAddress("SubJet1_CSVIVF" ,&SubJet1_CSVIVF );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV1_jetNTracks" ,&TagVarCSV1_jetNTracks );
intree->SetBranchAddress("TagVarCSV1_jetNTracksEtaRel" ,&TagVarCSV1_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV1_trackSumJetEtRatio" ,&TagVarCSV1_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV1_trackSumJetDeltaR" ,&TagVarCSV1_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV1_trackSip2dValAboveCharm" ,&TagVarCSV1_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip2dSigAboveCharm" ,&TagVarCSV1_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip3dValAboveCharm" ,&TagVarCSV1_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip3dSigAboveCharm" ,&TagVarCSV1_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV1_vertexCategory" ,&TagVarCSV1_vertexCategory );
intree->SetBranchAddress("TagVarCSV1_jetNSecondaryVertices" ,&TagVarCSV1_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV1_vertexMass" ,&TagVarCSV1_vertexMass );
intree->SetBranchAddress("TagVarCSV1_vertexNTracks" ,&TagVarCSV1_vertexNTracks );
intree->SetBranchAddress("TagVarCSV1_vertexEnergyRatio" ,&TagVarCSV1_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV1_vertexJetDeltaR" ,&TagVarCSV1_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV1_flightDistance2dVal" ,&TagVarCSV1_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV1_flightDistance2dSig" ,&TagVarCSV1_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV1_flightDistance3dVal" ,&TagVarCSV1_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV1_flightDistance3dSig" ,&TagVarCSV1_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_0" ,&TagVarCSV1_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_1" ,&TagVarCSV1_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_2" ,&TagVarCSV1_trackEtaRel_2 );
//######################################
// Subjet2 variables
//######################################
intree->SetBranchAddress("SubJet2_pt" ,&SubJet2_pt );
intree->SetBranchAddress("SubJet2_eta" ,&SubJet2_eta );
intree->SetBranchAddress("SubJet2_phi" ,&SubJet2_phi );
intree->SetBranchAddress("SubJet2_mass" ,&SubJet2_mass );
intree->SetBranchAddress("SubJet2_flavour" ,&SubJet2_flavour );
intree->SetBranchAddress("SubJet2_nbHadrons" ,&SubJet2_nbHadrons );
intree->SetBranchAddress("SubJet2_JP" ,&SubJet2_JP );
intree->SetBranchAddress("SubJet2_JBP" ,&SubJet2_JBP );
intree->SetBranchAddress("SubJet2_CSV" ,&SubJet2_CSV );
intree->SetBranchAddress("SubJet2_CSVIVF" ,&SubJet2_CSVIVF );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV2_jetNTracks" ,&TagVarCSV2_jetNTracks );
intree->SetBranchAddress("TagVarCSV2_jetNTracksEtaRel" ,&TagVarCSV2_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV2_trackSumJetEtRatio" ,&TagVarCSV2_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV2_trackSumJetDeltaR" ,&TagVarCSV2_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV2_trackSip2dValAboveCharm" ,&TagVarCSV2_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip2dSigAboveCharm" ,&TagVarCSV2_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip3dValAboveCharm" ,&TagVarCSV2_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip3dSigAboveCharm" ,&TagVarCSV2_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV2_vertexCategory" ,&TagVarCSV2_vertexCategory );
intree->SetBranchAddress("TagVarCSV2_jetNSecondaryVertices" ,&TagVarCSV2_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV2_vertexMass" ,&TagVarCSV2_vertexMass );
intree->SetBranchAddress("TagVarCSV2_vertexNTracks" ,&TagVarCSV2_vertexNTracks );
intree->SetBranchAddress("TagVarCSV2_vertexEnergyRatio" ,&TagVarCSV2_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV2_vertexJetDeltaR" ,&TagVarCSV2_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV2_flightDistance2dVal" ,&TagVarCSV2_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV2_flightDistance2dSig" ,&TagVarCSV2_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV2_flightDistance3dVal" ,&TagVarCSV2_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV2_flightDistance3dSig" ,&TagVarCSV2_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_0" ,&TagVarCSV2_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_1" ,&TagVarCSV2_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_2" ,&TagVarCSV2_trackEtaRel_2 );
std::cout << "Now looping over " << intree->GetEntries() << " entries..." << std::endl;
for(Long64_t iEntry = 0; iEntry < intree->GetEntries(); iEntry++){
if (iEntry % 1000 == 0) std::cout << "Processing Entry #" << iEntry << std::endl;
intree->GetEntry(iEntry); // all variables now filled!
bool isBkg = ( Jet_massGroomed>80 && Jet_massGroomed<150 );
float BDTG_Disc = reader->EvaluateMVA("BDTG_T1000D3_fat_BBvsQCD method");
if (isBkg) {
hBDTGDiscBkg->Fill(BDTG_Disc);
hFatCSVIVFDiscBkg->Fill(Jet_CSVIVF);
hSubCSVIVFDiscBkg->Fill(std::min(SubJet1_CSVIVF,SubJet2_CSVIVF));
}
}
// signal input tree
TString infilenameSig="RadionToHH_4b_M-800_TuneZ2star_8TeV-Madgraph_pythia6_JetTaggingVariables_evaluation.root";
TFile inSig(infilenameSig);
intree = (TTree*)inSig.Get("tagVars/ttree");
// set the branches to point to address of the variables declared above
//######################################
// Fat jet variables
//######################################
intree->SetBranchAddress("Jet_pt" ,&Jet_pt );
intree->SetBranchAddress("Jet_eta" ,&Jet_eta );
intree->SetBranchAddress("Jet_phi" ,&Jet_phi );
intree->SetBranchAddress("Jet_mass" ,&Jet_mass );
intree->SetBranchAddress("Jet_massGroomed" ,&Jet_massGroomed );
intree->SetBranchAddress("Jet_flavour" ,&Jet_flavour );
intree->SetBranchAddress("Jet_nbHadrons" ,&Jet_nbHadrons );
intree->SetBranchAddress("Jet_JP" ,&Jet_JP );
intree->SetBranchAddress("Jet_JBP" ,&Jet_JBP );
intree->SetBranchAddress("Jet_CSV" ,&Jet_CSV );
intree->SetBranchAddress("Jet_CSVIVF" ,&Jet_CSVIVF );
intree->SetBranchAddress("Jet_tau1" ,&Jet_tau1 );
intree->SetBranchAddress("Jet_tau2" ,&Jet_tau2 );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV_jetNTracks" ,&TagVarCSV_jetNTracks );
intree->SetBranchAddress("TagVarCSV_jetNTracksEtaRel" ,&TagVarCSV_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV_trackSumJetEtRatio" ,&TagVarCSV_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV_trackSumJetDeltaR" ,&TagVarCSV_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV_trackSip2dValAboveCharm" ,&TagVarCSV_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip2dSigAboveCharm" ,&TagVarCSV_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip3dValAboveCharm" ,&TagVarCSV_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV_trackSip3dSigAboveCharm" ,&TagVarCSV_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV_vertexCategory" ,&TagVarCSV_vertexCategory );
intree->SetBranchAddress("TagVarCSV_jetNSecondaryVertices" ,&TagVarCSV_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV_vertexMass" ,&TagVarCSV_vertexMass );
intree->SetBranchAddress("TagVarCSV_vertexNTracks" ,&TagVarCSV_vertexNTracks );
intree->SetBranchAddress("TagVarCSV_vertexEnergyRatio" ,&TagVarCSV_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV_vertexJetDeltaR" ,&TagVarCSV_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV_flightDistance2dVal" ,&TagVarCSV_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV_flightDistance2dSig" ,&TagVarCSV_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV_flightDistance3dVal" ,&TagVarCSV_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV_flightDistance3dSig" ,&TagVarCSV_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_0" ,&TagVarCSV_trackSip2dSig_0 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_1" ,&TagVarCSV_trackSip2dSig_1 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_2" ,&TagVarCSV_trackSip2dSig_2 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_3" ,&TagVarCSV_trackSip2dSig_3 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_4" ,&TagVarCSV_trackSip2dSig_4 );
intree->SetBranchAddress("TagVarCSV_trackSip2dSig_5" ,&TagVarCSV_trackSip2dSig_5 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_0" ,&TagVarCSV_trackSip3dSig_0 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_1" ,&TagVarCSV_trackSip3dSig_1 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_2" ,&TagVarCSV_trackSip3dSig_2 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_3" ,&TagVarCSV_trackSip3dSig_3 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_4" ,&TagVarCSV_trackSip3dSig_4 );
intree->SetBranchAddress("TagVarCSV_trackSip3dSig_5" ,&TagVarCSV_trackSip3dSig_5 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_0" ,&TagVarCSV_trackPtRel_0 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_1" ,&TagVarCSV_trackPtRel_1 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_2" ,&TagVarCSV_trackPtRel_2 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_3" ,&TagVarCSV_trackPtRel_3 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_4" ,&TagVarCSV_trackPtRel_4 );
intree->SetBranchAddress("TagVarCSV_trackPtRel_5" ,&TagVarCSV_trackPtRel_5 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_0" ,&TagVarCSV_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_1" ,&TagVarCSV_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV_trackEtaRel_2" ,&TagVarCSV_trackEtaRel_2 );
//######################################
// Subjet1 variables
//######################################
intree->SetBranchAddress("SubJet1_pt" ,&SubJet1_pt );
intree->SetBranchAddress("SubJet1_eta" ,&SubJet1_eta );
intree->SetBranchAddress("SubJet1_phi" ,&SubJet1_phi );
intree->SetBranchAddress("SubJet1_mass" ,&SubJet1_mass );
intree->SetBranchAddress("SubJet1_flavour" ,&SubJet1_flavour );
intree->SetBranchAddress("SubJet1_nbHadrons" ,&SubJet1_nbHadrons );
intree->SetBranchAddress("SubJet1_JP" ,&SubJet1_JP );
intree->SetBranchAddress("SubJet1_JBP" ,&SubJet1_JBP );
intree->SetBranchAddress("SubJet1_CSV" ,&SubJet1_CSV );
intree->SetBranchAddress("SubJet1_CSVIVF" ,&SubJet1_CSVIVF );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV1_jetNTracks" ,&TagVarCSV1_jetNTracks );
intree->SetBranchAddress("TagVarCSV1_jetNTracksEtaRel" ,&TagVarCSV1_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV1_trackSumJetEtRatio" ,&TagVarCSV1_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV1_trackSumJetDeltaR" ,&TagVarCSV1_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV1_trackSip2dValAboveCharm" ,&TagVarCSV1_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip2dSigAboveCharm" ,&TagVarCSV1_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip3dValAboveCharm" ,&TagVarCSV1_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV1_trackSip3dSigAboveCharm" ,&TagVarCSV1_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV1_vertexCategory" ,&TagVarCSV1_vertexCategory );
intree->SetBranchAddress("TagVarCSV1_jetNSecondaryVertices" ,&TagVarCSV1_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV1_vertexMass" ,&TagVarCSV1_vertexMass );
intree->SetBranchAddress("TagVarCSV1_vertexNTracks" ,&TagVarCSV1_vertexNTracks );
intree->SetBranchAddress("TagVarCSV1_vertexEnergyRatio" ,&TagVarCSV1_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV1_vertexJetDeltaR" ,&TagVarCSV1_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV1_flightDistance2dVal" ,&TagVarCSV1_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV1_flightDistance2dSig" ,&TagVarCSV1_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV1_flightDistance3dVal" ,&TagVarCSV1_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV1_flightDistance3dSig" ,&TagVarCSV1_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_0" ,&TagVarCSV1_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_1" ,&TagVarCSV1_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV1_trackEtaRel_2" ,&TagVarCSV1_trackEtaRel_2 );
//######################################
// Subjet2 variables
//######################################
intree->SetBranchAddress("SubJet2_pt" ,&SubJet2_pt );
intree->SetBranchAddress("SubJet2_eta" ,&SubJet2_eta );
intree->SetBranchAddress("SubJet2_phi" ,&SubJet2_phi );
intree->SetBranchAddress("SubJet2_mass" ,&SubJet2_mass );
intree->SetBranchAddress("SubJet2_flavour" ,&SubJet2_flavour );
intree->SetBranchAddress("SubJet2_nbHadrons" ,&SubJet2_nbHadrons );
intree->SetBranchAddress("SubJet2_JP" ,&SubJet2_JP );
intree->SetBranchAddress("SubJet2_JBP" ,&SubJet2_JBP );
intree->SetBranchAddress("SubJet2_CSV" ,&SubJet2_CSV );
intree->SetBranchAddress("SubJet2_CSVIVF" ,&SubJet2_CSVIVF );
//--------------------------------------
// CSV TaggingVariables
//--------------------------------------
intree->SetBranchAddress("TagVarCSV2_jetNTracks" ,&TagVarCSV2_jetNTracks );
intree->SetBranchAddress("TagVarCSV2_jetNTracksEtaRel" ,&TagVarCSV2_jetNTracksEtaRel );
intree->SetBranchAddress("TagVarCSV2_trackSumJetEtRatio" ,&TagVarCSV2_trackSumJetEtRatio );
intree->SetBranchAddress("TagVarCSV2_trackSumJetDeltaR" ,&TagVarCSV2_trackSumJetDeltaR );
intree->SetBranchAddress("TagVarCSV2_trackSip2dValAboveCharm" ,&TagVarCSV2_trackSip2dValAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip2dSigAboveCharm" ,&TagVarCSV2_trackSip2dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip3dValAboveCharm" ,&TagVarCSV2_trackSip3dValAboveCharm );
intree->SetBranchAddress("TagVarCSV2_trackSip3dSigAboveCharm" ,&TagVarCSV2_trackSip3dSigAboveCharm );
intree->SetBranchAddress("TagVarCSV2_vertexCategory" ,&TagVarCSV2_vertexCategory );
intree->SetBranchAddress("TagVarCSV2_jetNSecondaryVertices" ,&TagVarCSV2_jetNSecondaryVertices );
intree->SetBranchAddress("TagVarCSV2_vertexMass" ,&TagVarCSV2_vertexMass );
intree->SetBranchAddress("TagVarCSV2_vertexNTracks" ,&TagVarCSV2_vertexNTracks );
intree->SetBranchAddress("TagVarCSV2_vertexEnergyRatio" ,&TagVarCSV2_vertexEnergyRatio );
intree->SetBranchAddress("TagVarCSV2_vertexJetDeltaR" ,&TagVarCSV2_vertexJetDeltaR );
intree->SetBranchAddress("TagVarCSV2_flightDistance2dVal" ,&TagVarCSV2_flightDistance2dVal );
intree->SetBranchAddress("TagVarCSV2_flightDistance2dSig" ,&TagVarCSV2_flightDistance2dSig );
intree->SetBranchAddress("TagVarCSV2_flightDistance3dVal" ,&TagVarCSV2_flightDistance3dVal );
intree->SetBranchAddress("TagVarCSV2_flightDistance3dSig" ,&TagVarCSV2_flightDistance3dSig );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_0" ,&TagVarCSV2_trackEtaRel_0 );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_1" ,&TagVarCSV2_trackEtaRel_1 );
intree->SetBranchAddress("TagVarCSV2_trackEtaRel_2" ,&TagVarCSV2_trackEtaRel_2 );
std::cout << "Now looping over " << intree->GetEntries() << " entries..." << std::endl;
for(Long64_t iEntry = 0; iEntry < intree->GetEntries(); iEntry++){
if (iEntry % 1000 == 0) std::cout << "Processing Entry #" << iEntry << std::endl;
intree->GetEntry(iEntry); // all variables now filled!
bool isSig = ( Jet_massGroomed>80 && Jet_massGroomed<150 );
float BDTG_Disc = reader->EvaluateMVA("BDTG_T1000D3_fat_BBvsQCD method");
if (isSig) {
hBDTGDiscSig->Fill(BDTG_Disc);
hFatCSVIVFDiscSig->Fill(Jet_CSVIVF);
hSubCSVIVFDiscSig->Fill(std::min(SubJet1_CSVIVF,SubJet2_CSVIVF));
}
}
TString outname = "BDTG_vs_CSVv2IVF_fat_BBvsQCD.root";
TFile out(outname,"RECREATE");
hBDTGDiscSig->Write();
hBDTGDiscBkg->Write();
hFatCSVIVFDiscSig->Write();
hFatCSVIVFDiscBkg->Write();
hSubCSVIVFDiscSig->Write();
hSubCSVIVFDiscBkg->Write();
out.Close();
delete reader;
delete hBDTGDiscSig;
delete hBDTGDiscBkg;
delete hFatCSVIVFDiscSig;
delete hFatCSVIVFDiscBkg;
delete hSubCSVIVFDiscSig;
delete hSubCSVIVFDiscBkg;
std::cout << "Done analyzing!" << std::endl;
}
void ZTMVAClassificationApplication( string filename, TString myMethodList = "" )
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 1; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 1; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 1; // decorrelation + Adaptive Boost
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
Use["Plugin"] = 0;
Use["Category"] = 0;
Use["SVM_Gauss"] = 0;
Use["SVM_Poly"] = 0;
Use["SVM_Lin"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
Float_t B_s0_ln_FDCHI2; reader->AddVariable("B_s0_ln_FDCHI2", &B_s0_ln_FDCHI2 );
Float_t B_s0_ln_IPCHI2; reader->AddVariable("B_s0_ln_IPCHI2", &B_s0_ln_IPCHI2 );
Float_t B_s0_ln_EVCHI2; reader->AddVariable("B_s0_ln_EVCHI2", &B_s0_ln_EVCHI2 );
Float_t B_s0_PT_fiveGeV;reader->AddVariable("B_s0_PT_fiveGeV",&B_s0_PT_fiveGeV);
Float_t B_s0_Eta; reader->AddVariable("B_s0_Eta", &B_s0_Eta );
Float_t minK_PT_GeV; reader->AddVariable("minK_PT_GeV", &minK_PT_GeV );
Float_t minK_ln_IPCHI2; reader->AddVariable("minK_ln_IPCHI2", &minK_ln_IPCHI2 );
Float_t Category_cat1, Category_cat2, Category_cat3;
if (Use["Category"]){
// Add artificial spectators for distinguishing categories
reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
}
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVAClassification";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Book output histograms
UInt_t nbin = 100;
TH1F *histLk(0), *histLkD(0), *histLkPCA(0), *histLkKDE(0), *histLkMIX(0), *histPD(0), *histPDD(0);
TH1F *histPDPCA(0), *histPDEFoam(0), *histPDEFoamErr(0), *histPDEFoamSig(0), *histKNN(0), *histHm(0);
TH1F *histFi(0), *histFiG(0), *histFiB(0), *histLD(0), *histNn(0),*histNnbfgs(0),*histNnbnn(0);
TH1F *histNnC(0), *histNnT(0), *histBdt(0), *histBdtG(0), *histBdtD(0), *histRf(0), *histSVMG(0);
TH1F *histSVMP(0), *histSVML(0), *histFDAMT(0), *histFDAGA(0), *histCat(0), *histPBdt(0);
if (Use["Likelihood"]) histLk = new TH1F( "MVA_Likelihood", "MVA_Likelihood", nbin, -1, 1 );
if (Use["LikelihoodD"]) histLkD = new TH1F( "MVA_LikelihoodD", "MVA_LikelihoodD", nbin, -1, 0.9999 );
if (Use["LikelihoodPCA"]) histLkPCA = new TH1F( "MVA_LikelihoodPCA", "MVA_LikelihoodPCA", nbin, -1, 1 );
if (Use["LikelihoodKDE"]) histLkKDE = new TH1F( "MVA_LikelihoodKDE", "MVA_LikelihoodKDE", nbin, -0.00001, 0.99999 );
if (Use["LikelihoodMIX"]) histLkMIX = new TH1F( "MVA_LikelihoodMIX", "MVA_LikelihoodMIX", nbin, 0, 1 );
if (Use["PDERS"]) histPD = new TH1F( "MVA_PDERS", "MVA_PDERS", nbin, 0, 1 );
if (Use["PDERSD"]) histPDD = new TH1F( "MVA_PDERSD", "MVA_PDERSD", nbin, 0, 1 );
if (Use["PDERSPCA"]) histPDPCA = new TH1F( "MVA_PDERSPCA", "MVA_PDERSPCA", nbin, 0, 1 );
if (Use["KNN"]) histKNN = new TH1F( "MVA_KNN", "MVA_KNN", nbin, 0, 1 );
if (Use["HMatrix"]) histHm = new TH1F( "MVA_HMatrix", "MVA_HMatrix", nbin, -0.95, 1.55 );
if (Use["Fisher"]) histFi = new TH1F( "MVA_Fisher", "MVA_Fisher", nbin, -4, 4 );
if (Use["FisherG"]) histFiG = new TH1F( "MVA_FisherG", "MVA_FisherG", nbin, -1, 1 );
if (Use["BoostedFisher"]) histFiB = new TH1F( "MVA_BoostedFisher", "MVA_BoostedFisher", nbin, -2, 2 );
if (Use["LD"]) histLD = new TH1F( "MVA_LD", "MVA_LD", nbin, -2, 2 );
if (Use["MLP"]) histNn = new TH1F( "MVA_MLP", "MVA_MLP", nbin, -1.25, 1.5 );
if (Use["MLPBFGS"]) histNnbfgs = new TH1F( "MVA_MLPBFGS", "MVA_MLPBFGS", nbin, -1.25, 1.5 );
if (Use["MLPBNN"]) histNnbnn = new TH1F( "MVA_MLPBNN", "MVA_MLPBNN", nbin, -1.25, 1.5 );
if (Use["CFMlpANN"]) histNnC = new TH1F( "MVA_CFMlpANN", "MVA_CFMlpANN", nbin, 0, 1 );
if (Use["TMlpANN"]) histNnT = new TH1F( "MVA_TMlpANN", "MVA_TMlpANN", nbin, -1.3, 1.3 );
if (Use["BDT"]) histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -0.8, 0.8 );
if (Use["BDTD"]) histBdtD = new TH1F( "MVA_BDTD", "MVA_BDTD", nbin, -0.8, 0.8 );
if (Use["BDTG"]) histBdtG = new TH1F( "MVA_BDTG", "MVA_BDTG", nbin, -1.0, 1.0 );
if (Use["RuleFit"]) histRf = new TH1F( "MVA_RuleFit", "MVA_RuleFit", nbin, -2.0, 2.0 );
if (Use["SVM_Gauss"]) histSVMG = new TH1F( "MVA_SVM_Gauss", "MVA_SVM_Gauss", nbin, 0.0, 1.0 );
if (Use["SVM_Poly"]) histSVMP = new TH1F( "MVA_SVM_Poly", "MVA_SVM_Poly", nbin, 0.0, 1.0 );
if (Use["SVM_Lin"]) histSVML = new TH1F( "MVA_SVM_Lin", "MVA_SVM_Lin", nbin, 0.0, 1.0 );
if (Use["FDA_MT"]) histFDAMT = new TH1F( "MVA_FDA_MT", "MVA_FDA_MT", nbin, -2.0, 3.0 );
if (Use["FDA_GA"]) histFDAGA = new TH1F( "MVA_FDA_GA", "MVA_FDA_GA", nbin, -2.0, 3.0 );
if (Use["Category"]) histCat = new TH1F( "MVA_Category", "MVA_Category", nbin, -2., 2. );
if (Use["Plugin"]) histPBdt = new TH1F( "MVA_PBDT", "MVA_BDT", nbin, -0.8, 0.8 );
// PDEFoam also returns per-event error, fill in histogram, and also fill significance
if (Use["PDEFoam"]) {
histPDEFoam = new TH1F( "MVA_PDEFoam", "MVA_PDEFoam", nbin, 0, 1 );
histPDEFoamErr = new TH1F( "MVA_PDEFoamErr", "MVA_PDEFoam error", nbin, 0, 1 );
histPDEFoamSig = new TH1F( "MVA_PDEFoamSig", "MVA_PDEFoam significance", nbin, 0, 10 );
}
// Book example histogram for probability (the other methods are done similarly)
TH1F *probHistFi(0), *rarityHistFi(0);
if (Use["Fisher"]) {
probHistFi = new TH1F( "MVA_Fisher_Proba", "MVA_Fisher_Proba", nbin, 0, 1 );
rarityHistFi = new TH1F( "MVA_Fisher_Rarity", "MVA_Fisher_Rarity", nbin, 0, 1 );
}
//TFile * input = new TFile("../cloosepid.root"); // this is the signal
//TFile * input_Background = new TFile("Z4430Files/merged_ntuple_jpsi_s17.root"); // this is the background
//TFile * input = new TFile("../output/MCBsphif0_after_transform.root"); // this is the signal
TFile * input_Background;
input_Background = new TFile(filename.c_str());
//std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
std::cout << "--- TMVAClassificationApp : Using input file: " << input_Background->GetName() << std::endl;
// --- Event loop
//save the results here
/*
TTree* results= new TTree("results", "results");
Float_t Method_Likelihood; Float_t bdt;
results->Branch("Method_Likelihood",&Method_Likelihood ,"Method_Likelihood/D" );
results->Branch("BDTG method", &bdt, "BDTG method" );
*/
std::cout << "--- Select signal sample" << std::endl;
//TTree* theTree = (TTree*)input->Get("MCtree");
TTree* theTree = (TTree*)input_Background->Get("DecayTree");
//if(mode<3) TCut cut = TCut("time1>0. && abs(phi_mass-1019.455)<15");
// else TCut cut = TCut("time1>0. && abs(phi_mass-1019.455)<12 && abs(phi1_mass-1019.455)<12");
//else TCut cut = TCut("time1>0. && abs(phi_mass-1019.455)<15 && abs(phi1_mass-1019.455)<15");
//TFile* f_out =new TFile("../output/MCBsphif0_after_bdt.root","RECREATE");
TFile* f_out;
string oldLabel="mvaVars_vetoes";
string newLabel="mva";
filename.replace(filename.find(oldLabel), oldLabel.length(), newLabel);
f_out = new TFile(filename.c_str(),"RECREATE");
//TTree* smalltree = theTree->CopyTree(cut);
TTree* newtree = theTree->CloneTree(-1);
//TTree* smalltree = theTree->CloneTree(-1);
//TTree* newtree = theTree->CloneTree(-1);
float bdtg;
TBranch* b_bdtg = newtree->Branch("bdtg", &bdtg,"bdtg/F");
float bdt;
TBranch* b_bdt = newtree->Branch("bdt", &bdt,"bdt/F");
float bdtd;
TBranch* b_bdtd = newtree->Branch("bdtd", &bdtd,"bdtd/F");
float mlp;
TBranch* b_mlp = newtree->Branch("mlp", &mlp,"mlp/F");
// Float_t userptsum, userpionpt, userptj, userdmj , uservchi2dof;
// Float_t usermaxdphi; Float_t userptAsym;
theTree->SetBranchAddress("B_s0_ln_FDCHI2", &B_s0_ln_FDCHI2 );
theTree->SetBranchAddress("B_s0_ln_IPCHI2", &B_s0_ln_IPCHI2 );
theTree->SetBranchAddress("B_s0_ln_EVCHI2", &B_s0_ln_EVCHI2 );
theTree->SetBranchAddress("B_s0_PT_fiveGeV",&B_s0_PT_fiveGeV);
theTree->SetBranchAddress("B_s0_Eta", &B_s0_Eta );
theTree->SetBranchAddress("minK_PT_GeV", &minK_PT_GeV );
theTree->SetBranchAddress("minK_ln_IPCHI2", &minK_ln_IPCHI2 );
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
Int_t num_entries = newtree->GetEntries();
std::cout << "--- Processing: " << num_entries << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<num_entries;ievt++) {
// if (ievt%10000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
newtree->GetEntry(ievt);
// var1 = userVar1 + userVar2;
// var2 = userVar1 - userVar2;
// --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
if (Use["Likelihood" ]) {
histLk ->Fill( reader->EvaluateMVA( "Likelihood method" ) );
// Method_Likelihood = reader->EvaluateMVA( "Likelihood method" ) ;
//std::cout << Method_Likelihood << std::endl;
// results->Fill();
}
if (Use["LikelihoodD" ]) histLkD ->Fill( reader->EvaluateMVA( "LikelihoodD method" ) );
if (Use["LikelihoodPCA"]) histLkPCA ->Fill( reader->EvaluateMVA( "LikelihoodPCA method" ) );
if (Use["LikelihoodKDE"]) histLkKDE ->Fill( reader->EvaluateMVA( "LikelihoodKDE method" ) );
if (Use["LikelihoodMIX"]) histLkMIX ->Fill( reader->EvaluateMVA( "LikelihoodMIX method" ) );
if (Use["PDERS" ]) histPD ->Fill( reader->EvaluateMVA( "PDERS method" ) );
if (Use["PDERSD" ]) histPDD ->Fill( reader->EvaluateMVA( "PDERSD method" ) );
if (Use["PDERSPCA" ]) histPDPCA ->Fill( reader->EvaluateMVA( "PDERSPCA method" ) );
if (Use["KNN" ]) histKNN ->Fill( reader->EvaluateMVA( "KNN method" ) );
if (Use["HMatrix" ]) histHm ->Fill( reader->EvaluateMVA( "HMatrix method" ) );
if (Use["Fisher" ]) histFi ->Fill( reader->EvaluateMVA( "Fisher method" ) );
if (Use["FisherG" ]) histFiG ->Fill( reader->EvaluateMVA( "FisherG method" ) );
if (Use["BoostedFisher"]) histFiB ->Fill( reader->EvaluateMVA( "BoostedFisher method" ) );
if (Use["LD" ]) histLD ->Fill( reader->EvaluateMVA( "LD method" ) );
if (Use["MLP" ]) {
mlp = reader->EvaluateMVA( "MLP method" ) ;
b_mlp->Fill();
histNn ->Fill( reader->EvaluateMVA( "MLP method" ) );
}
if (Use["MLPBFGS" ]) histNnbfgs ->Fill( reader->EvaluateMVA( "MLPBFGS method" ) );
if (Use["MLPBNN" ]) histNnbnn ->Fill( reader->EvaluateMVA( "MLPBNN method" ) );
if (Use["CFMlpANN" ]) histNnC ->Fill( reader->EvaluateMVA( "CFMlpANN method" ) );
if (Use["TMlpANN" ]) histNnT ->Fill( reader->EvaluateMVA( "TMlpANN method" ) );
if (Use["BDT" ]) {
histBdt ->Fill( reader->EvaluateMVA( "BDT method" ) );
bdt = reader->EvaluateMVA( "BDT method" ) ;
b_bdt->Fill();
}
if (Use["BDTD" ]) {
histBdtD ->Fill( reader->EvaluateMVA( "BDTD method" ) );
bdtd = reader->EvaluateMVA( "BDTD method" );
b_bdtd->Fill();
}
if (Use["BDTG" ]) {
histBdtG ->Fill( reader->EvaluateMVA( "BDTG method" ) );
bdtg = reader->EvaluateMVA( "BDTG method" );
b_bdtg->Fill();
//cout << reader->EvaluateMVA( "BDTG method" ) <<endl;
}
if (Use["RuleFit" ]) histRf ->Fill( reader->EvaluateMVA( "RuleFit method" ) );
if (Use["SVM_Gauss" ]) histSVMG ->Fill( reader->EvaluateMVA( "SVM_Gauss method" ) );
if (Use["SVM_Poly" ]) histSVMP ->Fill( reader->EvaluateMVA( "SVM_Poly method" ) );
if (Use["SVM_Lin" ]) histSVML ->Fill( reader->EvaluateMVA( "SVM_Lin method" ) );
if (Use["FDA_MT" ]) histFDAMT ->Fill( reader->EvaluateMVA( "FDA_MT method" ) );
if (Use["FDA_GA" ]) histFDAGA ->Fill( reader->EvaluateMVA( "FDA_GA method" ) );
if (Use["Category" ]) histCat ->Fill( reader->EvaluateMVA( "Category method" ) );
if (Use["Plugin" ]) histPBdt ->Fill( reader->EvaluateMVA( "P_BDT method" ) );
// Retrieve also per-event error
if (Use["PDEFoam"]) {
Double_t val = reader->EvaluateMVA( "PDEFoam method" );
Double_t err = reader->GetMVAError();
histPDEFoam ->Fill( val );
histPDEFoamErr->Fill( err );
if (err>1.e-50) histPDEFoamSig->Fill( val/err );
}
// Retrieve probability instead of MVA output
if (Use["Fisher"]) {
probHistFi ->Fill( reader->GetProba ( "Fisher method" ) );
rarityHistFi->Fill( reader->GetRarity( "Fisher method" ) );
}
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
newtree->Write();
f_out->Close();
// --- Write histograms
TFile *target = new TFile( "TMVApp.root","RECREATE" );
if (Use["Likelihood" ]) histLk ->Write();
if (Use["LikelihoodD" ]) histLkD ->Write();
if (Use["LikelihoodPCA"]) histLkPCA ->Write();
if (Use["LikelihoodKDE"]) histLkKDE ->Write();
if (Use["LikelihoodMIX"]) histLkMIX ->Write();
if (Use["PDERS" ]) histPD ->Write();
if (Use["PDERSD" ]) histPDD ->Write();
if (Use["PDERSPCA" ]) histPDPCA ->Write();
if (Use["KNN" ]) histKNN ->Write();
if (Use["HMatrix" ]) histHm ->Write();
if (Use["Fisher" ]) histFi ->Write();
if (Use["FisherG" ]) histFiG ->Write();
if (Use["BoostedFisher"]) histFiB ->Write();
if (Use["LD" ]) histLD ->Write();
if (Use["MLP" ]) histNn ->Write();
if (Use["MLPBFGS" ]) histNnbfgs ->Write();
if (Use["MLPBNN" ]) histNnbnn ->Write();
if (Use["CFMlpANN" ]) histNnC ->Write();
if (Use["TMlpANN" ]) histNnT ->Write();
if (Use["BDT" ]) histBdt ->Write();
if (Use["BDTD" ]) histBdtD ->Write();
if (Use["BDTG" ]) histBdtG ->Write();
if (Use["RuleFit" ]) histRf ->Write();
if (Use["SVM_Gauss" ]) histSVMG ->Write();
if (Use["SVM_Poly" ]) histSVMP ->Write();
if (Use["SVM_Lin" ]) histSVML ->Write();
if (Use["FDA_MT" ]) histFDAMT ->Write();
if (Use["FDA_GA" ]) histFDAGA ->Write();
if (Use["Category" ]) histCat ->Write();
if (Use["Plugin" ]) histPBdt ->Write();
// results->Write();
// Write also error and significance histos
if (Use["PDEFoam"]) { histPDEFoam->Write(); histPDEFoamErr->Write(); histPDEFoamSig->Write(); }
// Write also probability hists
if (Use["Fisher"]) { if (probHistFi != 0) probHistFi->Write(); if (rarityHistFi != 0) rarityHistFi->Write(); }
target->Close();
std::cout << "--- Created_prob.root file: \"TMVApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVAClassificationApplication_new(TString myMethodList = "" , TString iFileName = "", TString bkgSample = "", TString sampleLocation = "", TString massPoint = "", TString oFileLocation = "")
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// 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;
//
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader("!Color:!Silent" );
TString weightTail = "_";
weightTail = weightTail + massPoint;
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t var1, var2, var3, var4, var5, var6, var7, var8, var9, var10, var11, var12, var13, var14, var15, var16, var17, var18;
