int main(int argc, char* argv[]) {
if (argc != 3) {
std::cout << " Usage: "
<< " <path to input files>"
<< " <path to output MVA file>"
<< std::endl;
return 1;
}
std::string inPath(argv[1]);
std::string outPath(argv[2]);
std::cout << " -- Input path: " << inPath << std::endl;
std::cout << " -- Output file: " << outPath << std::endl;
// This loads the library
TMVA::Tools::Instance();
// --- Here the preparation phase begins
TString outfileName( outPath );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable("jet1_pt","jet1_pt","", 'D');
// factory->AddVariable("jet2_pt","jet2_pt","", 'D');
factory->AddVariable("dijet_M","dijet_M","", 'D');
factory->AddVariable("dijet_deta","dijet_deta","", 'D');
factory->AddVariable("metnomu_significance","metnomu_significance","",'D');
factory->AddVariable("alljetsmetnomu_mindphi","alljetsmetnomu_mindphi","",'D');
// factory->AddSpectator( "nPhot_presel", "nPhot_presel", "", 'F' );
std::vector<std::string> backgrounds;
backgrounds.push_back("WJetsToLNu_HT-100to200_Tune4C_13TeV-madgraph-tauol");
backgrounds.push_back("WJetsToLNu_HT-200to400_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("WJetsToLNu_HT-400to600_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("WJetsToLNu_HT-600toInf_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("ZJetsToNuNu_HT-100to200_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("ZJetsToNuNu_HT-200to400_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("ZJetsToNuNu_HT-400to600_Tune4C_13TeV-madgraph-tauola");
backgrounds.push_back("ZJetsToNuNu_HT-600toInf_Tune4C_13TeV-madgraph-tauola");
std::vector<std::string> signals;
signals.push_back("VBF_HToInv_M-125_13TeV_powheg-pythia6");
double lumiData = 10000;//in pb-1
for (int i=0; i<signals.size(); i++){
float weight = getNormalisationFactor(lumiData,signals[i]);
TFile* f=TFile::Open(Form("%s/%s.root",inPath.c_str(),signals[i].c_str()));
TTree* sig=(TTree*) f->Get("lightTree/LightTree");
if (!sig)
{
std::cout << "====> ERROR: Sig tree " << signals[i] << " cannot be found" << std::endl;
continue;
}
factory->AddSignalTree ( sig, weight);
}
for (int i=0; i<backgrounds.size(); i++){
float weight = getNormalisationFactor(lumiData,backgrounds[i]);
TFile* f=TFile::Open(Form("%s/%s.root",inPath.c_str(),backgrounds[i].c_str()));
TTree* bkg=(TTree*) f->Get("lightTree/LightTree");
if (!bkg)
{
std::cout << "====> ERROR: Bkg tree " << backgrounds[i] << " cannot be found" << std::endl;
continue;
}
factory->AddBackgroundTree ( bkg, weight);
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts;
TCut mycutb;
//Preselection to get rid of QCD
mycuts = "passtrigger==1 && nvetomuons==0 && nvetoelectrons==0 && metnomuons>140 && abs(jet1_eta)<4.7 && abs(jet2_eta)<4.7 && dijet_M>700 && jet1_eta*jet2_eta<0 && metnomu_significance>4 && alljetsmetnomu_mindphi>2 && jet1_pt>50 && jet2_pt>40";
mycutb = "passtrigger==1 && nvetomuons==0 && nvetoelectrons==0 && metnomuons>140 && abs(jet1_eta)<4.7 && abs(jet2_eta)<4.7 && dijet_M>700 && jet1_eta*jet2_eta<0 && metnomu_significance>4 && alljetsmetnomu_mindphi>2 && jet1_pt>50 && jet2_pt>40";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
// factory->BookMethod( TMVA::Types::kCuts, "Cuts",
// // "!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp[0]=FSmart:VarProp[1]=FSmart:VarProp[2]=FSmart:VarProp[3]=FSmart:VarProp[4]=FSmart:VarProp[5]=FSmart" );
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95:VarProp[0]=FSmart:VarProp[1]=FSmart:VarProp[2]=FSmart:VarProp[3]=FSmart" );
// factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
// "!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=1000:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning");
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void Boost(){
TString outfileName = "boost.root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
factory->AddVariable( "var0", 'F' );
factory->AddVariable( "var1", 'F' );
TFile *input(0);
TString fname = "./data.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- BOOST : Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
else {
gROOT->LoadMacro( "./createData.C");
create_circ(20000);
cout << " created data.root with data and circle arranged in half circles"<<endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
gROOT->cd( outfileName+TString(":/") );
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
factory->PrepareTrainingAndTestTree( "", "",
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
TString fisher="H:!V";
factory->BookMethod( TMVA::Types::kFisher, "Fisher", fisher );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoost", fisher+":Boost_Num=100:Boost_Type=AdaBoost" );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoostLog", fisher+":Boost_Num=100:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=1.0" );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoostLog2", fisher+":Boost_Num=100:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=2.0" );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoostStep", fisher+":Boost_Num=100:Boost_Transform=step:Boost_Type=AdaBoost:Boost_AdaBoostBeta=1.0" );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoostStep2", fisher+":Boost_Num=100:Boost_Transform=step:Boost_Type=AdaBoost:Boost_AdaBoostBeta=1.2" );
factory->BookMethod( TMVA::Types::kFisher, "FisherBoostStep3", fisher+":Boost_Num=100:Boost_Transform=step:Boost_Type=AdaBoost:Boost_AdaBoostBeta=1.5" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void testBDT(){
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
/*
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "testBDT", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// global event weights per tree (see below for setting event-wise weights)
//Double_t signalWeight = 0.003582;
//Double_t backgroundWeight = 0.0269;
Double_t signalWeight = 1;
Double_t backgroundWeight = 1;
TFile *input_sig = TFile::Open( "signal_exclusif.root" );
TFile *input_wz = TFile::Open( "bruit_w_z.root" );
TTree *signal = (TTree*)input_sig->Get("tree");
TTree *background = (TTree*)input_wz->Get("tree");
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
factory->AddVariable("PT_z" , 'F');
factory->AddVariable("ASYM" , 'F');
factory->AddVariable("PHI_lw_b", 'F');
factory->AddVariable("M_top", 'F');
*/
TString outfileName( "bdtTMVA_FCNC_tZ.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "doBDT_FCNC_tZ", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// global event weights per tree (see below for setting event-wise weights)
//Double_t signalWeight = 0.003582;
//Double_t backgroundWeight = 0.0269;
Double_t signalWeight = 1;
Double_t backgroundWeight = 1;
TFile *input_sig = TFile::Open( "proof.root" );
TFile *input_wz = TFile::Open( "proof.root" );
TTree *signal = (TTree*)input_sig->Get("Ttree_FCNCkut");
TTree *background_WZ = (TTree*)input_wz->Get("Ttree_WZ");
/*TTree *background_ZZ = (TTree*)input_wz->Get("Ttree_ZZ");
TTree *background_WW = (TTree*)input_wz->Get("Ttree_WW");
TTree *background_TTbar = (TTree*)input_wz->Get("Ttree_TTbar");
TTree *background_Zjets = (TTree*)input_wz->Get("Ttree_Zjets");
TTree *background_Wjets = (TTree*)input_wz->Get("Ttree_Wjets");
TTree *background_TtW = (TTree*)input_wz->Get("Ttree_TtW");
TTree *background_TbartW = (TTree*)input_wz->Get("Ttree_TbartW");*/
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background_WZ, backgroundWeight );
/*factory->AddBackgroundTree( background_ZZ, backgroundWeight );
factory->AddBackgroundTree( background_WW, backgroundWeight );
factory->AddBackgroundTree( background_TTbar, backgroundWeight );
factory->AddBackgroundTree( background_Zjets, backgroundWeight );
factory->AddBackgroundTree( background_Wjets, backgroundWeight );
factory->AddBackgroundTree( background_TtW, backgroundWeight );
factory->AddBackgroundTree( background_TbartW, backgroundWeight );*/
factory->AddVariable("tree_topMass", 'F');
factory->AddVariable("tree_deltaPhilb", 'F');
factory->AddVariable("tree_asym", 'F');
factory->AddVariable("tree_Zpt", 'F');
// to set weights. The variable must exist in the tree
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=100:nEventsMin=100:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
//void TMVAClassification( TString myMethodList = "" )
void tmvaClassifier( TString myMethodList = "", TString inputDir="~/work/ewkzp2j_5311/ll/", bool minimalTrain=false, bool useQG=false)
{
gSystem->ExpandPathName(inputDir);
TString pf("base_weights");
if(!minimalTrain){
if(useQG) pf="full_weights";
else pf="weights";
}
TMVA::gConfig().GetIONames().fWeightFileDir = inputDir + pf;
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 1; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 1;
Use["FisherCat"] = 0;//added by loic