reader->AddVariable( "svMass", &var1);
reader->AddVariable( "dRTauTau", &var3 );
reader->AddVariable( "dRJJ", &var4 );
// reader->AddVariable( "svPt", &var5 );
// reader->AddVariable( "dRhh", &var6 );
reader->AddVariable( "met", &var7 );
reader->AddVariable( "mJJ", &var8 );
// reader->AddVariable( "metTau1DPhi", &var9 );
// reader->AddVariable( "metTau2DPhi", &var10);
// reader->AddVariable( "metJ1DPhi", &var11);
// reader->AddVariable( "metJ2DPhi", &var12 );
// reader->AddVariable( "metTauPairDPhi", &var13 );
// reader->AddVariable( "metSvTauPairDPhi", &var14 );
// reader->AddVariable( "metJetPairDPhi", &var15 );
// reader->AddVariable( "CSVJ1", &var16 );
// reader->AddVariable( "CSVJ2", &var17 );
reader->AddVariable( "fMassKinFit", &var2 );
reader->AddVariable( "chi2KinFit2", &var18 );
// Spectator variables declared in the training have to be added to the reader, too
// Float_t spec1,spec2;
// reader->AddSpectator( "spec1 := var1*2", &spec1 );
// reader->AddSpectator( "spec2 := var1*3", &spec2 );
// Float_t Category_cat1, Category_cat2, Category_cat3;
// if (Use["Category"]){
// // Add artificial spectators for distinguishing categories
// reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
// reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
// reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
// }
// --- Book the MVA methods
// Book method(s)
TString weightFileName = "/nfs_scratch/zmao/test/CMSSW_5_3_15/src/TMVA-v4.2.0/test/weights/TMVAClassification_BDT.weights_";
weightFileName += bkgSample;
weightFileName += weightTail;
reader->BookMVA("BDT method", weightFileName+".xml" );
// Book output histograms
UInt_t nbin = 200;
TH1F *histBdt(0);
histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -1.0, 1.0);
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fileName = iFileName;
TString fname = sampleLocation;
fname += fileName;
TString oFileName = oFileLocation;
oFileName += "ClassApp_" + bkgSample;
oFileName += "_";
oFileName += fileName;
if (!gSystem->AccessPathName( fname ))
input = TFile::Open(fname); // check if file in local directory exists
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
std::cout << "--- Select signal sample" << std::endl;
TTree* theTree = (TTree*)input->Get("eventTree");
TFile *target = new TFile( oFileName,"RECREATE" );
TTree *newTree = theTree->CloneTree();
Float_t BDT;
TBranch *branchBDT = newTree->Branch("BDT_"+bkgSample,&BDT,"BDT/F");
std::vector<Double_t> *vecVar1;
std::vector<Double_t> *vecVar5;
std::vector<Double_t> *vecVar7;
theTree->SetBranchAddress( "svMass", &vecVar1);
theTree->SetBranchAddress( "dRTauTau", &var3);
theTree->SetBranchAddress( "dRJJ", &var4 );
// theTree->SetBranchAddress( "svPt", &vecVar5 );
// theTree->SetBranchAddress( "dRhh", &var6 );
theTree->SetBranchAddress( "met", &vecVar7 );
theTree->SetBranchAddress( "mJJ", &var8 );
// theTree->SetBranchAddress( "metTau1DPhi", &var9 );
// theTree->SetBranchAddress( "metTau2DPhi", &var10);
// theTree->SetBranchAddress( "metJ1DPhi", &var11);
// theTree->SetBranchAddress( "metJ2DPhi", &var12 );
// theTree->SetBranchAddress( "metTauPairDPhi", &var13 );
// theTree->SetBranchAddress( "metSvTauPairDPhi", &var14 );
// theTree->SetBranchAddress( "metJetPairDPhi", &var15 );
// theTree->SetBranchAddress( "CSVJ1", &var16 );
// theTree->SetBranchAddress( "CSVJ2", &var17 );
theTree->SetBranchAddress( "fMassKinFit", &var2);
theTree->SetBranchAddress( "chi2KinFit2", &var18);
//to get initial pre-processed events
TH1F* cutFlow = (TH1F*)input->Get("preselection");
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
theTree->GetEntry(ievt);
var1 = vecVar1->at(0);
// var5 = vecVar5->at(0);
var7 = vecVar7->at(0);
// --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
BDT = reader->EvaluateMVA( "BDT method");
histBdt->Fill(BDT);
branchBDT->Fill();
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
// --- Write histograms
histBdt->Write();
cutFlow->Write();
newTree->Write();
target->Close();
std::cout << "--- Created root file: \""<<oFileName<<"\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVARegressionApplication( int wMs,int wM, string st,string st2,string option="",TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 0;
Use["KNN"] = 0;
//
// --- Linear Discriminant Analysis
Use["LD"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 0;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0;
Use["BDTG"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegressionApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
//Float_t var1, var2;
//reader->AddVariable( "var1", &var1 );
//reader->AddVariable( "var2", &var2 );
Float_t pt_AK8MatchedToHbb,eta_AK8MatchedToHbb,nsv_AK8MatchedToHbb,sv0mass_AK8MatchedToHbb,sv1mass_AK8MatchedToHbb,
nch_AK8MatchedToHbb,nmu_AK8MatchedToHbb,nel_AK8MatchedToHbb,muenfr_AK8MatchedToHbb,emenfr_AK8MatchedToHbb;
reader->AddVariable( "pt_AK8MatchedToHbb", &pt_AK8MatchedToHbb );
reader->AddVariable( "eta_AK8MatchedToHbb", &eta_AK8MatchedToHbb );
reader->AddVariable( "nsv_AK8MatchedToHbb", &nsv_AK8MatchedToHbb );
reader->AddVariable( "sv0mass_AK8MatchedToHbb", &sv0mass_AK8MatchedToHbb );
reader->AddVariable( "sv1mass_AK8MatchedToHbb", &sv1mass_AK8MatchedToHbb );
reader->AddVariable( "nch_AK8MatchedToHbb", &nch_AK8MatchedToHbb );
reader->AddVariable( "nmu_AK8MatchedToHbb", &nmu_AK8MatchedToHbb );
reader->AddVariable( "nel_AK8MatchedToHbb", &nel_AK8MatchedToHbb );
reader->AddVariable( "muenfr_AK8MatchedToHbb", &muenfr_AK8MatchedToHbb );
reader->AddVariable( "emenfr_AK8MatchedToHbb", &emenfr_AK8MatchedToHbb );
// Spectator variables declared in the training have to be added to the reader, too
Float_t spec1,spec2;
reader->AddSpectator( "spec1:=n_pv", &spec1 );
reader->AddSpectator( "spec2:=msoftdrop_AK8MatchedToHbb", &spec2 );
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVARegression";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = it->first + " method";
TString weightfile = dir + prefix + "_" + TString(it->first) + ".weights.xml";
reader->BookMVA( methodName, weightfile );
}
}
TH1* hists[100];
Int_t nhists = -1;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
TH1* h = new TH1F( it->first.c_str(), TString(it->first) + " method", 100, -100, 600 );
if (it->second) hists[++nhists] = h;
}
nhists++;
//1=signal ,0=QCD ,2=data
int nameRoot=1;
if((st2.find("QCD")!= std::string::npos)||
(st2.find("bGen")!= std::string::npos)||
(st2.find("bEnriched")!= std::string::npos))nameRoot=0;
if(st2.find("data")!= std::string::npos)nameRoot=2;
cout<<"nameRoot = "<<nameRoot<<endl;
//option-----------------------------------------------------------
int JESOption=0;
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *f;
TTree *tree;
int nPass[20]={0};
int total=0;
double fixScaleNum[2]={0};
TH1D* th1=new TH1D("a","a",150,50,200);
string massName[nMass]={"Thea","HCorr","Reg"};
string catName[nCat]={"PP","PF","FP","FF"};
string tau21Name[2]={"withTau21","woTau21"};
string catNameShort[nCat]={"P","F"};
string looseTight[2]={"loose","tight"};
TF1 *fa[nMass][2][2][2];
for(int i=0;i<nMass;i++){
for(int j=0;j<2;j++){
for(int k=0;k<2;k++){
for(int w=0;w<2;w++){
fa[i][j][k][w] = new TF1("fa","[0]+[1]*x+[2]*x*x+[3]*pow(x,3)",-3,3);
ifstream myfile (Form("PFRatio/%s_%s_%s_%s.txt",looseTight[w].data(),massName[i].data(),catNameShort[j].data(),tau21Name[k].data()));
double para[4];
for(int m=0;m<4;m++){
myfile>>para[m];
}
fa[i][j][k][w]->SetParameters(para[0],para[1],para[2],para[3]);
}
}
}
}
/*
TH1D* th2[nMass][nCat][2];
TH1D* th3[nMass][nCat][2];
for(int i=0;i<nMass;i++){
for(int j=0;j<nCat;j++){
for(int k=0;k<2;k++){
th2[i][j][k]=(TH1D*)th1->Clone(Form("loose_%s_%s_%s",massName[i].data(),catName[j].data(),tau21Name[k].data()));
th3[i][j][k]=(TH1D*)th1->Clone(Form("tight_%s_%s_%s",massName[i].data(),catName[j].data(),tau21Name[k].data()));
th2[i][j][k]->Sumw2();
th3[i][j][k]->Sumw2();
}
}
}
*/
TH1D* th2d[14];
th2d[0]=new TH1D("0a","0a",4000,1000,5000);
th2d[1]=new TH1D("0c","0c",4000,1000,5000);
th2d[2]=new TH1D("1a","1a",4000,1000,5000);
th2d[3]=new TH1D("1c","1c",4000,1000,5000);
th2d[4]=new TH1D("2a","2a",4000,1000,5000);
th2d[5]=new TH1D("2b","2b",4000,1000,5000);
th2d[6]=new TH1D("2d","2d",4000,1000,5000);
th2d[7]=new TH1D("0aL","0aL",4000,1000,5000);
th2d[8]=new TH1D("0cL","0cL",4000,1000,5000);
th2d[9]=new TH1D("1aL","1aL",4000,1000,5000);
th2d[10]=new TH1D("1cL","1cL",4000,1000,5000);
th2d[11]=new TH1D("2aL","2aL",4000,1000,5000);
th2d[12]=new TH1D("2bL","2bL",4000,1000,5000);
th2d[13]=new TH1D("2dL","2dL",4000,1000,5000);
//int nWidth=5,nBmin=11;
int width [nWidth]={25,30,35,40};
int bmin[nBmin]={100,105,110,115};
TH1D* th3d[14][nWidth][nBmin][2];
TH1D* th3f[14][nWidth][nBmin][2];
TH1D* th3v[14][nWidth][nBmin][2];
for(int i=0;i<nWidth;i++){
for(int j=0;j<nBmin;j++){
for(int k=0;k<2;k++){
for(int l=0;l<14;l++){
th3d[l][i][j][k]=(TH1D*) th2d[l]->Clone(Form("%s_%d_%d_%s",th2d[l]->GetTitle(),bmin[j],width[i]+bmin[j],tau21Name[k].data()));
th3f[l][i][j][k]=(TH1D*) th2d[l]->Clone(Form("fill_%s_%d_%d_%s",th2d[l]->GetTitle(),bmin[j],width[i]+bmin[j],tau21Name[k].data()));
th3v[l][i][j][k]=(TH1D*) th2d[l]->Clone(Form("valid_%s_%d_%d_%s",th2d[l]->GetTitle(),bmin[j],width[i]+bmin[j],tau21Name[k].data()));
th3d[l][i][j][k]->Sumw2();
th3f[l][i][j][k]->Sumw2();
th3v[l][i][j][k]->Sumw2();
}
}
}
}
for (int w=wMs;w<wM;w++){
if(w%20==0)cout<<w<<endl;
if (nameRoot!=1)f = TFile::Open(Form("%s%d.root",st.data(),w));
else f = TFile::Open(st.data());
if (!f || !f->IsOpen())continue;
TDirectory * dir;
if (nameRoot!=1)dir = (TDirectory*)f->Get(Form("%s%d.root:/tree",st.data(),w));
else dir = (TDirectory*)f->Get(Form("%s:/tree",st.data()));
dir->GetObject("treeMaker",tree);
//tree=(TTree*)f->Get("treeMaker");
TreeReader data(tree);
total+=data.GetEntriesFast();
for(Long64_t jEntry=0; jEntry<data.GetEntriesFast() ;jEntry++){
data.GetEntry(jEntry);
Int_t nVtx = data.GetInt("nVtx");
//0. has a good vertex
if(nVtx<1)continue;
nPass[0]++;
//1.trigger
std::string* trigName = data.GetPtrString("hlt_trigName");
vector<bool> &trigResult = *((vector<bool>*) data.GetPtr("hlt_trigResult"));
bool passTrigger=false;
for(int it=0; it< data.GetPtrStringSize();it++){
std::string thisTrig= trigName[it];
bool results = trigResult[it];
if( ((thisTrig.find("HLT_PFHT800")!= std::string::npos||
thisTrig.find("HLT_AK8DiPFJet300_200_TrimMass30_BTagCSV_p20")!= std::string::npos
) && results==1)){
passTrigger=true;
break;
}
}
if(!passTrigger && nameRoot==2)continue;
nPass[1]++;
const int nAK8Jet=data.GetInt("AK8PuppinJet");
//2.nJets
if(nAK8Jet<2)continue;nPass[2]++;
int* AK8PuppinSubSDJet=data.GetPtrInt("AK8PuppinSubSDJet");
if(AK8PuppinSubSDJet[0]!=2||AK8PuppinSubSDJet[1]!=2)continue;
TClonesArray* AK8PuppijetP4 = (TClonesArray*) data.GetPtrTObject("AK8PuppijetP4");
float* AK8PuppijetCorrUncUp = data.GetPtrFloat("AK8PuppijetCorrUncUp");
float* AK8PuppijetCorrUncDown = data.GetPtrFloat("AK8PuppijetCorrUncDown");
TLorentzVector* thisJet ,* thatJet;
thisJet=(TLorentzVector*)AK8PuppijetP4->At(0);
thatJet=(TLorentzVector*)AK8PuppijetP4->At(1);
//3. Pt
if(thisJet->Pt()>99998 ||thatJet->Pt()>99998 )continue;
if(thisJet->Pt()<300)continue;
if(thatJet->Pt()<300)continue;
nPass[3]++;
//4tightId-----------------------------------------
vector<bool> &AK8PuppijetPassIDTight = *((vector<bool>*) data.GetPtr("AK8PuppijetPassIDTight"));
if(AK8PuppijetPassIDTight[0]==0)continue;
if(AK8PuppijetPassIDTight[1]==0)continue;
Float_t* AK8PuppijetCEmEF = data.GetPtrFloat("AK8PuppijetCEmEF");
Float_t* AK8PuppijetMuoEF = data.GetPtrFloat("AK8PuppijetMuoEF");
if(AK8PuppijetMuoEF[0]>0.8)continue;
if(AK8PuppijetCEmEF[0]>0.9)continue;
if(AK8PuppijetMuoEF[1]>0.8)continue;
if(AK8PuppijetCEmEF[1]>0.9)continue;
nPass[4]++;
//5. Eta-----------------------------------------
if(fabs(thisJet->Eta())>2.4)continue;
if(fabs(thatJet->Eta())>2.4)continue;
nPass[5]++;
//6. DEta-----------------------------------------
float dEta = fabs(thisJet->Eta()-thatJet->Eta());
if(dEta>1.3)continue;
nPass[6]++;
//7. Mjj-----------------------------------------
//float mjjRed = (*thisJet+*thatJet).M()+250-thisJet->M()-thatJet->M();
//if(mjjRed<1000)continue;
nPass[7]++;
//8. fatjetPRmassL2L3Corr-----------------------------------------
nPass[8]++;
//9.-----------------------------------------
Float_t* AK8Puppijet_DoubleSV = data.GetPtrFloat("AK8Puppijet_DoubleSV");
int looseStat=-1;
int tightStat=-1;
if(AK8Puppijet_DoubleSV[0]>0.3 && AK8Puppijet_DoubleSV[1]>0.3)looseStat=0;
else if(AK8Puppijet_DoubleSV[0]>0.3 && AK8Puppijet_DoubleSV[1]<0.3)looseStat=1;
else if(AK8Puppijet_DoubleSV[0]<0.3 && AK8Puppijet_DoubleSV[1]>0.3)looseStat=2;
else looseStat=3;
if(AK8Puppijet_DoubleSV[0]>0.8 && AK8Puppijet_DoubleSV[1]>0.8)tightStat=0;
else if(AK8Puppijet_DoubleSV[0]>0.8 && AK8Puppijet_DoubleSV[1]<0.8)tightStat=1;
else if(AK8Puppijet_DoubleSV[0]<0.3 && AK8Puppijet_DoubleSV[1]>0.8)tightStat=2;
else if(AK8Puppijet_DoubleSV[0]<0.3 && AK8Puppijet_DoubleSV[1]<0.8)tightStat=3;
else tightStat=-1;
double varTemp[2];
Float_t* AK8PuppijetSDmass = data.GetPtrFloat("AK8PuppijetSDmass");
if(AK8PuppijetSDmass[0]<50||AK8PuppijetSDmass[1]<50)continue;
Int_t* AK8Puppijet_nSV=data.GetPtrInt("AK8Puppijet_nSV");
vector<float> *AK8Puppijet_SVMass = data.GetPtrVectorFloat("AK8Puppijet_SVMass");
int nEle= data.GetInt("nEle");
int nMu=data.GetInt("nMu");
Float_t* AK8PuppijetEleEF = data.GetPtrFloat("AK8PuppijetEleEF");
//Float_t* AK8PuppijetMuoEF = data.GetPtrFloat("AK8PuppijetMuoEF");
Int_t* AK8PuppijetCMulti=data.GetPtrInt("AK8PuppijetCMulti");
Int_t* AK8PuppijetEleMulti=data.GetPtrInt("AK8PuppijetEleMulti");
Int_t* AK8PuppijetMuoMulti=data.GetPtrInt("AK8PuppijetMuoMulti");
for(int i=0; i<2;i++){
TLorentzVector* thisAK8Jet ;
if(i==1)thisAK8Jet=thatJet;
else thisAK8Jet=thisJet;
pt_AK8MatchedToHbb=thisAK8Jet->Pt();
eta_AK8MatchedToHbb=thisAK8Jet->Eta();
nsv_AK8MatchedToHbb=AK8Puppijet_nSV[i];
sv0mass_AK8MatchedToHbb=AK8Puppijet_SVMass[i][0];
sv1mass_AK8MatchedToHbb=AK8Puppijet_SVMass[i][1];
nmu_AK8MatchedToHbb=AK8PuppijetMuoMulti[i];
nel_AK8MatchedToHbb=AK8PuppijetEleMulti[i];
muenfr_AK8MatchedToHbb=AK8PuppijetMuoEF[i];
nch_AK8MatchedToHbb=AK8PuppijetCMulti[i];
emenfr_AK8MatchedToHbb=AK8PuppijetEleEF[i];
spec1=nVtx;
spec2=AK8PuppijetSDmass[i];
Float_t val ;
for (Int_t ih=0; ih<nhists; ih++) {
TString title = hists[ih]->GetTitle();
val= (reader->EvaluateRegression( title ))[0];
}
varTemp[i]=val;
}
double PUPPIweight[2]={0};
PUPPIweight[0]=getPUPPIweight(thisJet->Pt(),thisJet->Eta());
PUPPIweight[1]=getPUPPIweight(thatJet->Pt(),thatJet->Eta());
double PUPPIweightThea[2]={0};
PUPPIweightThea[0]=getPUPPIweight_o(thisJet->Pt(),thisJet->Eta());
PUPPIweightThea[1]=getPUPPIweight_o(thatJet->Pt(),thatJet->Eta());
double Mjja= ((*thisJet)+(*thatJet)).M()+250
-((*thisJet)).M()-((*thatJet)).M();
TLorentzVector thisJetReg, thatJetReg;
thisJetReg=(*thisJet)*varTemp[0];
thatJetReg=(*thatJet)*varTemp[1];
double Mjjb= (thisJetReg+thatJetReg).M()+250
-(thisJetReg).M()-(thatJetReg).M();
double PUPPIweightOnRegressed[2]={0};
PUPPIweightOnRegressed[0]=getPUPPIweightOnRegressed(thisJetReg.Pt(),thisJetReg.Eta());
PUPPIweightOnRegressed[1]=getPUPPIweightOnRegressed(thatJetReg.Pt(),thatJetReg.Eta());
vector<float> *subjetSDPx = data.GetPtrVectorFloat("AK8PuppisubjetSDPx");
vector<float> *subjetSDPy = data.GetPtrVectorFloat("AK8PuppisubjetSDPy");
vector<float> *subjetSDPz = data.GetPtrVectorFloat("AK8PuppisubjetSDPz");
vector<float> *subjetSDE = data.GetPtrVectorFloat("AK8PuppisubjetSDE");
vector<float> *AK8PuppisubjetSDRawFactor = data.GetPtrVectorFloat("AK8PuppisubjetSDRawFactor");
TLorentzVector thisSDJet, thatSDJet;
TLorentzVector* subjetP4[2][2];
for(int i=0;i<2;i++){
for(int j=0;j<2;j++){
subjetP4[i][j]=new TLorentzVector(0,0,0,0);
subjetP4[i][j]->SetPxPyPzE(subjetSDPx[i][j],subjetSDPy[i][j],subjetSDPz[i][j],subjetSDE[i][j]);
// subjetP4[i][j]*=AK8PuppisubjetSDRawFactor[i][j];
}
}
thisSDJet=(*subjetP4[0][0])*AK8PuppisubjetSDRawFactor[0][0]+(*subjetP4[0][1])*AK8PuppisubjetSDRawFactor[0][1];
thatSDJet=(*subjetP4[1][0])*AK8PuppisubjetSDRawFactor[1][0]+(*subjetP4[1][1])*AK8PuppisubjetSDRawFactor[1][1];
//thatSDJet=(*subjetP4[1][0])+(*subjetP4[1][1]);
TLorentzVector thisSDJetReg, thatSDJetReg;
thisSDJetReg= thisSDJet*varTemp[0]*PUPPIweightOnRegressed[0];
thatSDJetReg= thatSDJet*varTemp[1]*PUPPIweightOnRegressed[1];
//double Mjjc= ((thisSDJet)+(thatSDJet)).M()+250
// -((thisSDJet)).M()-((thatSDJet)).M();
double Mjjd= ((thisSDJet)+(thatSDJet)).M()+250
-((thisSDJet)).M()-((thatSDJet)).M();
Float_t* AK8PuppijetTau1 = data.GetPtrFloat("AK8PuppijetTau1");
Float_t* AK8PuppijetTau2 = data.GetPtrFloat("AK8PuppijetTau2");
double puppiTau21[2];
puppiTau21[0]=(AK8PuppijetTau2[0]/AK8PuppijetTau1[0]),puppiTau21[1]=(AK8PuppijetTau2[1]/AK8PuppijetTau1[1]);
double mass_j0,mass_j1,MjjLoop;
int massCat;
for(int k=0;k<7;k++){
if(k==0||k==2||k==4){
if(thisJet->Pt()<300)continue;
if(thatJet->Pt()<300)continue;
}
else if (k==1){
if((thisSDJet*PUPPIweightThea[0]).Pt()<300)continue;
if((thatSDJet*PUPPIweightThea[1]).Pt()<300)continue;
}
else if (k==3){
if((thisSDJet*PUPPIweight[0]).Pt()<300)continue;
if((thatSDJet*PUPPIweight[1]).Pt()<300)continue;
}
else if (k==5){
if(thisJetReg.Pt()<300)continue;
if(thatJetReg.Pt()<300)continue;
}
else{
if(thisSDJetReg.Pt()<300)continue;
if(thatSDJetReg.Pt()<300)continue;
}
if(k==0||k==1){
mass_j0=AK8PuppijetSDmass[0]*PUPPIweightThea[0];
mass_j1=AK8PuppijetSDmass[1]*PUPPIweightThea[1];
massCat=0;
}
else if (k==2||k==3){
mass_j0=AK8PuppijetSDmass[0]*PUPPIweight[0];
mass_j1=AK8PuppijetSDmass[1]*PUPPIweight[1];
massCat=1;
}
else{
mass_j0=AK8PuppijetSDmass[0]*varTemp[0]*PUPPIweightOnRegressed[0];
mass_j1=AK8PuppijetSDmass[1]*varTemp[1]*PUPPIweightOnRegressed[1];
massCat=2;
}
if(k==0||k==2||k==4)MjjLoop=Mjja;
else if (k==1)MjjLoop=((thisSDJet)*PUPPIweightThea[0]+(thatSDJet)*PUPPIweightThea[1]).M()+250-((thisSDJet)*PUPPIweightThea[0]).M()-((thatSDJet)*PUPPIweightThea[1]).M();
else if (k==3)MjjLoop=((thisSDJet)*PUPPIweight[0]+(thatSDJet)*PUPPIweight[1]).M()+250-((thisSDJet)*PUPPIweight[0]).M()-((thatSDJet)*PUPPIweight[1]).M();
else if (k==5)MjjLoop=Mjjb;
else MjjLoop=Mjjd;
//cout<<mass_j0<<","<<mass_j1<<",k="<<k<<endl;
for(int i=0;i<nWidth;i++){
for(int j=0;j<nBmin;j++){
if(mass_j0<bmin[j] ||mass_j0>width[i]+bmin[j]
||mass_j1<bmin[j] ||mass_j1>width[i]+bmin[j] )continue;
for(int m=0;m<2;m++){
if(m==0 && (puppiTau21[0]>0.6 || puppiTau21[1]>0.6))continue;
double tightPFRatio=0,loosePFRatio=0;
tightPFRatio=fa[massCat][0][m][1]->Eval(mass_j0);
loosePFRatio=fa[massCat][0][m][0]->Eval(mass_j0);
if(tightStat==0){
th3d[k][i][j][m]->Fill(MjjLoop);
}
else if (tightStat==1){
th3f[k][i][j][m]->Fill(MjjLoop);
}
else if(tightStat==3){
tightPFRatio=fa[massCat][1][m][1]->Eval(mass_j0);
th3v[k][i][j][m]->Fill(MjjLoop,tightPFRatio);
}
if(looseStat==0 && tightStat!=0){
th3d[k+7][i][j][m]->Fill(MjjLoop);
}
else if (looseStat==1){
th3f[k+7][i][j][m]->Fill(MjjLoop);
}
else if(looseStat==3){
loosePFRatio=fa[massCat][1][m][0]->Eval(mass_j0);
th3v[k+7][i][j][m]->Fill(MjjLoop,loosePFRatio);
}
}
}
}
}
}
}
for(int i=0;i<10;i++)cout<<"npass["<<i<<"]="<<nPass[i]<<endl;
TFile* outFile;//= new TFile(Form("PFRatio/%s.root",st2.data()),"recreate");
outFile= new TFile(Form("MjjVC/%s.root",st2.data()),"recreate");
for(int i=0;i<nWidth;i++){
for(int j=0;j<nBmin;j++){
for(int k=0;k<2;k++){
for(int l=0;l<14;l++){
th3d[l][i][j][k]->Write();
th3f[l][i][j][k]->Write();
th3v[l][i][j][k]->Write();
}
}
}
}
outFile->Close();
for(int i=0;i<nWidth;i++){
for(int j=0;j<nBmin;j++){
for(int k=0;k<2;k++){
for(int l=0;l<14;l++){
delete th3d[l][i][j][k];
delete th3f[l][i][j][k];
delete th3v[l][i][j][k];
}
}
}
}
delete reader;
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName" << std::endl ;
return 1;
}
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString){
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
//==== list of methods
std::string MVADirectory = gConfigParser -> readStringOption ("Options::MVADirectory");
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
std::vector<std::string> vectorMyMethodMassList = gConfigParser -> readStringListOption("Options::MVAmethodsMass");
std::string outputDirectory = gConfigParser -> readStringOption("Output::outputDirectory");
//---- variables
float jetpt1;
float jetpt2;
float mjj;
float detajj;
float dphilljetjet;
float pt1;
float pt2;
float mll;
float dphill;
float mth;
float dphillmet;
float mpmet;
float channel;
//~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
TFile* outputRootFile[500];
TTree* cloneTreeJetLepVect[500];
TTree *treeJetLepVect[500];
TFile* file[500];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++){
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
file[iSample] = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) file[iSample]->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
treeJetLepVect[iSample] -> SetBranchAddress("jetpt1", &jetpt1);
treeJetLepVect[iSample] -> SetBranchAddress("jetpt2", &jetpt2);
treeJetLepVect[iSample] -> SetBranchAddress("mjj", &mjj);
treeJetLepVect[iSample] -> SetBranchAddress("detajj", &detajj);
treeJetLepVect[iSample] -> SetBranchAddress("dphilljetjet", &dphilljetjet);
treeJetLepVect[iSample] -> SetBranchAddress("pt1", &pt1);
treeJetLepVect[iSample] -> SetBranchAddress("pt2", &pt2);
treeJetLepVect[iSample] -> SetBranchAddress("mll", &mll);
treeJetLepVect[iSample] -> SetBranchAddress("dphill", &dphill);
treeJetLepVect[iSample] -> SetBranchAddress("mth", &mth);
treeJetLepVect[iSample] -> SetBranchAddress("dphillmet", &dphillmet);
treeJetLepVect[iSample] -> SetBranchAddress("mpmet", &mpmet);
treeJetLepVect[iSample] -> SetBranchAddress("channel", &channel);
sprintf(nameFile,"%s/%s%s.root",outputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
outputRootFile[iSample] = new TFile ( nameFile, "RECREATE") ;
outputRootFile[iSample] -> cd () ;
cloneTreeJetLepVect[iSample] = treeJetLepVect[iSample] -> CloneTree (0) ;
}
/**
* cycle on MVA (method-mass)
* * cycle on samples
* * * cycle on events
*/
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
std::cout << " vectorMyMethodList[" << iMVA << "] = " << vectorMyMethodList.at(iMVA) << std::endl;
TString myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
for (int iMVAMass = 0; iMVAMass < vectorMyMethodMassList.size(); iMVAMass++) {
std::cout << " vectorMyMethodMassList[" << iMVAMass << "] = " << vectorMyMethodMassList.at(iMVAMass) << std::endl;
TMVA::Reader *TMVAreader = new TMVA::Reader( "!Color:!Silent" );
// TMVAreader->AddVariable("jetpt1", &jetpt1);
// TMVAreader->AddVariable("jetpt2", &jetpt2);
// TMVAreader->AddVariable("mjj", &mjj);
// TMVAreader->AddVariable("detajj", &detajj);
// TMVAreader->AddVariable("dphilljetjet", &dphilljetjet);
// TMVAreader->AddVariable("pt1", &pt1);
// TMVAreader->AddVariable("pt2", &pt2);
// TMVAreader->AddVariable("mll", &mll);
// TMVAreader->AddVariable("dphill", &dphill);
// TMVAreader->AddVariable("mth", &mth);
// TMVAreader->AddVariable("dphillmet", &dphillmet);
// TMVAreader->AddVariable("mpmet", &mpmet);
Float_t input_variables[1000];
// float input_variables[1000];
// TMVAreader->AddVariable("jetpt1", &(input_variables[0]));
// TMVAreader->AddVariable("jetpt2", &(input_variables[1]));
// TMVAreader->AddVariable("mjj", &(input_variables[2]));
// TMVAreader->AddVariable("detajj", &(input_variables[3]));
// TMVAreader->AddVariable("dphilljetjet", &(input_variables[4]));
// TMVAreader->AddVariable("pt1", &(input_variables[5]));
// TMVAreader->AddVariable("pt2", &(input_variables[6]));
// TMVAreader->AddVariable("mll", &(input_variables[7]));
// TMVAreader->AddVariable("dphill", &(input_variables[8]));
// TMVAreader->AddVariable("mth", &(input_variables[9]));
// TMVAreader->AddVariable("dphillmet", &(input_variables[10]));
// TMVAreader->AddVariable("mpmet", &(input_variables[11]));
TMVAreader->AddVariable("jetpt1", &input_variables[0]);
TMVAreader->AddVariable("jetpt2", &input_variables[1]);
TMVAreader->AddVariable("mjj", &input_variables[2]);
TMVAreader->AddVariable("detajj", &input_variables[3]);
TMVAreader->AddVariable("dphilljetjet", &input_variables[4]);
TMVAreader->AddVariable("pt1", &input_variables[5]);
TMVAreader->AddVariable("pt2", &input_variables[6]);
TMVAreader->AddVariable("mll", &input_variables[7]);
TMVAreader->AddVariable("dphill", &input_variables[8]);
TMVAreader->AddVariable("mth", &input_variables[9]);
TMVAreader->AddVariable("dphillmet", &input_variables[10]);
TMVAreader->AddVariable("mpmet", &input_variables[11]);
TMVAreader->AddSpectator("channel", &input_variables[12]);
TString myMethodMassList = Form ("%s",vectorMyMethodMassList.at(iMVAMass).c_str());
TString weightfile = Form ("%s/weights_%s_testVariables/TMVAMulticlass_%s.weights.xml",MVADirectory.c_str(),myMethodMassList.Data(),myMethodList.Data());
std::cout << " myMethodList = " << myMethodList.Data() << std::endl;
std::cout << " weightfile = " << weightfile.Data() << std::endl;
// TString myMethodListBook = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
// TMVAreader->BookMVA( myMethodListBook, weightfile );
TMVAreader->BookMVA( myMethodList, weightfile );
for (int iSample=0; iSample<numberOfSamples; iSample++){
std::cout << " iSample = " << iSample << " :: " << numberOfSamples << std::endl;
file[iSample] -> cd();
Double_t MVA_Value;
TBranch *newBranch;
TString methodName4Tree = Form ("%s_%s_MVAHiggs",myMethodList.Data(),myMethodMassList.Data());
TString methodName4Tree2 = Form ("%s_%s_MVAHiggs/D",myMethodList.Data(),myMethodMassList.Data());
newBranch = cloneTreeJetLepVect[iSample]->Branch(methodName4Tree,&MVA_Value,methodName4Tree2);
// newBranch = treeJetLepVect[iSample]->Branch(methodName4Tree,&MVA_Value,methodName4Tree2);
///==== loop ====
Long64_t nentries = treeJetLepVect[iSample]->GetEntries();
for (Long64_t iEntry = 0; iEntry < nentries; iEntry++){
if((iEntry%1000) == 0) std::cout << ">>>>> analysis::GetEntry " << iEntry << " : " << nentries << std::endl;
treeJetLepVect[iSample]->GetEntry(iEntry);
input_variables[0] = static_cast<Float_t>(jetpt1);
input_variables[1] = static_cast<Float_t>(jetpt2);
input_variables[2] = static_cast<Float_t>(mjj);
input_variables[3] = static_cast<Float_t>(detajj);
input_variables[4] = static_cast<Float_t>(dphilljetjet);
input_variables[5] = static_cast<Float_t>(pt1);
input_variables[6] = static_cast<Float_t>(pt2);
input_variables[7] = static_cast<Float_t>(mll);
input_variables[8] = static_cast<Float_t>(dphill);
input_variables[9] = static_cast<Float_t>(mth);
input_variables[10] = static_cast<Float_t>(dphillmet);
input_variables[11] = static_cast<Float_t>(mpmet);
input_variables[12] = static_cast<Float_t>(channel);
int num = TMVAreader->EvaluateMulticlass(myMethodList).size();
double max = -1e9;
double tempmax;
int numsel = -1;
for (int inum = 0; inum<(num-2); inum++) { // il -2 è dovuto a Sig e Bkg che mi salva il training! Uffi!
tempmax = (TMVAreader->EvaluateMulticlass(myMethodList))[inum];
if (tempmax > max) {
max = tempmax;
numsel = inum;
}
}
MVA_Value = max + 3*numsel;
// newBranch -> Fill();
cloneTreeJetLepVect[iSample] -> Fill () ;
}
}
}
}
for (int iSample=0; iSample<numberOfSamples; iSample++){
// save only the new version of the tree
// treeJetLepVect[iSample]->Write("", TObject::kOverwrite);
cloneTreeJetLepVect[iSample] -> SetName (treeName.c_str());
cloneTreeJetLepVect[iSample] -> AutoSave () ;
outputRootFile[iSample] -> Close () ;
}
}
////////////////////////////////////////////////////////////////////////////////
/// Main ///
////////////////////////////////////////////////////////////////////////////////
void GrowTree(TString process, std::string regMethod="BDTG", Long64_t beginEntry=0, Long64_t endEntry=-1)
{
gROOT->SetBatch(1);
TH1::SetDefaultSumw2(1);
gROOT->LoadMacro("HelperFunctions.h"); //< make functions visible to TTreeFormula
if (!TString(gROOT->GetVersion()).Contains("5.34")) {
std::cout << "INCORRECT ROOT VERSION! Please use 5.34:" << std::endl;
std::cout << "source /uscmst1/prod/sw/cms/slc5_amd64_gcc462/lcg/root/5.34.02-cms/bin/thisroot.csh" << std::endl;
std::cout << "Return without doing anything." << std::endl;
return;
}
const TString indir = "/afs/cern.ch/work/d/degrutto/public/MiniAOD/ZnnHbb_Phys14_PU20bx25/skimV11/";
const TString outdir = "/afs/cern.ch/work/d/degrutto/public/MiniAOD/ZnnHbb_Phys14_PU20bx25/skimV11/step3/";
const TString prefix = "skim_";
const TString suffix = ".root";
TFile *input = TFile::Open(indir + prefix + process + suffix);
if (!input) {
std::cout << "ERROR: Could not open input file." << std::endl;
exit(1);
}
/// Make output directory if it doesn't exist
if (gSystem->AccessPathName(outdir))
gSystem->mkdir(outdir);
std::cout << "--- GrowTree : Using input file: " << input->GetName() << std::endl;
TTree *inTree = (TTree *) input->Get("tree");
TH1F *hcount = (TH1F *) input->Get("Count");
TFile *output(0);
if (beginEntry == 0 && endEntry == -1)
output = TFile::Open(outdir + "Step3_" + process + suffix, "RECREATE");
else
output = TFile::Open(outdir + "Step3_" + process + TString::Format("_%Li_%Li", beginEntry, endEntry) + suffix, "RECREATE");
TTree *outTree = inTree->CloneTree(0); // Do no copy the data yet
/// The clone should not delete any shared i/o buffers.
ResetDeleteBranches(outTree);
///-- Set branch addresses -------------------------------------------------
EventInfo EVENT;
double hJet_pt[MAXJ], hJet_eta[MAXJ], hJet_phi[MAXJ], hJet_m[MAXJ], hJet_ptRaw[MAXJ], hJet_genPt[MAXJ];
int hJCidx[2];
inTree->SetBranchStatus("*", 1);
inTree->SetBranchStatus("hJCidx",1);
inTree->SetBranchStatus("Jet_*",1);
inTree->SetBranchAddress("hJCidx", &hJCidx);
inTree->SetBranchAddress("Jet_pt", &hJet_pt);
inTree->SetBranchAddress("Jet_eta", &hJet_eta);
inTree->SetBranchAddress("Jet_phi", &hJet_phi);
inTree->SetBranchAddress("Jet_mass", &hJet_m);
inTree->SetBranchAddress("Jet_rawPt", &hJet_ptRaw);
inTree->SetBranchAddress("Jet_mcPt", &hJet_genPt);
///-- Make new branches ----------------------------------------------------
int EVENT_run, EVENT_event; // set these as TTree index?
float lumi_ = lumi, efflumi, efflumi_old,
efflumi_UEPS_up, efflumi_UEPS_down;
float hJet_ptReg[2];
float HptNorm, HptGen, HptReg;
float HmassNorm, HmassGen, HmassReg;
outTree->Branch("EVENT_run", &EVENT_run, "EVENT_run/I");
outTree->Branch("EVENT_event", &EVENT_event, "EVENT_event/I");
outTree->Branch("lumi", &lumi_, "lumi/F");
outTree->Branch("efflumi", &efflumi, "efflumi/F");
outTree->Branch("efflumi_old", &efflumi_old, "efflumi_old/F");
outTree->Branch("efflumi_UEPS_up", &efflumi_UEPS_up, "efflumi_UEPS_up/F");
outTree->Branch("efflumi_UEPS_down", &efflumi_UEPS_down, "efflumi_UEPS_down/F");
outTree->Branch("hJet_ptReg", &hJet_ptReg, "hJet_ptReg[2]/F");
outTree->Branch("HptNorm", &HptNorm, "HptNorm/F");
outTree->Branch("HptGen", &HptGen, "HptGen/F");
outTree->Branch("HptReg", &HptReg, "HptReg/F");
outTree->Branch("HmassNorm", &HmassNorm, "HmassNorm/F");
outTree->Branch("HmassGen", &HmassGen, "HmassGen/F");
outTree->Branch("HmassReg", &HmassReg, "HmassReg/F");
/// Get effective lumis
std::map < std::string, float > efflumis = GetLumis();
efflumi = efflumis[process.Data()];
assert(efflumi > 0);
efflumi_old = efflumi;
efflumi_UEPS_up = efflumi * hcount->GetBinContent(2) / hcount->GetBinContent(3);
efflumi_UEPS_down = efflumi * hcount->GetBinContent(2) / hcount->GetBinContent(4);
TTreeFormula* ttf_lheweight = new TTreeFormula("ttf_lheweight", Form("%f", efflumi), inTree);
#ifdef STITCH
std::map < std::string, std::string > lheweights = GetLHEWeights();
TString process_lhe = process;
if (process_lhe.BeginsWith("WJets") && process_lhe != "WJetsHW")
process_lhe = "WJets";
else if (process_lhe.BeginsWith("ZJets") && process_lhe != "ZJetsHW")
process_lhe = "ZJets";
else
process_lhe = "";
TString lheweight = lheweights[process_lhe.Data()];
if (lheweight != "") {
delete ttf_lheweight;
// Bug fix for ZJetsPtZ100
if (process == "ZJetsPtZ100")
lheweight.ReplaceAll("lheV_pt", "999");
std::cout << "BUGFIX: " << lheweight << std::endl;
ttf_lheweight = new TTreeFormula("ttf_lheweight", lheweight, inTree);
}
#endif
ttf_lheweight->SetQuickLoad(1);
// regression stuff here
///-- Setup TMVA Reader ----------------------------------------------------
TMVA::Tools::Instance(); //< This loads the library
TMVA::Reader * reader = new TMVA::Reader("!Color:!Silent");
/// Get the variables
const std::vector < std::string > & inputExpressionsReg = GetInputExpressionsReg();
const UInt_t nvars = inputExpressionsReg.size();
Float_t readerVars[nvars];
int idx_rawpt = -1, idx_pt = -1, idx_et = -1, idx_mt = -1;
for (UInt_t iexpr = 0; iexpr < nvars; iexpr++) {
const TString& expr = inputExpressionsReg.at(iexpr);
reader->AddVariable(expr, &readerVars[iexpr]);
if (expr.BeginsWith("breg_rawptJER := ")) idx_rawpt = iexpr;
else if (expr.BeginsWith("breg_pt := ")) idx_pt = iexpr;
else if (expr.BeginsWith("breg_et := ")) idx_et = iexpr;
else if (expr.BeginsWith("breg_mt := ")) idx_mt = iexpr;
}
// assert(idx_rawpt!=-1 && idx_pt!=-1 && idx_et!=-1 && idx_mt!=-1);
assert(idx_rawpt!=-1 && idx_pt!=-1 );
/// Setup TMVA regression inputs
const std::vector < std::string > & inputExpressionsReg0 = GetInputExpressionsReg0();
const std::vector < std::string > & inputExpressionsReg1 = GetInputExpressionsReg1();
assert(inputExpressionsReg0.size() == nvars);
assert(inputExpressionsReg1.size() == nvars);
/// Load TMVA weights
TString weightdir = "weights/";
TString weightfile = weightdir + "TMVARegression_" + regMethod + ".testweights.xml";
reader->BookMVA(regMethod + " method", weightfile);
TStopwatch sw;
sw.Start();
/// Create TTreeFormulas
TTreeFormula *ttf = 0;
std::vector < TTreeFormula * >::const_iterator formIt, formItEnd;
std::vector < TTreeFormula * > inputFormulasReg0;
std::vector < TTreeFormula * > inputFormulasReg1;
std::vector < TTreeFormula * > inputFormulasFJReg0;
std::vector < TTreeFormula * > inputFormulasFJReg1;
std::vector < TTreeFormula * > inputFormulasFJReg2;
for (UInt_t iexpr = 0; iexpr < nvars; iexpr++) {
ttf = new TTreeFormula(Form("ttfreg%i_0", iexpr), inputExpressionsReg0.at(iexpr).c_str(), inTree);
ttf->SetQuickLoad(1);
inputFormulasReg0.push_back(ttf);
ttf = new TTreeFormula(Form("ttfreg%i_1", iexpr), inputExpressionsReg1.at(iexpr).c_str(), inTree);
ttf->SetQuickLoad(1);
inputFormulasReg1.push_back(ttf);
}
///-- Loop over events -----------------------------------------------------
Int_t curTree = inTree->GetTreeNumber();
const Long64_t nentries = inTree->GetEntries();
if (endEntry < 0) endEntry = nentries;
Long64_t ievt = 0;
for (ievt=TMath::Max(ievt, beginEntry); ievt<TMath::Min(nentries, endEntry); ievt++) {
if (ievt % 2000 == 0)
std::cout << "--- ... Processing event: " << ievt << std::endl;
const Long64_t local_entry = inTree->LoadTree(ievt); // faster, but only for TTreeFormula
if (local_entry < 0) break;
inTree->GetEntry(ievt); // same event as received by LoadTree()
if (inTree->GetTreeNumber() != curTree) {
curTree = inTree->GetTreeNumber();
for (formIt=inputFormulasReg0.begin(), formItEnd=inputFormulasReg0.end(); formIt!=formItEnd; formIt++)
(*formIt)->UpdateFormulaLeaves(); // if using TChain
for (formIt=inputFormulasReg1.begin(), formItEnd=inputFormulasReg1.end(); formIt!=formItEnd; formIt++)
(*formIt)->UpdateFormulaLeaves(); // if using TChain
for (formIt=inputFormulasFJReg0.begin(), formItEnd=inputFormulasFJReg0.end(); formIt!=formItEnd; formIt++)
(*formIt)->UpdateFormulaLeaves(); // if using TChain
for (formIt=inputFormulasFJReg1.begin(), formItEnd=inputFormulasFJReg1.end(); formIt!=formItEnd; formIt++)
(*formIt)->UpdateFormulaLeaves(); // if using TChain
for (formIt=inputFormulasFJReg2.begin(), formItEnd=inputFormulasFJReg2.end(); formIt!=formItEnd; formIt++)
(*formIt)->UpdateFormulaLeaves(); // if using TChain
ttf_lheweight->UpdateFormulaLeaves();
}
/// These need to be called when arrays of variable size are used in TTree.
for (formIt=inputFormulasReg0.begin(), formItEnd=inputFormulasReg0.end(); formIt!=formItEnd; formIt++)
(*formIt)->GetNdata();
for (formIt=inputFormulasReg1.begin(), formItEnd=inputFormulasReg1.end(); formIt!=formItEnd; formIt++)
(*formIt)->GetNdata();
for (formIt=inputFormulasFJReg0.begin(), formItEnd=inputFormulasFJReg0.end(); formIt!=formItEnd; formIt++)
(*formIt)->GetNdata();
for (formIt=inputFormulasFJReg1.begin(), formItEnd=inputFormulasFJReg1.end(); formIt!=formItEnd; formIt++)
(*formIt)->GetNdata();
for (formIt=inputFormulasFJReg2.begin(), formItEnd=inputFormulasFJReg2.end(); formIt!=formItEnd; formIt++)
(*formIt)->GetNdata();
ttf_lheweight->GetNdata();
/// Fill branches
EVENT_run = EVENT.run;
EVENT_event = EVENT.event;
#ifdef STITCH
efflumi = ttf_lheweight->EvalInstance();
// efflumi_UEPS_up = efflumi * hcount->GetBinContent(2) / hcount->GetBinContent(3);
//efflumi_UEPS_down = efflumi * hcount->GetBinContent(2) / hcount->GetBinContent(4);
#endif
bool verbose = false;
for (Int_t ihj = 0; ihj < 2; ihj++) {
/// Evaluate TMVA regression output
for (UInt_t iexpr = 0; iexpr < nvars; iexpr++) {
if (ihj==0) {
readerVars[iexpr] = inputFormulasReg0.at(iexpr)->EvalInstance();
} else if (ihj==1) {
readerVars[iexpr] = inputFormulasReg1.at(iexpr)->EvalInstance();
}
}
hJet_ptReg[ihj] = (reader->EvaluateRegression(regMethod + " method"))[0];
if (verbose) std::cout << readerVars[idx_pt] << " " << readerVars[idx_rawpt] << " " << hJet_pt[ihj] << " " << hJet_ptReg[ihj] << " " << hJet_genPt[ihj] << std::endl;
const TLorentzVector p4Zero = TLorentzVector(0., 0., 0., 0.);
// int idx = hJCidx[0] ;
// std::cout << "the regressed pt for jet 0 is " << hJet_ptReg[0] << "; the hJCidx is " << hJCidx[0] << ", hence the origianl pt is " << hJet_pt[idx] << std::endl;
const TLorentzVector& hJet_p4Norm_0 = makePtEtaPhiM(hJet_pt[hJCidx[0]] , hJet_pt[hJCidx[0]], hJet_eta[hJCidx[0]], hJet_phi[hJCidx[0]], hJet_m[hJCidx[0]]);
const TLorentzVector& hJet_p4Norm_1 = makePtEtaPhiM(hJet_pt[hJCidx[1]] , hJet_pt[hJCidx[1]], hJet_eta[hJCidx[1]], hJet_phi[hJCidx[1]], hJet_m[hJCidx[1]]);
const TLorentzVector& hJet_p4Gen_0 = hJet_genPt[hJCidx[0]] > 0 ?
makePtEtaPhiM(hJet_genPt[hJCidx[0]] , hJet_pt[hJCidx[0]], hJet_eta[hJCidx[0]], hJet_phi[hJCidx[0]], hJet_m[hJCidx[0]]) : p4Zero;
const TLorentzVector& hJet_p4Gen_1 = hJet_genPt[hJCidx[1]] > 0 ?
makePtEtaPhiM(hJet_genPt[hJCidx[1]] , hJet_pt[hJCidx[1]], hJet_eta[hJCidx[1]], hJet_phi[hJCidx[1]], hJet_m[hJCidx[1]]) : p4Zero;
const TLorentzVector& hJet_p4Reg_0 = makePtEtaPhiM(hJet_ptReg[0] , hJet_pt[hJCidx[0]], hJet_eta[hJCidx[0]], hJet_phi[hJCidx[0]], hJet_m[hJCidx[0]]);
const TLorentzVector& hJet_p4Reg_1 = makePtEtaPhiM(hJet_ptReg[1] , hJet_pt[hJCidx[1]], hJet_eta[hJCidx[1]], hJet_phi[hJCidx[1]], hJet_m[hJCidx[1]]);
HptNorm = (hJet_p4Norm_0 + hJet_p4Norm_1 ).Pt();
HptGen = (hJet_p4Gen_0 + hJet_p4Gen_1 ).Pt();
HptReg = (hJet_p4Reg_0 + hJet_p4Reg_1 ).Pt();
HmassNorm = (hJet_p4Norm_0 + hJet_p4Norm_1 ).M();
HmassGen = (hJet_p4Gen_0 + hJet_p4Gen_1 ).M();
HmassReg = (hJet_p4Reg_0 + hJet_p4Reg_1 ).M();
// std::cout << "HmassReg is " << HmassReg << std::endl;
}
outTree->Fill(); // fill it!
} // end loop over TTree entries
/// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: ";
sw.Print();
output->cd();
outTree->Write();
output->Close();
input->Close();
delete input;
delete output;
for (formIt=inputFormulasReg0.begin(), formItEnd=inputFormulasReg0.end(); formIt!=formItEnd; formIt++)
delete *formIt;
for (formIt=inputFormulasReg1.begin(), formItEnd=inputFormulasReg1.end(); formIt!=formItEnd; formIt++)
delete *formIt;
for (formIt=inputFormulasFJReg0.begin(), formItEnd=inputFormulasFJReg0.end(); formIt!=formItEnd; formIt++)
delete *formIt;
for (formIt=inputFormulasFJReg1.begin(), formItEnd=inputFormulasFJReg1.end(); formIt!=formItEnd; formIt++)
delete *formIt;
for (formIt=inputFormulasFJReg2.begin(), formItEnd=inputFormulasFJReg2.end(); formIt!=formItEnd; formIt++)
delete *formIt;
delete ttf_lheweight;
std::cout << "==> GrowTree is done!" << std::endl << std::endl;
return;
}
void TMVAClassificationApplication( TString SampleName = "" )
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// 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"] = 1;
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"] = 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"] = 1; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 1; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 1; // decorrelation + Adaptive Boost
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
Use["Plugin"] = 0;
Use["Category"] = 0;
Use["SVM_Gauss"] = 0;
Use["SVM_Poly"] = 0;
Use["SVM_Lin"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t var1, var2;
Float_t var3, var4;
reader->AddVariable( "jet_csv[0]", &var1 );
reader->AddVariable( "jet_csv[1]", &var2 );
reader->AddVariable( "jet_csv[2]", &var3 );
reader->AddVariable( "jet_csv[3]", &var4 );
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVAClassification";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fname = Form("file:/cms/home/youngjo/CATools/ntuple_v741/result4/result_%s.root",SampleName.Data());
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
// else
// input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << fname.Data() << std::endl;
exit(1);
}
TH1F *htotevents = (TH1F*) input->Get("hNEvent");
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
std::cout << "--- Select signal sample" << std::endl;
TTree* theTree = (TTree*)input->Get("myresult2");
TFile *target = new TFile( Form("result_TMVA_%s.root",SampleName.Data()),"RECREATE" );
TTree *tree_ = new TTree(Form("myresult3"),"");
FlatTree* fevent_ = new FlatTree();
FlatTree* fevent2_ = new FlatTree();
fevent_->book(tree_);
fevent2_->setBranch(theTree);
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
int counter=0;
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
fevent_->clear();
theTree->GetEntry(ievt);
fevent_->copy(fevent2_);
counter++;
//if(counter>2000) break;
var1 = fevent_->jet_csv_->at(0);
var2 = fevent_->jet_csv_->at(1);
var3 = fevent_->jet_csv_->at(2);
var4 = fevent_->jet_csv_->at(3);
//fevent_->CutsD_ = (float) 99.;
fevent_->LikelihoodD_= (float) reader->EvaluateMVA( "LikelihoodD method" ) ;
fevent_->MLP_ = (float) reader->EvaluateMVA( "MLP method" ) ;
fevent_->MLPBFGS_ = (float) reader->EvaluateMVA( "MLPBFGS method" ) ;
fevent_->MLPBNN_ = (float) reader->EvaluateMVA( "MLPBNN method" ) ;
fevent_->BDT_ = (float) reader->EvaluateMVA( "BDT method" ) ;
fevent_->BDTD_ = (float) reader->EvaluateMVA( "BDTD method" ) ;
fevent_->BDTG_ = (float) reader->EvaluateMVA( "BDTG method" ) ;
tree_->Fill();
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// --- Write histograms
tree_->Write();
htotevents->Write();
target->Close();
std::cout << "--- Created root file: \"result_TMVA_"+SampleName+".root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName" << std::endl ;
return 1;
}
std::cout << " " << std::endl;
std::cout << " " << std::endl;
std::cout << " " << std::endl;
std::cout << " \\ | \\ \\ / \\ \\ | | \\ \\ / _) | | ___ \\ | \\ \\ / __ ) ____| " << std::endl;
std::cout << " |\\/ | \\ \\ / _ \\ _ \\ _` | _` | \\ \\ / _` | __| | _` | __ \\ | _ \\ ) | | \\ \\ / __ \\ | " << std::endl;
std::cout << " | | \\ \\ / ___ \\ ___ \\ ( | ( | \\ \\ / ( | | | ( | | | | __/ __/ \\ | \\ \\ / | | __| " << std::endl;
std::cout << " _| _| \\_/ _/ _\\ _/ _\\ \\__,_| \\__,_| \\_/ \\__,_| _| _| \\__,_| _.__/ _| \\___| _____| \\___/ \\_/ ____/ _| " << std::endl;
std::cout << " " << std::endl;
std::cout << " " << std::endl;
std::cout << " " << std::endl;
std::cout << " " << std::endl;
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString){
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
//==== list of methods
std::string MVADirectory = gConfigParser -> readStringOption ("Options::MVADirectory");
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
std::vector<std::string> vectorMyMethodMassList = gConfigParser -> readStringListOption("Options::MVAmethodsMass");
std::string outputDirectory = gConfigParser -> readStringOption("Output::outputDirectory");
//---- variables
//-- by YY --
float pt1;
float pt2;
float dphill;
float drll;
float mll;
float channel;
float mth;
float mjj;
float detajj;
float jeteta1;
//~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
TFile* outputRootFile[500];
TTree* cloneTreeJetLepVect[500];
TTree *treeJetLepVect[500];
TFile* file[500];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++){
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
file[iSample] = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) file[iSample]->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
treeJetLepVect[iSample] -> SetBranchAddress("pt1", &pt1);
treeJetLepVect[iSample] -> SetBranchAddress("pt2", &pt2);
treeJetLepVect[iSample] -> SetBranchAddress("dphill", &dphill);
treeJetLepVect[iSample] -> SetBranchAddress("drll", &drll);
treeJetLepVect[iSample] -> SetBranchAddress("mll", &mll);
treeJetLepVect[iSample] -> SetBranchAddress("channel", &channel);
treeJetLepVect[iSample] -> SetBranchAddress("mth", &mth);
treeJetLepVect[iSample] -> SetBranchAddress("mjj", &mjj);
treeJetLepVect[iSample] -> SetBranchAddress("detajj", &detajj);
treeJetLepVect[iSample] -> SetBranchAddress("jeteta1", &jeteta1);
sprintf(nameFile,"%s/%s%s.root",outputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
outputRootFile[iSample] = new TFile ( nameFile, "RECREATE") ;
outputRootFile[iSample] -> cd () ;
cloneTreeJetLepVect[iSample] = treeJetLepVect[iSample] -> CloneTree (0) ;
}
for (int iSample=0; iSample<numberOfSamples; iSample++){
file[iSample] -> cd();
///==== loop ====
Long64_t nentries = treeJetLepVect[iSample]->GetEntries();
for (Long64_t iEntry = 0; iEntry < nentries; iEntry++){
treeJetLepVect[iSample]->GetEntry(iEntry);
cloneTreeJetLepVect[iSample] -> Fill () ;
}
}
/**
* cycle on MVA (method-mass)
* * cycle on samples
* * * cycle on events
*/
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
std::cout << " vectorMyMethodList[" << iMVA << "] = " << vectorMyMethodList.at(iMVA) << std::endl;
TString myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
for (int iMVAMass = 0; iMVAMass < vectorMyMethodMassList.size(); iMVAMass++) {
std::cout << " vectorMyMethodMassList[" << iMVAMass << "] = " << vectorMyMethodMassList.at(iMVAMass) << std::endl;
TMVA::Reader *TMVAreader = new TMVA::Reader( "!Color:!Silent" );
Float_t input_variables[1000];
TMVAreader->AddVariable("lep1pt", &input_variables[0]);
TMVAreader->AddVariable("lep2pt", &input_variables[1]);
TMVAreader->AddVariable("dPhi", &input_variables[2]);
TMVAreader->AddVariable("dR", &input_variables[3]);
TMVAreader->AddVariable("dilmass", &input_variables[4]);
TMVAreader->AddVariable("type", &input_variables[5]);
TMVAreader->AddVariable("mt", &input_variables[6]);
TMVAreader->AddVariable("mjj", &input_variables[7]);
TMVAreader->AddVariable("detajj", &input_variables[8]);
TMVAreader->AddVariable("jet1eta", &input_variables[9]);
TString myMethodMassList = Form ("%s",vectorMyMethodMassList.at(iMVAMass).c_str());
TString weightfile = Form ("%s/weights_%s_testVariables/TMVAClassification_%s.weights.xml",MVADirectory.c_str(),myMethodMassList.Data(),myMethodList.Data());
std::cout << " myMethodList = " << myMethodList.Data() << std::endl;
std::cout << " weightfile = " << weightfile.Data() << std::endl;
TMVAreader->BookMVA( myMethodList, weightfile );
for (int iSample=0; iSample<numberOfSamples; iSample++){
std::cout << " iSample = " << iSample << " :: " << numberOfSamples << std::endl;
file[iSample] -> cd();
Double_t MVA_Value;
TBranch *newBranch;
TString methodName4Tree = Form ("%s_%s_MVAHiggs",myMethodList.Data(),myMethodMassList.Data());
TString methodName4Tree2 = Form ("%s_%s_MVAHiggs_2JVBF/D",myMethodList.Data(),myMethodMassList.Data());
newBranch = cloneTreeJetLepVect[iSample]->Branch(methodName4Tree,&MVA_Value,methodName4Tree2);
///==== loop ====
Long64_t nentries = treeJetLepVect[iSample]->GetEntries();
for (Long64_t iEntry = 0; iEntry < nentries; iEntry++){
if((iEntry%1000) == 0) std::cout << ">>>>> analysis::GetEntry " << iEntry << " : " << nentries << std::endl;
treeJetLepVect[iSample]->GetEntry(iEntry);
input_variables[0] = static_cast<Float_t>(pt1);
input_variables[1] = static_cast<Float_t>(pt2);
input_variables[2] = static_cast<Float_t>(dphill);
input_variables[3] = static_cast<Float_t>(drll);
input_variables[4] = static_cast<Float_t>(mll);
float smurfChannel = -1;
if ( channel == 0 ) smurfChannel = 0 ;
if ( channel == 1 ) smurfChannel = 3 ;
if ( channel == 2 ) smurfChannel = 2 ;
if ( channel == 3 ) smurfChannel = 1 ;
input_variables[5] = static_cast<Float_t>(smurfChannel);
input_variables[6] = static_cast<Float_t>(mth);
input_variables[7] = static_cast<Float_t>(mjj);
input_variables[8] = static_cast<Float_t>(detajj);
input_variables[9] = static_cast<Float_t>(jeteta1);
MVA_Value = TMVAreader->EvaluateMVA(myMethodList);
newBranch -> Fill();
}
}
}
}
for (int iSample=0; iSample<numberOfSamples; iSample++){
outputRootFile[iSample]->cd();
// save only the new version of the tree
// treeJetLepVect[iSample]->Write("", TObject::kOverwrite);
cloneTreeJetLepVect[iSample] -> SetName (treeName.c_str());
// cloneTreeJetLepVect[iSample] -> AutoSave () ;
cloneTreeJetLepVect[iSample]->Write(treeName.c_str(),TObject::kOverwrite);
outputRootFile[iSample] -> Close () ;
}
}
void tmva_reader(const int type = 1){
// type = 1 -> Signal
// type = 2 -> Continuum
// type = 0 -> Data
/////////////////
// TMVA Reader //
/////////////////
rooksfw* ksfw = new rooksfw("ksfw0", ksfw0_alpha, ksfw0_sigpdf, ksfw0_bkgpdf);
TMVA::Reader* reader = new TMVA::Reader("!Color:!Silent:V");
// TMVA::Reader* reader1 = new TMVA::Reader("!Color:!Silent:V");
string fname;
if(type == 1) fname = string("/home/vitaly/B0toDh0/Tuples/fil_b2dh_sigmc.root");
else if(type == 2 ) fname = string("/home/vitaly/B0toDh0/Tuples/fil_b2dh_cont.root");
else if(type == 0) fname = string("/home/vitaly/B0toDh0/Tuples/fil_b2dh_data.root");
else{
cout << "Wrong type " << type << endl;
return;
}
stinrg treename;
if(type) treename = string("TEventEx");
else treename = string("TEvent");
TFile *ifile = TFile::Open(fname.c_str());
TTree *tree = (TTree*)ifile->Get(treename.c_str());
if(type == 1) fname = string("fil_b2dh_sig.root");
else if(type == 2) fname = string("fil_b2dh_cont.root");
else if(type == 0) fname = string("fil_b2dh_data.root");
TFile ofile(fname.c_str(),"RECREATE");
TTree *TEvent = new TTree("TEvent","TEvent");
double k0vars[17];
Double_t cos_b0,p_ks,p_pp,p_pm,p_pi0,chi2_ndf_D0,chi2_ndf_B0,chi2_tag_vtx,cos_thr,thr_sig,thr_oth;
Double_t k0mm2,k0et,k0hso00,k0hso02,k0hso04,k0hso10,k0hso12,k0hso14,k0hso20,k0hso22,k0hso24,k0hoo0,k0hoo1,k0hoo2,k0hoo3,k0hoo4;
Double_t k1mm2,k1et,k1hso00,k1hso02,k1hso04,k1hso10,k1hso12,k1hso14,k1hso20,k1hso22,k1hso24,k1hoo0,k1hoo1,k1hoo2,k1hoo3,k1hoo4;
Double_t pi0_chi2,egamma,ptgamma;
Int_t ndf_tag_vtx;
Double_t mbc,de,mp,mm,dz,dt,atckpi_max,mpi0,mk,md;
Double_t bdt,bdtg,bdts,bdtgs,lh,bdtlh,bdtglh,bdtlhs,bdtglhs;
Double_t ks_dr,ks_dz,ks_dphi,ks_fl,tag_LH,tag_LH_err,dzerr;
Int_t phsp,bin,exp,run,evtn;
Float_t m_cos_b0,m_p_ks,m_p_pp,m_p_pm,m_p_pi0,m_chi2_ndf_D0,m_chi2_ndf_B0,m_chi2_ndf_tag_vtx,m_cos_thr,m_thr_sig,m_thr_oth;
Float_t m_ks_dr,m_ks_dz,m_ks_dphi,m_ks_fl,m_tag_LH_err,m_dzerr;
Float_t m_pi0_chi2,m_egamma,m_ptgamma,m_lh;
Float_t m_k1mm2,m_k1et,m_k1hso00,m_k1hso02,m_k1hso04,m_k1hso10,m_k1hso12,m_k1hso14,m_k1hso20,m_k1hso22,m_k1hso24,m_k1hoo0,m_k1hoo1,m_k1hoo2,m_k1hoo3,m_k1hoo4;
Double_t mp_mc,mm_mc;
Double_t t_mc,d0_t_mc;
Double_t dt_mc,dz_mc;
Int_t bin_mc;
Int_t flv_mc,d0_flv_mc;
Int_t mcflag,d0_mcflag;
Int_t b0f,d0f;
tree->SetBranchAddress("mp_mc",&mp_mc);
tree->SetBranchAddress("mm_mc",&mm_mc);
tree->SetBranchAddress("t_mc",&t_mc);
tree->SetBranchAddress("d0_t_mc",&d0_t_mc);
tree->SetBranchAddress("dt_mc",&dt_mc);
tree->SetBranchAddress("dz_mc",&dz_mc);
tree->SetBranchAddress("bin_mc",&bin_mc);
tree->SetBranchAddress("flv_mc",&flv_mc);
tree->SetBranchAddress("d0_flv_mc",&d0_flv_mc);
// tree->SetBranchAddress("mcflag",&mcflag);
// tree->SetBranchAddress("d0_mcflag",&d0_mcflag);
tree->SetBranchAddress("b0f",&b0f);
tree->SetBranchAddress("d0f",&d0f);
tree->SetBranchAddress("exp",&exp);
tree->SetBranchAddress("run",&run);
tree->SetBranchAddress("evtn",&evtn);
tree->SetBranchAddress("mbc",&mbc);
tree->SetBranchAddress("de",&de);
tree->SetBranchAddress("mp",&mp);
tree->SetBranchAddress("mm",&mm);
tree->SetBranchAddress("bin",&bin);
tree->SetBranchAddress("dz",&dz);
tree->SetBranchAddress("dt",&dt);
tree->SetBranchAddress("atckpi_max",&atckpi_max);
tree->SetBranchAddress("phsp",&phsp);
tree->SetBranchAddress("mpi0_raw",&mpi0);
tree->SetBranchAddress("mks_raw",&mk);
tree->SetBranchAddress("md0_raw",&md);
tree->SetBranchAddress("cos_b0",&cos_b0);
tree->SetBranchAddress("p_ks",&p_ks);
// tree->SetBranchAddress("p_pp",&p_pp);
// tree->SetBranchAddress("p_pm",&p_pm);
// tree->SetBranchAddress("p_pi0",&p_pi0);
tree->SetBranchAddress("chi2_ndf_D0",&chi2_ndf_D0);
tree->SetBranchAddress("chi2_ndf_B0",&chi2_ndf_B0);
tree->SetBranchAddress("chi2_tag_vtx",&chi2_tag_vtx);
tree->SetBranchAddress("ndf_tag_vtx",&ndf_tag_vtx);
tree->SetBranchAddress("cos_thr",&cos_thr);
tree->SetBranchAddress("thr_sig",&thr_sig);
tree->SetBranchAddress("thr_oth",&thr_oth);
tree->SetBranchAddress("tag_LH",&tag_LH);
tree->SetBranchAddress("tag_LH_err",&tag_LH_err);
tree->SetBranchAddress("dzerr",&dzerr);
tree->SetBranchAddress("pi0_chi2",&pi0_chi2);
tree->SetBranchAddress("egamma",&egamma);
// tree->SetBranchAddress("ptgamma",&ptgamma);
// tree->SetBranchAddress("lh",&m_lh);
tree->SetBranchAddress("ks_dr",&ks_dr);
tree->SetBranchAddress("ks_dz",&ks_dz);
tree->SetBranchAddress("ks_dphi",&ks_dphi);
tree->SetBranchAddress("ks_fl",&ks_fl);
tree->SetBranchAddress("k0mm2",&k0mm2);
tree->SetBranchAddress("k0et",&k0et);
tree->SetBranchAddress("k0hso00",&k0hso00);
tree->SetBranchAddress("k0hso02",&k0hso02);
tree->SetBranchAddress("k0hso04",&k0hso04);
tree->SetBranchAddress("k0hso10",&k0hso10);
tree->SetBranchAddress("k0hso12",&k0hso12);
tree->SetBranchAddress("k0hso14",&k0hso14);
tree->SetBranchAddress("k0hso20",&k0hso20);
tree->SetBranchAddress("k0hso22",&k0hso22);
tree->SetBranchAddress("k0hso24",&k0hso24);
tree->SetBranchAddress("k0hoo0",&k0hoo0);
tree->SetBranchAddress("k0hoo1",&k0hoo1);
tree->SetBranchAddress("k0hoo2",&k0hoo2);
tree->SetBranchAddress("k0hoo3",&k0hoo3);
tree->SetBranchAddress("k0hoo4",&k0hoo4);
tree->SetBranchAddress("k1mm2",&k1mm2);
tree->SetBranchAddress("k1et",&k1et);
tree->SetBranchAddress("k1hso00",&k1hso00);
tree->SetBranchAddress("k1hso02",&k1hso02);
tree->SetBranchAddress("k1hso04",&k1hso04);
tree->SetBranchAddress("k1hso10",&k1hso10);
tree->SetBranchAddress("k1hso12",&k1hso12);
tree->SetBranchAddress("k1hso14",&k1hso14);
tree->SetBranchAddress("k1hso20",&k1hso20);
tree->SetBranchAddress("k1hso22",&k1hso22);
tree->SetBranchAddress("k1hso24",&k1hso24);
tree->SetBranchAddress("k1hoo0",&k1hoo0);
tree->SetBranchAddress("k1hoo1",&k1hoo1);
tree->SetBranchAddress("k1hoo2",&k1hoo2);
tree->SetBranchAddress("k1hoo3",&k1hoo3);
tree->SetBranchAddress("k1hoo4",&k1hoo4);
TEvent->Branch("mp_mc",&mp_mc,"mp_mc/D");
TEvent->Branch("mm_mc",&mm_mc,"mm_mc/D");
TEvent->Branch("t_mc",&t_mc,"t_mc/D");
TEvent->Branch("d0_t_mc",&d0_t_mc,"d0_t_mc/D");
TEvent->Branch("dt_mc",&dt_mc,"dt_mc/D");
TEvent->Branch("dz_mc",&dz_mc,"dz_mc/D");
TEvent->Branch("bin_mc",&bin_mc,"bin_mc/I");
TEvent->Branch("flv_mc",&flv_mc,"flv_mc/I");
TEvent->Branch("d0_flv_mc",&d0_flv_mc,"d0_flv_mc/I");
TEvent->Branch("mcflag",&mcflag,"mcflag/I");
TEvent->Branch("d0_mcflag",&d0_mcflag,"d0_mcflag/I");
TEvent->Branch("exp",&exp,"exp/I");
TEvent->Branch("run",&run,"run/I");
TEvent->Branch("evtn",&evtn,"evtn/I");
TEvent->Branch("b0f",&b0f,"b0f/I");
TEvent->Branch("d0f",&d0f,"d0f/I");
TEvent->Branch("mbc",&mbc,"mbc/D");
TEvent->Branch("de",&de,"de/D");
TEvent->Branch("bdt",&bdt,"bdt/D");
TEvent->Branch("bdtg",&bdtg,"bdtg/D");
TEvent->Branch("bdts",&bdts,"bdts/D");
TEvent->Branch("bdtgs",&bdtgs,"bdtgs/D");
TEvent->Branch("bdtlh",&bdtlh,"bdtlh/D");
TEvent->Branch("bdtglh",&bdtglh,"bdtglh/D");
TEvent->Branch("bdtlhs",&bdtlhs,"bdtlhs/D");
TEvent->Branch("bdtglhs",&bdtglhs,"bdtglhs/D");
TEvent->Branch("lh",&lh,"lh/D");
TEvent->Branch("mp",&mp,"mp/D");
TEvent->Branch("mm",&mm,"mm/D");
TEvent->Branch("bin",&bin,"bin/I");
TEvent->Branch("dz",&dz,"dz/D");
TEvent->Branch("dt",&dt,"dt/D");
TEvent->Branch("tag_LH",&tag_LH,"tag_LH/D");
TEvent->Branch("tag_LH_err",&tag_LH_err,"tag_LH_err/D");
TEvent->Branch("atckpi_max",&atckpi_max,"atckpi_max/D");
TEvent->Branch("mpi0",&mpi0,"mpi0/D");
TEvent->Branch("mk",&mk,"mk/D");
TEvent->Branch("md",&md,"md/D");
reader->AddVariable("abs(cos_b0)",&m_cos_b0);
// reader->AddVariable("p_ks",&m_p_ks);
reader->AddVariable("log(chi2_ndf_D0)",&m_chi2_ndf_D0);
// reader->AddVariable("log(chi2_ndf_B0)",&m_chi2_ndf_B0);
// reader->AddVariable("log(chi2_tag_vtx/ndf_tag_vtx)",&m_chi2_ndf_tag_vtx);
reader->AddVariable("abs(cos_thr)",&m_cos_thr);