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 1; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
// TString fname = "./tmva_class_example.root";
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
// std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
// --- Register the training and test trees
TChain *signal = new TChain("ewkzp2j");
TChain *background = new TChain("ewkzp2j");
TSystemDirectory dir(inputDir,inputDir);
TList *files = dir.GetListOfFiles();
if (files) {
TSystemFile *file;
TString fname;
TIter next(files);
while ((file=(TSystemFile*)next())) {
fname = file->GetName();
if(!fname.EndsWith("_summary.root")) continue;
if(fname.Contains("Data")) continue;
if(!fname.Contains("DY")) continue;
bool isSignal(false);
if(fname.Contains("JJ")) { signal->Add(fname); isSignal=true; }
else if(fname.Contains("50toInf") && fname.Contains("DY")) background->Add(fname);
cout << fname << " added as " << (isSignal ? "signal" : "background") << endl;
}
}else{
cout << "[Error] no files found in " << inputDir << endl;
}
cout << "Signal has " << signal->GetEntries() << " raw events" << endl
<< "Background has " << background->GetEntries() << " raw events"<< endl;
// global event weights per tree
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// event-per-event weights per tree
factory->SetBackgroundWeightExpression( "weight/cnorm" );
factory->SetSignalWeightExpression( "weight/cnorm" );
//define variables for the training
if(minimalTrain)
{
factory->AddVariable( "mjj", "M_{jj}" "GeV", 'F' );
factory->AddVariable( "detajj", "#Delta#eta_{jj}", "", 'F' );
factory->AddVariable( "spt", "#Delta_{rel}", "GeV", 'F' );
}
else
{
factory->AddVariable( "mjj", "M_{jj}" "GeV", 'F' );
factory->AddVariable( "detajj", "#Delta#eta_{jj}", "", 'F' );
factory->AddVariable( "setajj", "#Sigma#eta_{j}", "", 'F' );
factory->AddVariable( "eta1", "#eta(1)", "", 'F' );
factory->AddVariable( "eta2", "#eta(2)", "", 'F' );
factory->AddVariable( "pt1", "p_{T}(1)", "GeV", 'F' );
factory->AddVariable( "pt2", "p_{T}(2)", "GeV", 'F' );
factory->AddVariable( "spt", "#Delta_{rel}", "GeV", 'F' );
if(useQG) factory->AddVariable( "qg1", "q/g(1)", "", 'F' );
if(useQG) factory->AddVariable( "qg2", "q/g(2)", "", 'F' );
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
if (Use["FisherCat"]){
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
TMVA::MethodCategory* mcategory = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcategory->AddMethod( "mjj<250", "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat1", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=250&&mjj<350" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0000", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=350&&mjj<450" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0350", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=450&&mjj<550" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0450", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=550&&mjj<750" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0550", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=750&&mjj<1000", "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat0750", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
mcategory->AddMethod( "mjj>=1000" , "mjj:detajj:spt:", TMVA::Types::kFisher, "Fisher_Cat1000", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
}
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:MaxDepth=2" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=25:PruneMethod=CostComplexity:PruneStrength=25.0:VarTransform=Decorrelate");
//"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
std::cout << " ==> Weights are stored in " << TMVA::gConfig().GetIONames().fWeightFileDir << std::endl;
delete factory;
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void Reg(){
TMVA::Tools::Instance();
std::cout << "==> Start TMVARegression" << std::endl;
ifstream myfile;
myfile.open("99per.txt");
ostringstream xcS,xcH,xcP,xcC,xcN;
double xS,xH,xC,xN,xP;
if(myfile.is_open()){
while(!myfile.eof()){
myfile>>xS>>xH>>xC>>xN>>xP;
}
}
xcS<<xS;
xcH<<xH;
xcC<<xC;
xcN<<xN;
xcP<<xP;
//Output file
TString outfileName( "Ex1out_FullW_def.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
//Declaring the factory
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
//Declaring Input Varibles
factory->AddVariable( "Sieie",'F');
factory->AddVariable( "ToE", 'F' );
factory->AddVariable( "isoC",'F' );
factory->AddVariable( "isoN",'F' );
factory->AddVariable( "isoP",'F' );
TString fname = "../../CutTMVATrees_Barrel.root";
input = TFile::Open( fname );
// --- Register the regression tree
TTree *signal = (TTree*)input->Get("t_S");
TTree *background = (TTree*)input->Get("t_B");
//Just Some more settings
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddSignalTree( signal, signalWeight );
factory->AddBackgroundTree( background , backgroundWeight );
TCut mycuts ="";
TCut mycutb ="";
// factory->PrepareTrainingAndTestTree(mycuts,mycutb,"nTrain_Signal=9000:nTrain_Background=9000:nTest_Signal=10000:nTest_Background=10000");
factory->SetBackgroundWeightExpression("weightPT*weightXS");
factory->SetSignalWeightExpression("weightPT*weightXS");
TString methodName = "Cuts_FullsampleW_def";
TString methodOptions ="!H:!V:FitMethod=GA:EffMethod=EffSEl";
methodOptions +=":VarProp[0]=FMin:VarProp[1]=FMin:VarProp[2]=FMin:VarProp[3]=FMin:VarProp[4]=FMin";
methodOptions +=":CutRangeMax[0]="+xcS.str();
methodOptions +=":CutRangeMax[1]="+xcH.str();
methodOptions +=":CutRangeMax[2]="+xcC.str();
methodOptions +=":CutRangeMax[3]="+xcN.str();
methodOptions +=":CutRangeMax[4]="+xcP.str();
//************
factory->BookMethod(TMVA::Types::kCuts,methodName,methodOptions);
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
}
int TestBDT_forreal_test(TString sig) {
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
//TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());//was not commented, but does not work anymore
//gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());//was not commented, but cannot not work anymore
//gROOT->ProcessLine(".L TMVAGui.C");
TString outfileName( "rootfiles/TMVA/resultTMVA_"+sig+"VsTTbar2l.root" );
TString weightname( "weightsTMVA_"+sig+"VsTTbar2l" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( weightname, outputFile,"!V:!Silent:Color:DrawProgressBar");
vector<TString> histonames; histonames.clear();
map<string, float> value;
//histonames.push_back("MT2W");
//histonames.push_back("MT2_lb_b");
//histonames.push_back("MT2_lb_bqq");
//histonames.push_back("MT2_lb_b_mass");
//histonames.push_back("MT2_lb_bqq_mass");
histonames.push_back("Mlb_lead_bdiscr");
//histonames.push_back("Mjjj");
//histonames.push_back("topness");
//histonames.push_back("topnessMod");
histonames.push_back("pfmet");
//histonames.push_back("ak4_HT");
//histonames.push_back("MET_over_sqrtHT");
//histonames.push_back("ak4_htratiom");
histonames.push_back("dR_lep_leadb");
//histonames.push_back("hadronic_top_chi2");
//histonames.push_back("ngoodbtags");
histonames.push_back("ngoodjets");
//histonames.push_back("mindphi_met_j1_j2");
//histonames.push_back("lep1_pt");
histonames.push_back("ak4pfjets_leadMEDbjet_p4_Pt");
for(unsigned int b = 0; b<histonames.size(); ++b){
factory->AddVariable(histonames[b], 'F' );
}
TString signame = "/nfs-7/userdata/stopRun2/testMVA/"+sig+".root";
TString bkgname1 = "/nfs-7/userdata/stopRun2/testMVA/TTJets_DiLept_madgraph_25ns_1.root";
TString bkgname2 = "/nfs-7/userdata/stopRun2/testMVA/TTJets_DiLept_madgraph_25ns_2.root";
/*
TString signame = "/hadoop/cms/store/user/haweber/forBDT/"+sig+".root";
TString bkgname1 = "/hadoop/cms/store/user/haweber/forBDT/TTJets_DiLept_madgraph_25ns_1.root";
TString bkgname2 = "/hadoop/cms/store/user/haweber/forBDT/TTJets_DiLept_madgraph_25ns_2.root";
*/
cout << "signame " << signame << endl;
TFile *inputSig = TFile::Open( signame );
TFile *inputBkg1 = TFile::Open( bkgname1 );
TFile *inputBkg2 = TFile::Open( bkgname2 );
TTree *signal = (TTree*)inputSig->Get("t");
TTree *background1 = (TTree*)inputBkg1->Get("t");
TTree *background2 = (TTree*)inputBkg2->Get("t");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background1, backgroundWeight );
factory->AddBackgroundTree( background2, backgroundWeight );
//factory->SetBackgroundWeightExpression( "weight" );
// Apply additional cuts on the signal and background samples (can be different)
//TCut mycuts = "MT2W>200&&mindphi_met_j1_j2>0.8"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
//TCut mycutb = "MT2W>200&&mindphi_met_j1_j2>0.8"; // for example: TCut mycutb = "abs(var1)<0.5";
//if(sig.Contains("T2tt_425_325")||sig.Contains("T2tt_500_325")){ mycuts = "mindphi_met_j1_j2>0.8"; mycutb = "mindphi_met_j1_j2>0.8"; }
TCut mycuts = "";
TCut mycutb = "";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