reader->AddVariable("abs(thr_sig-0.885)",&m_thr_sig);
reader->AddVariable("thr_oth",&m_thr_oth);
reader->AddVariable("log(tag_LH_err)",&m_tag_LH_err);
reader->AddVariable("log(dzerr)",&m_dzerr);
reader->AddVariable("log(pi0_chi2)",&m_pi0_chi2);
reader->AddVariable("log(egamma)",&m_egamma);
reader->AddVariable("k1mm2",&m_k1mm2);
reader->AddVariable("k1et",&m_k1et);
reader->AddVariable("k1hso00",&m_k1hso00);
reader->AddVariable("k1hso02",&m_k1hso02);
reader->AddVariable("k1hso04",&m_k1hso04);
reader->AddVariable("k1hso10",&m_k1hso10);
reader->AddVariable("k1hso12",&m_k1hso12);
reader->AddVariable("k1hso14",&m_k1hso14);
reader->AddVariable("k1hso20",&m_k1hso20);
reader->AddVariable("k1hso22",&m_k1hso22);
reader->AddVariable("k1hso24",&m_k1hso24);
reader->AddVariable("k1hoo0",&m_k1hoo0);
reader->AddVariable("k1hoo1",&m_k1hoo1);
reader->AddVariable("k1hoo2",&m_k1hoo2);
reader->AddVariable("k1hoo3",&m_k1hoo3);
reader->AddVariable("k1hoo4",&m_k1hoo4);
reader->BookMVA("BDT","weights/MVAnalysis_BDT.weights.xml");
reader->BookMVA("BDTG","weights/MVAnalysis_BDTG.weights.xml");
reader->BookMVA("BDTs","weights/MVAnalysis_sig_BDT.weights.xml");
reader->BookMVA("BDTGs","weights/MVAnalysis_sig_BDTG.weights.xml");
reader1->AddVariable("abs(cos_b0)",&m_cos_b0);
reader1->AddVariable("p_ks",&m_p_ks);
reader1->AddVariable("log(chi2_ndf_D0)",&m_chi2_ndf_D0);
reader1->AddVariable("log(chi2_ndf_B0)",&m_chi2_ndf_B0);
reader1->AddVariable("log(chi2_tag_vtx/ndf_tag_vtx)",&m_chi2_ndf_tag_vtx);
reader1->AddVariable("abs(cos_thr)",&m_cos_thr);
reader1->AddVariable("abs(thr_sig-0.885)",&m_thr_sig);
reader1->AddVariable("thr_oth",&m_thr_oth);
reader1->AddVariable("log(tag_LH_err)",&m_tag_LH_err);
reader1->AddVariable("log(dzerr)",&m_dzerr);
reader1->AddVariable("log(pi0_chi2)",&m_pi0_chi2);
reader1->AddVariable("log(egamma)",&m_egamma);
reader1->AddVariable("lh",&m_lh);
reader1->BookMVA("BDTlh","weights/MVAnalysis_lh_BDT.weights.xml");
reader1->BookMVA("BDTGlh","weights/MVAnalysis_lh_BDTG.weights.xml");
reader1->BookMVA("BDTlhs","weights/MVAnalysis_lh_sig_BDT.weights.xml");
reader1->BookMVA("BDTGlhs","weights/MVAnalysis_lh_sig_BDTG.weights.xml");
const int NTot = tree->GetEntries();
for(int i=0; i<NTot; i++){
if(!(i%10000)) cout << i << " events" << endl;
tree->GetEvent(i);
// if(!phsp) continue;
// if(chi2_ndf_B0>1000) continue;
m_cos_b0 = (float)TMath::Abs(cos_b0);
m_p_ks = (float)p_ks;
m_p_pp = (float)p_pp;
m_p_pm = (float)p_pm;
m_p_pi0 = (float)p_pi0;
m_chi2_ndf_D0 = (float)TMath::Log(chi2_ndf_D0);
m_chi2_ndf_B0 = (float)TMath::Log(chi2_ndf_B0);
m_chi2_ndf_tag_vtx = (float)TMath::Log(chi2_tag_vtx/ndf_tag_vtx);
m_cos_thr = (float)TMath::Abs(cos_thr);
m_thr_sig = (float)TMath::Abs(thr_sig-0.885);
m_thr_oth = (float)thr_oth;
m_dzerr = (float)TMath::Log(dzerr);
m_ks_dr = (float)ks_dr;
m_ks_dz = (float)ks_dz;
m_ks_dphi = (float)ks_dphi;
m_ks_fl = (float)ks_fl;
m_pi0_chi2 = (float)TMath::Log(pi0_chi2);
m_egamma = (float)TMath::Log(egamma);
m_ptgamma = (float)ptgamma;
m_k1mm2 = (float)k1mm2;
m_k1et = (float)k1et;
m_k1hso00 = (float)k1hso00;
m_k1hso02 = (float)k1hso02;
m_k1hso04 = (float)k1hso04;
m_k1hso10 = (float)k1hso10;
m_k1hso12 = (float)k1hso12;
m_k1hso14 = (float)k1hso14;
m_k1hso20 = (float)k1hso20;
m_k1hso22 = (float)k1hso22;
m_k1hso24 = (float)k1hso24;
m_k1hoo0 = (float)k1hoo0;
m_k1hoo1 = (float)k1hoo1;
m_k1hoo2 = (float)k1hoo2;
m_k1hoo3 = (float)k1hoo3;
m_k1hoo4 = (float)k1hoo4;
m_lh = 0;//(float)lh;
k0vars[0] = k0et;
k0vars[1] = k0hso00;
k0vars[2] = k0hso10;
k0vars[3] = k0hso20;
k0vars[4] = 0;//k0hso01;
k0vars[5] = k0hso02;
k0vars[6] = k0hso12;
k0vars[7] = k0hso22;
k0vars[8] = 0;//k0hso03;
k0vars[9] = k0hso04;
k0vars[10] = k0hso14;
k0vars[11] = k0hso24;
k0vars[12] = k0hoo0;
k0vars[13] = k0hoo1;
k0vars[14] = k0hoo2;
k0vars[15] = k0hoo3;
k0vars[16] = k0hoo4;
ksfw->input(k0mm2, k0vars);
if(ksfw->ls() + ksfw->lb() > 0){
lh = ksfw->ls()/(ksfw->ls()+ksfw->lb());
} else{
lh = -1;
}
bdt = reader->EvaluateMVA("BDT");
bdtg = reader->EvaluateMVA("BDTG");
bdts = reader->EvaluateMVA("BDTs");
bdtgs = reader->EvaluateMVA("BDTGs");
bdtlh = reader1->EvaluateMVA("BDTlh");
bdtglh = reader1->EvaluateMVA("BDTGlh");
bdtlhs = reader1->EvaluateMVA("BDTlhs");
bdtglhs = reader1->EvaluateMVA("BDTGlhs");
TEvent->Fill();
}
TEvent->Write();
ofile.Write();
ofile.Close();
}
void TMVAClassificationApplication_cc1pcoh_bdt_ver3noveractFFFSI( TString myMethodList = "", TString fname)
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t mumucl, pmucl;
Float_t pang_t, muang_t;
Float_t veract;
Float_t ppe, mupe;
Float_t range, coplanarity;
Float_t opening;//newadd
reader->AddVariable( "mumucl", &mumucl );
reader->AddVariable( "pmucl", &pmucl );
reader->AddVariable( "pang_t", &pang_t );
reader->AddVariable( "muang_t", &muang_t );
//reader->AddVariable( "veract", &veract );
reader->AddVariable( "ppe", &ppe);
reader->AddVariable( "mupe", &mupe);
reader->AddVariable( "range", &range);
reader->AddVariable( "coplanarity", &coplanarity);
reader->AddVariable( "opening", &opening);//newadd
// Spectator variables declared in the training have to be added to the reader, too
Int_t fileIndex, inttype;
Float_t nuE, norm, totcrsne;
reader->AddSpectator( "fileIndex", &fileIndex );
reader->AddSpectator( "nuE", &nuE );
reader->AddSpectator( "inttype", &inttype );
reader->AddSpectator( "norm", &norm );
reader->AddSpectator( "totcrsne", &totcrsne );
reader->AddSpectator( "veract", &veract );
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVAClassification_ver3noveractFFFSI";//newchange
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
//for prange/pang_t corrected and other information included
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/datamc_merged_ccqe_addpidFFnew.root";
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/datamc_genie_merged_ccqe_addpidFFnew.root";
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/mc_merged_ccqe_addpidFFnew.root";
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/mcgenie_merged_ccqe_tot_addpidFFnew.root";
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/merged_ccqe_forResponseFunction.root";
//TString fname = "/home/cvson/scraid2/cc1picoh/FIT/datafsi/pmnue_merged_ccqe_tot_addpidFFnew.root";
std::cout << "--- Selecting data sample" << std::endl;
TFile *pfile = new TFile(fname,"update");
TTree* theTree = (TTree*)pfile->Get("tree");
theTree->SetBranchAddress( "mumucl", &mumucl );
theTree->SetBranchAddress( "pmucl", &pmucl );
theTree->SetBranchAddress( "pang_t", &pang_t );
theTree->SetBranchAddress( "muang_t", &muang_t );
theTree->SetBranchAddress( "veract", &veract );
theTree->SetBranchAddress( "ppe", &ppe);
theTree->SetBranchAddress( "mupe", &mupe);
theTree->SetBranchAddress( "range", &range);
theTree->SetBranchAddress( "coplanarity", &coplanarity);
theTree->SetBranchAddress( "opening", &opening);
Int_t Ntrack;
theTree->SetBranchAddress( "Ntrack", &Ntrack );
Float_t pidfsi;
TBranch *bpidfsi = theTree->Branch("pidfsi",&pidfsi,"pidfsi/F");
std::vector<Float_t> vecVar(9); // vector for EvaluateMVA tests
Long64_t nentries = theTree->GetEntriesFast();
Long64_t iprintProcess = Long64_t(nentries/100.);
std::cout << "--- Processing: " << nentries << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<nentries;ievt++) {
if (ievt%iprintProcess == 0) cout<<"Processing "<<int(ievt*100./nentries)<<"% of events"<<endl;
theTree->GetEntry(ievt);
Float_t pidfsi_tem;
if (Use["BDT"]) {
//if (Ntrack!=2) pidfsi_tem = -999;//changehere
if (Ntrack<2) pidfsi_tem = -999;
else pidfsi_tem = reader->EvaluateMVA("BDT method");
}
pidfsi = pidfsi_tem;
bpidfsi->Fill();
}
theTree->Write();
delete pfile;
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVAClassificationApplication( TString weightFile = "TMVAClassificationPtOrd_qqH115vsWZttQCD_Cuts.weights.xml",
Double_t effS_ = 0.5 )
{
TMVA::Tools::Instance();
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
Float_t pt1, pt2;
Float_t Deta, Mjj;
Float_t eta1,eta2;
reader->AddVariable( "pt1", &pt1);
reader->AddVariable( "pt2", &pt2);
reader->AddVariable( "Deta",&Deta);
reader->AddVariable( "Mjj", &Mjj);
reader->AddSpectator("eta1",&eta1);
reader->AddSpectator("eta2",&eta2);
reader->BookMVA( "Cuts", TString("weights/")+weightFile );
// mu+tau iso, OS, Mt<40
TString fSignalName = "/data_CMS/cms/lbianchini/VbfJetsStudy/looseSelection/nTupleVBFH115-PU-L.root";
//TString fSignalName = "/data_CMS/cms/lbianchini/VbfJetsStudy/nTupleVbf.root";
// mu+tau iso, OS, Mt<40
//TString fBackgroundNameDYJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/looseSelection/nTupleDYJets-madgraph-50-PU-L.root";
TString fBackgroundNameDYJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/nTupleZJets.root";
// Mt<40
TString fBackgroundNameWJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/looseSelection/nTupleWJets-madgraph-PU-L.root";
// Mt<40
TString fBackgroundNameQCD = "/data_CMS/cms/lbianchini/VbfJetsStudy/looseSelection/nTupleQCD-pythia-PU-L.root";
// Mt<40
TString fBackgroundNameTTbar = "/data_CMS/cms/lbianchini/VbfJetsStudy/looseSelection/nTupleTT-madgraph-PU-L.root";
TFile *fSignal(0);
TFile *fBackgroundDYJets(0);
TFile *fBackgroundWJets(0);
TFile *fBackgroundQCD(0);
TFile *fBackgroundTTbar(0);
fSignal = TFile::Open( fSignalName );
fBackgroundDYJets = TFile::Open( fBackgroundNameDYJets );
fBackgroundWJets = TFile::Open( fBackgroundNameWJets );
fBackgroundQCD = TFile::Open( fBackgroundNameQCD );
fBackgroundTTbar = TFile::Open( fBackgroundNameTTbar );
if(!fSignal || !fBackgroundDYJets || !fBackgroundWJets || !fBackgroundQCD || !fBackgroundTTbar) {
std::cout << "ERROR: could not open files" << std::endl;
exit(1);
}
TString tree = "outTreePtOrd";
TTree *signal = (TTree*)fSignal->Get(tree);
TTree *backgroundDYJets = (TTree*)fBackgroundDYJets->Get(tree);
TTree *backgroundWJets = (TTree*)fBackgroundWJets->Get(tree);
TTree *backgroundQCD = (TTree*)fBackgroundQCD->Get(tree);
TTree *backgroundTTbar = (TTree*)fBackgroundTTbar->Get(tree);
TCut mycuts = "pt1>0 && abs(eta1*eta2)/eta1/eta2<0";
TCut mycutb = "pt1>0 && abs(eta1*eta2)/eta1/eta2<0";
std::map<std::string,TTree*> tMap;
tMap["qqH115"]=signal;
tMap["Zjets"]=backgroundDYJets;
tMap["Wjets"]=backgroundWJets;
tMap["QCD"]=backgroundQCD;
tMap["TTbar"]=backgroundTTbar;
Double_t pt1_, pt2_;
Double_t Deta_, Mjj_;
for(std::map<std::string,TTree*>::iterator it = tMap.begin(); it != tMap.end(); it++) {
TFile* dummy = new TFile("dummy.root","RECREATE");
TTree* currentTree = (TTree*)(it->second)->CopyTree(mycuts);
Int_t counter = 0;
currentTree->SetBranchAddress( "pt1", &pt1_ );
currentTree->SetBranchAddress( "pt2", &pt2_ );
currentTree->SetBranchAddress( "Deta",&Deta_ );
currentTree->SetBranchAddress( "Mjj", &Mjj_ );
for (Long64_t ievt=0; ievt<currentTree->GetEntries(); ievt++) {
currentTree->GetEntry(ievt);
pt1 = pt1_;
pt2 = pt2_;
Deta = Deta_;
Mjj = Mjj_;
if (ievt%1000000 == 0) {
std::cout << "--- ... Processing event: " << ievt << std::endl;
//cout << pt1 << ", " << pt2 << ", " << Deta << ", " << Mjj << endl;
}
if(reader->EvaluateMVA( "Cuts", effS_ )) counter++;
}
cout<< "Sample " << it->first << " has a rejection factor " << (Float_t)counter/(Float_t)currentTree->GetEntries() << "+/-" <<
TMath::Sqrt((Float_t)counter/currentTree->GetEntries()*(1-counter/currentTree->GetEntries())/currentTree->GetEntries())
<< " for effS="<< effS_ << endl;
}
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVAClassificationApplication( TString myMethodList = "" )
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 0; // Recommended ANN
Use["BDT"] = 1; // uses Adaptive Boost
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t var1, var2;
Float_t var3, var4;
reader->AddVariable( "myvar1 := var1+var2", &var1 );
reader->AddVariable( "myvar2 := var1-var2", &var2 );
reader->AddVariable( "var3", &var3 );
reader->AddVariable( "var4", &var4 );
// Spectator variables declared in the training have to be added to the reader, too
Float_t spec1,spec2;
reader->AddSpectator( "spec1 := var1*2", &spec1 );
reader->AddSpectator( "spec2 := var1*3", &spec2 );
Float_t Category_cat1, Category_cat2, Category_cat3;
if (Use["Category"]){
// Add artificial spectators for distinguishing categories
reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
}
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVAClassification";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Book output histograms
UInt_t nbin = 100;
TH1F *histLk(0), *histLkD(0), *histLkPCA(0), *histLkKDE(0), *histLkMIX(0), *histPD(0), *histPDD(0);
TH1F *histPDPCA(0), *histPDEFoam(0), *histPDEFoamErr(0), *histPDEFoamSig(0), *histKNN(0), *histHm(0);
TH1F *histFi(0), *histFiG(0), *histFiB(0), *histLD(0), *histNn(0),*histNnbfgs(0),*histNnbnn(0);
TH1F *histNnC(0), *histNnT(0), *histBdt(0), *histBdtG(0), *histBdtD(0), *histRf(0), *histSVMG(0);
TH1F *histSVMP(0), *histSVML(0), *histFDAMT(0), *histFDAGA(0), *histCat(0), *histPBdt(0);
if (Use["Likelihood"]) histLk = new TH1F( "MVA_Likelihood", "MVA_Likelihood", nbin, -1, 1 );
if (Use["LikelihoodD"]) histLkD = new TH1F( "MVA_LikelihoodD", "MVA_LikelihoodD", nbin, -1, 0.9999 );
if (Use["LikelihoodPCA"]) histLkPCA = new TH1F( "MVA_LikelihoodPCA", "MVA_LikelihoodPCA", nbin, -1, 1 );
if (Use["LikelihoodKDE"]) histLkKDE = new TH1F( "MVA_LikelihoodKDE", "MVA_LikelihoodKDE", nbin, -0.00001, 0.99999 );
if (Use["LikelihoodMIX"]) histLkMIX = new TH1F( "MVA_LikelihoodMIX", "MVA_LikelihoodMIX", nbin, 0, 1 );
if (Use["PDERS"]) histPD = new TH1F( "MVA_PDERS", "MVA_PDERS", nbin, 0, 1 );
if (Use["PDERSD"]) histPDD = new TH1F( "MVA_PDERSD", "MVA_PDERSD", nbin, 0, 1 );
if (Use["PDERSPCA"]) histPDPCA = new TH1F( "MVA_PDERSPCA", "MVA_PDERSPCA", nbin, 0, 1 );
if (Use["KNN"]) histKNN = new TH1F( "MVA_KNN", "MVA_KNN", nbin, 0, 1 );
if (Use["HMatrix"]) histHm = new TH1F( "MVA_HMatrix", "MVA_HMatrix", nbin, -0.95, 1.55 );
if (Use["Fisher"]) histFi = new TH1F( "MVA_Fisher", "MVA_Fisher", nbin, -4, 4 );
if (Use["FisherG"]) histFiG = new TH1F( "MVA_FisherG", "MVA_FisherG", nbin, -1, 1 );
if (Use["BoostedFisher"]) histFiB = new TH1F( "MVA_BoostedFisher", "MVA_BoostedFisher", nbin, -2, 2 );
if (Use["LD"]) histLD = new TH1F( "MVA_LD", "MVA_LD", nbin, -2, 2 );
if (Use["MLP"]) histNn = new TH1F( "MVA_MLP", "MVA_MLP", nbin, -1.25, 1.5 );
if (Use["MLPBFGS"]) histNnbfgs = new TH1F( "MVA_MLPBFGS", "MVA_MLPBFGS", nbin, -1.25, 1.5 );
if (Use["MLPBNN"]) histNnbnn = new TH1F( "MVA_MLPBNN", "MVA_MLPBNN", nbin, -1.25, 1.5 );
if (Use["CFMlpANN"]) histNnC = new TH1F( "MVA_CFMlpANN", "MVA_CFMlpANN", nbin, 0, 1 );
if (Use["TMlpANN"]) histNnT = new TH1F( "MVA_TMlpANN", "MVA_TMlpANN", nbin, -1.3, 1.3 );
if (Use["BDT"]) histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -0.8, 0.8 );
if (Use["BDTD"]) histBdtD = new TH1F( "MVA_BDTD", "MVA_BDTD", nbin, -0.8, 0.8 );
if (Use["BDTG"]) histBdtG = new TH1F( "MVA_BDTG", "MVA_BDTG", nbin, -1.0, 1.0 );
if (Use["RuleFit"]) histRf = new TH1F( "MVA_RuleFit", "MVA_RuleFit", nbin, -2.0, 2.0 );
if (Use["SVM_Gauss"]) histSVMG = new TH1F( "MVA_SVM_Gauss", "MVA_SVM_Gauss", nbin, 0.0, 1.0 );
if (Use["SVM_Poly"]) histSVMP = new TH1F( "MVA_SVM_Poly", "MVA_SVM_Poly", nbin, 0.0, 1.0 );
if (Use["SVM_Lin"]) histSVML = new TH1F( "MVA_SVM_Lin", "MVA_SVM_Lin", nbin, 0.0, 1.0 );
if (Use["FDA_MT"]) histFDAMT = new TH1F( "MVA_FDA_MT", "MVA_FDA_MT", nbin, -2.0, 3.0 );
if (Use["FDA_GA"]) histFDAGA = new TH1F( "MVA_FDA_GA", "MVA_FDA_GA", nbin, -2.0, 3.0 );
if (Use["Category"]) histCat = new TH1F( "MVA_Category", "MVA_Category", nbin, -2., 2. );
if (Use["Plugin"]) histPBdt = new TH1F( "MVA_PBDT", "MVA_BDT", nbin, -0.8, 0.8 );
// PDEFoam also returns per-event error, fill in histogram, and also fill significance
if (Use["PDEFoam"]) {
histPDEFoam = new TH1F( "MVA_PDEFoam", "MVA_PDEFoam", nbin, 0, 1 );
histPDEFoamErr = new TH1F( "MVA_PDEFoamErr", "MVA_PDEFoam error", nbin, 0, 1 );
histPDEFoamSig = new TH1F( "MVA_PDEFoamSig", "MVA_PDEFoam significance", nbin, 0, 10 );
}
// Book example histogram for probability (the other methods are done similarly)
TH1F *probHistFi(0), *rarityHistFi(0);
if (Use["Fisher"]) {
probHistFi = new TH1F( "MVA_Fisher_Proba", "MVA_Fisher_Proba", nbin, 0, 1 );
rarityHistFi = new TH1F( "MVA_Fisher_Rarity", "MVA_Fisher_Rarity", nbin, 0, 1 );
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fname = "./tmva_example.root";
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
std::cout << "--- Select signal sample" << std::endl;
TTree* theTree = (TTree*)input->Get("TreeS");
Float_t userVar1, userVar2;
theTree->SetBranchAddress( "var1", &userVar1 );
theTree->SetBranchAddress( "var2", &userVar2 );
theTree->SetBranchAddress( "var3", &var3 );
theTree->SetBranchAddress( "var4", &var4 );
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
theTree->GetEntry(ievt);
var1 = userVar1 + userVar2;
var2 = userVar1 - userVar2;
// --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
if (Use["Likelihood" ]) histLk ->Fill( reader->EvaluateMVA( "Likelihood method" ) );
if (Use["LikelihoodD" ]) histLkD ->Fill( reader->EvaluateMVA( "LikelihoodD method" ) );
if (Use["LikelihoodPCA"]) histLkPCA ->Fill( reader->EvaluateMVA( "LikelihoodPCA method" ) );
if (Use["LikelihoodKDE"]) histLkKDE ->Fill( reader->EvaluateMVA( "LikelihoodKDE method" ) );
if (Use["LikelihoodMIX"]) histLkMIX ->Fill( reader->EvaluateMVA( "LikelihoodMIX method" ) );
if (Use["PDERS" ]) histPD ->Fill( reader->EvaluateMVA( "PDERS method" ) );
if (Use["PDERSD" ]) histPDD ->Fill( reader->EvaluateMVA( "PDERSD method" ) );
if (Use["PDERSPCA" ]) histPDPCA ->Fill( reader->EvaluateMVA( "PDERSPCA method" ) );
if (Use["KNN" ]) histKNN ->Fill( reader->EvaluateMVA( "KNN method" ) );
if (Use["HMatrix" ]) histHm ->Fill( reader->EvaluateMVA( "HMatrix method" ) );
if (Use["Fisher" ]) histFi ->Fill( reader->EvaluateMVA( "Fisher method" ) );
if (Use["FisherG" ]) histFiG ->Fill( reader->EvaluateMVA( "FisherG method" ) );
if (Use["BoostedFisher"]) histFiB ->Fill( reader->EvaluateMVA( "BoostedFisher method" ) );
if (Use["LD" ]) histLD ->Fill( reader->EvaluateMVA( "LD method" ) );
if (Use["MLP" ]) histNn ->Fill( reader->EvaluateMVA( "MLP method" ) );
if (Use["MLPBFGS" ]) histNnbfgs ->Fill( reader->EvaluateMVA( "MLPBFGS method" ) );
if (Use["MLPBNN" ]) histNnbnn ->Fill( reader->EvaluateMVA( "MLPBNN method" ) );
if (Use["CFMlpANN" ]) histNnC ->Fill( reader->EvaluateMVA( "CFMlpANN method" ) );
if (Use["TMlpANN" ]) histNnT ->Fill( reader->EvaluateMVA( "TMlpANN method" ) );
if (Use["BDT" ]) histBdt ->Fill( reader->EvaluateMVA( "BDT method" ) );
if (Use["BDTD" ]) histBdtD ->Fill( reader->EvaluateMVA( "BDTD method" ) );
if (Use["BDTG" ]) histBdtG ->Fill( reader->EvaluateMVA( "BDTG method" ) );
if (Use["RuleFit" ]) histRf ->Fill( reader->EvaluateMVA( "RuleFit method" ) );
if (Use["SVM_Gauss" ]) histSVMG ->Fill( reader->EvaluateMVA( "SVM_Gauss method" ) );
if (Use["SVM_Poly" ]) histSVMP ->Fill( reader->EvaluateMVA( "SVM_Poly method" ) );
if (Use["SVM_Lin" ]) histSVML ->Fill( reader->EvaluateMVA( "SVM_Lin method" ) );
if (Use["FDA_MT" ]) histFDAMT ->Fill( reader->EvaluateMVA( "FDA_MT method" ) );
if (Use["FDA_GA" ]) histFDAGA ->Fill( reader->EvaluateMVA( "FDA_GA method" ) );
if (Use["Category" ]) histCat ->Fill( reader->EvaluateMVA( "Category method" ) );
if (Use["Plugin" ]) histPBdt ->Fill( reader->EvaluateMVA( "P_BDT method" ) );
// Retrieve also per-event error
if (Use["PDEFoam"]) {
Double_t val = reader->EvaluateMVA( "PDEFoam method" );
Double_t err = reader->GetMVAError();
histPDEFoam ->Fill( val );
histPDEFoamErr->Fill( err );
if (err>1.e-50) histPDEFoamSig->Fill( val/err );
}
// Retrieve probability instead of MVA output
if (Use["Fisher"]) {
probHistFi ->Fill( reader->GetProba ( "Fisher method" ) );
rarityHistFi->Fill( reader->GetRarity( "Fisher method" ) );
}
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
// --- Write histograms
TFile *target = new TFile( "TMVApp.root","RECREATE" );
if (Use["Likelihood" ]) histLk ->Write();
if (Use["LikelihoodD" ]) histLkD ->Write();
if (Use["LikelihoodPCA"]) histLkPCA ->Write();
if (Use["LikelihoodKDE"]) histLkKDE ->Write();
if (Use["LikelihoodMIX"]) histLkMIX ->Write();
if (Use["PDERS" ]) histPD ->Write();
if (Use["PDERSD" ]) histPDD ->Write();
if (Use["PDERSPCA" ]) histPDPCA ->Write();
if (Use["KNN" ]) histKNN ->Write();
if (Use["HMatrix" ]) histHm ->Write();
if (Use["Fisher" ]) histFi ->Write();
if (Use["FisherG" ]) histFiG ->Write();
if (Use["BoostedFisher"]) histFiB ->Write();
if (Use["LD" ]) histLD ->Write();
if (Use["MLP" ]) histNn ->Write();
if (Use["MLPBFGS" ]) histNnbfgs ->Write();
if (Use["MLPBNN" ]) histNnbnn ->Write();
if (Use["CFMlpANN" ]) histNnC ->Write();
if (Use["TMlpANN" ]) histNnT ->Write();
if (Use["BDT" ]) histBdt ->Write();
if (Use["BDTD" ]) histBdtD ->Write();
if (Use["BDTG" ]) histBdtG ->Write();
if (Use["RuleFit" ]) histRf ->Write();
if (Use["SVM_Gauss" ]) histSVMG ->Write();
if (Use["SVM_Poly" ]) histSVMP ->Write();
if (Use["SVM_Lin" ]) histSVML ->Write();
if (Use["FDA_MT" ]) histFDAMT ->Write();
if (Use["FDA_GA" ]) histFDAGA ->Write();
if (Use["Category" ]) histCat ->Write();
if (Use["Plugin" ]) histPBdt ->Write();
// Write also error and significance histos
if (Use["PDEFoam"]) { histPDEFoam->Write(); histPDEFoamErr->Write(); histPDEFoamSig->Write(); }
// Write also probability hists
if (Use["Fisher"]) { if (probHistFi != 0) probHistFi->Write(); if (rarityHistFi != 0) rarityHistFi->Write(); }
target->Close();
std::cout << "--- Created root file: \"TMVApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVAapply_double::Loop(TString inputfile, TString output_dir, int sample_type)
{
if (fChain == 0) return;
Long64_t nentries = fChain->GetEntriesFast();
Long64_t nbytes = 0, nb = 0;
Int_t presel=0;
Int_t loopJet_max;
TFile *output = new TFile("main_tmva_v13_Data_4_"+output_dir+".root","recreate");
TTree *tree = fChain->CloneTree(0);
float BDT_VBF;
TBranch *branchBDT_VBF = tree->Branch("BDT_VBF",&BDT_VBF,"BDT_VBF/F");
TString weightfile = "../weights/TMVAClassification_BDTG_double_all_4.weights.xml";
TMVA::Reader *reader = new TMVA::Reader("Silent");
float var1,var2,var3,var4,var5,var6,var7,var8,var9,var10, var11, var12;
reader->AddVariable("Mqq",&var1);
reader->AddVariable("DeltaEtaQQ",&var2);
reader->AddVariable("DeltaPhiQQ",&var3);
reader->AddVariable("SoftN5",&var4);
reader->AddVariable("HTsoft",&var5);
reader->AddVariable("CSV1",&var6);
reader->AddVariable( "CSV2", &var7 );
reader->AddVariable( "cosOqqbb", &var8 );
reader->AddVariable( "DeltaEtaQB1", &var9 );
reader->AddVariable( "DeltaEtaQB2", &var10 );
reader->AddVariable("qgl1",&var11);
reader->AddVariable("qgl2",&var12);
reader->BookMVA("BDTG", weightfile);
TFile *input_file = new TFile(inputfile);
TH1F* Count = (TH1F*)input_file->Get("Count");
TH1F* CountPosWeight = (TH1F*)input_file->Get("CountPosWeight");
TH1F* CountNegWeight =(TH1F*)input_file->Get("CountNegWeight");
int events_saved=0;
for (Long64_t jentry=0; jentry<nentries;jentry++) {
Long64_t ientry = LoadTree(jentry);
nb = fChain->GetEntry(jentry); nbytes += nb;
int btag_max1_number = -1;
int btag_max2_number = -1;
int pt_max1_number = -1;
int pt_max2_number = -1;
TLorentzVector Bjet1;
TLorentzVector Bjet2;
TLorentzVector Qjet1;
TLorentzVector Qjet2;
TLorentzVector qq;
if (preselection_double(nJet, Jet_pt,Jet_eta, Jet_phi, Jet_mass, Jet_btagCSV, Jet_id, btag_max1_number, btag_max2_number, pt_max1_number, pt_max2_number, HLT_BIT_HLT_QuadPFJet_DoubleBTagCSV_VBF_Mqq200_v, Bjet1, Bjet2, Qjet1, Qjet2, qq) !=0) continue;
Float_t Mqq = qq.M();
Float_t bbDeltaPhi = TMath::Abs(Bjet1.DeltaPhi(Bjet2));
Double_t qqDeltaPhi = TMath::Abs(Qjet1.DeltaPhi(Qjet2));
Float_t qqDeltaEta = TMath::Abs(Qjet1.Eta()-Qjet2.Eta());
TLorentzVector bb;
bb = Bjet1+Bjet2;
Float_t Mbb = bb.M();
TLorentzVector bbqq;
bbqq = Bjet1 + Bjet2 + Qjet1 + Qjet2;
Float_t cosOqqbb =TMath::Cos( ( ( Bjet1.Vect() ).Cross(Bjet2.Vect()) ).Angle( ( Qjet1.Vect() ).Cross(Qjet2.Vect()) ) );
Float_t EtaBQ1;
Float_t EtaBQ2;
Float_t PhiBQ1;
Float_t PhiBQ2;
if (Qjet1.Eta() >= Qjet2.Eta()) {
if (Bjet1.Eta() >= Bjet2.Eta()) {
EtaBQ1 = Qjet1.Eta()-Bjet1.Eta();
PhiBQ1 = TMath::Abs(Bjet1.DeltaPhi(Qjet1));
}
else {
EtaBQ1 = Qjet1.Eta()-Bjet2.Eta();
PhiBQ1 = TMath::Abs(Bjet2.DeltaPhi(Qjet1));
}
} else if (Bjet1.Eta() >= Bjet2.Eta()) {
EtaBQ1 = Qjet2.Eta()-Bjet1.Eta();
PhiBQ1 = TMath::Abs(Bjet1.DeltaPhi(Qjet2));
}
else {
EtaBQ1 = Qjet2.Eta()-Bjet2.Eta();
PhiBQ1 = TMath::Abs(Bjet2.DeltaPhi(Qjet2));
}
if (Qjet1.Eta() <= Qjet2.Eta()) {
if (Bjet1.Eta() <= Bjet2.Eta()) {
EtaBQ2 = Qjet1.Eta()-Bjet1.Eta();
PhiBQ2 = TMath::Abs(Bjet1.DeltaPhi(Qjet1));
}
else {
EtaBQ2 = Qjet1.Eta()-Bjet2.Eta();
PhiBQ2 = TMath::Abs(Bjet2.DeltaPhi(Qjet1));
}
} else if (Bjet1.Eta() <= Bjet2.Eta()) {
EtaBQ2 = Qjet2.Eta()-Bjet1.Eta();
PhiBQ2 = TMath::Abs(Bjet1.DeltaPhi(Qjet2));
}
else {
EtaBQ2 = Qjet2.Eta()-Bjet2.Eta();
PhiBQ2 = TMath::Abs(Bjet2.DeltaPhi(Qjet2));
}
Float_t Etot = Bjet1.E()+Bjet2.E()+Qjet1.E()+Qjet2.E();
Float_t PzTot = Bjet1.Pz()+Bjet2.Pz()+Qjet1.Pz()+Qjet2.Pz();
Float_t PxTot = Bjet1.Px()+Bjet2.Px()+Qjet1.Px()+Qjet2.Px();
Float_t PyTot = Bjet1.Py()+Bjet2.Py()+Qjet1.Py()+Qjet2.Py();
Float_t x1 = 0.;
Float_t x2 = 0.;
x1 = (Etot + PzTot)/2./13000.;
x2 = (Etot - PzTot)/2./13000.;
TLorentzVector q1,q2,q1_after,q2_after, VB1, VB2;
q1.SetPxPyPzE(0.,0.,13000./2.*x1,13000./2.*x1);
q2.SetPxPyPzE(0.,0.,-13000./2.*x2,13000./2.*x2);
q1_after.SetPxPyPzE(Qjet1.Px()/Qjet1.Beta(),Qjet1.Py()/Qjet1.Beta(),Qjet1.Pz()/Qjet1.Beta(),Qjet1.E());
q2_after.SetPxPyPzE(Qjet2.Px()/Qjet2.Beta(),Qjet2.Py()/Qjet2.Beta(),Qjet2.Pz()/Qjet2.Beta(),Qjet2.E());
if (q1_after.Eta()>=0.) {
VB1 = -q1_after+q1;
VB2 = -q2_after+q2;
} else {
VB1 = -q2_after+q1;
VB2 = -q1_after+q2;
}
Float_t VB1_mass, VB2_mass;
VB1_mass = TMath::Abs(VB1.M());
VB2_mass = TMath::Abs(VB2.M());
for (int i=0;i<nJet;i++){
if (Jet_btagCSV[i]>1) Jet_btagCSV[i]=1.;
if (Jet_btagCSV[i]<0) Jet_btagCSV[i]=0.;
}
var1= Mqq;
var6= Jet_btagCSV[btag_max1_number];
var7= Jet_btagCSV[btag_max2_number];
var2= qqDeltaEta;
var3= qqDeltaPhi;
var4= softActivity_njets5;
var5= softActivity_HT;
var9= EtaBQ1;
var10= EtaBQ2;
var8= cosOqqbb;
var11=Jet_qgl[pt_max1_number];
var12 = Jet_qgl[pt_max2_number];
BDT_VBF = reader->EvaluateMVA("BDTG");
tree->Fill();
// events_saved++;
// if (sample_type==2)
// if (events_saved>=108767) break; //for 500-700
}
delete reader;
output->cd();
tree->AutoSave();
Count->Write();
CountPosWeight->Write();
CountNegWeight->Write();
output->Close();
}
void Classify_HWW( TString myMethodList = "" )
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//--------------------------------------------------------------------
// path to weights dir (this is where MVA training info is stored)
// output root file will be stored at [path]/output
//--------------------------------------------------------------------
TString path = "Trainings/v5/H160_WW_10vars_dphi10/";
//TString path = "./";
//-----------------------------------
// select samples to run over
//-----------------------------------
char* babyPath = "/tas/cerati/HtoWWmvaBabies/latest";
int mH = 160; // choose Higgs mass
vector<char*> samples;
samples.push_back("WWTo2L2Nu");
samples.push_back("GluGluToWWTo4L");
samples.push_back("WZ");
samples.push_back("ZZ");
samples.push_back("TTJets");
samples.push_back("tW");
samples.push_back("WJetsToLNu");
samples.push_back("DY");
//samples.push_back("WJetsFO3");
if ( mH == 130 ) samples.push_back("Higgs130");
else if( mH == 160 ) samples.push_back("Higgs160");
else if( mH == 200 ) samples.push_back("Higgs200");
else{
cout << "Error, unrecognized Higgs mass " << mH << " GeV, quitting" << endl;
exit(0);
}
//--------------------------------------------------------------------------------
// IMPORTANT: set the following variables to the same set used for MVA training!!!