// Train MVAs using the set of training events
cout << "Train methods" << endl;
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
cout << "Test methods" << endl;
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
cout << "Evaluate methods" << endl;
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVA::TMVAGui( outfileName );
return 0;
}
void TMVATrainer(){
// This loads the library
TMVA::Tools::Instance();
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName = "TMVATrainingResults_fat_BBvsGSP.root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVATrainer", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable("TagVarCSV_vertexCategory","TagVarCSV_vertexCategory","units",'F');
factory->AddVariable("TagVarCSV_jetNTracks","TagVarCSV_jetNTracks","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_0","TagVarCSV_trackSip2dSig_0","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_1","TagVarCSV_trackSip2dSig_1","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_2","TagVarCSV_trackSip2dSig_2","units",'F');
//factory->AddVariable("TagVarCSV_trackSip2dSig_3","TagVarCSV_trackSip2dSig_3","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_0","TagVarCSV_trackSip3dSig_0","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_1","TagVarCSV_trackSip3dSig_1","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_2","TagVarCSV_trackSip3dSig_2","units",'F');
factory->AddVariable("TagVarCSV_trackSip3dSig_3","TagVarCSV_trackSip3dSig_3","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_0","TagVarCSV_trackPtRel_0","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_1","TagVarCSV_trackPtRel_1","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_2","TagVarCSV_trackPtRel_2","units",'F');
//factory->AddVariable("TagVarCSV_trackPtRel_3","TagVarCSV_trackPtRel_3","units",'F');
factory->AddVariable("TagVarCSV_trackSip2dSigAboveCharm","TagVarCSV_trackSip2dSigAboveCharm","units",'F');
//factory->AddVariable("TagVarCSV_trackSip3dSigAboveCharm","TagVarCSV_trackSip3dSigAboveCharm","units",'F');
//factory->AddVariable("TagVarCSV_trackSumJetEtRatio","TagVarCSV_trackSumJetEtRatio","units",'F');
//factory->AddVariable("TagVarCSV_trackSumJetDeltaR","TagVarCSV_trackSumJetDeltaR","units",'F');
factory->AddVariable("TagVarCSV_jetNTracksEtaRel","TagVarCSV_jetNTracksEtaRel","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_0","TagVarCSV_trackEtaRel_0","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_1","TagVarCSV_trackEtaRel_1","units",'F');
factory->AddVariable("TagVarCSV_trackEtaRel_2","TagVarCSV_trackEtaRel_2","units",'F');
factory->AddVariable("TagVarCSV_jetNSecondaryVertices","TagVarCSV_jetNSecondaryVertices","units",'F');
factory->AddVariable("TagVarCSV_vertexMass","TagVarCSV_vertexMass","units",'F');
factory->AddVariable("TagVarCSV_vertexNTracks","TagVarCSV_vertexNTracks","units",'F');
factory->AddVariable("TagVarCSV_vertexEnergyRatio","TagVarCSV_vertexEnergyRatio","units",'F');
factory->AddVariable("TagVarCSV_vertexJetDeltaR","TagVarCSV_vertexJetDeltaR","units",'F');
factory->AddVariable("TagVarCSV_flightDistance2dSig","TagVarCSV_flightDistance2dSig","units",'F');
//factory->AddVariable("TagVarCSV_flightDistance3dSig","TagVarCSV_flightDistance3dSig","units",'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator("Jet_pt","Jet_pt","units",'F');
factory->AddSpectator("Jet_eta","Jet_eta","units",'F');
factory->AddSpectator("Jet_phi","Jet_phi","units",'F');
factory->AddSpectator("Jet_mass","Jet_mass","units",'F');
factory->AddSpectator("Jet_massGroomed","Jet_massGroomed","units",'F');
factory->AddSpectator("Jet_flavour","Jet_flavour","units",'F');
factory->AddSpectator("Jet_nbHadrons","Jet_nbHadrons","units",'F');
factory->AddSpectator("Jet_JP","Jet_JP","units",'F');
factory->AddSpectator("Jet_JBP","Jet_JBP","units",'F');
factory->AddSpectator("Jet_CSV","Jet_CSV","units",'F');
factory->AddSpectator("Jet_CSVIVF","Jet_CSVIVF","units",'F');
factory->AddSpectator("Jet_tau1","Jet_tau1","units",'F');
factory->AddSpectator("Jet_tau2","Jet_tau2","units",'F');
factory->AddSpectator("SubJet1_CSVIVF","SubJet1_CSVIVF","units",'F');
factory->AddSpectator("SubJet2_CSVIVF","SubJet2_CSVIVF","units",'F');
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString fnameSig = "RadionToHH_4b_M-800_TuneZ2star_8TeV-Madgraph_pythia6_JetTaggingVariables_training.root";
TString fnameBkg = "QCD_Pt-300to470_TuneZ2star_8TeV_pythia6_JetTaggingVariables_training.root";
TFile *inputSig = TFile::Open( fnameSig );
TFile *inputBkg = TFile::Open( fnameBkg );
std::cout << "--- TMVAClassification : Using input files: " << inputSig->GetName() << std::endl
<< inputBkg->GetName() << std::endl;
// --- Register the training and test trees
TTree *sigTree = (TTree*)inputSig->Get("tagVars/ttree");
TTree *bkgTree = (TTree*)inputBkg->Get("tagVars/ttree");
// // global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// factory->SetInputTrees( tree,signalCut,backgroundCut );
factory->AddSignalTree ( sigTree, signalWeight );
factory->AddBackgroundTree( bkgTree, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut signalCut = "Jet_massGroomed>80 && Jet_massGroomed<150";
TCut backgroundCut = "abs(Jet_flavour)==5 && Jet_nbHadrons>1 && Jet_massGroomed>80 && Jet_massGroomed<150";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree( signalCut, backgroundCut,
"nTrain_Signal=22000:nTest_Signal=20000:nTrain_Background=22000:nTest_Background=2730:SplitMode=Random:!V" );
// Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG_T1000D3_fat_BBvsGSP",
"!H:!V:NTrees=1000:MaxDepth=3:MinNodeSize=1.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG_T1000D5_fat_BBvsGSP",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20" );
// // Adaptive Boost
// factory->BookMethod( TMVA::Types::kBDT, "BDT",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
// // Bagging
// factory->BookMethod( TMVA::Types::kBDT, "BDTB",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
// // Decorrelation + Adaptive Boost
// factory->BookMethod( TMVA::Types::kBDT, "BDTD",
// "!H:!V:NTrees=1000:MaxDepth=5:MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVATraining_ch4( )
{
TFile* outputFile = TFile::Open( "TMVA_ch4.root", "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "MVAnalysis", outputFile,"!V");
TFile *signal = TFile::Open("../production/BGx0/Prod2_iptubeK0/B0_etapr-eta-3pi2pi_KS-pi+pi-_output_signal_iptubeK0.root");
TFile *background = TFile::Open("../production/BGx0/Prod2_iptubeK0/B0_etapr-eta-3pi2pi_KS-pi+pi-_output_ccbar_iptubeK0.root");
factory->AddSignalTree ( (TTree*)signal->Get("B0"), 1.0 );
factory->AddBackgroundTree ( (TTree*)background->Get("B0"), 1.0 );
sigCut = TCut("B0__isContinuumEvent==0");
bgCut = TCut("B0__isContinuumEvent==1");
factory->AddVariable("B0_ThrustB",'F');
factory->AddVariable("B0_ThrustO",'F');
factory->AddVariable("B0_CosTBTO",'F');
factory->AddVariable("B0_CosTBz",'F');
factory->AddVariable("B0_R2",'F');
factory->AddVariable("B0_cc1",'F');
factory->AddVariable("B0_cc2",'F');
factory->AddVariable("B0_cc3",'F');
factory->AddVariable("B0_cc4",'F');
factory->AddVariable("B0_cc5",'F');
factory->AddVariable("B0_cc6",'F');
factory->AddVariable("B0_cc7",'F');
factory->AddVariable("B0_cc8",'F');
factory->AddVariable("B0_cc9",'F');
factory->AddVariable("B0_mm2",'F');
factory->AddVariable("B0_et",'F');
factory->AddVariable("B0_hso00",'F');
// factory->AddVariable("B0_hso01",'F');
factory->AddVariable("B0_hso02",'F');
//factory->AddVariable("B0_hso03",'F');
factory->AddVariable("B0_hso04",'F');
factory->AddVariable("B0_hso10",'F');
factory->AddVariable("B0_hso12",'F');
factory->AddVariable("B0_hso14",'F');
factory->AddVariable("B0_hso20",'F');
factory->AddVariable("B0_hso22",'F');
factory->AddVariable("B0_hso24",'F');
factory->AddVariable("B0_hoo0",'F');
factory->AddVariable("B0_hoo1",'F');
factory->AddVariable("B0_hoo2",'F');
factory->AddVariable("B0_hoo3",'F');
factory->AddVariable("B0_hoo4",'F');
factory->PrepareTrainingAndTestTree(sigCut, bgCut, "!V:nTrain_Signal=10000:nTest_Signal=10000:nTrain_Background=10000:nTest_Background=10000:SplitMode=Random:NormMode=NumEvents" );
//factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood", "H:V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA");
//factory->BookMethod( TMVA::Types::kMLP, "MLP", "!V:NCycles=200:HiddenLayers=N+1,N:TestRate=5" );
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" );
factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
factory->BookMethod( TMVA::Types::kSVM, "SVM", "!H:!V:Gamma=0.25:Tol=0.001:VarTransform=Norm" );
//factory->BookMethod( TMVA::Types::kBDT, "FastBDT", "!H:!V:CreateMVAPdfs:NbinsMVAPdf=40:NTrees=100:Shrinkage=0.10"); //:RandRatio=0.5:NCutLevel=8:NTreeLayers=3");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVA::TMVAGui( "TMVA_ch4.root" );
}
int main ()
{
TFile * outputfile = TFile::Open ("outputTMVA.root","RECREATE");
TMVA::Factory * TMVAtest = new TMVA::Factory ("TMVAtest", outputfile, "S") ;
//PG get the signal and deliver it to the TMVA factory
TChain signalTree ("sample") ;
signalTree.Add ("data/sig_0.root") ;
std::cout << "READ " << signalTree.GetEntries () << " signal events\n" ;
TMVAtest->AddSignalTree (&signalTree, 1) ;
//PG get the bkg and deliver it to the TMVA factory
TChain bkgTree ("sample") ;
bkgTree.Add ("data/bkg_0.root") ;
std::cout << "READ " << bkgTree.GetEntries () << " bkg events\n" ;
TMVAtest->AddBackgroundTree (&bkgTree, 1) ;
//PG get the training and test samples and deliver them to the TMVA factory
TChain signalTrainTree ("sample") ;
signalTrainTree.Add ("data/sig_1.root") ;
std::cout << "READ " << signalTrainTree.GetEntries () << " signal train events\n" ;
TChain bkgTrainTree ("sample") ;
bkgTrainTree.Add ("data/bkg_1.root") ;
std::cout << "READ " << bkgTrainTree.GetEntries () << " bkg train events\n" ;
TMVAtest->SetInputTrees (signalTrainTree.GetTree (), bkgTrainTree.GetTree (), 1., 1.) ;
//PG variables to be used for the selection
//PG must be defined in the TTrees
TMVAtest->AddVariable ("vars.x", 'F') ;
TMVAtest->AddVariable ("vars.y" , 'F') ;
int signalNumTrain = signalTrainTree.GetEntries () * 4 / 5 ;
int bkgNumTrain = bkgTrainTree.GetEntries () * 4 / 5 ;
int signalNumTest = signalTrainTree.GetEntries () - signalNumTrain ;
int bkgNumTest = bkgTrainTree.GetEntries () - bkgNumTrain ;
char trainOptions[120] ;
sprintf (trainOptions,"NSigTrain=%d:NBkgTrain=%d:NSigTest=%d:NBkgTest=%d",
signalNumTrain, bkgNumTrain,
signalNumTest, bkgNumTest) ;
sprintf (trainOptions,"NSigTrain=%d:NBkgTrain=%d:NSigTest=%d:NBkgTest=%d",
0,0,0,0) ;
std::cout << "TRAINING CONFIGURATION : " << trainOptions << "\n" ;
TMVAtest->PrepareTrainingAndTestTree ("",trainOptions) ;
//PG prepare the classifier
//PG cut-based, default params
TMVAtest->BookMethod (TMVA::Types::kCuts, "Cuts") ;
TMVAtest->TrainAllMethods () ;
TMVAtest->TestAllMethods () ;
TMVAtest->EvaluateAllMethods () ;
delete TMVAtest ;
delete outputfile ;
}
int main(int argc, char * argv[])
{
//Processing input options
int c;
std::string outFname;
outFname = std::string("QualityNaF.root");
// Open input files, get the trees
TChain *mc = InputFileReader("FileListNtuples_ext.txt","parametri_geo");
// Preparing options for the TMVA::Factory
std::string options(
"!V:"
"!Silent:"
"Color:"
"DrawProgressBar:"
"Transformations=I;D;P;G,D:"
"AnalysisType=Classification"
);
//Creating the factory
TFile * ldFile = new TFile(outFname.c_str(),"RECREATE");
TMVA::Factory * factory = new TMVA::Factory("QualityNaF", ldFile, options.c_str());
//Preparing variables
//general
/*factory->AddVariable("Chisquare", 'F');
factory->AddVariable("Layernonusati", 'I');
factory->AddVariable("NTofUsed", 'I');
factory->AddVariable("diffR", 'F');
factory->AddVariable("TOF_Up_Down", 'F');*/
//Tof
//factory->AddVariable("TOFchisq_s", 'F');
//factory->AddVariable("TOFchisq_t", 'F');
//RICH
factory->AddVariable("Richtotused", 'F');
factory->AddVariable("RichPhEl", 'F');
factory->AddVariable("RICHprob", 'F');
factory->AddVariable("RICHcollovertotal");
factory->AddVariable("RICHLipBetaConsistency");
factory->AddVariable("RICHTOFBetaConsistency");
factory->AddVariable("RICHChargeConsistency");
factory->AddVariable("RICHPmts");
factory->AddVariable("RICHgetExpected");
factory->AddVariable("tot_hyp_p_uncorr");
factory->AddVariable("Bad_ClusteringRICH");
factory->AddVariable("NSecondariesRICHrich");
//factory->AddVariable("HitHValldir");
//factory->AddVariable("HitHVallrefl");
//factory->AddVariable("HVBranchCheck:= (HitHValldir - HitHVoutdir) - (HitHVallrefl - HitHVoutrefl)");
factory->AddVariable("HitHVoutdir");
factory->AddVariable("HitHVoutrefl");
//Spectator Variables
factory->AddSpectator("R", 'F');
factory->AddSpectator("BetaRICH_new", 'F');
//Preselection cuts
std::string PreSelection = "qL1>0&&(joinCutmask&187)==187&&qL1<1.75&&R>0";
std::string ChargeCut = "qUtof>0.8&&qUtof<1.3&&qLtof>0.8&&qLtof<1.3";
std::string VelocityCut = /*"Beta<0.8";*/"((joinCutmask>>11))==1024&&BetaRICH_new>0&&BetaRICH_new<0.975";
std::string signalCut = /*"(R/Beta)*(1-Beta^2)^0.5>1.65&&GenMass>1&&GenMass<2";*/"(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5>0.5&&(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5<1.5";
std::string bkgndCut = /*"(R/Beta)*(1-Beta^2)^0.5>1.65&&GenMass>0&&GenMass<1";*/"(R/BetaRICH_new)*(1-BetaRICH_new^2)^0.5>3";
factory->AddTree(mc,"Signal" ,1,(PreSelection +"&&"+ ChargeCut + "&&" + VelocityCut + "&&"+ signalCut).c_str());
factory->AddTree(mc,"Background",1,(PreSelection +"&&"+ ChargeCut + "&&" + VelocityCut + "&&"+ bkgndCut).c_str());
// Preparing
std::string preselection = "";
std::string inputparams(
"SplitMode=Random:"
"NormMode=NumEvents:"
"!V"
);
factory->PrepareTrainingAndTestTree(preselection.c_str(),inputparams.c_str());
// Training
std::string trainparams ="!H:!V:MaxDepth=3";
factory->BookMethod(TMVA::Types::kBDT, "BDT", trainparams.c_str());
trainparams ="!H:!V";
factory->BookMethod(TMVA::Types::kLikelihood, "Likelihood", trainparams.c_str());
trainparams ="!H:!V:VarTransform=Decorrelate";
//factory->BookMethod(TMVA::Types::kLikelihood, "LikelihoodD", trainparams.c_str());
trainparams ="!H:!V";
//factory->BookMethod(TMVA::Types::kCuts, "Cuts", trainparams.c_str());
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
}
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
bool batchMode(false);
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "var1", 'F' );
factory->AddVariable( "var2", 'F' );
factory->AddVariable( "var3", 'F' );
factory->AddVariable( "var4", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "eta" );
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname( "" );
if (UseOffsetMethod) fname = "../execs/data/toy_sigbkg_categ_offset.root";
else fname = "../execs/data/toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
/// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
/// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Fisher discriminant
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Categorised classifier
TMVA::MethodCategory* mcat = 0;
// the variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// the Fisher
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kFisher,"Category_Fisher_1","!H:!V:Fisher");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher,"Category_Fisher_2","!H:!V:Fisher");
// the Likelihood
TMVA::MethodBase* liCat = factory->BookMethod( TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod("abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
mcat->AddMethod("abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50");
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void WWTMVAClassification( TString myMethodList = "", double mH=400., int njets, TString chan="el" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
// ---
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDERSkNN"] = 0; // depreciated until further notice
Use["PDEFoam"] = 0;
// --
Use["KNN"] = 0;
// ---
Use["HMatrix"] = 0;
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0;
Use["LD"] = 1;
// ---
Use["FDA_GA"] = 0;
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
// ---
Use["MLP"] = 0; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["CFMlpANN"] = 0; // *** missing
Use["TMlpANN"] = 0;
// ---
Use["SVM"] = 0;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 0;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 0;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
///////TString outfileName( "TMVA.root" );
char outfileName[192];
sprintf(outfileName,"TMVA_%3.0f_nJ%i_%s.root",mH,njets,chan.Data());
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
char classifierName[192];
sprintf(classifierName,"TMVAClassification_%3.0f_nJ%i_%s",mH,njets,chan.Data());
TMVA::Factory *factory = new TMVA::Factory( classifierName, outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
//TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
// "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// leptonic W
factory->AddVariable("WWpt := ptlvjj", 'F');
factory->AddVariable("WWy := ylvjj", 'F');
//factory->AddVariable("Wpt := W_pt", 'F');
//factory->AddVariable("MET := event_met_pfmet", 'F');
if (chan = "mu"){
factory->AddVariable("LepCharge := W_muon_charge", 'F');
}
else if (chan = "el"){
factory->AddVariable("LepCharge := W_electron_charge", 'F');
}
else{
std::cout << "Invalid channel!" << std::endl;
return;
}
// factory->AddVariable("J1QGL := JetPFCor_QGLikelihood[0]", 'F');
// factory->AddVariable("J2QGL := JetPFCor_QGLikelihood[1]", 'F');