//--------------------------------------------------------------------------------
std::map<std::string,int> mvaVar;
mvaVar[ "lephard_pt" ] = 1;
mvaVar[ "lepsoft_pt" ] = 1;
mvaVar[ "dil_dphi" ] = 1;
mvaVar[ "dil_mass" ] = 1;
mvaVar[ "event_type" ] = 0;
mvaVar[ "met_projpt" ] = 1;
mvaVar[ "met_pt" ] = 0;
mvaVar[ "mt_lephardmet" ] = 1;
mvaVar[ "mt_lepsoftmet" ] = 1;
mvaVar[ "mthiggs" ] = 1;
mvaVar[ "dphi_lephardmet" ] = 1;
mvaVar[ "dphi_lepsoftmet" ] = 1;
mvaVar[ "lepsoft_fbrem" ] = 0;
mvaVar[ "lepsoft_eOverPIn" ] = 0;
mvaVar[ "lepsoft_qdphi" ] = 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"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
Use["Plugin"] = 0;
Use["Category"] = 0;
Use["SVM_Gauss"] = 0;
Use["SVM_Poly"] = 0;
Use["SVM_Lin"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
const unsigned int nsamples = samples.size();
for( unsigned int i = 0 ; i < nsamples ; ++i ){
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
// Float_t var1, var2;
// Float_t var3, var4;
// reader->AddVariable( "myvar1 := var1+var2", &var1 );
// reader->AddVariable( "myvar2 := var1-var2", &var2 );
// reader->AddVariable( "var3", &var3 );
// reader->AddVariable( "var4", &var4 );
Float_t lephard_pt;
Float_t lepsoft_pt;
Float_t dil_dphi;
Float_t dil_mass;
Float_t event_type;
Float_t met_projpt;
Float_t met_pt;
Float_t mt_lephardmet;
Float_t mt_lepsoftmet;
Float_t mthiggs;
Float_t dphi_lephardmet;
Float_t dphi_lepsoftmet;
Float_t lepsoft_fbrem;
Float_t lepsoft_eOverPIn;
Float_t lepsoft_qdphi;
if( mvaVar["lephard_pt"]) reader->AddVariable( "lephard_pt" , &lephard_pt );
if( mvaVar["lepsoft_pt"]) reader->AddVariable( "lepsoft_pt" , &lepsoft_pt );
if( mvaVar["dil_dphi"]) reader->AddVariable( "dil_dphi" , &dil_dphi );
if( mvaVar["dil_mass"]) reader->AddVariable( "dil_mass" , &dil_mass );
if( mvaVar["event_type"]) reader->AddVariable( "event_type" , &event_type );
if( mvaVar["met_projpt"]) reader->AddVariable( "met_projpt" , &met_pt );
if( mvaVar["met_pt"]) reader->AddVariable( "met_pt" , &met_pt );
if( mvaVar["mt_lephardmet"]) reader->AddVariable( "mt_lephardmet" , &mt_lephardmet );
if( mvaVar["mt_lepsoftmet"]) reader->AddVariable( "mt_lepsoftmet" , &mt_lepsoftmet );
if( mvaVar["mthiggs"]) reader->AddVariable( "mthiggs" , &mthiggs );
if( mvaVar["dphi_lephardmet"]) reader->AddVariable( "dphi_lephardmet" , &dphi_lephardmet );
if( mvaVar["dphi_lepsoftmet"]) reader->AddVariable( "dphi_lepsoftmet" , &dphi_lepsoftmet );
if( mvaVar["lepsoft_fbrem"]) reader->AddVariable( "lepsoft_fbrem" , &lepsoft_fbrem );
if( mvaVar["lepsoft_eOverPIn"]) reader->AddVariable( "lepsoft_eOverPIn" , &lepsoft_eOverPIn );
if( mvaVar["lepsoft_qdphi"]) reader->AddVariable( "lepsoft_q * lepsoft_dPhiIn" , &lepsoft_qdphi );
// Spectator variables declared in the training have to be added to the reader, too
// Float_t spec1,spec2;
// reader->AddSpectator( "spec1 := var1*2", &spec1 );
// reader->AddSpectator( "spec2 := var1*3", &spec2 );
Float_t Category_cat1, Category_cat2, Category_cat3;
if (Use["Category"]){
// Add artificial spectators for distinguishing categories
// reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
// reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
// reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
}
// --- Book the MVA methods
//--------------------------------------------------------------------------------------
// tell Classify_HWW where to find the weights dir, which contains the trained MVA's.
// In this example, the weights dir is located at [path]/[dir]
// and the output root file is written to [path]/[output]
//--------------------------------------------------------------------------------------
TString dir = path + "weights/";
TString outdir = path + "output/";
TString prefix = "TMVAClassification";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Book output histograms
UInt_t nbin = 1000;
TH1F *histLk(0), *histLkD(0), *histLkPCA(0), *histLkKDE(0), *histLkMIX(0), *histPD(0), *histPDD(0);
TH1F *histPDPCA(0), *histPDEFoam(0), *histPDEFoamErr(0), *histPDEFoamSig(0), *histKNN(0), *histHm(0);
TH1F *histFi(0), *histFiG(0), *histFiB(0), *histLD(0), *histNn(0),*histNnbfgs(0),*histNnbnn(0);
TH1F *histNnC(0), *histNnT(0), *histBdt(0), *histBdtG(0), *histBdtD(0), *histRf(0), *histSVMG(0);
TH1F *histSVMP(0), *histSVML(0), *histFDAMT(0), *histFDAGA(0), *histCat(0), *histPBdt(0);
if (Use["Likelihood"]) histLk = new TH1F( "MVA_Likelihood", "MVA_Likelihood", nbin, -1, 1 );
if (Use["LikelihoodD"]) histLkD = new TH1F( "MVA_LikelihoodD", "MVA_LikelihoodD", nbin, -1, 0.9999 );
if (Use["LikelihoodPCA"]) histLkPCA = new TH1F( "MVA_LikelihoodPCA", "MVA_LikelihoodPCA", nbin, -1, 1 );
if (Use["LikelihoodKDE"]) histLkKDE = new TH1F( "MVA_LikelihoodKDE", "MVA_LikelihoodKDE", nbin, -0.00001, 0.99999 );
if (Use["LikelihoodMIX"]) histLkMIX = new TH1F( "MVA_LikelihoodMIX", "MVA_LikelihoodMIX", nbin, 0, 1 );
if (Use["PDERS"]) histPD = new TH1F( "MVA_PDERS", "MVA_PDERS", nbin, 0, 1 );
if (Use["PDERSD"]) histPDD = new TH1F( "MVA_PDERSD", "MVA_PDERSD", nbin, 0, 1 );
if (Use["PDERSPCA"]) histPDPCA = new TH1F( "MVA_PDERSPCA", "MVA_PDERSPCA", nbin, 0, 1 );
if (Use["KNN"]) histKNN = new TH1F( "MVA_KNN", "MVA_KNN", nbin, 0, 1 );
if (Use["HMatrix"]) histHm = new TH1F( "MVA_HMatrix", "MVA_HMatrix", nbin, -0.95, 1.55 );
if (Use["Fisher"]) histFi = new TH1F( "MVA_Fisher", "MVA_Fisher", nbin, -4, 4 );
if (Use["FisherG"]) histFiG = new TH1F( "MVA_FisherG", "MVA_FisherG", nbin, -1, 1 );
if (Use["BoostedFisher"]) histFiB = new TH1F( "MVA_BoostedFisher", "MVA_BoostedFisher", nbin, -2, 2 );
if (Use["LD"]) histLD = new TH1F( "MVA_LD", "MVA_LD", nbin, -2, 2 );
if (Use["MLP"]) histNn = new TH1F( "MVA_MLP", "MVA_MLP", nbin, -1.25, 1.5 );
if (Use["MLPBFGS"]) histNnbfgs = new TH1F( "MVA_MLPBFGS", "MVA_MLPBFGS", nbin, -1.25, 1.5 );
if (Use["MLPBNN"]) histNnbnn = new TH1F( "MVA_MLPBNN", "MVA_MLPBNN", nbin, -1.25, 1.5 );
if (Use["CFMlpANN"]) histNnC = new TH1F( "MVA_CFMlpANN", "MVA_CFMlpANN", nbin, 0, 1 );
if (Use["TMlpANN"]) histNnT = new TH1F( "MVA_TMlpANN", "MVA_TMlpANN", nbin, -1.3, 1.3 );
if (Use["BDT"]) histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -1. , 1. );
if (Use["BDTD"]) histBdtD = new TH1F( "MVA_BDTD", "MVA_BDTD", nbin, -0.8, 0.8 );
if (Use["BDTG"]) histBdtG = new TH1F( "MVA_BDTG", "MVA_BDTG", nbin, -1.0, 1.0 );
if (Use["RuleFit"]) histRf = new TH1F( "MVA_RuleFit", "MVA_RuleFit", nbin, -2.0, 2.0 );
if (Use["SVM_Gauss"]) histSVMG = new TH1F( "MVA_SVM_Gauss", "MVA_SVM_Gauss", nbin, 0.0, 1.0 );
if (Use["SVM_Poly"]) histSVMP = new TH1F( "MVA_SVM_Poly", "MVA_SVM_Poly", nbin, 0.0, 1.0 );
if (Use["SVM_Lin"]) histSVML = new TH1F( "MVA_SVM_Lin", "MVA_SVM_Lin", nbin, 0.0, 1.0 );
if (Use["FDA_MT"]) histFDAMT = new TH1F( "MVA_FDA_MT", "MVA_FDA_MT", nbin, -2.0, 3.0 );
if (Use["FDA_GA"]) histFDAGA = new TH1F( "MVA_FDA_GA", "MVA_FDA_GA", nbin, -2.0, 3.0 );
if (Use["Category"]) histCat = new TH1F( "MVA_Category", "MVA_Category", nbin, -2., 2. );
if (Use["Plugin"]) histPBdt = new TH1F( "MVA_PBDT", "MVA_BDT", nbin, -0.8, 0.8 );
if (Use["Likelihood"]) histLk ->Sumw2();
if (Use["LikelihoodD"]) histLkD ->Sumw2();
if (Use["LikelihoodPCA"]) histLkPCA ->Sumw2();
if (Use["LikelihoodKDE"]) histLkKDE ->Sumw2();
if (Use["LikelihoodMIX"]) histLkMIX ->Sumw2();
if (Use["PDERS"]) histPD ->Sumw2();
if (Use["PDERSD"]) histPDD ->Sumw2();
if (Use["PDERSPCA"]) histPDPCA ->Sumw2();
if (Use["KNN"]) histKNN ->Sumw2();
if (Use["HMatrix"]) histHm ->Sumw2();
if (Use["Fisher"]) histFi ->Sumw2();
if (Use["FisherG"]) histFiG ->Sumw2();
if (Use["BoostedFisher"]) histFiB ->Sumw2();
if (Use["LD"]) histLD ->Sumw2();
if (Use["MLP"]) histNn ->Sumw2();
if (Use["MLPBFGS"]) histNnbfgs ->Sumw2();
if (Use["MLPBNN"]) histNnbnn ->Sumw2();
if (Use["CFMlpANN"]) histNnC ->Sumw2();
if (Use["TMlpANN"]) histNnT ->Sumw2();
if (Use["BDT"]) histBdt ->Sumw2();
if (Use["BDTD"]) histBdtD ->Sumw2();
if (Use["BDTG"]) histBdtG ->Sumw2();
if (Use["RuleFit"]) histRf ->Sumw2();
if (Use["SVM_Gauss"]) histSVMG ->Sumw2();
if (Use["SVM_Poly"]) histSVMP ->Sumw2();
if (Use["SVM_Lin"]) histSVML ->Sumw2();
if (Use["FDA_MT"]) histFDAMT ->Sumw2();
if (Use["FDA_GA"]) histFDAGA ->Sumw2();
if (Use["Category"]) histCat ->Sumw2();
if (Use["Plugin"]) histPBdt ->Sumw2();
// PDEFoam also returns per-event error, fill in histogram, and also fill significance
if (Use["PDEFoam"]) {
histPDEFoam = new TH1F( "MVA_PDEFoam", "MVA_PDEFoam", nbin, 0, 1 );
histPDEFoamErr = new TH1F( "MVA_PDEFoamErr", "MVA_PDEFoam error", nbin, 0, 1 );
histPDEFoamSig = new TH1F( "MVA_PDEFoamSig", "MVA_PDEFoam significance", nbin, 0, 10 );
}
// Book example histogram for probability (the other methods are done similarly)
TH1F *probHistFi(0), *rarityHistFi(0);
if (Use["Fisher"]) {
probHistFi = new TH1F( "MVA_Fisher_Proba", "MVA_Fisher_Proba", nbin, 0, 1 );
rarityHistFi = new TH1F( "MVA_Fisher_Rarity", "MVA_Fisher_Rarity", nbin, 0, 1 );
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TChain *ch = new TChain("Events");
if( strcmp( samples.at(i) , "DY" ) == 0 ){
ch -> Add( Form("%s/DYToMuMuM20_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/DYToMuMuM10To20_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/DYToEEM20_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/DYToEEM10To20_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/DYToTauTauM20_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/DYToTauTauM10To20_PU_testFinal_baby.root",babyPath) );
}
if( strcmp( samples.at(i) , "WJetsFO3" ) == 0 ){
ch -> Add( Form("%s/WJetsToLNu_FOv3_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/WToLNu_FOv3_testFinal_baby.root",babyPath) );
}
else if( strcmp( samples.at(i) , "Higgs130" ) == 0 ){
ch -> Add( Form("%s/HToWWTo2L2NuM130_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWToLNuTauNuM130_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWTo2Tau2NuM130_PU_testFinal_baby.root",babyPath) );
}
else if( strcmp( samples.at(i) , "Higgs160" ) == 0 ){
ch -> Add( Form("%s/HToWWTo2L2NuM160_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWToLNuTauNuM160_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWTo2Tau2NuM160_PU_testFinal_baby.root",babyPath) );
}
else if( strcmp( samples.at(i) , "Higgs200" ) == 0 ){
ch -> Add( Form("%s/HToWWTo2L2NuM200_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWToLNuTauNuM200_PU_testFinal_baby.root",babyPath) );
ch -> Add( Form("%s/HToWWTo2Tau2NuM200_PU_testFinal_baby.root",babyPath) );
}
else{
ch -> Add( Form("%s/%s_PU_testFinal_baby.root",babyPath,samples.at(i)) );
}
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
TTree *theTree = (TTree*) ch;
std::cout << "--- Using input files: -------------------" << std::endl;
TObjArray *listOfFiles = ch->GetListOfFiles();
TIter fileIter(listOfFiles);
TChainElement* currentFile = 0;
while((currentFile = (TChainElement*)fileIter.Next())) {
std::cout << currentFile->GetTitle() << std::endl;
}
Float_t lephard_pt_;
Float_t lepsoft_pt_;
Float_t lepsoft_fr_;
Float_t dil_dphi_;
Float_t dil_mass_;
Float_t event_type_;
Float_t met_projpt_;
Int_t jets_num_;
Int_t extralep_num_;
Int_t lowptbtags_num_;
Int_t softmu_num_;
Float_t event_scale1fb_;
Float_t met_pt_;
Int_t lepsoft_passTighterId_;
Float_t mt_lephardmet_;
Float_t mt_lepsoftmet_;
Float_t mthiggs_;
Float_t dphi_lephardmet_;
Float_t dphi_lepsoftmet_;
Float_t lepsoft_fbrem_;
Float_t lepsoft_eOverPIn_;
Float_t lepsoft_q_;
Float_t lepsoft_dPhiIn_;
theTree->SetBranchAddress( "lephard_pt_" , &lephard_pt_ );
theTree->SetBranchAddress( "lepsoft_pt_" , &lepsoft_pt_ );
theTree->SetBranchAddress( "lepsoft_fr_" , &lepsoft_fr_ );
theTree->SetBranchAddress( "dil_dphi_" , &dil_dphi_ );
theTree->SetBranchAddress( "dil_mass_" , &dil_mass_ );
theTree->SetBranchAddress( "event_type_" , &event_type_ );
theTree->SetBranchAddress( "met_projpt_" , &met_projpt_ );
theTree->SetBranchAddress( "jets_num_" , &jets_num_ );
theTree->SetBranchAddress( "extralep_num_" , &extralep_num_ );
theTree->SetBranchAddress( "lowptbtags_num_" , &lowptbtags_num_ );
theTree->SetBranchAddress( "softmu_num_" , &softmu_num_ );
theTree->SetBranchAddress( "event_scale1fb_" , &event_scale1fb_ );
theTree->SetBranchAddress( "lepsoft_passTighterId_" , &lepsoft_passTighterId_ );
theTree->SetBranchAddress( "met_pt_" , &met_pt_ );
theTree->SetBranchAddress( "mt_lephardmet_" , &mt_lephardmet_ );
theTree->SetBranchAddress( "mt_lepsoftmet_" , &mt_lepsoftmet_ );
theTree->SetBranchAddress( "mthiggs_" , &mthiggs_ );
theTree->SetBranchAddress( "dphi_lephardmet_" , &dphi_lephardmet_ );
theTree->SetBranchAddress( "dphi_lepsoftmet_" , &dphi_lepsoftmet_ );
theTree->SetBranchAddress( "lepsoft_fbrem_" , &lepsoft_fbrem_ );
theTree->SetBranchAddress( "lepsoft_eOverPIn_" , &lepsoft_eOverPIn_ );
theTree->SetBranchAddress( "lepsoft_q_" , &lepsoft_q_ );
theTree->SetBranchAddress( "lepsoft_dPhiIn_" , &lepsoft_dPhiIn_ );
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
int npass = 0;
float yield = 0.;
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
theTree->GetEntry(ievt);
//-------------------------------------------------------
// event selection
//-------------------------------------------------------
if( dil_dphi_ > 1. ) continue;
//em
if( event_type_ > 0.5 && event_type_ < 2.5 ){
if( met_projpt_ < 20. ) continue;
}
//ee/mm
if( event_type_ < 0.5 || event_type_ > 2.5 ){
if( met_projpt_ < 35. ) continue;
}
if( lephard_pt_ < 20. ) continue;
if( jets_num_ > 0 ) continue;
if( extralep_num_ > 0 ) continue;
if( lowptbtags_num_ > 0 ) continue;
if( softmu_num_ > 0 ) continue;
if( dil_mass_ < 12. ) continue;
if( lepsoft_passTighterId_ == 0 ) continue;
//if( event_type_ < 1.5 ) continue;
//if( event_type > 1.5 && lepsoft_pt_ < 15. ) continue;
//mH-dependent selection
if( mH == 130 ){
if( lepsoft_pt_ < 10. ) continue;
if( dil_mass_ > 90. ) continue;
}
else if( mH == 160 ){
if( lepsoft_pt_ < 20. ) continue;
if( dil_mass_ > 100. ) continue;
}
else if( mH == 200 ){
if( lepsoft_pt_ < 20. ) continue;
if( dil_mass_ > 130. ) continue;
}
float weight = event_scale1fb_ * lepsoft_fr_ * 0.5;
//--------------------------------------------------------
// important: here we associate branches to MVA variables
//--------------------------------------------------------
lephard_pt = lephard_pt_;
lepsoft_pt = lepsoft_pt_;
dil_mass = dil_mass_;
dil_dphi = dil_dphi_;
event_type = event_type_;
met_pt = met_pt_;
met_projpt = met_projpt_;
mt_lephardmet = mt_lephardmet_;
mt_lepsoftmet = mt_lepsoftmet_;
mthiggs = mthiggs_;
dphi_lephardmet = dphi_lephardmet_;
dphi_lepsoftmet = dphi_lepsoftmet_;
lepsoft_fbrem = lepsoft_fbrem_;
lepsoft_eOverPIn = lepsoft_eOverPIn_;
lepsoft_qdphi = lepsoft_q_ * lepsoft_dPhiIn_;
npass++;
yield+=weight;
// var1 = userVar1 + userVar2;
// var2 = userVar1 - userVar2;
// --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
if (Use["Likelihood" ]) histLk ->Fill( reader->EvaluateMVA( "Likelihood method" ) , weight);
if (Use["LikelihoodD" ]) histLkD ->Fill( reader->EvaluateMVA( "LikelihoodD method" ) , weight);
if (Use["LikelihoodPCA"]) histLkPCA ->Fill( reader->EvaluateMVA( "LikelihoodPCA method" ) , weight);
if (Use["LikelihoodKDE"]) histLkKDE ->Fill( reader->EvaluateMVA( "LikelihoodKDE method" ) , weight);
if (Use["LikelihoodMIX"]) histLkMIX ->Fill( reader->EvaluateMVA( "LikelihoodMIX method" ) , weight);
if (Use["PDERS" ]) histPD ->Fill( reader->EvaluateMVA( "PDERS method" ) , weight);
if (Use["PDERSD" ]) histPDD ->Fill( reader->EvaluateMVA( "PDERSD method" ) , weight);
if (Use["PDERSPCA" ]) histPDPCA ->Fill( reader->EvaluateMVA( "PDERSPCA method" ) , weight);
if (Use["KNN" ]) histKNN ->Fill( reader->EvaluateMVA( "KNN method" ) , weight);
if (Use["HMatrix" ]) histHm ->Fill( reader->EvaluateMVA( "HMatrix method" ) , weight);
if (Use["Fisher" ]) histFi ->Fill( reader->EvaluateMVA( "Fisher method" ) , weight);
if (Use["FisherG" ]) histFiG ->Fill( reader->EvaluateMVA( "FisherG method" ) , weight);
if (Use["BoostedFisher"]) histFiB ->Fill( reader->EvaluateMVA( "BoostedFisher method" ) , weight);
if (Use["LD" ]) histLD ->Fill( reader->EvaluateMVA( "LD method" ) , weight);
if (Use["MLP" ]) histNn ->Fill( reader->EvaluateMVA( "MLP method" ) , weight);
if (Use["MLPBFGS" ]) histNnbfgs ->Fill( reader->EvaluateMVA( "MLPBFGS method" ) , weight);
if (Use["MLPBNN" ]) histNnbnn ->Fill( reader->EvaluateMVA( "MLPBNN method" ) , weight);
if (Use["CFMlpANN" ]) histNnC ->Fill( reader->EvaluateMVA( "CFMlpANN method" ) , weight);
if (Use["TMlpANN" ]) histNnT ->Fill( reader->EvaluateMVA( "TMlpANN method" ) , weight);
if (Use["BDT" ]) histBdt ->Fill( reader->EvaluateMVA( "BDT method" ) , weight);
if (Use["BDTD" ]) histBdtD ->Fill( reader->EvaluateMVA( "BDTD method" ) , weight);
if (Use["BDTG" ]) histBdtG ->Fill( reader->EvaluateMVA( "BDTG method" ) , weight);
if (Use["RuleFit" ]) histRf ->Fill( reader->EvaluateMVA( "RuleFit method" ) , weight);
if (Use["SVM_Gauss" ]) histSVMG ->Fill( reader->EvaluateMVA( "SVM_Gauss method" ) , weight);
if (Use["SVM_Poly" ]) histSVMP ->Fill( reader->EvaluateMVA( "SVM_Poly method" ) , weight);
if (Use["SVM_Lin" ]) histSVML ->Fill( reader->EvaluateMVA( "SVM_Lin method" ) , weight);
if (Use["FDA_MT" ]) histFDAMT ->Fill( reader->EvaluateMVA( "FDA_MT method" ) , weight);
if (Use["FDA_GA" ]) histFDAGA ->Fill( reader->EvaluateMVA( "FDA_GA method" ) , weight);
if (Use["Category" ]) histCat ->Fill( reader->EvaluateMVA( "Category method" ) , weight);
if (Use["Plugin" ]) histPBdt ->Fill( reader->EvaluateMVA( "P_BDT method" ) , weight);
// Retrieve also per-event error
if (Use["PDEFoam"]) {
Double_t val = reader->EvaluateMVA( "PDEFoam method" );
Double_t err = reader->GetMVAError();
histPDEFoam ->Fill( val );
histPDEFoamErr->Fill( err );
if (err>1.e-50) histPDEFoamSig->Fill( val/err , weight);
}
// Retrieve probability instead of MVA output
if (Use["Fisher"]) {
probHistFi ->Fill( reader->GetProba ( "Fisher method" ) , weight);
rarityHistFi->Fill( reader->GetRarity( "Fisher method" ) , weight);
}
}
std::cout << npass << " events passing selection, yield " << yield << std::endl;
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
// --- Write histograms
cout << "dir " << dir << endl;
char* mydir = outdir;
TFile *target = new TFile( Form("%s/%s.root",mydir,samples.at(i) ) ,"RECREATE" );
cout << "Writing to file " << Form("%s/%s.root",mydir,samples.at(i) ) << endl;
if (Use["Likelihood" ]) histLk ->Write();
if (Use["LikelihoodD" ]) histLkD ->Write();
if (Use["LikelihoodPCA"]) histLkPCA ->Write();
if (Use["LikelihoodKDE"]) histLkKDE ->Write();
if (Use["LikelihoodMIX"]) histLkMIX ->Write();
if (Use["PDERS" ]) histPD ->Write();
if (Use["PDERSD" ]) histPDD ->Write();
if (Use["PDERSPCA" ]) histPDPCA ->Write();
if (Use["KNN" ]) histKNN ->Write();
if (Use["HMatrix" ]) histHm ->Write();
if (Use["Fisher" ]) histFi ->Write();
if (Use["FisherG" ]) histFiG ->Write();
if (Use["BoostedFisher"]) histFiB ->Write();
if (Use["LD" ]) histLD ->Write();
if (Use["MLP" ]) histNn ->Write();
if (Use["MLPBFGS" ]) histNnbfgs ->Write();
if (Use["MLPBNN" ]) histNnbnn ->Write();
if (Use["CFMlpANN" ]) histNnC ->Write();
if (Use["TMlpANN" ]) histNnT ->Write();
if (Use["BDT" ]) histBdt ->Write();
if (Use["BDTD" ]) histBdtD ->Write();
if (Use["BDTG" ]) histBdtG ->Write();
if (Use["RuleFit" ]) histRf ->Write();
if (Use["SVM_Gauss" ]) histSVMG ->Write();
if (Use["SVM_Poly" ]) histSVMP ->Write();
if (Use["SVM_Lin" ]) histSVML ->Write();
if (Use["FDA_MT" ]) histFDAMT ->Write();
if (Use["FDA_GA" ]) histFDAGA ->Write();
if (Use["Category" ]) histCat ->Write();
if (Use["Plugin" ]) histPBdt ->Write();
// Write also error and significance histos
if (Use["PDEFoam"]) { histPDEFoam->Write(); histPDEFoamErr->Write(); histPDEFoamSig->Write(); }
// Write also probability hists
if (Use["Fisher"]) { if (probHistFi != 0) probHistFi->Write(); if (rarityHistFi != 0) rarityHistFi->Write(); }
target->Close();
delete reader;
std::cout << "==> TMVAClassificationApplication is done with sample " << samples.at(i) << endl << std::endl;
}
}
void PlotDecisionBoundary( TString weightFile = "weights/TMVAClassification_BDT.weights.xml",TString v0="var0", TString v1="var1", TString dataFileName = "/home/hvoss/TMVA/TMVA_data/data/data_circ.root")
{
//---------------------------------------------------------------
// default MVA methods to be trained + tested
// this loads the library
TMVA::Tools::Instance();
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
//
// create the Reader object
//
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// create a set of variables and declare them to the reader
// - the variable names must corresponds in name and type to
// those given in the weight file(s) that you use
Float_t var0, var1;
reader->AddVariable( v0, &var0 );
reader->AddVariable( v1, &var1 );
//
// book the MVA method
//
reader->BookMVA( "M1", weightFile );
TFile *f = new TFile(dataFileName);
TTree *signal = (TTree*)f->Get("TreeS");
TTree *background = (TTree*)f->Get("TreeB");
//Declaration of leaves types
Float_t svar0;
Float_t svar1;
Float_t bvar0;
Float_t bvar1;
Float_t sWeight=1.0; // just in case you have weight defined, also set these branchaddresses
Float_t bWeight=1.0*signal->GetEntries()/background->GetEntries(); // just in case you have weight defined, also set these branchaddresses
// Set branch addresses.
signal->SetBranchAddress(v0,&svar0);
signal->SetBranchAddress(v1,&svar1);
background->SetBranchAddress(v0,&bvar0);
background->SetBranchAddress(v1,&bvar1);
UInt_t nbin = 50;
Float_t xmax = signal->GetMaximum(v0.Data());
Float_t xmin = signal->GetMinimum(v0.Data());
Float_t ymax = signal->GetMaximum(v1.Data());
Float_t ymin = signal->GetMinimum(v1.Data());
xmax = TMath::Max(xmax,background->GetMaximum(v0.Data()));
xmin = TMath::Min(xmin,background->GetMinimum(v0.Data()));
ymax = TMath::Max(ymax,background->GetMaximum(v1.Data()));
ymin = TMath::Min(ymin,background->GetMinimum(v1.Data()));
TH2D *hs=new TH2D("hs","",nbin,xmin,xmax,nbin,ymin,ymax);
TH2D *hb=new TH2D("hb","",nbin,xmin,xmax,nbin,ymin,ymax);
hs->SetXTitle(v0);
hs->SetYTitle(v1);
hb->SetXTitle(v0);
hb->SetYTitle(v1);
hs->SetMarkerColor(4);
hb->SetMarkerColor(2);
TH2F * hist = new TH2F( "MVA", "MVA", nbin,xmin,xmax,nbin,ymin,ymax);
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
Float_t MinMVA=10000, MaxMVA=-100000;
for (Int_t ibin=1; ibin<nbin+1; ibin++){
for (Int_t jbin=1; jbin<nbin+1; jbin++){
var0 = hs->GetXaxis()->GetBinCenter(ibin);
var1 = hs->GetYaxis()->GetBinCenter(jbin);
Float_t mvaVal=reader->EvaluateMVA( "M1" ) ;
if (MinMVA>mvaVal) MinMVA=mvaVal;
if (MaxMVA<mvaVal) MaxMVA=mvaVal;
hist->SetBinContent(ibin,jbin, mvaVal);
}
}
// creating a fine histograms containing the error rate
const Int_t nValBins=100;
Double_t sum = 0.;
TH1F *mvaS= new TH1F("mvaS","",nValBins,MinMVA,MaxMVA);
TH1F *mvaB= new TH1F("mvaB","",nValBins,MinMVA,MaxMVA);
TH1F *mvaSC= new TH1F("mvaSC","",nValBins,MinMVA,MaxMVA);
TH1F *mvaBC= new TH1F("mvaBC","",nValBins,MinMVA,MaxMVA);
Long64_t nentries;
nentries = TreeS->GetEntries();
for (Long64_t is=0; is<nentries;is++) {
signal->GetEntry(is);
sum +=sWeight;
var0 = svar0;
var1 = svar1;
Float_t mvaVal=reader->EvaluateMVA( "M1" ) ;
hs->Fill(svar0,svar1);
mvaS->Fill(mvaVal,sWeight);
}
nentries = TreeB->GetEntries();
for (Long64_t ib=0; ib<nentries;ib++) {
background->GetEntry(ib);
sum +=bWeight;
var0 = bvar0;
var1 = bvar1;
Float_t mvaVal=reader->EvaluateMVA( "M1" ) ;
hb->Fill(bvar0,bvar1);
mvaB->Fill(mvaVal,bWeight);
}
//SeparationBase *sepGain = new MisClassificationError();
//SeparationBase *sepGain = new GiniIndex();
SeparationBase *sepGain = new CrossEntropy();
Double_t sTot = mvaS->GetSum();
Double_t bTot = mvaB->GetSum();
mvaSC->SetBinContent(1,mvaS->GetBinContent(1));
mvaBC->SetBinContent(1,mvaB->GetBinContent(1));
Double_t sSel=mvaSC->GetBinContent(1);
Double_t bSel=mvaBC->GetBinContent(1);
Double_t separationGain=sepGain->GetSeparationGain(sSel,bSel,sTot,bTot);
Double_t mvaCut=mvaSC->GetBinCenter(1);
Double_t mvaCutOrientation=1; // 1 if mva > mvaCut --> Signal and -1 if mva < mvaCut (i.e. mva*-1 > mvaCut*-1) --> Signal
for (Int_t ibin=2;ibin<nValBins;ibin++){
mvaSC->SetBinContent(ibin,mvaS->GetBinContent(ibin)+mvaSC->GetBinContent(ibin-1));
mvaBC->SetBinContent(ibin,mvaB->GetBinContent(ibin)+mvaBC->GetBinContent(ibin-1));
sSel=mvaSC->GetBinContent(ibin);
bSel=mvaBC->GetBinContent(ibin);
if (separationGain < sepGain->GetSeparationGain(sSel,bSel,sTot,bTot) && mvaSC->GetBinCenter(ibin)<0){
separationGain = sepGain->GetSeparationGain(sSel,bSel,sTot,bTot);
mvaCut=mvaSC->GetBinCenter(ibin);
if (sSel/bSel > (sTot-sSel)/(bTot-bSel)) mvaCutOrientation=-1;
else mvaCutOrientation=1;
}
}
cout << "Min="<<MinMVA << " Max=" << MaxMVA
<< " sTot=" << sTot
<< " bTot=" << bTot
<< " sepGain="<<separationGain
<< " cut=" << mvaCut
<< " cutOrientation="<<mvaCutOrientation
<< endl;
delete reader;
gStyle->SetPalette(1);
plot(hs,hb,hist ,v0,v1,mvaCut);
TCanvas *cm=new TCanvas ("cm","",900,1200);
cm->cd();
cm->Divide(1,2);
cm->cd(1);
mvaS->SetLineColor(4);
mvaB->SetLineColor(2);
mvaS->Draw();
mvaB->Draw("same");
cm->cd(2);
mvaSC->SetLineColor(4);
mvaBC->SetLineColor(2);
mvaBC->Draw();
mvaSC->Draw("same");
// TH1F *add=(TH1F*)mvaBC->Clone("add");
// add->Add(mvaSC);
// add->Draw();
// errh->Draw("same");
//
// write histograms
//
TFile *target = new TFile( "TMVAPlotDecisionBoundary.root","RECREATE" );
hs->Write();
hb->Write();
hist->Write();
target->Close();
}
void TMVAClassificationApplication( TString myMethodList = "" )
{
//---------------------------------------------------------------
// default MVA methods to be trained + tested
// this loads the library
TMVA::Tools::Instance();
std::map<std::string,int> Use;
Use["CutsGA"] = 0; // other "Cuts" methods work identically
// ---
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; //
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["Category"] = 0;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 0;
}
}
//
// create the Reader object
//
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
Float_t Z_rapidity_z;
reader->AddVariable("Z_rapidity_z",&Z_rapidity_z);
Float_t THRUST_2D;
reader->AddVariable("THRUST_2D",&THRUST_2D);
Float_t L1_L2_cosangle;
reader->AddVariable("L1_L2_cosangle",&L1_L2_cosangle);
Float_t TransMass_ZH150_uncl;
reader->AddVariable("TransMass_ZH150_uncl",&TransMass_ZH150_uncl);
Float_t TransMass_ZH150;
reader->AddVariable("TransMass_ZH150",&TransMass_ZH150);
Float_t DeltaPhi_ZH;
reader->AddVariable("DeltaPhi_ZH",&DeltaPhi_ZH);
Float_t DeltaPhi_ZH_uncl;
reader->AddVariable("DeltaPhi_ZH_uncl",&DeltaPhi_ZH_uncl);
Float_t CMAngle;
reader->AddVariable("CMAngle",&CMAngle);
Float_t CS_cosangle;
reader->AddVariable("CS_cosangle",&CS_cosangle);
// create a set of variables and declare them to the reader
// - the variable names must corresponds in name and type to
// those given in the weight file(s) that you use
Float_t var1, var2;
Float_t var3, var4;
// reader->AddVariable( "myvar1 := var1+var2", &var1 );
// reader->AddVariable( "myvar2 := var1-var2", &var2 );
// reader->AddVariable( "var3", &var3 );
// reader->AddVariable( "var4", &var4 );
//Spectator variables declared in the training have to be added to the reader, too
Float_t spec1,spec2;
// reader->AddSpectator( "spec1 := var1*2", &spec1 );
float nonsense =0;
// reader->AddSpectator( "spec2 := var1*3", &spec2 );
float nonsense =0;
Float_t Category_cat1, Category_cat2, Category_cat3;
if (Use["Category"]){
// add artificial spectators for distinguishing categories
// reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
float nonsense =0;
// reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
float nonsense =0;
// reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
float nonsense =0;
}
//
// book the MVA methods
//
TString dir = "weights/";
TString prefix = "TMVAClassification";
// book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = it->first + " method";
TString weightfile = dir + prefix + "_" + TString(it->first) + ".weights.xml";
reader->BookMVA( methodName, weightfile );
}
}
// example how to use your own method as plugin
if (Use["Plugin"]) {
// the weight file contains a line
// Method : MethodName::InstanceName
// if MethodName is not a known TMVA method, it is assumed to be
// a user implemented method which has to be loaded via the
// plugin mechanism
// for user implemented methods the line in the weight file can be
// Method : PluginName::InstanceName
// where PluginName can be anything
// before usage the plugin has to be defined, which can happen
// either through the following line in .rootrc:
// # plugin handler plugin class library constructor format
// Plugin.TMVA@@MethodBase: PluginName MethodClassName UserPackage "MethodName(DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "PluginName", "MethodClassName", "UserPackage", "MethodName(DataSet&,TString)");
// the class is then looked for in libUserPackage.so
// now the method can be booked like any other
reader->BookMVA( "User method", dir + prefix + "_User.weights.txt" );
}
// book output histograms
UInt_t nbin = 100;
TH1F *histLk(0), *histLkD(0), *histLkPCA(0), *histLkKDE(0), *histLkMIX(0), *histPD(0), *histPDD(0);
TH1F *histPDPCA(0), *histPDEFoam(0), *histPDEFoamErr(0), *histPDEFoamSig(0), *histKNN(0), *histHm(0);
TH1F *histFi(0), *histFiG(0), *histFiB(0), *histLD(0), *histNn(0),*histNnbfgs(0),*histNnbnn(0), *histNnC(0), *histNnT(0), *histBdt(0), *histBdtG(0), *histBdtD(0);
TH1F *histRf(0), *histSVMG(0), *histSVMP(0), *histSVML(0), *histFDAMT(0), *histFDAGA(0), *histCat(0), *histPBdt(0);
if (Use["Likelihood"]) histLk = new TH1F( "MVA_Likelihood", "MVA_Likelihood", nbin, -1, 1 );
if (Use["LikelihoodD"]) histLkD = new TH1F( "MVA_LikelihoodD", "MVA_LikelihoodD", nbin, -1, 0.9999 );
if (Use["LikelihoodPCA"]) histLkPCA = new TH1F( "MVA_LikelihoodPCA", "MVA_LikelihoodPCA", nbin, -1, 1 );
if (Use["LikelihoodKDE"]) histLkKDE = new TH1F( "MVA_LikelihoodKDE", "MVA_LikelihoodKDE", nbin, -0.00001, 0.99999 );
if (Use["LikelihoodMIX"]) histLkMIX = new TH1F( "MVA_LikelihoodMIX", "MVA_LikelihoodMIX", nbin, 0, 1 );
if (Use["PDERS"]) histPD = new TH1F( "MVA_PDERS", "MVA_PDERS", nbin, 0, 1 );
if (Use["PDERSD"]) histPDD = new TH1F( "MVA_PDERSD", "MVA_PDERSD", nbin, 0, 1 );
if (Use["PDERSPCA"]) histPDPCA = new TH1F( "MVA_PDERSPCA", "MVA_PDERSPCA", nbin, 0, 1 );
if (Use["KNN"]) histKNN = new TH1F( "MVA_KNN", "MVA_KNN", nbin, 0, 1 );
if (Use["HMatrix"]) histHm = new TH1F( "MVA_HMatrix", "MVA_HMatrix", nbin, -0.95, 1.55 );
if (Use["Fisher"]) histFi = new TH1F( "MVA_Fisher", "MVA_Fisher", nbin, -4, 4 );
if (Use["FisherG"]) histFiG = new TH1F( "MVA_FisherG", "MVA_FisherG", nbin, -1, 1 );
if (Use["BoostedFisher"]) histFiB = new TH1F( "MVA_BoostedFisher", "MVA_BoostedFisher", nbin, -2, 2 );
if (Use["LD"]) histLD = new TH1F( "MVA_LD", "MVA_LD", nbin, -2, 2 );
if (Use["MLP"]) histNn = new TH1F( "MVA_MLP", "MVA_MLP", nbin, -1.25, 1.5 );
if (Use["MLPBFGS"]) histNnbfgs = new TH1F( "MVA_MLPBFGS", "MVA_MLPBFGS", nbin, -1.25, 1.5 );
if (Use["MLPBNN"]) histNnbnn = new TH1F( "MVA_MLPBNN", "MVA_MLPBNN", nbin, -1.25, 1.5 );
if (Use["CFMlpANN"]) histNnC = new TH1F( "MVA_CFMlpANN", "MVA_CFMlpANN", nbin, 0, 1 );
if (Use["TMlpANN"]) histNnT = new TH1F( "MVA_TMlpANN", "MVA_TMlpANN", nbin, -1.3, 1.3 );
if (Use["BDT"]) histBdt = new TH1F( "MVA_BDT", "MVA_BDT", nbin, -0.8, 0.8 );
if (Use["BDTD"]) histBdtD = new TH1F( "MVA_BDTD", "MVA_BDTD", nbin, -0.8, 0.8 );
if (Use["BDTG"]) histBdtG = new TH1F( "MVA_BDTG", "MVA_BDTG", nbin, -1.0, 1.0 );
if (Use["RuleFit"]) histRf = new TH1F( "MVA_RuleFit", "MVA_RuleFit", nbin, -2.0, 2.0 );
if (Use["SVM_Gauss"]) histSVMG = new TH1F( "MVA_SVM_Gauss", "MVA_SVM_Gauss", nbin, 0.0, 1.0 );
if (Use["SVM_Poly"]) histSVMP = new TH1F( "MVA_SVM_Poly", "MVA_SVM_Poly", nbin, 0.0, 1.0 );
if (Use["SVM_Lin"]) histSVML = new TH1F( "MVA_SVM_Lin", "MVA_SVM_Lin", nbin, 0.0, 1.0 );
if (Use["FDA_MT"]) histFDAMT = new TH1F( "MVA_FDA_MT", "MVA_FDA_MT", nbin, -2.0, 3.0 );
if (Use["FDA_GA"]) histFDAGA = new TH1F( "MVA_FDA_GA", "MVA_FDA_GA", nbin, -2.0, 3.0 );
if (Use["Category"]) histCat = new TH1F( "MVA_Category", "MVA_Category", nbin, -2., 2. );
if (Use["Plugin"]) histPBdt = new TH1F( "MVA_PBDT", "MVA_BDT", nbin, -0.8, 0.8 );
// PDEFoam also returns per-event error, fill in histogram, and also fill significance
if (Use["PDEFoam"]) {
histPDEFoam = new TH1F( "MVA_PDEFoam", "MVA_PDEFoam", nbin, 0, 1 );
histPDEFoamErr = new TH1F( "MVA_PDEFoamErr", "MVA_PDEFoam error", nbin, 0, 1 );
histPDEFoamSig = new TH1F( "MVA_PDEFoamSig", "MVA_PDEFoam significance", nbin, 0, 10 );
}
// book example histogram for probability (the other methods are done similarly)
TH1F *probHistFi(0), *rarityHistFi(0);
if (Use["Fisher"]) {
probHistFi = new TH1F( "MVA_Fisher_Proba", "MVA_Fisher_Proba", nbin, 0, 1 );
rarityHistFi = new TH1F( "MVA_Fisher_Rarity", "MVA_Fisher_Rarity", nbin, 0, 1 );
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fname = "/tmp/chasco/ORIGINAL//Data_MuEG2011B_1.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
else {
input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
//
// prepare the tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
TTree* BigTree = (TTree*)input->Get("data");
TFile *tmp = new TFile( "tmp.root","RECREATE" );
TTree* theTree = BigTree->CopyTree("((cat == 1) + (cat == 2))*(ln==0)*(Cosmic==0)*(fabs(Mass_Z - 91.18)<10)*(Pt_Z>30)*(DeltaPhi_metjet>0.5)*(Pt_J1 < 30)*(pfMEToverPt_Z > 0.4)*(pfMEToverPt_Z < 1.8)*((Pt_Jet_btag_CSV_max > 20)*(btag_CSV_max < 0.244) + (1-(Pt_Jet_btag_CSV_max > 20)))*(sqrt(pow(dilepPROJLong + 1.25*recoilPROJLong + 0.0*uncertPROJLong,2)*(dilepPROJLong + 1.25*recoilPROJLong + 0.0*uncertPROJLong > 0) + 1.0*pow(dilepPROJPerp + 1.25*recoilPROJPerp + 0.0*uncertPROJPerp,2)*(dilepPROJPerp + 1.25*recoilPROJPerp + 0.0*uncertPROJPerp > 0)) > 45.0)");
std::cout << "--- Select signal sample" << std::endl;
Float_t userVar1, userVar2;
// theTree->SetBranchAddress( "var1", &userVar1 );
// theTree->SetBranchAddress( "var2", &userVar2 );
// theTree->SetBranchAddress( "var3", &var3 );
// theTree->SetBranchAddress( "var4", &var4 );
theTree->SetBranchAddress( " Z_rapidity_z", &Z_rapidity_z);
theTree->SetBranchAddress( " THRUST_2D", &THRUST_2D);
theTree->SetBranchAddress( " L1_L2_cosangle", &L1_L2_cosangle);
theTree->SetBranchAddress( " TransMass_ZH150_uncl", &TransMass_ZH150_uncl);
theTree->SetBranchAddress( " TransMass_ZH150", &TransMass_ZH150);
theTree->SetBranchAddress( " DeltaPhi_ZH", &DeltaPhi_ZH);
theTree->SetBranchAddress( " DeltaPhi_ZH_uncl", &DeltaPhi_ZH_uncl);
theTree->SetBranchAddress( " CMAngle", &CMAngle);
theTree->SetBranchAddress( " CS_cosangle", &CS_cosangle);
// efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(9); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0){
std::cout << "--- ... Processing event: " << ievt << std::endl;
}
theTree->GetEntry(ievt);
var1 = userVar1 + userVar2;
var2 = userVar1 - userVar2;
if (ievt <20){
// test the twodifferent Reader::EvaluateMVA functions
// access via registered variables compared to access via vector<float>
// vecVar[0]=var1;
// vecVar[1]=var2;
// vecVar[2]=var3;
// vecVar[3]=var4;
vecVar[0]=Z_rapidity_z;
vecVar[1]=THRUST_2D;
vecVar[2]=L1_L2_cosangle;
vecVar[3]=TransMass_ZH150_uncl;
vecVar[4]=TransMass_ZH150;
vecVar[5]=DeltaPhi_ZH;
vecVar[6]=DeltaPhi_ZH_uncl;
vecVar[7]=CMAngle;
vecVar[8]=CS_cosangle;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString mName = it->first + " method";
Double_t mva1 = reader->EvaluateMVA( mName);
Double_t mva2 = reader->EvaluateMVA( vecVar, mName);
if (mva1 != mva2) {
std::cout << "++++++++++++++ ERROR in "<< mName <<", comparing different EvaluateMVA results val1=" << mva1 << " val2="<<mva2<<std::endl;
}
}
}
// now test that the inputs do matter
TRandom3 rand(0);
// vecVar[0]=rand.Rndm();
// vecVar[1]=rand.Rndm();
// vecVar[2]=rand.Rndm();
// vecVar[3]=rand.Rndm();
vecVar[0]=rand.Rndm();
vecVar[1]=rand.Rndm();
vecVar[2]=rand.Rndm();
vecVar[3]=rand.Rndm();
vecVar[4]=rand.Rndm();
vecVar[5]=rand.Rndm();
vecVar[6]=rand.Rndm();
vecVar[7]=rand.Rndm();
vecVar[8]=rand.Rndm();
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString mName = it->first + " method";
Double_t mva1 = reader->EvaluateMVA( mName);
Double_t mva2 = reader->EvaluateMVA( vecVar, mName);
if (mva1 == mva2) {
std::cout << "++++++++++++++ ERROR in "<< mName <<", obtaining idnetical output for different inputs" <<std::endl;
}
}
}
}
//
// return the MVAs and fill to histograms
//
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
if (Use["Likelihood" ]) histLk ->Fill( reader->EvaluateMVA( "Likelihood method" ) );
if (Use["LikelihoodD" ]) histLkD ->Fill( reader->EvaluateMVA( "LikelihoodD method" ) );
if (Use["LikelihoodPCA"]) histLkPCA ->Fill( reader->EvaluateMVA( "LikelihoodPCA method" ) );
if (Use["LikelihoodKDE"]) histLkKDE ->Fill( reader->EvaluateMVA( "LikelihoodKDE method" ) );
if (Use["LikelihoodMIX"]) histLkMIX ->Fill( reader->EvaluateMVA( "LikelihoodMIX method" ) );
if (Use["PDERS" ]) histPD ->Fill( reader->EvaluateMVA( "PDERS method" ) );
if (Use["PDERSD" ]) histPDD ->Fill( reader->EvaluateMVA( "PDERSD method" ) );
if (Use["PDERSPCA" ]) histPDPCA ->Fill( reader->EvaluateMVA( "PDERSPCA method" ) );
if (Use["KNN" ]) histKNN ->Fill( reader->EvaluateMVA( "KNN method" ) );
if (Use["HMatrix" ]) histHm ->Fill( reader->EvaluateMVA( "HMatrix method" ) );
if (Use["Fisher" ]) histFi ->Fill( reader->EvaluateMVA( "Fisher method" ) );
if (Use["FisherG" ]) histFiG ->Fill( reader->EvaluateMVA( "FisherG method" ) );
if (Use["BoostedFisher"]) histFiB ->Fill( reader->EvaluateMVA( "BoostedFisher method" ) );
if (Use["LD" ]) histLD ->Fill( reader->EvaluateMVA( "LD method" ) );
if (Use["MLP" ]) histNn ->Fill( reader->EvaluateMVA( "MLP method" ) );
if (Use["MLPBFGS" ]) histNnbfgs ->Fill( reader->EvaluateMVA( "MLPBFGS method" ) );
if (Use["MLPBNN" ]) histNnbnn ->Fill( reader->EvaluateMVA( "MLPBNN method" ) );
if (Use["CFMlpANN" ]) histNnC ->Fill( reader->EvaluateMVA( "CFMlpANN method" ) );
if (Use["TMlpANN" ]) histNnT ->Fill( reader->EvaluateMVA( "TMlpANN method" ) );
if (Use["BDT" ]) histBdt ->Fill( reader->EvaluateMVA( "BDT method" ) );
if (Use["BDTD" ]) histBdtD ->Fill( reader->EvaluateMVA( "BDTD method" ) );
if (Use["BDTG" ]) histBdtG ->Fill( reader->EvaluateMVA( "BDTG method" ) );
if (Use["RuleFit" ]) histRf ->Fill( reader->EvaluateMVA( "RuleFit method" ) );
if (Use["SVM_Gauss" ]) histSVMG ->Fill( reader->EvaluateMVA( "SVM_Gauss method" ) );
if (Use["SVM_Poly" ]) histSVMP ->Fill( reader->EvaluateMVA( "SVM_Poly method" ) );
if (Use["SVM_Lin" ]) histSVML ->Fill( reader->EvaluateMVA( "SVM_Lin method" ) );
if (Use["FDA_MT" ]) histFDAMT ->Fill( reader->EvaluateMVA( "FDA_MT method" ) );
if (Use["FDA_GA" ]) histFDAGA ->Fill( reader->EvaluateMVA( "FDA_GA method" ) );
if (Use["Category" ]) histCat ->Fill( reader->EvaluateMVA( "Category method" ) );
if (Use["Plugin" ]) histPBdt ->Fill( reader->EvaluateMVA( "P_BDT method" ) );
// retrieve also per-event error
if (Use["PDEFoam"]) {
Double_t val = reader->EvaluateMVA( "PDEFoam method" );
Double_t err = reader->GetMVAError();
histPDEFoam ->Fill( val );
histPDEFoamErr->Fill( err );
histPDEFoamSig->Fill( val/err );
}
// retrieve probability instead of MVA output
if (Use["Fisher"]) {
probHistFi ->Fill( reader->GetProba ( "Fisher method" ) );
rarityHistFi->Fill( reader->GetRarity( "Fisher method" ) );
}
}
// get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
//
// write histograms
//
TFile *target = new TFile( "TMVApp.root","RECREATE" );
if (Use["Likelihood" ]) histLk ->Write();
if (Use["LikelihoodD" ]) histLkD ->Write();
if (Use["LikelihoodPCA"]) histLkPCA ->Write();
if (Use["LikelihoodKDE"]) histLkKDE ->Write();
if (Use["LikelihoodMIX"]) histLkMIX ->Write();
if (Use["PDERS" ]) histPD ->Write();
if (Use["PDERSD" ]) histPDD ->Write();
if (Use["PDERSPCA" ]) histPDPCA ->Write();
if (Use["KNN" ]) histKNN ->Write();
if (Use["HMatrix" ]) histHm ->Write();
if (Use["Fisher" ]) histFi ->Write();
if (Use["FisherG" ]) histFiG ->Write();
if (Use["BoostedFisher"]) histFiB ->Write();
if (Use["LD" ]) histLD ->Write();
if (Use["MLP" ]) histNn ->Write();
if (Use["MLPBFGS" ]) histNnbfgs ->Write();
if (Use["MLPBNN" ]) histNnbnn ->Write();
if (Use["CFMlpANN" ]) histNnC ->Write();
if (Use["TMlpANN" ]) histNnT ->Write();
if (Use["BDT" ]) histBdt ->Write();
if (Use["BDTD" ]) histBdtD ->Write();
if (Use["BDTG" ]) histBdtG ->Write();
if (Use["RuleFit" ]) histRf ->Write();
if (Use["SVM_Gauss" ]) histSVMG ->Write();
if (Use["SVM_Poly" ]) histSVMP ->Write();
if (Use["SVM_Lin" ]) histSVML ->Write();
if (Use["FDA_MT" ]) histFDAMT ->Write();
if (Use["FDA_GA" ]) histFDAGA ->Write();
if (Use["Category" ]) histCat ->Write();
if (Use["Plugin" ]) histPBdt ->Write();
// write also error and significance histos
if (Use["PDEFoam"]) { histPDEFoam->Write(); histPDEFoamErr->Write(); histPDEFoamSig->Write(); }
// write also probability hists
if (Use["Fisher"]) { if (probHistFi != 0) probHistFi->Write(); if (rarityHistFi != 0) rarityHistFi->Write(); }
target->Close();
std::cout << "--- Created root file: \"TMVApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void TMVAMulticlassApplication( TString myMethodList = "" )
{
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 1;
Use["BDTG"] = 1;
Use["FDA_GA"] = 0;
Use["PDEFoam"] = 0;
//---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAMulticlassApplication" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " " << std::endl;
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// create a set of variables and declare them to the reader
// - the variable names must corresponds in name and type to
// those given in the weight file(s) that you use
Float_t var1, var2, var3, var4;
reader->AddVariable( "var1", &var1 );
reader->AddVariable( "var2", &var2 );
reader->AddVariable( "var3", &var3 );
reader->AddVariable( "var4", &var4 );
// book the MVA methods
TString dir = "dataset/weights/";
TString prefix = "TMVAMulticlass";
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// book output histograms
UInt_t nbin = 100;
TH1F *histMLP_signal(0), *histBDTG_signal(0), *histFDAGA_signal(0), *histPDEFoam_signal(0);
if (Use["MLP"])
histMLP_signal = new TH1F( "MVA_MLP_signal", "MVA_MLP_signal", nbin, 0., 1.1 );
if (Use["BDTG"])
histBDTG_signal = new TH1F( "MVA_BDTG_signal", "MVA_BDTG_signal", nbin, 0., 1.1 );
if (Use["FDA_GA"])
histFDAGA_signal = new TH1F( "MVA_FDA_GA_signal", "MVA_FDA_GA_signal", nbin, 0., 1.1 );
if (Use["PDEFoam"])
histPDEFoam_signal = new TH1F( "MVA_PDEFoam_signal", "MVA_PDEFoam_signal", nbin, 0., 1.1 );
TFile *input(0);
TString fname = "./tmva_example_multiple_background.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
if (!input) {
std::cout << "ERROR: could not open data file, please generate example data first!" << std::endl;
exit(1);
}
std::cout << "--- TMVAMulticlassApp : Using input file: " << input->GetName() << std::endl;
// prepare the tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
TTree* theTree = (TTree*)input->Get("TreeS");
std::cout << "--- Select signal sample" << std::endl;
theTree->SetBranchAddress( "var1", &var1 );
theTree->SetBranchAddress( "var2", &var2 );
theTree->SetBranchAddress( "var3", &var3 );
theTree->SetBranchAddress( "var4", &var4 );
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0){
std::cout << "--- ... Processing event: " << ievt << std::endl;
}
theTree->GetEntry(ievt);
if (Use["MLP"])
histMLP_signal->Fill((reader->EvaluateMulticlass( "MLP method" ))[0]);
if (Use["BDTG"])
histBDTG_signal->Fill((reader->EvaluateMulticlass( "BDTG method" ))[0]);
if (Use["FDA_GA"])
histFDAGA_signal->Fill((reader->EvaluateMulticlass( "FDA_GA method" ))[0]);
if (Use["PDEFoam"])
histPDEFoam_signal->Fill((reader->EvaluateMulticlass( "PDEFoam method" ))[0]);
}
// get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
TFile *target = new TFile( "TMVAMulticlassApp.root","RECREATE" );
if (Use["MLP"])
histMLP_signal->Write();
if (Use["BDTG"])
histBDTG_signal->Write();
if (Use["FDA_GA"])
histFDAGA_signal->Write();
if (Use["PDEFoam"])
histPDEFoam_signal->Write();
target->Close();
std::cout << "--- Created root file: \"TMVMulticlassApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << std::endl << std::endl;
}
void TMVAClassificationApplication_TX(TString myMethodList = "" , TString iFileName = "", TString sampleLocation = "", TString outputLocation = "")
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// 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;