factory->AddVariable("costheta1 := ang_ha", 'F');
factory->AddVariable("costheta2 := ang_hb", 'F');
factory->AddVariable("costhetaS := ang_hs", 'F');
factory->AddVariable("Phi := ang_phi", 'F');
factory->AddVariable("Phi2 := ang_phib", 'F');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator("run := event_runNo", "I");
factory->AddSpectator("lumi := event_lumi", "I");
factory->AddSpectator("event := event_evtNo", "I");
factory->AddSpectator("mjj := Mass2j_PFCor", "F");
factory->AddSpectator("mlvjj := MassV2j_PFCor", "F");
factory->AddSpectator("masslvjj := masslvjj", "F");
//factory->AddSpectator("ggdevt := ggdevt", "F");
//factory->AddSpectator("fit_mlvjj := fit_mlvjj", "F");
// read training and test data
char signalOutputName[192];
sprintf(signalOutputName,"/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_%s_HWWMH%3.0f_CMSSW428.root",chan.Data(),mH);
TFile *input1 = TFile::Open( signalOutputName );
//TFile *input1 = TFile::Open( "/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_mu_HWWMH400_CMSSW428.root");
char backgroundOutputName[192];
sprintf(backgroundOutputName,"/uscms_data/d2/kalanand/WjjTrees/Full2011DataFall11MC/ReducedTree/RD_%s_WpJ_CMSSW428.root",chan.Data());
TFile *input2 = TFile::Open( backgroundOutputName );
std::cout << "--- TMVAClassification : Using input file: " << input1->GetName() << std::endl;
TTree *signal = (TTree*)input1->Get("WJet");
TTree *background = (TTree*)input2->Get("WJet");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
// TCut mycuts = "abs(eta)>1.5"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
// TCut mycutb = "abs(eta)>1.5"; // for example: TCut mycutb = "abs(var1)<0.5";
char * mass4bodycut = "";
if(njets==2) {
if(chan.Contains("mu")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>176 && fit_mlvjj<262)"; // 2j170mu =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>179 && fit_mlvjj<256)"; // 2j180mu
if(mH==190.) mass4bodycut = "(fit_mlvjj>186 && fit_mlvjj<214)"; // 2j190mu
if(mH==200.) mass4bodycut = "(fit_mlvjj>191 && fit_mlvjj<226)"; // 2j200mu
if(mH==250.) mass4bodycut = "(fit_mlvjj>226 && fit_mlvjj<287)"; // 2j250mu
if(mH==300.) mass4bodycut = "(fit_mlvjj>265 && fit_mlvjj<347)"; // 2j300mu
if(mH==350.) mass4bodycut = "(fit_mlvjj>308 && fit_mlvjj<401)"; // 2j350mu
if(mH==400.) mass4bodycut = "(fit_mlvjj>346 && fit_mlvjj<457)"; // 2j400mu
if(mH==450.) mass4bodycut = "(fit_mlvjj>381 && fit_mlvjj<512)"; // 2j450mu
if(mH==500.) mass4bodycut = "(fit_mlvjj>415 && fit_mlvjj<568)"; // 2j500mu
if(mH==550.) mass4bodycut = "(fit_mlvjj>440 && fit_mlvjj<617)"; // 2j550mu
if(mH==600.) mass4bodycut = "(fit_mlvjj>462 && fit_mlvjj<663)"; // 2j600mu
}
if(chan.Contains("el")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>176 && fit_mlvjj<262)"; // 2j170el =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>179 && fit_mlvjj<256)"; // 2j180el
if(mH==190.) mass4bodycut = "(fit_mlvjj>186 && fit_mlvjj<214)"; // 2j190el
if(mH==200.) mass4bodycut = "(fit_mlvjj>191 && fit_mlvjj<226)"; // 2j200el
if(mH==250.) mass4bodycut = "(fit_mlvjj>226 && fit_mlvjj<287)"; // 2j250el
if(mH==300.) mass4bodycut = "(fit_mlvjj>265 && fit_mlvjj<347)"; // 2j300el
if(mH==350.) mass4bodycut = "(fit_mlvjj>308 && fit_mlvjj<401)"; // 2j350el
if(mH==400.) mass4bodycut = "(fit_mlvjj>346 && fit_mlvjj<457)"; // 2j400el
if(mH==450.) mass4bodycut = "(fit_mlvjj>381 && fit_mlvjj<512)"; // 2j450el
if(mH==500.) mass4bodycut = "(fit_mlvjj>415 && fit_mlvjj<568)"; // 2j500el
if(mH==550.) mass4bodycut = "(fit_mlvjj>440 && fit_mlvjj<617)"; // 2j550el
if(mH==600.) mass4bodycut = "(fit_mlvjj>462 && fit_mlvjj<663)"; // 2j600el
}
}
if(njets==3) {
if(chan.Contains("mu")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>150 && fit_mlvjj<271)"; // 3j170mu =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>175 && fit_mlvjj<284)"; // 3j180mu
if(mH==190.) mass4bodycut = "(fit_mlvjj>185 && fit_mlvjj<290)"; // 3j190mu
if(mH==200.) mass4bodycut = "(fit_mlvjj>188 && fit_mlvjj<293)"; // 3j200mu
if(mH==250.) mass4bodycut = "(fit_mlvjj>216 && fit_mlvjj<300)"; // 3j250mu
if(mH==300.) mass4bodycut = "(fit_mlvjj>241 && fit_mlvjj<355)"; // 3j300mu
if(mH==350.) mass4bodycut = "(fit_mlvjj>269 && fit_mlvjj<407)"; // 3j350mu
if(mH==400.) mass4bodycut = "(fit_mlvjj>300 && fit_mlvjj<465)"; // 3j400mu
if(mH==450.) mass4bodycut = "(fit_mlvjj>332 && fit_mlvjj<518)"; // 3j450mu
if(mH==500.) mass4bodycut = "(fit_mlvjj>362 && fit_mlvjj<569)"; // 3j500mu
if(mH==550.) mass4bodycut = "(fit_mlvjj>398 && fit_mlvjj<616)"; // 3j550mu
if(mH==600.) mass4bodycut = "(fit_mlvjj>419 && fit_mlvjj<660)"; // 3j600mu
}
if(chan.Contains("el")) {
if(mH==170.) mass4bodycut = "(fit_mlvjj>150 && fit_mlvjj<271)"; // 3j170el =====
if(mH==180.) mass4bodycut = "(fit_mlvjj>175 && fit_mlvjj<284)"; // 3j180el
if(mH==190.) mass4bodycut = "(fit_mlvjj>185 && fit_mlvjj<290)"; // 3j190el
if(mH==200.) mass4bodycut = "(fit_mlvjj>188 && fit_mlvjj<293)"; // 3j200el
if(mH==250.) mass4bodycut = "(fit_mlvjj>216 && fit_mlvjj<300)"; // 3j250el
if(mH==300.) mass4bodycut = "(fit_mlvjj>241 && fit_mlvjj<355)"; // 3j300el
if(mH==350.) mass4bodycut = "(fit_mlvjj>269 && fit_mlvjj<407)"; // 3j350el
if(mH==400.) mass4bodycut = "(fit_mlvjj>300 && fit_mlvjj<465)"; // 3j400el
if(mH==450.) mass4bodycut = "(fit_mlvjj>332 && fit_mlvjj<518)"; // 3j450el
if(mH==500.) mass4bodycut = "(fit_mlvjj>362 && fit_mlvjj<569)"; // 3j500el
if(mH==550.) mass4bodycut = "(fit_mlvjj>398 && fit_mlvjj<616)"; // 3j550el
if(mH==600.) mass4bodycut = "(fit_mlvjj>419 && fit_mlvjj<660)"; // 3j600el
}
}
char mycutschar[1000];
sprintf(mycutschar,"ggdevt == %i &&(Mass2j_PFCor>65 && Mass2j_PFCor<95) && %s", njets, mass4bodycut);
TCut mycuts (mycutschar);
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycuts,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+5:TestRate=10:EpochMonitoring" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+5:TestRate=10:TrainingMethod=BFGS:!EpochMonitoring" );
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
/**********************************************************************************
* Project : TMVA - a ROOT-integrated toolkit for multivariate data analysis *
* Package : TMVA *
* Root Macro: TMVAClassification *
* *
* This macro provides examples for the training and testing of the *
* TMVA classifiers. *
* *
* As input data is used a toy-MC sample consisting of four Gaussian-distributed *
* and linearly correlated input variables. *
* *
* The methods to be used can be switched on and off by means of booleans, or *
* via the prompt command, for example: *
* *
* root -l ./TMVAClassification.C\(\"Fisher,Likelihood\"\) *
* *
* (note that the backslashes are mandatory) *
* If no method given, a default set of classifiers is used. *
* *
* The output file "TMVA.root" can be analysed with the use of dedicated *
* macros (simply say: root -l <macro.C>), which can be conveniently *
* invoked through a GUI that will appear at the end of the run of this macro. *
* Launch the GUI via the command: *
* *
* root -l ./TMVAGui.C *
* *
**********************************************************************************/
void TMVAClassification( TString myMethodList = "")
{
TTree *signal = (TTree *)gDirectory->Get("VertexG");
if (! signal) { std::cout << "No signal TTree" << std::endl; return;}
TTree *background = (TTree *)gDirectory->Get("VertexB");
if (! background) { std::cout << "No background TTree" << std::endl; return;}
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string, int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
Use["myBDTD"] = 1; // mine
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string, int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (size_t i = 0; i < mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string, int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile *outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// load the signal and background event samples from ROOT trees
std::cout << " starts ... " << std::endl;
// global event weights per tree (see below for setting event-wise weights)
// Float_t w;
double signalWeight = 1.0;
double backgroundWeight = 1.0;
std::cout << " signalWeight = " << signalWeight << " backWeight = " << backgroundWeight << std::endl;
factory->AddSignalTree( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
TString separator(":");
TString Vnames(vnames);
TObjArray *array = Vnames.Tokenize(separator);
std::vector<std::string> inputVars;
TIter next(array);
TObjString *objs;
while ((objs = (TObjString *) next())) {
// std::cout << objs->GetString() << std::endl;
TString name(objs->GetString());
if (name == "BEMC") continue;
if (name == "noBEMC") continue;
factory->AddVariable(name, 'F');
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// commented JB : 04/26 ??
//factory->dSetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
//factory->PrepareTrainingAndTestTree( mycuts,mycutb,"NSigTrain=9000:NBkgTrain=50000:NSigTest=9000:NBkgTest=50000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb, "nTrain_Signal=4900:nTrain_Background=49000:nTest_Signal=4900:nTest_Background=49000:SplitMode=Random:!V"); // for KFVertex
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,"nTrain_Signal=20000:nTrain_Background=40000:nTest_Signal=20000:nTest_Background=40000:SplitMode=Random:!V"); // for PPV
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["myBDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTDTEST",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// TMVA::IMethod* category = factory->BookMethod( TMVA::Types::kCategory,"Category","" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
#if 0
factory->OptimizeAllMethods("SigEffAt001", "Scan");
factory->OptimizeAllMethods("ROCIntegral", "GA");
#endif
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
}
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
// Example for usage of different event categories with classifiers
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
bool batchMode = false;
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object (see TMVAClassification.C for more information)
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// Define the input variables used for the MVA training
factory->AddVariable( "var1", 'F' );
factory->AddVariable( "var2", 'F' );
factory->AddVariable( "var3", 'F' );
factory->AddVariable( "var4", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "eta" );
// Load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname( "" );
if (UseOffsetMethod) fname = "data/toy_sigbkg_categ_offset.root";
else fname = "data/toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
/// Global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
/// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
// Fisher discriminant
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// --- Categorised classifier
TMVA::MethodCategory* mcat = 0;
// The variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// Fisher with categories
TMVA::MethodBase* fiCat = factory->BookMethod( TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod( "abs(eta)<=1.3", theCat1Vars, TMVA::Types::kFisher, "Category_Fisher_1","!H:!V:Fisher" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher, "Category_Fisher_2","!H:!V:Fisher" );
// Likelihood with categories
TMVA::MethodBase* liCat = factory->BookMethod( TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod( "abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassificationHwwNtuple( TString myMethodList = "" )
{
// This loads the library
TMVA::Tools::Instance();
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
cout<<regMethod<<" is on"<<endl;
}
}
// -------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// For one variable
//TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
// "!V:!Silent:Color:DrawProgressBar:Transformations=I:AnalysisType=Classification" );
// For Multiple Variables
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
//factory->AddVariable( "pt1", "LeadLepton pt", "", 'F' );
//factory->AddVariable( "pt2", "TailLepton pt", "", 'F' );
factory->AddVariable( "pfmet", "MissingEt", "", 'F' );
factory->AddVariable( "mpmet", "Minimum Proj. Met", "", 'F' );
factory->AddVariable( "dphill", "DeltPhiOfLepLep", "", 'F' );
//factory->AddVariable( "mll", "DiLepton Mass", "", 'F' );
factory->AddVariable( "ptll", "DiLepton pt", "", 'F' );
//
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
//factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
//factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
//
//factory->AddSpectator( "mWW", "Higgs Mass", "", 'F' );
factory->AddSpectator( "pt1", "LeadLepton pt", "", 'F' );
factory->AddSpectator( "pt2", "TailLepton pt", "", 'F' );
factory->AddSpectator( "pfmet", "MissingEt", "", 'F' );
factory->AddSpectator( "mpmet", "Minimum Proj. Met", "", 'F' );
factory->AddSpectator( "dphill", "DeltPhiOfLepLep", "", 'F' );
factory->AddSpectator( "mll", "DiLepton Mass", "", 'F' );
factory->AddSpectator( "ptll", "DiLepton pt", "", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
//TString fname = "./tmva_class_example.root";
//TString fname = "/afs/cern.ch/work/s/salee/private/HWWwidth/HWW/GGVvAnalyzer/MkNtuple/Hw1Int8TeV/MkNtuple.root";
//TString fname = "/terranova_0/HWWwidth/HWW/GGVvAnalyzer/MkNtuple/Hw1Int8TeV/MkNtuple.root";
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// exit(-1);
//gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
//TFile *input = TFile::Open( fname );
//TFile *SB_OnPeak = TFile::Open("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntOnPeak_8TeV.root");
//TTree *SB_OnPeak_Tree = (TTree*)SB_OnPeak->Get("latino");
TChain *S_Chain = new TChain("latino");
TChain *C_Chain = new TChain("latino");
TChain *SCI_Chain = new TChain("latino");
TChain *qqWW_Chain = new TChain("latino");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigOnPeak_8TeV.root");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigShoulder_8TeV.root");
S_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_SigTail_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntOnPeak_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntShoulder_8TeV.root");
SCI_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw1_IntTail_8TeV.root");
C_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw25_CotHead_8TeV.root");
C_Chain->Add("root://eoscms.cern.ch//eos/cms/store/group/phys_higgs/cmshww/amassiro/HiggsWidth/gg2vv/latinogg2vv_Hw25_CotTail_8TeV.root");
qqWW_Chain->Add("/afs/cern.ch/user/m/maiko/work/public/Tree/tree_skim_wwmin/nominals/latino_000_WWJets2LMad.root");
// --- Register the training and test trees
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( S_Chain );
factory->AddBackgroundTree( qqWW_Chain );
factory->AddBackgroundTree( C_Chain );
// Classification training and test data in ROOT tree format with signal and background events being located in the same tree
//factory->SetInputTrees(SCI_Chain, GenOffCut, GenOnCut);
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
factory->SetWeightExpression ("2.1*puW*baseW*effW*triggW*19.468");
//factory->SetSignalWeightExpression ("2.1*puW*baseW*effW*triggW*19.468");
//factory->SetBackgroundWeightExpression("puW*baseW*effW*triggW*19.468");
//factory->PrepareTrainingAndTestTree( ChanCommOff,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=None:!V" );
//"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V";
factory->PrepareTrainingAndTestTree( ChanCommOff0J,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=None:!V" );
// ---- Book MVA methods
//
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
//"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// -----------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// -----------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char* argv[]){
// Configurable parameters
// int max_events; // Maximum number of events to process
//string filelist; // The file containing a list of files to use as input
//string input_prefix; // A prefix that will be added to the path of each input file
string folder;
string output_name; // Name of the ouput ROOT File
string output_folder; // Folder to write the output in
string paramfile;
string paramfile2;
string classname;
bool twotag;
bool onetag;
po::options_description config("Configuration");
po::variables_map vm;
po::notify(vm);
config.add_options()
("folder", po::value<string>(&folder)->default_value("output/Paper_2012/"))
// ("input_prefix", po::value<string>(&input_prefix)->default_value(""))
("output_name", po::value<string>(&output_name)->default_value("test_tmva.root"))
("output_folder", po::value<string>(&output_folder)->default_value(""))
("paramfile", po::value<string>(¶mfile)->default_value("./scripts/Paper_params_2012.dat"))
("paramfile2", po::value<string>(¶mfile2)->default_value("./scripts/TMVAinputshad.dat"))
("classname", po::value<string>(&classname)->default_value("HhhMVA"))
("twotag", po::value<bool>(&twotag)->default_value(true))
("onetag", po::value<bool>(&onetag)->default_value(false))
;
po::store(po::command_line_parser(argc, argv).