//
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
std::cout << std::endl;
std::cout << "==> Start TMVAClassificationApplication" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader("!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t var1, var2, var3, var4, var5, var6, var7, var8, var9, var10, var11, var12, var13, var14, var15, var16, var17, var18, var19, var20, var21, var22, var23, var24, var25, var26, var27, var28, var29;
//reader->AddVariable( "Alt$(jet_pt_singleLepCalc[0],0)", &var1);
//reader->AddVariable( "Alt$(jet_pt_singleLepCalc[1],0)", &var2 );
//reader->AddVariable( "Alt$(jet_pt_singleLepCalc[2],0)", &var3 );
reader->AddVariable( "Alt$(bJetPt_CATopoCalc[0],0)", &var4 );
reader->AddVariable( "Alt$(bJetPt_CATopoCalc[1],0)", &var5 );
//reader->AddVariable( "corr_met_singleLepCalc", &var6 );
//reader->AddVariable( "muon_1_pt_singleLepCalc", &var7 );
//reader->AddVariable( "nBJets_CATopoCalc", &var8 );
//reader->AddVariable( "nSelJets_CommonCalc", &var9 );
//reader->AddVariable( "LeptonJet_DeltaR_LjetsTopoCalcNew", &var10);
reader->AddVariable( "Mevent_LjetsTopoCalcNew", &var11);
//reader->AddVariable( "W_Pt_LjetsTopoCalcNew", &var12 );
reader->AddVariable( "Jet1Jet2_Pt_LjetsTopoCalcNew", &var13 );
//reader->AddVariable( "BestTop_LjetsTopoCalcNew", &var14 );
//reader->AddVariable( "BTagTopMass_LjetsTopoCalcNew", &var15 );
//reader->AddVariable( "Alt$(CAHEPTopJetMass_JetSubCalc[0],0)", &var16 );
//reader->AddVariable( "Alt$(CAWCSVMSubJets_JetSubCalc[0],0)", &var17 );
//reader->AddVariable( "Alt$(CAWCSVLSubJets_JetSubCalc[0],0)", &var18 );
reader->AddVariable( "Alt$(CAWJetPt_JetSubCalc[0],0)", &var19 );
reader->AddVariable( "Alt$(CAWJetMass_JetSubCalc[0],0)", &var20 );
//reader->AddVariable( "Alt$(CAHEPTopJetMass_JetSubCalc[1],0)", &var21 );
//reader->AddVariable( "Hz_LjetsTopoCalcNew", &var22 );
//reader->AddVariable( "Centrality_LjetsTopoCalcNew", &var23 );
reader->AddVariable( "SqrtsT_LjetsTopoCalcNew", &var24 );
reader->AddVariable( "CAMindrBMass_CATopoCalc", &var28 );
reader->AddVariable( "minDRCAtoB_CATopoCalc", &var29 );
//reader->AddVariable( "HT2prime_LjetsTopoCalcNew", &var25 );
reader->AddVariable( "HT2_LjetsTopoCalcNew", &var26 );
//reader->AddVariable( "dphiLepMet_LjetsTopoCalcNew", &var27 );
// Spectator variables declared in the training have to be added to the reader, too
// Float_t spec1,spec2;
// reader->AddSpectator( "spec1 := var1*2", &spec1 );
// reader->AddSpectator( "spec2 := var1*3", &spec2 );
// Float_t Category_cat1, Category_cat2, Category_cat3;
// if (Use["Category"]){
// // Add artificial spectators for distinguishing categories
// reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
// reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
// reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
// }
// --- Book the MVA methods
// Book method(s)
TString weightFileName = "weights/TMVAClassification_BDT.weights";
reader->BookMVA("BDT method", weightFileName+".xml" );
// Book output histograms
UInt_t nbin = 100;
TH1F *histBdt(0);
histBdt = new TH1F( "MVA_BDT_TX", "MVA_BDT_TX", nbin, -1.0, 1.0);
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fileName = iFileName;
TString fname = sampleLocation+"/";
fname += fileName;
TString oFileName = fileName;
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
std::cout << "--- Select signal sample" << std::endl;
TTree* theTree = (TTree*)input->Get("ljmet");
gSystem->mkdir( outputLocation );
TFile *target = new TFile( outputLocation+"/"+oFileName,"RECREATE" );
TTree *newTree = theTree->CloneTree();
Float_t BDT;
TBranch *branchBDT = newTree->Branch("__BDT_TX__",&BDT,"__BDT_TX__/F");
std::vector<Double_t> *vecVar1;
std::vector<Double_t> *vecVar4;
std::vector<Double_t> *vecVar16;
std::vector<Int_t> *vecVar17;
std::vector<Int_t> *vecVar18;
std::vector<Double_t> *vecVar19;
std::vector<Double_t> *vecVar20;
Int_t *intVar5, *intVar8, *intVar9;
Double_t *dVar2, *dVar3, *dVar6, *dVar7, *dVar10, *dVar11, *dVar12, *dVar13, *dVar14, *dVar15, *dVar22, *dVar23, *dVar24, dVar25, *dVar26, *dVar27, *dVar28, *dVar29;
theTree->SetBranchAddress( "jet_pt_singleLepCalc", &vecVar1);
theTree->SetBranchAddress( "bJetPt_CATopoCalc", &vecVar4 );
theTree->SetBranchAddress( "corr_met_singleLepCalc", &dVar6 );
theTree->SetBranchAddress( "muon_1_pt_singleLepCalc", &dVar7 );
theTree->SetBranchAddress( "nBJets_CATopoCalc", &intVar8 );
theTree->SetBranchAddress( "nSelJets_CommonCalc", &intVar9 );
theTree->SetBranchAddress( "LeptonJet_DeltaR_LjetsTopoCalcNew", &dVar10);
theTree->SetBranchAddress( "Mevent_LjetsTopoCalcNew", &dVar11);
theTree->SetBranchAddress( "W_Pt_LjetsTopoCalcNew", &dVar12 );
theTree->SetBranchAddress( "Jet1Jet2_Pt_LjetsTopoCalcNew", &dVar13 );
theTree->SetBranchAddress( "BestTop_LjetsTopoCalcNew", &dVar14 );
theTree->SetBranchAddress( "BTagTopMass_LjetsTopoCalcNew", &dVar15 );
theTree->SetBranchAddress( "CAHEPTopJetMass_JetSubCalc", &vecVar16 );
theTree->SetBranchAddress( "CAWCSVMSubJets_JetSubCalc", &vecVar17 );
theTree->SetBranchAddress( "CAWCSVLSubJets_JetSubCalc", &vecVar18 );
theTree->SetBranchAddress( "CAWJetPt_JetSubCalc", &vecVar19 );
theTree->SetBranchAddress( "CAWJetMass_JetSubCalc", &vecVar20 );
theTree->SetBranchAddress( "Hz_LjetsTopoCalcNew", &dVar22 );
theTree->SetBranchAddress( "Centrality_LjetsTopoCalcNew", &dVar23 );
theTree->SetBranchAddress( "SqrtsT_LjetsTopoCalcNew", &dVar24 );
theTree->SetBranchAddress( "HT2prime_LjetsTopoCalcNew", &dVar25 );
theTree->SetBranchAddress( "HT2_LjetsTopoCalcNew", &dVar26 );
theTree->SetBranchAddress( "dphiLepMet_LjetsTopoCalcNew", &dVar27 );
theTree->SetBranchAddress( "CAMindrBMass_CATopoCalc", &dVar28 );
theTree->SetBranchAddress( "minDRCAtoB_CATopoCalc", &dVar29 );
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
theTree->GetEntry(ievt);
if(vecVar1->size()>0){
var1 = vecVar1->at(0);
}
if(vecVar1->size()>1){
var2 = vecVar1->at(1);
}
if(vecVar1->size()>2){
var3 = vecVar1->at(2);
}
if(vecVar4->size()>0){
var4 = vecVar4->at(0);
}
if(vecVar4->size()>1){
var5 = vecVar4->at(1);
}
var6 = dVar6;
var7 = dVar7;
var8 = intVar8;
var9 = intVar9;
var10 = dVar10;
var11 = dVar11;
var12 = dVar12;
var13 = dVar13;
var14 = dVar14;
var15 = dVar15;
if(vecVar16->size()>0){
var16 = vecVar16->at(0);
}
else{
var16 = 0;
}
if(vecVar17->size()>0){
var17 = vecVar17->at(0);
}
else{
var18 = 0;
}
if(vecVar19->size()>0){
var19 = vecVar19->at(0);
}
else{
var19 = 0;
}
if(vecVar20->size()>0){
var20 = vecVar20->at(0);
}
else{
var20 = 0;
}
if(vecVar16->size()>1){
var21 = vecVar16->at(1);
}
else{
var21 = 0;
}
var22 = dVar22;
var23 = dVar23;
var24 = dVar24;
var25 = dVar25;
var26 = dVar26;
var27 = dVar27;
var28 = dVar28;
var29 = dVar29; // --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
BDT = reader->EvaluateMVA( "BDT method");
histBdt->Fill(BDT);
branchBDT->Fill();
}
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
// --- Write histograms
newTree->Write("",TObject::kOverwrite);
target->Close();
std::cout << "--- Created root file: \""<<oFileName<<"\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << endl << std::endl;
}
void DYPtZ_HF_BDTCut( TString myMethodList = "" )
{
#ifdef __CINT__
gROOT->ProcessLine( ".O0" ); // turn off optimization in CINT
#endif
//---------------------------------------------------------------
// 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 using this
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
Use["Plugin"] = 0;
Use["Category"] = 0;
Use["SVM_Gauss"] = 0;
Use["SVM_Poly"] = 0;
Use["SVM_Lin"] = 0;
std::cout << std::endl;
std::cout << "==> Start DYPtZ_HF_BDTCut" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod
<< "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
std::cout << it->first << " ";
}
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// Create a set of variables and declare them to the reader
// - the variable names MUST corresponds in name and type to those given in the weight file(s) used
Float_t Hmass, Emumass;
Float_t Hpt, Zpt;
Float_t CSV0, CSV1;
Float_t DeltaPhiHV, DetaJJ;
Int_t nJets, eventFlavor, Naj;
Float_t BDTvalue, Trigweight, B2011PUweight, A2011PUweight, btag2CSF, MET;
Float_t alpha_j, qtb1, jetPhi0, jetPhi1, jetEta0, jetEta1, Zphi, Hphi;
Float_t Ht, EvntShpCircularity, jetCHF0, jetCHF1;
Float_t EtaStandDev, lep_pfCombRelIso0, lep_pfCombRelIso1, EvntShpIsotropy;
Float_t lep0pt, lep1pt, UnweightedEta, DphiJJ, RMS_eta, EvntShpSphericity;
Float_t PtbalZH, EventPt, AngleEMU, Centrality, EvntShpAplanarity;
Float_t UnweightedEta, lep0pt;
Int_t naJets, nSV;
Float_t Mte, Mtmu, dPhiHMET, Dphiemu, delRjj, delRemu, DphiZMET, DeltaPhijetMETmin;
Float_t MassEleb0, DphiEleMET, PtbalMETH,dphiEleMET, dEtaJJ, dphiZMET, ScalarSumPt;
Float_t ZmassSVD, AngleHemu, ProjVisT, topMass, topPt, ZmassSVDnegSol, Mt, Zmass, ZmassNegInclu;
Float_t dphiEMU, dphiZMET;
reader->AddVariable( "Hmass", &Hmass );
//reader->AddVariable( "Naj", &Naj );
reader->AddVariable( "CSV0", &CSV0 );
reader->AddVariable( "Emumass", &Emumass );
reader->AddVariable( "DeltaPhiHV", &DeltaPhiHV );
reader->AddVariable( "Mt", &Mt );
reader->AddVariable( "dPhiHMET", &dPhiHMET );
reader->AddVariable( "dphiEMU := abs(Dphiemu)", &dphiEMU );
reader->AddVariable( "dphiZMET:=abs(DphiZMET)", &dphiZMET );
reader->AddVariable( "PtbalMETH", &PtbalMETH );
reader->AddVariable( "EtaStandDev", &EtaStandDev );
reader->AddVariable( "jetCHF0", &jetCHF0 );
reader->AddVariable( "ProjVisT", &ProjVisT );
// Spectator variables declared in the training have to be added to the reader, too
// reader->AddSpectator( "UnweightedEta", &UnweightedEta );
// reader->AddSpectator( "lep0pt", &lep0pt );
/* Float_t Category_cat1, Category_cat2, Category_cat3;
if (Use["Category"]){
// Add artificial spectators for distinguishing categories
reader->AddSpectator( "Category_cat1 := var3<=0", &Category_cat1 );
reader->AddSpectator( "Category_cat2 := (var3>0)&&(var4<0)", &Category_cat2 );
reader->AddSpectator( "Category_cat3 := (var3>0)&&(var4>=0)", &Category_cat3 );
}
*/
// --- Book the MVA methods
TString dir = "weights/";
TString prefix = "TMVAClassification";
// Book method(s)
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// Book output histograms
TH1F* hCHFb0_OpenSelection= new TH1F ("hCHFb0_OpenSelection", "charged Hadron Energy Fraction b1", 40, 0.0, 1.2);
TH1F* hCHFb1_OpenSelection= new TH1F ("hCHFb1_OpenSelection", "charged Hadron Energy Fraction b2", 40, 0.0, 1.2);
TH1F* hPtjj_OpenSelection= new TH1F ("hPtjj_OpenSelection","Pt of two b jets with highest CSV ", 50, 0.0, 400);
TH1F* hPtmumu_OpenSelection= new TH1F ("hPtmumu_OpenSelection","Pt of two muons with highest pt ", 50, 0.0, 400);
TH1F* hPtbalZH_OpenSelection= new TH1F ("hPtbalZH_OpenSelection", "Pt balance of Z and H", 40, -80, 80);
TH1F* hPtmu0_OpenSelection= new TH1F ("hPtmu0_OpenSelection","Pt of muon with highest pt ", 30, 0.0, 300);
TH1F* hPtmu1_OpenSelection= new TH1F ("hPtmu1_OpenSelection","Pt of muon with second highest pt ", 30, 0.0, 300);
TH1F* hPFRelIsomu0_OpenSelection= new TH1F ("hPFRelIsomu0_OpenSelection", "PF Rel Iso of muon with highest Pt", 40, 0., 0.2);
TH1F* hPFRelIsomu1_OpenSelection= new TH1F ("hPFRelIsomu1_OpenSelection", "PF Rel Iso of muon with second highest Pt", 40, 0., 0.2);
TH1F* hCSV0_OpenSelection= new TH1F ("hCSV0_OpenSelection","Jet with highest CSV ", 40, 0, 1.5);
TH1F* hCSV1_OpenSelection= new TH1F ("hCSV1_OpenSelection","Jet with second highest CSV ", 40, 0, 1.5);
TH1F* hdphiVH_OpenSelection= new TH1F ("hdphiVH_OpenSelection","Delta phi between Z and Higgs ", 50, -0.1, 4.5);
TH1F* hdetaJJ_OpenSelection= new TH1F ("hdetaJJ_OpenSelection","Delta eta between two jets ", 60, -4, 4);
TH1F* hNjets_OpenSelection= new TH1F ("hNjets_OpenSelection", "Number of Jets", 13, -2.5, 10.5);
TH1F* hMjj_OpenSelection = new TH1F ("hMjj_OpenSelection", "Invariant Mass of two Jets ", 50, 0, 300);
TH1F* hMmumu_OpenSelection = new TH1F ("hMmumu_OpenSelection", "Invariant Mass of two muons ", 75, 0, 200);
TH1F* hRMSeta_OpenSelection= new TH1F ("hRMSeta_OpenSelection", "RMS Eta", 30, 0, 3);
TH1F* hStaDeveta_OpenSelection= new TH1F ("hStaDeveta_OpenSelection", "Standard Deviation Eta", 30, 0, 3);
TH1F* hUnweightedEta_OpenSelection= new TH1F ("hUnweightedEta_OpenSelection", "Unweighted Eta ", 50, 0, 15);
TH1F* hdphiJJ_vect_OpenSelection= new TH1F ("hdphiJJ_vect_OpenSelection", "Delta phi between two jets", 30, -3.5, 4);
TH1F* hCircularity_OpenSelection= new TH1F("hCircularity_OpenSelection","EventShapeVariables circularity", 30, 0.0, 1.2);
TH1F* hHt_OpenSelection= new TH1F("hHt_OpenSelection","scalar sum of pt of four particles", 50, 0.0, 500);
TH1F* hCentrality_OpenSelection= new TH1F ("hCentrality_OpenSelection", "Centrality", 40, 0.0, 0.8);
TH1F* hEventPt_OpenSelection= new TH1F ("hEventPt_OpenSelection", "Pt of HV system", 50, 0.0, 100);
TH1F* hAngleEMU_OpenSelection= new TH1F ("hAngleEMU_OpenSelection", "AngleEMU between H and Z", 45, 0, 4.5);
TH1F* hSphericity_OpenSelection= new TH1F ("hSphericity_OpenSelection", "EventShapeVariables sphericity", 50, 0.0, 1);
TH1F* hAplanarity_OpenSelection= new TH1F ("hAplanarity_OpenSelection", "EventShapeVariables Aplanarity", 50, -0.1, .4);
TH1F* hIsotropy_OpenSelection= new TH1F ("hIsotropy_OpenSelection", "EventShapeVariables isotropy", 30, 0.0, 1.3);
TH2F* hDphiDetajj_OpenSelection= new TH2F ("hDphiDetajj_OpenSelection", "#Delta#phi vs #Delta#eta JJ", 25, -5, 5, 25, -5, 5);
TH1F* hMtmu_OpenSelection= new TH1F ("hMtmu_OpenSelection", "Mt with respect to Muon", 101, -0.1, 200);
TH1F* hMte_OpenSelection= new TH1F ("hMte_OpenSelection", "Mt with respect to Electron", 101, -0.1, 200);
TH1F* hdPhiHMET_OpenSelection= new TH1F ("hdPhiHMET_OpenSelection", "Delta phi between MET and Higgs", 50, -0.1, 4.5);
TH1F* hDphiemu_OpenSelection= new TH1F ("hDphiemu_OpenSelection", "Delta phi between e and muon", 50, -3.5, 4.5);
TH1F* hdelRjj_OpenSelection= new TH1F ("hdelRjj_OpenSelection", "Delta R jj", 55, 0, 5.5);
TH1F* hdelRemu_OpenSelection= new TH1F ("hdelRemu_OpenSelection", "Delta R emu", 55, 0, 5.5);
TH1F* hDphiZMET_OpenSelection= new TH1F ("hDphiZMET_OpenSelection", "Delta phi between Z and MET", 71, -3.5, 4);
TH1F* hDeltaPhijetMETmin_OpenSelection= new TH1F ("hDeltaPhijetMETmin_OpenSelection", "Delta phi between MET and nearest jet", 50, -0.1, 4.5);
TH1F* hAngleHemu_OpenSelection= new TH1F ("hAngleHemu_OpenSelection", "Angle between H and Z", 30, 0, 3.5);
TH1F* hProjVisT_OpenSelection= new TH1F ("hProjVisT_OpenSelection", "Transverse componenet of Projection of Z onto bisector", 80, 0, 200);
TH1F* htopMass_OpenSelection= new TH1F ("htopMass_OpenSelection", "Top Mass single lepton", 100, 75, 375);
TH1F* htopPt_OpenSelection= new TH1F ("htopPt_OpenSelection", "Pt of Top", 125, 0, 250);
TH1F* hVMt_OpenSelection= new TH1F ("hVMt_OpenSelection", "VMt", 75, 0, 150);
TH1F* hZmassSVD_OpenSelection= new TH1F ("hZmassSVD_OpenSelection", "Invariant Mass of two Leptons corrected SVD", 75, 0, 150);
TH1F* hZmassSVDnegSol_OpenSelection= new TH1F ("hZmassSVDnegSol_OpenSelection", "Invariant Mass of two Leptons corrected SVD", 100, -50, 200);
TH1F* hZmass_OpenSelection= new TH1F ("hZmass_OpenSelection", "Zmass ", 5, 0, 150);
TH1F* hZmassNegInclu_OpenSelection= new TH1F ("hZmassNegInclu_OpenSelection", "Invariant Mass of two Leptons corrected SVD", 100, -50, 200);
TTree *treeWithBDT = new TTree("treeWithBDT","Tree wiht BDT output");
treeWithBDT->SetDirectory(0);
treeWithBDT->Branch("nJets",&nJets, "nJets/I");
treeWithBDT->Branch("naJets",&naJets, "naJets/I");
treeWithBDT->Branch("eventFlavor",&eventFlavor, "eventFlavor/I");
treeWithBDT->Branch("CSV0",&CSV0, "CSV0/F");
treeWithBDT->Branch("CSV1",&CSV1, "CSV1/F");
treeWithBDT->Branch("Emumass",&Emumass, "Emumass/F");
treeWithBDT->Branch("Hmass",&Hmass, "Hmass/F");
treeWithBDT->Branch("DeltaPhiHV",&DeltaPhiHV, "DeltaPhiHV/F");
treeWithBDT->Branch("Hpt",&Hpt, "Hpt/F");
treeWithBDT->Branch("Zpt",&Zpt, "Zpt/F");
treeWithBDT->Branch("lep0pt",&lep0pt, "lep0pt/F");
treeWithBDT->Branch("Ht",&Ht, "Ht/F");
treeWithBDT->Branch("EtaStandDev",&EtaStandDev, "EtaStandDev/F");
treeWithBDT->Branch("UnweightedEta",&UnweightedEta, "UnweightedEta/F");
treeWithBDT->Branch("EvntShpCircularity",&EvntShpCircularity, "EvntShpCircularity/F");
treeWithBDT->Branch("alpha_j",&alpha_j, "alpha_j/F");
treeWithBDT->Branch("qtb1",&qtb1, "qtb1/F");
treeWithBDT->Branch("nSV",&nSV, "nSV/I");
treeWithBDT->Branch("Trigweight",&Trigweight, "Trigweight/F");
treeWithBDT->Branch("B2011PUweight",&B2011PUweight, "B2011PUweight/F");
treeWithBDT->Branch("A2011PUweight",&A2011PUweight, "A2011PUweight/F");
treeWithBDT->Branch("btag2CSF",&btag2CSF, "btag2CSF/F");
treeWithBDT->Branch("DetaJJ",&DetaJJ, "DetaJJ/F");
treeWithBDT->Branch("jetCHF0",&jetCHF0, "jetCHF0/F");
treeWithBDT->Branch("jetCHF1",&jetCHF1, "jetCHF1/F");
treeWithBDT->Branch("jetPhi0",&jetPhi0, "jetPhi0/F");
treeWithBDT->Branch("jetPhi1",&jetPhi1, "jetPhi1/F");
treeWithBDT->Branch("jetEta0",&jetEta0, "jetEta0/F");
treeWithBDT->Branch("jetEta1",&jetEta1, "jetEta1/F");
treeWithBDT->Branch("lep1pt",&lep1pt, "lep1pt/F");
treeWithBDT->Branch("lep_pfCombRelIso0",&lep_pfCombRelIso0, "lep_pfCombRelIso0/F");
treeWithBDT->Branch("lep_pfCombRelIso1",&lep_pfCombRelIso1, "lep_pfCombRelIso1/F");
treeWithBDT->Branch("DphiJJ",&DphiJJ, "DphiJJ/F");
treeWithBDT->Branch("RMS_eta",&RMS_eta, "RMS_eta/F");
treeWithBDT->Branch("PtbalZH",&PtbalZH, "PtbalZH/F");
treeWithBDT->Branch("EventPt",&EventPt, "EventPt/F");
treeWithBDT->Branch("AngleEMU",&AngleEMU, "AngleEMU/F");
treeWithBDT->Branch("Centrality",&Centrality, "Centrality/F");
treeWithBDT->Branch("MET",&MET, "MET/F");
treeWithBDT->Branch("EvntShpAplanarity",&EvntShpAplanarity, "EvntShpAplanarity/F");
treeWithBDT->Branch("EvntShpSphericity",&EvntShpSphericity, "EvntShpSphericity/F");
treeWithBDT->Branch("EvntShpIsotropy",&EvntShpIsotropy, "EvntShpIsotropy/F");
treeWithBDT->Branch("Zphi",&Zphi, "Zphi/F");
treeWithBDT->Branch("Hphi",&Hphi, "Hphi/F");
treeWithBDT->Branch("Mte",&Mte, "Mte/F");
treeWithBDT->Branch("Mtmu",&Mtmu, "Mtmu/F");
treeWithBDT->Branch("dPhiHMET",&dPhiHMET, "dPhiHMET/F");
treeWithBDT->Branch("Dphiemu",&Dphiemu, "Dphiemu/F");
treeWithBDT->Branch("delRjj",&delRjj, "delRjj/F");
treeWithBDT->Branch("delRemu",&delRemu, "delRemu/F");
treeWithBDT->Branch("DphiZMET",&DphiZMET, "DphiZMET/F");
treeWithBDT->Branch("DeltaPhijetMETmin",&DeltaPhijetMETmin, "DeltaPhijetMETmin/F");
treeWithBDT->Branch("BDTvalue",&BDTvalue, "BDTvalue/F");
treeWithBDT->Branch("AngleHemu",&AngleHemu, "AngleHemu/F");
treeWithBDT->Branch("ProjVisT",&ProjVisT, "ProjVisT/F");
treeWithBDT->Branch("topMass",&topMass, "topMass/F");
treeWithBDT->Branch("topPt",&topPt, "topPt/F");
treeWithBDT->Branch("ZmassSVD",&ZmassSVD, "ZmassSVD/F");
treeWithBDT->Branch("ZmassSVDnegSol",&ZmassSVDnegSol, "ZmassSVDnegSol/F");
treeWithBDT->Branch("Zmass",&Zmass, "Zmass/F");
treeWithBDT->Branch("ZmassNegInclu",&ZmassNegInclu, "ZmassNegInclu/F");
treeWithBDT->Branch("topMass",&topMass, "topMass/F");
treeWithBDT->Branch("Mt",&Mt, "Mt/F");
UInt_t nbin = 15;
TH1F *histLk(0), *histLkD(0), *histLkPCA(0), *histLkKDE(0), *histLkMIX(0), *histPD(0), *histPDD(0);
TH1F *histPDPCA(0), *histPDEFoam(0), *histPDEFoamErr(0), *histPDEFoamSig(0), *histKNN(0), *histHm(0);
TH1F *histFi(0), *histFiG(0), *histFiB(0), *histLD(0), *histNn(0),*histNnbfgs(0),*histNnbnn(0);
TH1F *histNnC(0), *histNnT(0), *histBdt(0), *histBdtG(0), *histBdtD(0), *histRf(0), *histSVMG(0);
TH1F *histSVMP(0), *histSVML(0), *histFDAMT(0), *histFDAGA(0), *histCat(0), *histPBdt(0);
if (Use["Likelihood"]) histLk = new TH1F( "MVA_Likelihood", "MVA_Likelihood", nbin, -1, 1 );
if (Use["LikelihoodD"]) histLkD = new TH1F( "MVA_LikelihoodD", "MVA_LikelihoodD", nbin, -1, 0.9999 );
if (Use["LikelihoodPCA"]) histLkPCA = new TH1F( "MVA_LikelihoodPCA", "MVA_LikelihoodPCA", nbin, -1, 1 );
if (Use["LikelihoodKDE"]) histLkKDE = new TH1F( "MVA_LikelihoodKDE", "MVA_LikelihoodKDE", nbin, -0.00001, 0.99999 );
if (Use["LikelihoodMIX"]) histLkMIX = new TH1F( "MVA_LikelihoodMIX", "MVA_LikelihoodMIX", nbin, 0, 1 );
if (Use["PDERS"]) histPD = new TH1F( "MVA_PDERS", "MVA_PDERS", nbin, 0, 1 );
if (Use["PDERSD"]) histPDD = new TH1F( "MVA_PDERSD", "MVA_PDERSD", nbin, 0, 1 );
if (Use["PDERSPCA"]) histPDPCA = new TH1F( "MVA_PDERSPCA", "MVA_PDERSPCA", nbin, 0, 1 );
if (Use["KNN"]) histKNN = new TH1F( "MVA_KNN", "MVA_KNN", nbin, 0, 1 );
if (Use["HMatrix"]) histHm = new TH1F( "MVA_HMatrix", "MVA_HMatrix", nbin, -0.95, 1.55 );
if (Use["Fisher"]) histFi = new TH1F( "MVA_Fisher", "MVA_Fisher", nbin, -4, 4 );
if (Use["FisherG"]) histFiG = new TH1F( "MVA_FisherG", "MVA_FisherG", nbin, -1, 1 );
if (Use["BoostedFisher"]) histFiB = new TH1F( "MVA_BoostedFisher", "MVA_BoostedFisher", nbin, -2, 2 );
if (Use["LD"]) histLD = new TH1F( "MVA_LD", "MVA_LD", nbin, -2, 2 );
if (Use["MLP"]) histNn = new TH1F( "MVA_MLP", "MVA_MLP", nbin, -1.25, 1.5 );
if (Use["MLPBFGS"]) histNnbfgs = new TH1F( "MVA_MLPBFGS", "MVA_MLPBFGS", nbin, -1.25, 1.5 );
if (Use["MLPBNN"]) histNnbnn = new TH1F( "MVA_MLPBNN", "MVA_MLPBNN", nbin, -1.25, 1.5 );
if (Use["CFMlpANN"]) histNnC = new TH1F( "MVA_CFMlpANN", "MVA_CFMlpANN", nbin, 0, 1 );
if (Use["TMlpANN"]) histNnT = new TH1F( "MVA_TMlpANN", "MVA_TMlpANN", nbin, -1.3, 1.3 );
if (Use["BDT"]) {
histMattBdt = new TH1F( "Matt_BDT", "Matt_BDT", 15, -1.1, 0.35 );
histTMVABdt = new TH1F( "TMVA_BDT", "TMVA_BDT", 36, -1.0, -0.1 );
}
if (Use["BDTD"]) histBdtD = new TH1F( "MVA_BDTD", "MVA_BDTD", nbin, -0.8, 0.8 );
if (Use["BDTG"]) histBdtG = new TH1F( "MVA_BDTG", "MVA_BDTG", nbin, -1.0, 1.0 );
if (Use["RuleFit"]) histRf = new TH1F( "MVA_RuleFit", "MVA_RuleFit", nbin, -2.0, 2.0 );
if (Use["SVM_Gauss"]) histSVMG = new TH1F( "MVA_SVM_Gauss", "MVA_SVM_Gauss", nbin, 0.0, 1.0 );
if (Use["SVM_Poly"]) histSVMP = new TH1F( "MVA_SVM_Poly", "MVA_SVM_Poly", nbin, 0.0, 1.0 );
if (Use["SVM_Lin"]) histSVML = new TH1F( "MVA_SVM_Lin", "MVA_SVM_Lin", nbin, 0.0, 1.0 );
if (Use["FDA_MT"]) histFDAMT = new TH1F( "MVA_FDA_MT", "MVA_FDA_MT", nbin, -2.0, 3.0 );
if (Use["FDA_GA"]) histFDAGA = new TH1F( "MVA_FDA_GA", "MVA_FDA_GA", nbin, -2.0, 3.0 );
if (Use["Category"]) histCat = new TH1F( "MVA_Category", "MVA_Category", nbin, -2., 2. );
if (Use["Plugin"]) histPBdt = new TH1F( "MVA_PBDT", "MVA_BDT", nbin, -0.8, 0.8 );
// PDEFoam also returns per-event error, fill in histogram, and also fill significance
if (Use["PDEFoam"]) {
histPDEFoam = new TH1F( "MVA_PDEFoam", "MVA_PDEFoam", nbin, 0, 1 );
histPDEFoamErr = new TH1F( "MVA_PDEFoamErr", "MVA_PDEFoam error", nbin, 0, 1 );
histPDEFoamSig = new TH1F( "MVA_PDEFoamSig", "MVA_PDEFoam significance", nbin, 0, 10 );
}
// Book example histogram for probability (the other methods are done similarly)
TH1F *probHistFi(0), *rarityHistFi(0);
if (Use["Fisher"]) {
probHistFi = new TH1F( "MVA_Fisher_Proba", "MVA_Fisher_Proba", nbin, 0, 1 );
rarityHistFi = new TH1F( "MVA_Fisher_Rarity", "MVA_Fisher_Rarity", nbin, 0, 1 );
}
// Prepare input tree (this must be replaced by your data source)
// in this example, there is a toy tree with signal and one with background events
// we'll later on use only the "signal" events for the test in this example.
//
TFile *input(0);
TString fname = "/home/hep/wilken/taus/CMSSW_4_4_2_patch8/src/UserCode/wilken/V21/DY_PtZ.root";
double lumi = 4.457;
Double_t DY_PtZ_weight = lumi/(lumiZJH/2.0); //WW_TuneZ2_7TeV_pythia6_tauola
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassificationApp : Using input file: " << input->GetName() << std::endl;
// --- Event loop
// Prepare the event tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
//
std::cout << "--- Select signal sample" << std::endl;
TTree* theTree = (TTree*)input->Get("BDT_btree");
theTree->SetBranchAddress( "Hmass", &Hmass );
theTree->SetBranchAddress( "Emumass", &Emumass );
theTree->SetBranchAddress( "Hpt", &Hpt );
theTree->SetBranchAddress( "Zpt", &Zpt );
theTree->SetBranchAddress( "CSV0", &CSV0 );
theTree->SetBranchAddress( "CSV1", &CSV1 );
theTree->SetBranchAddress( "DeltaPhiHV", &DeltaPhiHV );
theTree->SetBranchAddress( "DetaJJ", &DetaJJ );
theTree->SetBranchAddress( "UnweightedEta", &UnweightedEta );
theTree->SetBranchAddress( "lep0pt", &lep0pt );
theTree->SetBranchAddress( "Ht", &Ht );
theTree->SetBranchAddress( "EvntShpCircularity", &EvntShpCircularity );
theTree->SetBranchAddress( "nJets", &nJets );
theTree->SetBranchAddress( "naJets",&naJets);
theTree->SetBranchAddress( "nSV", &nSV );
theTree->SetBranchAddress( "lep1pt", &lep1pt );
theTree->SetBranchAddress( "lep0pt", &lep0pt );
theTree->SetBranchAddress( "EtaStandDev", &EtaStandDev );
theTree->SetBranchAddress( "UnweightedEta", &UnweightedEta );
theTree->SetBranchAddress( "jetCHF0", &jetCHF0 );
theTree->SetBranchAddress( "jetCHF1", &jetCHF1 );
theTree->SetBranchAddress( "lep_pfCombRelIso0", &lep_pfCombRelIso0 );
theTree->SetBranchAddress( "lep_pfCombRelIso1", &lep_pfCombRelIso1 );
theTree->SetBranchAddress( "DphiJJ", &DphiJJ );
theTree->SetBranchAddress( "RMS_eta", &RMS_eta );
theTree->SetBranchAddress( "PtbalZH", &PtbalZH );
theTree->SetBranchAddress( "EventPt", &EventPt );
theTree->SetBranchAddress( "AngleEMU", &AngleEMU );
theTree->SetBranchAddress( "Centrality", &Centrality );
theTree->SetBranchAddress( "EvntShpAplanarity", &EvntShpAplanarity );
theTree->SetBranchAddress( "EvntShpSphericity", &EvntShpSphericity );
theTree->SetBranchAddress( "EvntShpIsotropy", &EvntShpIsotropy );
theTree->SetBranchAddress( "Trigweight", &Trigweight );
theTree->SetBranchAddress( "B2011PUweight", &B2011PUweight );
theTree->SetBranchAddress( "A2011PUweight", &A2011PUweight );
theTree->SetBranchAddress( "btag2CSF", &btag2CSF );
theTree->SetBranchAddress( "MET", &MET );
theTree->SetBranchAddress( "Mte" , &Mte );
theTree->SetBranchAddress( "Mtmu" , &Mtmu );
theTree->SetBranchAddress( "dPhiHMET" , &dPhiHMET );
theTree->SetBranchAddress( "DeltaPhijetMETmin" , &DeltaPhijetMETmin );
theTree->SetBranchAddress( "delRjj" , &delRjj );
theTree->SetBranchAddress( "delRemu" , &delRemu );
theTree->SetBranchAddress( "DphiZMET" , &DphiZMET );
theTree->SetBranchAddress( "Dphiemu" , &Dphiemu );
theTree->SetBranchAddress( "DeltaPhijetMETmin" , &DeltaPhijetMETmin );
theTree->SetBranchAddress("AngleHemu",&AngleHemu);
theTree->SetBranchAddress("ProjVisT",&ProjVisT);
theTree->SetBranchAddress("topMass",&topMass);
theTree->SetBranchAddress("topPt",&topPt);
theTree->SetBranchAddress("ZmassSVD",&ZmassSVD);
theTree->SetBranchAddress("ZmassSVDnegSol",&ZmassSVDnegSol);
theTree->SetBranchAddress("Zmass",&Zmass);
theTree->SetBranchAddress("ZmassNegInclu",&ZmassNegInclu);
theTree->SetBranchAddress("topMass",&topMass);
theTree->SetBranchAddress("Mt",&Mt);
theTree->SetBranchAddress( "eventFlavor", &eventFlavor );
// Efficiency calculator for cut method
Int_t nSelCutsGA = 0;
Double_t effS = 0.7;
TTree* TMVATree = (TTree*)input->Get("TMVA_tree");
int NumInTree = theTree->GetEntries();
int NumberTMVAtree = TMVATree->GetEntries();
DY_PtZ_weight = DY_PtZ_weight* ( NumInTree /float(NumberTMVAtree)) ;
std::vector<Float_t> vecVar(4); // vector for EvaluateMVA tests
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
int Nevents = 0, NpassBDT = 0;
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
Nevents++;
if (ievt%1000 == 0) std::cout << "--- ... Processing event: " << ievt << std::endl;
theTree->GetEntry(ievt);
// var1 = userVar1 + userVar2;
// var2 = userVar1 - userVar2;
// --- Return the MVA outputs and fill into histograms
if (Use["CutsGA"]) {
// Cuts is a special case: give the desired signal efficienciy
Bool_t passed = reader->EvaluateMVA( "CutsGA method", effS );
if (passed) nSelCutsGA++;
}
if (Use["Likelihood" ]) histLk ->Fill( reader->EvaluateMVA( "Likelihood method" ) );
if (Use["LikelihoodD" ]) histLkD ->Fill( reader->EvaluateMVA( "LikelihoodD method" ) );
if (Use["LikelihoodPCA"]) histLkPCA ->Fill( reader->EvaluateMVA( "LikelihoodPCA method" ) );
if (Use["LikelihoodKDE"]) histLkKDE ->Fill( reader->EvaluateMVA( "LikelihoodKDE method" ) );
if (Use["LikelihoodMIX"]) histLkMIX ->Fill( reader->EvaluateMVA( "LikelihoodMIX method" ) );
if (Use["PDERS" ]) histPD ->Fill( reader->EvaluateMVA( "PDERS method" ) );
if (Use["PDERSD" ]) histPDD ->Fill( reader->EvaluateMVA( "PDERSD method" ) );
if (Use["PDERSPCA" ]) histPDPCA ->Fill( reader->EvaluateMVA( "PDERSPCA method" ) );
if (Use["KNN" ]) histKNN ->Fill( reader->EvaluateMVA( "KNN method" ) );
if (Use["HMatrix" ]) histHm ->Fill( reader->EvaluateMVA( "HMatrix method" ) );
if (Use["Fisher" ]) histFi ->Fill( reader->EvaluateMVA( "Fisher method" ) );
if (Use["FisherG" ]) histFiG ->Fill( reader->EvaluateMVA( "FisherG method" ) );
if (Use["BoostedFisher"]) histFiB ->Fill( reader->EvaluateMVA( "BoostedFisher method" ) );
if (Use["LD" ]) histLD ->Fill( reader->EvaluateMVA( "LD method" ) );
if (Use["MLP" ]) histNn ->Fill( reader->EvaluateMVA( "MLP method" ) );
if (Use["MLPBFGS" ]) histNnbfgs ->Fill( reader->EvaluateMVA( "MLPBFGS method" ) );
if (Use["MLPBNN" ]) histNnbnn ->Fill( reader->EvaluateMVA( "MLPBNN method" ) );
if (Use["CFMlpANN" ]) histNnC ->Fill( reader->EvaluateMVA( "CFMlpANN method" ) );
if (Use["TMlpANN" ]) histNnT ->Fill( reader->EvaluateMVA( "TMlpANN method" ) );
if (Use["BDT" ]) {
BDTvalue = reader->EvaluateMVA( "BDT method" );
histMattBdt ->Fill( BDTvalue,DY_PtZ_weight*Trigweight*B2011PUweight );
histTMVABdt ->Fill( BDTvalue,DY_PtZ_weight*Trigweight*B2011PUweight );
}
if (Use["BDTD" ]) histBdtD ->Fill( reader->EvaluateMVA( "BDTD method" ) );
if (Use["BDTG" ]) histBdtG ->Fill( reader->EvaluateMVA( "BDTG method" ) );
if (Use["RuleFit" ]) histRf ->Fill( reader->EvaluateMVA( "RuleFit method" ) );
if (Use["SVM_Gauss" ]) histSVMG ->Fill( reader->EvaluateMVA( "SVM_Gauss method" ) );
if (Use["SVM_Poly" ]) histSVMP ->Fill( reader->EvaluateMVA( "SVM_Poly method" ) );
if (Use["SVM_Lin" ]) histSVML ->Fill( reader->EvaluateMVA( "SVM_Lin method" ) );
if (Use["FDA_MT" ]) histFDAMT ->Fill( reader->EvaluateMVA( "FDA_MT method" ) );
if (Use["FDA_GA" ]) histFDAGA ->Fill( reader->EvaluateMVA( "FDA_GA method" ) );
if (Use["Category" ]) histCat ->Fill( reader->EvaluateMVA( "Category method" ) );
if (Use["Plugin" ]) histPBdt ->Fill( reader->EvaluateMVA( "P_BDT method" ) );
// Retrieve also per-event error
if (Use["PDEFoam"]) {
Double_t val = reader->EvaluateMVA( "PDEFoam method" );
Double_t err = reader->GetMVAError();
histPDEFoam ->Fill( val );
histPDEFoamErr->Fill( err );
if (err>1.e-50) histPDEFoamSig->Fill( val/err );
}
// Retrieve probability instead of MVA output
if (Use["Fisher"]) {
probHistFi ->Fill( reader->GetProba ( "Fisher method" ) );
rarityHistFi->Fill( reader->GetRarity( "Fisher method" ) );
}
// std::cout << "Ht is "<< Ht << endl;
if(BDTvalue>-1.50){
NpassBDT++;
hMjj_OpenSelection->Fill(Hmass,DY_PtZ_weight*Trigweight*B2011PUweight );
hMmumu_OpenSelection->Fill(Emumass,DY_PtZ_weight*Trigweight*B2011PUweight );
hPtjj_OpenSelection->Fill(Hpt,DY_PtZ_weight*Trigweight*B2011PUweight );
hPtmumu_OpenSelection->Fill(Zpt,DY_PtZ_weight*Trigweight*B2011PUweight );
hCSV0_OpenSelection->Fill(CSV0,DY_PtZ_weight*Trigweight*B2011PUweight );
hCSV1_OpenSelection->Fill(CSV1,DY_PtZ_weight*Trigweight*B2011PUweight );
hdphiVH_OpenSelection->Fill(DeltaPhiHV,DY_PtZ_weight*Trigweight*B2011PUweight );
hdetaJJ_OpenSelection->Fill(DetaJJ,DY_PtZ_weight*Trigweight*B2011PUweight );
hUnweightedEta_OpenSelection->Fill(UnweightedEta,DY_PtZ_weight*Trigweight*B2011PUweight );
hPtmu0_OpenSelection->Fill(lep0pt,DY_PtZ_weight*Trigweight*B2011PUweight );
hHt_OpenSelection->Fill(Ht,DY_PtZ_weight*Trigweight*B2011PUweight );
hCircularity_OpenSelection->Fill(EvntShpCircularity,DY_PtZ_weight*Trigweight*B2011PUweight );
hCHFb0_OpenSelection->Fill(jetCHF0, DY_PtZ_weight*Trigweight*B2011PUweight );
hCHFb1_OpenSelection->Fill(jetCHF1, DY_PtZ_weight*Trigweight*B2011PUweight );
hPtbalZH_OpenSelection->Fill(PtbalZH, DY_PtZ_weight*Trigweight*B2011PUweight );
hPtmu1_OpenSelection->Fill(lep1pt, DY_PtZ_weight*Trigweight*B2011PUweight );
hPFRelIsomu0_OpenSelection->Fill(lep_pfCombRelIso0, DY_PtZ_weight*Trigweight*B2011PUweight );
hPFRelIsomu1_OpenSelection->Fill(lep_pfCombRelIso1, DY_PtZ_weight*Trigweight*B2011PUweight );
hNjets_OpenSelection->Fill(nJets, DY_PtZ_weight*Trigweight*B2011PUweight );
hRMSeta_OpenSelection->Fill(RMS_eta, DY_PtZ_weight*Trigweight*B2011PUweight );
hStaDeveta_OpenSelection->Fill(EtaStandDev, DY_PtZ_weight*Trigweight*B2011PUweight );
hdphiJJ_vect_OpenSelection->Fill(DphiJJ, DY_PtZ_weight*Trigweight*B2011PUweight );
hCentrality_OpenSelection->Fill(Centrality, DY_PtZ_weight*Trigweight*B2011PUweight );
hEventPt_OpenSelection->Fill(EventPt, DY_PtZ_weight*Trigweight*B2011PUweight );
hAngleEMU_OpenSelection->Fill(AngleEMU, DY_PtZ_weight*Trigweight*B2011PUweight );
hSphericity_OpenSelection->Fill(EvntShpSphericity, DY_PtZ_weight*Trigweight*B2011PUweight );
hAplanarity_OpenSelection->Fill(EvntShpAplanarity, DY_PtZ_weight*Trigweight*B2011PUweight );
hIsotropy_OpenSelection->Fill(EvntShpIsotropy, DY_PtZ_weight*Trigweight*B2011PUweight );
hDphiDetajj_OpenSelection->Fill(DphiJJ, DetaJJ, DY_PtZ_weight*Trigweight*B2011PUweight );
hMte_OpenSelection->Fill(Mte, DY_PtZ_weight*Trigweight*B2011PUweight );
hMtmu_OpenSelection->Fill(Mtmu, DY_PtZ_weight*Trigweight*B2011PUweight );
hdPhiHMET_OpenSelection->Fill(dPhiHMET, DY_PtZ_weight*Trigweight*B2011PUweight );
hDphiemu_OpenSelection->Fill(DeltaPhijetMETmin, DY_PtZ_weight*Trigweight*B2011PUweight );
hdelRjj_OpenSelection->Fill(delRjj, DY_PtZ_weight*Trigweight*B2011PUweight );
hdelRemu_OpenSelection->Fill(delRemu, DY_PtZ_weight*Trigweight*B2011PUweight );
hDphiZMET_OpenSelection->Fill(DphiZMET, DY_PtZ_weight*Trigweight*B2011PUweight );
hDphiemu_OpenSelection->Fill(Dphiemu, DY_PtZ_weight*Trigweight*B2011PUweight );
hDeltaPhijetMETmin_OpenSelection->Fill(DeltaPhijetMETmin, DY_PtZ_weight*Trigweight*B2011PUweight );
hAngleHemu_OpenSelection->Fill(AngleHemu, DY_PtZ_weight*Trigweight*B2011PUweight );
hProjVisT_OpenSelection->Fill(ProjVisT, DY_PtZ_weight*Trigweight*B2011PUweight );
htopMass_OpenSelection->Fill(topMass, DY_PtZ_weight*Trigweight*B2011PUweight );
htopPt_OpenSelection->Fill(topPt, DY_PtZ_weight*Trigweight*B2011PUweight );
hVMt_OpenSelection->Fill(Mt, DY_PtZ_weight*Trigweight*B2011PUweight );
hZmassSVD_OpenSelection->Fill(ZmassSVD, DY_PtZ_weight*Trigweight*B2011PUweight );
hZmassSVDnegSol_OpenSelection->Fill(ZmassSVDnegSol, DY_PtZ_weight*Trigweight*B2011PUweight );
hZmass_OpenSelection->Fill(Zmass, DY_PtZ_weight*Trigweight*B2011PUweight );
hZmassNegInclu_OpenSelection->Fill(ZmassNegInclu, DY_PtZ_weight*Trigweight*B2011PUweight );
}
treeWithBDT->Fill();
}//end event loop
// Get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
std::cout << "Number of Events: "<< Nevents << " Events passed BDT " << NpassBDT<< endl;
// Get efficiency for cuts classifier
if (Use["CutsGA"]) std::cout << "--- Efficiency for CutsGA method: " << double(nSelCutsGA)/theTree->GetEntries()
<< " (for a required signal efficiency of " << effS << ")" << std::endl;
if (Use["CutsGA"]) {
// test: retrieve cuts for particular signal efficiency
// CINT ignores dynamic_casts so we have to use a cuts-secific Reader function to acces the pointer
TMVA::MethodCuts* mcuts = reader->FindCutsMVA( "CutsGA method" ) ;
if (mcuts) {
std::vector<Double_t> cutsMin;
std::vector<Double_t> cutsMax;
mcuts->GetCuts( 0.7, cutsMin, cutsMax );
std::cout << "--- -------------------------------------------------------------" << std::endl;
std::cout << "--- Retrieve cut values for signal efficiency of 0.7 from Reader" << std::endl;
for (UInt_t ivar=0; ivar<cutsMin.size(); ivar++) {
std::cout << "... Cut: "
<< cutsMin[ivar]
<< " < \""
<< mcuts->GetInputVar(ivar)
<< "\" <= "
<< cutsMax[ivar] << std::endl;
}
std::cout << "--- -------------------------------------------------------------" << std::endl;
}
}
// --- Write histograms
TFile *target = new TFile( "BDTCut_DYPtZ_HF.root","RECREATE" );
if (Use["Likelihood" ]) histLk ->Write();
if (Use["LikelihoodD" ]) histLkD ->Write();
if (Use["LikelihoodPCA"]) histLkPCA ->Write();
if (Use["LikelihoodKDE"]) histLkKDE ->Write();
if (Use["LikelihoodMIX"]) histLkMIX ->Write();
if (Use["PDERS" ]) histPD ->Write();
if (Use["PDERSD" ]) histPDD ->Write();
if (Use["PDERSPCA" ]) histPDPCA ->Write();
if (Use["KNN" ]) histKNN ->Write();
if (Use["HMatrix" ]) histHm ->Write();
if (Use["Fisher" ]) histFi ->Write();
if (Use["FisherG" ]) histFiG ->Write();
if (Use["BoostedFisher"]) histFiB ->Write();
if (Use["LD" ]) histLD ->Write();
if (Use["MLP" ]) histNn ->Write();
if (Use["MLPBFGS" ]) histNnbfgs ->Write();
if (Use["MLPBNN" ]) histNnbnn ->Write();
if (Use["CFMlpANN" ]) histNnC ->Write();
if (Use["TMlpANN" ]) histNnT ->Write();
if (Use["BDT" ]) {
histMattBdt ->Write();
histTMVABdt ->Write();
}
if (Use["BDTD" ]) histBdtD ->Write();
if (Use["BDTG" ]) histBdtG ->Write();
if (Use["RuleFit" ]) histRf ->Write();
if (Use["SVM_Gauss" ]) histSVMG ->Write();
if (Use["SVM_Poly" ]) histSVMP ->Write();
if (Use["SVM_Lin" ]) histSVML ->Write();
if (Use["FDA_MT" ]) histFDAMT ->Write();
if (Use["FDA_GA" ]) histFDAGA ->Write();
if (Use["Category" ]) histCat ->Write();
if (Use["Plugin" ]) histPBdt ->Write();
// Write also error and significance histos
if (Use["PDEFoam"]) { histPDEFoam->Write(); histPDEFoamErr->Write(); histPDEFoamSig->Write(); }
// Write also probability hists
if (Use["Fisher"]) { if (probHistFi != 0) probHistFi->Write(); if (rarityHistFi != 0) rarityHistFi->Write(); }
hCHFb0_OpenSelection->Write();
hCHFb1_OpenSelection->Write();
hPtbalZH_OpenSelection->Write();
hPtmu1_OpenSelection->Write();
hPFRelIsomu0_OpenSelection->Write();
hPFRelIsomu1_OpenSelection->Write();
hMjj_OpenSelection->Write();
hMmumu_OpenSelection->Write();
hPtjj_OpenSelection->Write();
hPtmumu_OpenSelection->Write();
hCSV0_OpenSelection->Write();
hCSV1_OpenSelection->Write();
hdphiVH_OpenSelection->Write();
hdetaJJ_OpenSelection->Write();
hUnweightedEta_OpenSelection->Write();
hPtmu0_OpenSelection->Write();
hCircularity_OpenSelection->Write();
hHt_OpenSelection->Write();
hNjets_OpenSelection->Write();
hRMSeta_OpenSelection->Write();
hStaDeveta_OpenSelection->Write();
hdphiJJ_vect_OpenSelection->Write();
hCentrality_OpenSelection->Write();
hEventPt_OpenSelection->Write();
hAngleEMU_OpenSelection->Write();
hSphericity_OpenSelection->Write();
hAplanarity_OpenSelection->Write();
hIsotropy_OpenSelection->Write();
hDphiDetajj_OpenSelection->Write();
hMtmu_OpenSelection->Write();
hMte_OpenSelection->Write();
hdPhiHMET_OpenSelection->Write();
hDphiemu_OpenSelection->Write();
hdelRjj_OpenSelection->Write();
hdelRemu_OpenSelection->Write();
hDphiZMET_OpenSelection->Write();
hDeltaPhijetMETmin_OpenSelection->Write();
hAngleHemu_OpenSelection->Write();
hProjVisT_OpenSelection->Write();
htopMass_OpenSelection->Write();
htopPt_OpenSelection->Write();
hVMt_OpenSelection->Write();
hZmassSVD_OpenSelection->Write();
hZmassSVDnegSol_OpenSelection->Write();
hZmass_OpenSelection->Write();
hZmassNegInclu_OpenSelection->Write();
treeWithBDT->Write();
target->Close();
delete reader;
hCHFb0_OpenSelection->Delete();
hCHFb1_OpenSelection->Delete();
hPtbalZH_OpenSelection->Delete();
hPtmu1_OpenSelection->Delete();
hPFRelIsomu0_OpenSelection->Delete();
hPFRelIsomu1_OpenSelection->Delete();
hMjj_OpenSelection->Delete();
hMmumu_OpenSelection->Delete();
hPtjj_OpenSelection->Delete();
hPtmumu_OpenSelection->Delete();
hCSV0_OpenSelection->Delete();
hCSV1_OpenSelection->Delete();
hdphiVH_OpenSelection->Delete();
hdetaJJ_OpenSelection->Delete();
hUnweightedEta_OpenSelection->Delete();
hPtmu0_OpenSelection->Delete();
hCircularity_OpenSelection->Delete();
hHt_OpenSelection->Delete();
hNjets_OpenSelection->Delete();
hRMSeta_OpenSelection->Delete();
hStaDeveta_OpenSelection->Delete();
hdphiJJ_vect_OpenSelection->Delete();
hCentrality_OpenSelection->Delete();
hEventPt_OpenSelection->Delete();
hAngleEMU_OpenSelection->Delete();
hSphericity_OpenSelection->Delete();
hAplanarity_OpenSelection->Delete();
hIsotropy_OpenSelection->Delete();
hDphiDetajj_OpenSelection->Delete();
hMtmu_OpenSelection->Delete();
hMte_OpenSelection->Delete();
hdPhiHMET_OpenSelection->Delete();
hDphiemu_OpenSelection->Delete();
hdelRjj_OpenSelection->Delete();
hdelRemu_OpenSelection->Delete();
hDphiZMET_OpenSelection->Delete();
hDeltaPhijetMETmin_OpenSelection->Delete();
hAngleHemu_OpenSelection->Delete();
hProjVisT_OpenSelection->Delete();
htopMass_OpenSelection->Delete();
htopPt_OpenSelection->Delete();
hVMt_OpenSelection->Delete();
hZmassSVD_OpenSelection->Delete();
hZmassSVDnegSol_OpenSelection->Delete();
hZmass_OpenSelection->Delete();
hZmassNegInclu_OpenSelection->Delete();
if (Use["BDT" ]) {
histMattBdt ->Delete();
histTMVABdt ->Delete();
}
treeWithBDT->Delete();
std::cout << "==> DYPtZ_HF_BDTCut is done!" << endl << std::endl;
gROOT->ProcessLine(".q");
}
//------------------------------------------------------------------------------
// MVARead
//------------------------------------------------------------------------------
void MVARead(TString signal, TString filename)
{
TMVA::Reader* reader = new TMVA::Reader("!Color:!Silent");
// float channel;
float metPfType1;
float m2l;
// float njet;
// float nbjet20cmvav2l;
float lep1pt;
float lep2pt;
// float jet1pt;
float jet2pt;
float mtw1;
float dphill;
float dphilep1jet1;
// float dphilep1jet2;
// float dphilmet1;
// float dphilep2jet1;
// float dphilep2jet2;
// float dphilmet2;
// float dphijj;
// float dphijet1met;
// float dphijet2met;
float dphillmet;
float eventW;
float mva;
// reader->AddVariable("channel", &channel);
reader->AddVariable("metPfType1", &metPfType1);
reader->AddVariable("m2l", &m2l);
// reader->AddVariable("njet", &njet);
// reader->AddVariable("nbjet20cmvav2l", &nbjet20cmvav2l);
reader->AddVariable("lep1pt", &lep1pt);
reader->AddVariable("lep2pt", &lep2pt);
// reader->AddVariable("jet1pt", &jet1pt);
reader->AddVariable("jet2pt", &jet2pt);
reader->AddVariable("mtw1", &mtw1);
reader->AddVariable("dphill", &dphill);
reader->AddVariable("dphilep1jet1", &dphilep1jet1);
// reader->AddVariable("dphilep1jet2", &dphilep1jet2);
// reader->AddVariable("dphilmet1", &dphilmet1);
// reader->AddVariable("dphilep2jet1", &dphilep2jet1);
// reader->AddVariable("dphilep2jet2", &dphilep2jet2);
// reader->AddVariable("dphilmet2", &dphilmet2);
// reader->AddVariable("dphijj", &dphijj);
// reader->AddVariable("dphijet1met", &dphijet1met);
// reader->AddVariable("dphijet2met", &dphijet2met);
reader->AddVariable("dphillmet", &dphillmet);
// Book MVA methods
//----------------------------------------------------------------------------
reader->BookMVA("MLP", weightsdir + signal + "_MLP.weights.xml");
// Get MVA response
//----------------------------------------------------------------------------
TH1D* h_mva = new TH1D("h_mva_" + signal, "", 100, -0.05, 1.05);
TFile* input = TFile::Open(inputdir + filename + ".root", "update");
TTree* theTree = (TTree*)input->Get("latino");
TBranch* b_mva = theTree->Branch("mva_" + signal, &mva, "mva/F" );
// theTree->SetBranchAddress("channel", &channel);
theTree->SetBranchAddress("metPfType1", &metPfType1);
theTree->SetBranchAddress("m2l", &m2l);
// theTree->SetBranchAddress("njet", &njet);
// theTree->SetBranchAddress("nbjet20cmvav2l", &nbjet20cmvav2l);
theTree->SetBranchAddress("lep1pt", &lep1pt);
theTree->SetBranchAddress("lep2pt", &lep2pt);
// theTree->SetBranchAddress("jet1pt", &jet1pt);
theTree->SetBranchAddress("jet2pt", &jet2pt);
theTree->SetBranchAddress("mtw1", &mtw1);
theTree->SetBranchAddress("dphill", &dphill);
theTree->SetBranchAddress("dphilep1jet1", &dphilep1jet1);
// theTree->SetBranchAddress("dphilep1jet2", &dphilep1jet2);
// theTree->SetBranchAddress("dphilmet1", &dphilmet1);
// theTree->SetBranchAddress("dphilep2jet1", &dphilep2jet1);
// theTree->SetBranchAddress("dphilep2jet2", &dphilep2jet2);
// theTree->SetBranchAddress("dphilmet2", &dphilmet2);
// theTree->SetBranchAddress("dphijj", &dphijj);
// theTree->SetBranchAddress("dphijet1met", &dphijet1met);
// theTree->SetBranchAddress("dphijet2met", &dphijet2met);
theTree->SetBranchAddress("dphillmet", &dphillmet);
theTree->SetBranchAddress("eventW", &eventW);
Long64_t nentries = theTree->GetEntries();
for (Long64_t ievt=0; ievt<nentries; ievt++) {
theTree->GetEntry(ievt);
mva = reader->EvaluateMVA("MLP");
b_mva->Fill();
// Comentado por Alberto Manjon
//if (njet > 1) h_mva->Fill(mva, eventW);
h_mva->Fill(mva, eventW);
}
// Save
//----------------------------------------------------------------------------
theTree->Write("", TObject::kOverwrite);
input->Close();
TFile* target = TFile::Open(applicationdir + signal + "__" + filename + ".root", "recreate");
h_mva->Write();
target->Close();
h_mva->Delete();
delete reader;
}
void computeBDT(std::string iName="../samples/boostedv-v8_s12-zll-ptz100-v7c_noskim_flatntuple.root",
std::string iWeightFile="weights/TMVAClassificationCategory_BDT_simple_alpha.weights.xml") {
TMVA::Tools::Instance();
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
float jet1QGtagComb = 0.; reader->AddVariable("2*fjet1QGtagSub2+fjet1QGtagSub1",&jet1QGtagComb);
float fjet1QGtagSub1 = 0.; reader->AddVariable("fjet1QGtagSub1",&fjet1QGtagSub1);
float fjet1QGtagSub2 = 0.; reader->AddVariable("fjet1QGtagSub2",&fjet1QGtagSub2);
float fjet1QGtag = 0.; reader->AddVariable("fjet1QGtag",&fjet1QGtag);
float fjet1PullAngle = 0.; reader->AddVariable("fjet1PullAngle",&fjet1PullAngle);
float fjet1Pull = 0.; reader->AddVariable("fjet1Pull",&fjet1Pull);
float fjet1MassTrimmed = 0.; reader->AddVariable("fjet1MassTrimmed",&fjet1MassTrimmed);
float fjet1MassPruned = 0.; reader->AddVariable("fjet1MassPruned",&fjet1MassPruned);
float fjet1MassSDbm1 = 0.; reader->AddVariable("fjet1MassSDbm1",&fjet1MassSDbm1);
float fjet1MassSDb2 = 0.; reader->AddVariable("fjet1MassSDb2",&fjet1MassSDb2);
float fjet1MassSDb0 = 0.; reader->AddVariable("fjet1MassSDb0",&fjet1MassSDb0);
float fjet1QJetVol = 0.; reader->AddVariable("fjet1QJetVol",&fjet1QJetVol);
float fjet1C2b2 = 0.; reader->AddVariable("fjet1C2b2",&fjet1C2b2);
float fjet1C2b1 = 0.; reader->AddVariable("fjet1C2b1",&fjet1C2b1);
float fjet1C2b0p5 = 0.; reader->AddVariable("fjet1C2b0p5",&fjet1C2b0p5);
float fjet1C2b0p2 = 0.; reader->AddVariable("fjet1C2b0p2",&fjet1C2b0p2);
float fjet1C2b0 = 0.; reader->AddVariable("fjet1C2b0",&fjet1C2b0);
float fjet1Tau2 = 0.; reader->AddVariable("fjet1Tau2",&fjet1Tau2);
float fjet1Tau1 = 0.; reader->AddVariable("fjet1Tau1",&fjet1Tau1);
float tau2tau1 = 0.; reader->AddVariable("fjet1Tau2/fjet1Tau1",&tau2tau1);
std::string lJetName = "BDT";
reader->BookMVA(lJetName .c_str(),iWeightFile.c_str());
TFile *lFile = new TFile(iName.c_str());
TTree *lTree = (TTree*) lFile->FindObjectAny("DMSTree");
TString pExpress0 = "2*fjet1QGtagSub2+fjet1QGtagSub1";
TString pExpr0(pExpress0);
TTreeFormula* lFVars0 = new TTreeFormula(pExpr0,pExpr0,lTree);
TString pExpress1 = "fjet1QGtagSub1";
TString pExpr1(pExpress1);
TTreeFormula* lFVars1 = new TTreeFormula(pExpr1,pExpr1,lTree);
TString pExpress2 = "fjet1QGtagSub2";
TString pExpr2(pExpress2);
TTreeFormula* lFVars2 = new TTreeFormula(pExpr2,pExpr2,lTree);
TString pExpress3 = "fjet1QGtag";
TString pExpr3(pExpress3);
TTreeFormula* lFVars3 = new TTreeFormula(pExpr3,pExpr3,lTree);
TString pExpress4 = "fjet1PullAngle";
TString pExpr4(pExpress4);
TTreeFormula* lFVars4 = new TTreeFormula(pExpr4,pExpr4,lTree);
TString pExpress5 = "fjet1Pull";
TString pExpr5(pExpress5);
TTreeFormula* lFVars5 = new TTreeFormula(pExpr5,pExpr5,lTree);
TString pExpress6 = "fjet1MassTrimmed";
TString pExpr6(pExpress6);
TTreeFormula* lFVars6 = new TTreeFormula(pExpr6,pExpr6,lTree);
TString pExpress7 = "fjet1MassPruned";
TString pExpr7(pExpress7);
TTreeFormula* lFVars7 = new TTreeFormula(pExpr7,pExpr7,lTree);
TString pExpress8 = "fjet1MassSDbm1";
TString pExpr8(pExpress8);
TTreeFormula* lFVars8 = new TTreeFormula(pExpr8,pExpr8,lTree);
TString pExpress9 = "fjet1MassSDb2";
TString pExpr9(pExpress9);
TTreeFormula* lFVars9 = new TTreeFormula(pExpr9,pExpr9,lTree);
TString pExpress10 = "fjet1MassSDb0";
TString pExpr10(pExpress10);
TTreeFormula* lFVars10 = new TTreeFormula(pExpr10,pExpr10,lTree);
TString pExpress11 = "fjet1QJetVol";
TString pExpr11(pExpress11);
TTreeFormula* lFVars11 = new TTreeFormula(pExpr11,pExpr11,lTree);
TString pExpress12 = "fjet1C2b2";
TString pExpr12(pExpress12);
TTreeFormula* lFVars12 = new TTreeFormula(pExpr12,pExpr12,lTree);
TString pExpress13 = "fjet1C2b1";
TString pExpr13(pExpress13);
TTreeFormula* lFVars13 = new TTreeFormula(pExpr13,pExpr13,lTree);
TString pExpress14 = "fjet1C2b0p5";
TString pExpr14(pExpress14);
TTreeFormula* lFVars14 = new TTreeFormula(pExpr14,pExpr14,lTree);
TString pExpress15 = "fjet1C2b0p2";
TString pExpr15(pExpress15);
TTreeFormula* lFVars15 = new TTreeFormula(pExpr15,pExpr15,lTree);
TString pExpress16 = "fjet1C2b0";
TString pExpr16(pExpress16);
TTreeFormula* lFVars16 = new TTreeFormula(pExpr16,pExpr16,lTree);
TString pExpress17 = "fjet1Tau2";
TString pExpr17(pExpress17);
TTreeFormula* lFVars17 = new TTreeFormula(pExpr17,pExpr17,lTree);
TString pExpress18 = "fjet1Tau1";
TString pExpr18(pExpress18);
TTreeFormula* lFVars18 = new TTreeFormula(pExpr18,pExpr18,lTree);
TString pExpress19 = "fjet1Tau2/fjet1Tau1";
TString pExpr19(pExpress19);
TTreeFormula* lFVars19 = new TTreeFormula(pExpr19,pExpr19,lTree);
//lTree->SetBranchAddress( "jet1mprune" , &lJP);
//lTree->SetBranchAddress( iVar1.c_str() , &lJT1);
//if(iVar1 != iVar2) lTree->SetBranchAddress( iVar2.c_str() , &lJT2);
int lNEvents = lTree->GetEntries();
TFile *lOFile = new TFile("Output.root","RECREATE");
TTree *lOTree = new TTree("DMSTree","DMSTree");
float lMVA = 0; lOTree->Branch("bdt_all",&lMVA ,"bdt_all/F");
for (Long64_t i0=0; i0<lNEvents;i0++) {
if (i0 % 10000 == 0) std::cout << "--- ... Processing event: " << double(i0)/double(lNEvents) << std::endl;
lTree->GetEntry(i0);
jet1QGtagComb = lFVars0->EvalInstance();
fjet1QGtagSub1 = lFVars1->EvalInstance();
fjet1QGtagSub2 = lFVars2->EvalInstance();
fjet1QGtag = lFVars3->EvalInstance();
fjet1PullAngle = lFVars4->EvalInstance();
fjet1Pull = lFVars5->EvalInstance();
fjet1MassTrimmed = lFVars6->EvalInstance();
fjet1MassPruned = lFVars7->EvalInstance();
fjet1MassSDbm1 = lFVars8->EvalInstance();
fjet1MassSDb2 = lFVars9->EvalInstance();
fjet1MassSDb0 = lFVars10->EvalInstance();
fjet1QJetVol = lFVars11->EvalInstance();
fjet1C2b2 = lFVars12->EvalInstance();
fjet1C2b1 = lFVars13->EvalInstance();
fjet1C2b0p5 = lFVars14->EvalInstance();
fjet1C2b0p2 = lFVars15->EvalInstance();
fjet1C2b0 = lFVars16->EvalInstance();
fjet1Tau2 = lFVars17->EvalInstance();
fjet1Tau1 = lFVars18->EvalInstance();
tau2tau1 = lFVars19->EvalInstance();
lMVA = float(reader->EvaluateMVA(lJetName.c_str()));
lOTree->Fill();
}
lOTree->Write();
lOFile->Close();
delete reader;
}