options(config).allow_unregistered().run(), vm);
po::notify(vm);
std::cout << "-------------------------------------" << std::endl;
std::cout << "Train MVA" << std::endl;
std::cout << "-------------------------------------" << std::endl; string param_fmt = "%-25s %-40s\n";
std::vector<string> bckglist;
bckglist.push_back("TTJetsFullLept");
bckglist.push_back("TTJetsSemiLept");
bckglist.push_back("TTJetsHadronicExt");
// bckglist.push_back("WWJetsTo2L2Nu");
// bckglist.push_back("WZJetsTo2L2Q");
// bckglist.push_back("WZJetsTo3LNu");
// bckglist.push_back("ZZJetsTo2L2Nu");
// bckglist.push_back("ZZJetsTo2L2Q");
// bckglist.push_back("ZZJetsTo4L");
// bckglist.push_back("DYJetsToTauTauSoup");
// bckglist.push_back("DYJetsToLLSoup");
// bckglist.push_back("DYJetsToTauTau");
// bckglist.push_back("DYJetsToLL");
// bckglist.push_back("T-tW");
// bckglist.push_back("Tbar-tW");
std::vector<string> signallist;
signallist.push_back("GluGluToHTohhTo2Tau2B_mH-300");
sample_names_.reserve(bckglist.size()+signallist.size());
sample_names_.insert(sample_names_.end(),bckglist.begin(),bckglist.end());
sample_names_.insert(sample_names_.end(),signallist.begin(),signallist.end());
std::vector<TFile*> BackgroundSamples;
for(unsigned int iter=0;iter<bckglist.size();++iter){
BackgroundSamples.push_back(TFile::Open((folder+bckglist.at(iter)+"_mt_2012.root").c_str()));
}
std::vector<TFile*> SignalSamples;
for(unsigned int sigIter=0;sigIter<signallist.size();++sigIter){
SignalSamples.push_back(TFile::Open((folder+signallist.at(sigIter)+"_mt_2012.root").c_str()));
}
std::vector<TTree*> backgroundTrees;
for(unsigned int iter2=0;iter2<BackgroundSamples.size();++iter2){
backgroundTrees.push_back(dynamic_cast<TTree*>(BackgroundSamples.at(iter2)->Get("ntuple")));
}
std::vector<TTree*> signalTrees;
for(unsigned int sigIter2=0;sigIter2<SignalSamples.size();++sigIter2){
signalTrees.push_back(dynamic_cast<TTree*>(SignalSamples.at(sigIter2)->Get("ntuple")));
}
TFile *outfile = new TFile((output_folder+output_name).c_str(),"RECREATE");
TMVA::Factory *factory = new TMVA::Factory(classname,outfile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
std::vector<std::string> vars;
std::ifstream parafile(paramfile2.c_str());
std::cout<<paramfile2.c_str()<<std::endl;
string line;
while(getline(parafile,line)){
vars.push_back(line);
}
parafile.close();
std::cout<<(vars.at(0)).c_str()<<std::endl;
std::vector<float> var2;
for(unsigned int variter=0;variter<vars.size();++variter){
var2.push_back(::atof((vars.at(variter)).c_str()));
}
for(unsigned int variter=0;variter<vars.size();++variter){
factory->AddVariable((vars.at(variter)).c_str(),(vars.at(variter)).c_str(),"",'F');
}
factory->AddSpectator("mt_1","mt_1","",'F');
factory->AddSpectator("n_prebjets","n_prebjets","",'I');
factory->AddSpectator("prebjetbcsv_1","prebjetbcsv_1","",'F');
factory->AddSpectator("prebjetbcsv_2","prebjetbcsv_2","",'F');
double weightval_=0;
ParseParamFile(paramfile);
for(unsigned int bckgit=0;bckgit<backgroundTrees.size();++bckgit){
auto it = sample_info_.find(bckglist.at(bckgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs = it->second.second;
weightval_=(double) xs/evt;
std::cout<<weightval_<<std::endl;
}
factory->AddBackgroundTree(backgroundTrees.at(bckgit),weightval_);
}
for(unsigned int sgit=0;sgit<signalTrees.size();++sgit){
auto it = sample_info_.find(signallist.at(sgit).c_str());
if(it!=sample_info_.end()){
double evt = it->second.first;
double xs=it->second.second;
weightval_=(Double_t) xs/evt;
}
std::cout<<weightval_<<std::endl;
factory->AddSignalTree(signalTrees.at(sgit),weightval_);
}
factory->SetBackgroundWeightExpression("wt");
factory->SetSignalWeightExpression("wt");
TCut mycutb, mycuts;
if(twotag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2>0.679";
}
else if(onetag){
mycutb="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
mycuts="n_prebjets>1&&mt_1<30&&prebjetbcsv_1>0.679&&prebjetbcsv_2<0.679";
}
else{
mycutb="n_prebjets>1&&mt_1<30";
mycuts="n_prebjets>1&&mt_1<30";
}
//TCut mycutb="";
//TCut mycuts="";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,"SplitMode=Random:!V");
factory->BookMethod( TMVA::Types::kBDT, "BDT","!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outfile->Close();
delete factory;
return 0;
}
void TMVAClassify_SepSSFromOS( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString tmva_dir(TString(gRootDir) + "/tmva");
if(gSystem->Getenv("TMVASYS"))
tmva_dir = TString(gSystem->Getenv("TMVASYS"));
gROOT->SetMacroPath(tmva_dir + "/test/:" + gROOT->GetMacroPath() );
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0; // uses Adaptive Boost
Use["BDTG"] = 1; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "../../classifiers/D02KPi/TMVA/TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "track_angletod", "Angle to D0", "", 'F' );
factory->AddVariable( "track_angletochild1", "Angle to kaon from D0", "", 'F' );
factory->AddVariable( "track_angletochild2", "Angle to pion from D0", "", 'F' );
factory->AddVariable( "log(track_devdist)", "log(DOCA to D0 vertex)", "", 'F' );
//factory->AddVariable( "log(track_docatochild1)", "log(DOCA to kaon from D0)", "", 'F' );
//factory->AddVariable( "log(track_docatochild2)", "log(DOCA to pion from D0)", "", 'F' );
//factory->AddVariable( "log(track_docatod)", "Distance to D0 trajectory", "", 'F' );
factory->AddVariable( "track_ptratiod", "Ratio track PT to D0 PT ", "", 'F' );
factory->AddVariable( "track_ptratiochild1", "Ratio track PT to kaon PT", "", 'F' );
factory->AddVariable( "track_ptratiochild2", "Distance track PT to pion PT", "", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
//factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
//factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TFile *input_ss = TFile::Open( "../../data/mcd02kpi_ss_forsepssfromos.root" );
TFile *input_os = TFile::Open( "../../data/mcd02kpi_os_forsepssfromos.root" );
// --- Register the training and test trees
TTree *intree_ss = (TTree*)input_ss->Get("DecayTree");
TTree *intree_os = (TTree*)input_os->Get("DecayTree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
factory->AddSignalTree ( intree_os, signalWeight );
factory->AddBackgroundTree( intree_ss, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=80000:nTrain_Background=80000:nTest_Signal=80000:nTest_Background=80000:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+2:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=4000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=3" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification_cuts( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
//factory->AddVariable( "myvar1 := var1+var2", 'F' );
//factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
factory->AddVariable( "CSV1", "CSV 1", "", 'F' );
factory->AddVariable( "CSV2", "CSV 2", "", 'F' );
factory->AddVariable( "nJets", "nJets", "", 'I' );
// factory->AddVariable( "Zmass", "Zmass", "", 'F' );
// factory->AddVariable( "Hmass", "Hmass", "", 'F' );
factory->AddVariable( "DeltaPhiHV", "Deltaphi HB", "", 'F' );
factory->AddVariable( "Hpt", "p_{T} Higgs", "", 'F' );
factory->AddVariable( "Zpt", "p_{T} Z Boson", "", 'F' );
factory->AddVariable( "mu1pt", "#mu1 p_{T}", "", 'F' );
factory->AddVariable( "Ht", "H_{T}", "", 'F' );
factory->AddVariable( "EtaStandDev", "Standard Deviation #eta", "", 'F' );
factory->AddVariable( "UnweightedEta", "unweighted #eta", "", 'F' );
factory->AddVariable( "EvntShpCircularity", "Circularity", "", 'F' );
factory->AddVariable( "alpha_j", "A-P #alpha jets", "", 'F' );
factory->AddVariable( "qtb1", "q_{T} b1", "", 'F' );
/// factory->AddVariable( "nSV", "nSV", "", 'I' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
TString ZZname = "ZZ.root";
TString DYname = "DY.root";
TString WZname = "WZ.root";
TString TTJetsname = "TTJets.root";
TString sname = "H115.root";
//if (gSystem->AccessPathName( fname )) // file does not exist in local directory
// gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *H115_file = TFile::Open( sname );
TFile *ZZ_file = TFile::Open( ZZname );
TFile *DY_file = TFile::Open( DYname );
TFile *WZ_file = TFile::Open( WZname );
TFile *TTJets_file = TFile::Open( TTJetsname );
std::cout << "--- TMVAClassification : Using input file: " << H115_file->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)H115_file->Get("TMVA_tree");
TTree *ZZ_tree = (TTree*)ZZ_file->Get("TMVA_tree");
TTree *DY_tree = (TTree*)DY_file->Get("TMVA_tree");
TTree *WZ_tree = (TTree*)WZ_file->Get("TMVA_tree");
TTree *TTJets_tree = (TTree*)TTJets_file->Get("TMVA_tree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 0.4107*0.704*0.101*10000/219999.0;
Double_t ZZ_weight = 7.41*10000/4157882.0;
Double_t DY_weight = 3151.864553*10000/ 36217940.0;
Double_t WZ_weight = 18.2*10000/ 18.2*10000/4145240.0;
Double_t TTJets_weight = 157.5*10000/ 3611944.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight);
factory->AddBackgroundTree( ZZ_tree, ZZ_weight );
factory->AddBackgroundTree( DY_tree, DY_weight );
factory->AddBackgroundTree( WZ_tree, WZ_weight );
factory->AddBackgroundTree( TTJets_tree, TTJets_weight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4], weight;
//
// // Signal
// for (UInt_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2.0) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// // Background (has event weights)
// background->SetBranchAddress( "weight", &weight );
// for (UInt_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight*weight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight*weight );
// }
// --- end ------------------------------------------------------------
//
// --- end of tree registration
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
//factory->SetBackgroundWeightExpression( "weight" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "CSV1 > -1 && CSV2 > -1 && Zmass > 70 && Zmass < 110"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut nocut = "CSV1 > -1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
//TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
factory->PrepareTrainingAndTestTree(nocut, "SplitMode=random:!V");
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
//factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=GA:EffSel:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassificationElecTau(std::string ordering_ = "Pt", std::string bkg_ = "qqH115vsWZttQCD") {
TMVA::Tools::Instance();
TString outfileName( "TMVAElecTau"+ordering_+"Ord_"+bkg_+".root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationElecTau"+ordering_+"Ord_"+bkg_, outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
factory->AddVariable( "pt1", "pT-tag1", "GeV/c" , 'F' );
factory->AddVariable( "pt2", "pT-tag2", "GeV/c" , 'F' );
factory->AddVariable( "Deta","|y-tag1 - y-tag2|","" , 'F' );
//factory->AddVariable( "opposite:=abs(eta1*eta2)/eta1/eta2","sign1*sign2","" , 'F' );
//factory->AddVariable( "Dphi", "#Delta#phi" ,"" , 'F' );
factory->AddVariable( "Mjj", "M(tag1,tag2)", "GeV/c^{2}" , 'F' );
factory->AddSpectator( "eta1", "#eta_{tag1}" , 'F' );
factory->AddSpectator( "eta2", "#eta_{tag2}" , 'F' );
factory->SetWeightExpression( "sampleWeight" );
TString fSignalName = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleVBFH115-powheg-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameDYJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleZjets-alpgen-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameWJets = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleWJets-madgraph-PUS1_Open_ElecTauStream.root";
TString fBackgroundNameQCD = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleQCD_Open_ElecTauStream.root";
TString fBackgroundNameTTbar = "/data_CMS/cms/lbianchini/VbfJetsStudy/OpenNtuples/ElecTauStream2011/nTupleTTJets-madgraph-PUS1_Open_ElecTauStream.root";
TFile *fSignal(0);
TFile *fBackgroundDYJets(0);
TFile *fBackgroundWJets(0);
TFile *fBackgroundQCD(0);
TFile *fBackgroundTTbar(0);
fSignal = TFile::Open( fSignalName );
fBackgroundDYJets = TFile::Open( fBackgroundNameDYJets );
fBackgroundWJets = TFile::Open( fBackgroundNameWJets );
fBackgroundQCD = TFile::Open( fBackgroundNameQCD );
fBackgroundTTbar = TFile::Open( fBackgroundNameTTbar );
if(!fSignal || !fBackgroundDYJets || !fBackgroundWJets || !fBackgroundQCD || !fBackgroundTTbar) {
std::cout << "ERROR: could not open files" << std::endl;
exit(1);
}
TString tree = "outTree"+ordering_+"Ord";
TCut mycuts = "";
TCut mycutb = "";
TCut cutA = "pt1>0 && tightestHPSWP>0";
TCut cutB = "pt1>0 && combRelIsoLeg1<0.1";
TCut cutBl = "pt1>0 && combRelIsoLeg1<0.3";
TCut cutC = "pt1>0 && diTauCharge==0";
TCut cutD = "pt1>0 && MtLeg1<40";
// select events for training
TFile* dummy = new TFile("dummy.root","RECREATE");
TH1F* allEvents = new TH1F("allEvents","",1,-10,10);
float totalEvents, cutEvents;
// signal: all
TTree *signal = ((TTree*)(fSignal->Get(tree)))->CopyTree(cutA&&cutB&&cutC&&cutD);
cout << "Copied signal tree with full selection: " << ((TTree*)(fSignal->Get(tree)))->GetEntries() << " --> " << signal->GetEntries() << endl;
allEvents->Reset();
signal->Draw("eta1>>allEvents","sampleWeight");
cutEvents = allEvents->Integral();
Double_t signalWeight = 1.0;
cout << "Signal: expected yield " << cutEvents << " -- weight " << signalWeight << endl;
// Z+jets: all
TTree *backgroundDYJets = ((TTree*)(fBackgroundDYJets->Get(tree)))->CopyTree(cutA&&cutB&&cutC&&cutD);
cout << "Copied DYJets tree with full selection: " << ((TTree*)(fBackgroundDYJets->Get(tree)))->GetEntries() << " --> " << backgroundDYJets->GetEntries() << endl;
allEvents->Reset();
backgroundDYJets->Draw("eta1>>allEvents","sampleWeight");
cutEvents = allEvents->Integral();
Double_t backgroundDYJetsWeight = 1.0;
cout << "ZJets: expected yield " << cutEvents << " -- weight " << backgroundDYJetsWeight << endl;
// W+jets: iso+Mt
TTree *backgroundWJets = ((TTree*)(fBackgroundWJets->Get(tree)))->CopyTree(cutB&&cutD);
cout << "Copied WJets tree with iso+Mt selection: " << ((TTree*)(fBackgroundWJets->Get(tree)))->GetEntries() << " --> " << backgroundWJets->GetEntries() << endl;
allEvents->Reset();
backgroundWJets->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundWJets->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0)");
cutEvents = allEvents->Integral();
Double_t backgroundWJetsWeight = cutEvents / totalEvents;
cout << "WJets: expected yield " << cutEvents << " -- weight " << backgroundWJetsWeight << endl;
// QCD: Mt+loose iso
TTree *backgroundQCD = ((TTree*)(fBackgroundQCD->Get(tree)))->CopyTree(cutD&&cutBl);
cout << "Copied QCD tree with Mt selection: " << ((TTree*)(fBackgroundQCD->Get(tree)))->GetEntries() << " --> " << backgroundQCD->GetEntries() << endl;
allEvents->Reset();
backgroundQCD->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundQCD->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0 && combRelIsoLeg1<0.1)");
cutEvents = allEvents->Integral();
Double_t backgroundQCDWeight = cutEvents / totalEvents;
cout << "QCD: expected yield " << cutEvents << " -- weight " << backgroundQCDWeight << endl;
// TTbar: iso+Mt
TTree *backgroundTTbar = ((TTree*)(fBackgroundTTbar->Get(tree)))->CopyTree(cutB&&cutD);
cout << "Copied TTbar tree with iso+Mt selection: " << ((TTree*)(fBackgroundTTbar->Get(tree)))->GetEntries() << " --> " << backgroundTTbar->GetEntries() << endl;
allEvents->Reset();
backgroundTTbar->Draw("eta1>>allEvents","sampleWeight");
totalEvents = allEvents->Integral();
allEvents->Reset();
backgroundTTbar->Draw("eta1>>allEvents","sampleWeight*(tightestHPSWP>0 && diTauCharge==0)");
cutEvents = allEvents->Integral();
Double_t backgroundTTbarWeight = cutEvents / totalEvents;
cout << "TTbar: expected yield " << cutEvents << " -- weight " << backgroundTTbarWeight << endl;
delete allEvents;
factory->AddSignalTree ( signal, signalWeight );
//factory->AddBackgroundTree( backgroundDYJets, backgroundDYJetsWeight );
//factory->AddBackgroundTree( backgroundWJets, backgroundWJetsWeight );
factory->AddBackgroundTree( backgroundQCD, backgroundQCDWeight );
//factory->AddBackgroundTree( backgroundTTbar, backgroundTTbarWeight );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=1:nTest_Background=1:SplitMode=Random:NormMode=NumEvents:!V" );
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=GA:EffSel:CutRangeMin[0]=25.:CutRangeMax[0]=999:CutRangeMin[1]=25.:CutRangeMax[1]=999.:CutRangeMin[2]=1.0:CutRangeMax[2]=9.:CutRangeMin[3]=100:CutRangeMax[3]=7000:VarProp=FSmart" );
/*
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=200:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
*/
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
//------------------------------------------------------------------------------
// MVATrain
//------------------------------------------------------------------------------
void MVATrain(float metPfType1_cut, float mt2ll_cut, TString signal)
{
TFile* outputfile = TFile::Open(trainingdir + signal + ".root", "recreate");
// Factory
//----------------------------------------------------------------------------
TMVA::Factory* factory = new TMVA::Factory(signal, outputfile,
// "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
"!V:!Silent:Color:DrawProgressBar:AnalysisType=Classification");
// Get the trees
//----------------------------------------------------------------------------
_mctree.clear();
AddProcess("signal" , signal);//"01_Data_reduced_1outof6"); //signal
AddProcess("background", "04_TTTo2L2Nu");
/*AddProcess("background", "14_HZ");
AddProcess("background", "10_HWW");
AddProcess("background", "06_WW");
AddProcess("background", "02_WZTo3LNu");
AddProcess("background", "03_VZ");
AddProcess("background", "11_Wg");
AddProcess("background", "07_ZJets");
AddProcess("background", "09_TTV");
AddProcess("background", "05_ST");
AddProcess("background", "00_Fakes_reduced_1outof6");*/
Double_t weight = 1.0;
factory->AddSignalTree(_signaltree, weight);
for (UInt_t i=0; i<_mctree.size(); i++) factory->AddBackgroundTree(_mctree[i], weight);
factory->SetWeightExpression("eventW");
// Add variables
//----------------------------------------------------------------------------
// Be careful with the order: it must be respected at the reading step
// factory->AddVariable("<var1>+<var2>", "pretty title", "unit", 'F');
factory->AddVariable("newdarkpt" , "", "", 'F');
//factory->AddVariable("topRecoW" , "", "", 'F');
//factory->AddVariable("lep1pt" , "", "", 'F');
//factory->AddVariable("lep1eta" , "", "", 'F');
//factory->AddVariable("lep1phi" , "", "", 'F');
//factory->AddVariable("lep1mass" , "", "", 'F');
//factory->AddVariable("lep2pt" , "", "", 'F');
//factory->AddVariable("lep2eta" , "", "", 'F');
//factory->AddVariable("lep2phi" , "", "", 'F');
//factory->AddVariable("lep2mass" , "", "", 'F');
//factory->AddVariable("jet1pt " , "", "", 'F');
//factory->AddVariable("jet1eta" , "", "", 'F');
//factory->AddVariable("jet1phi" , "", "", 'F');
//factory->AddVariable("jet1mass" , "", "", 'F');
//factory->AddVariable("jet2pt" , "", "", 'F');
//factory->AddVariable("jet2eta" , "", "", 'F');
//factory->AddVariable("jet2phi" , "", "", 'F');
//factory->AddVariable("jet2mass" , "", "", 'F');
factory->AddVariable("metPfType1" , "", "", 'F');
//factory->AddVariable("metPfType1Phi", "", "", 'F');
//factory->AddVariable("m2l" , "", "", 'F');
factory->AddVariable("mt2ll" , "", "", 'F');
//factory->AddVariable("mt2lblb" , "", "", 'F');
//factory->AddVariable("mtw1" , "", "", 'F');
//factory->AddVariable("mtw2" , "", "", 'F');
//factory->AddVariable("ht" , "", "", 'F');
//factory->AddVariable("htjets" , "", "", 'F');
//factory->AddVariable("htnojets" , "", "", 'F');
//factory->AddVariable("njet" , "", "", 'F');
//factory->AddVariable("nbjet30csvv2l", "", "", 'F');
//factory->AddVariable("nbjet30csvv2m", "", "", 'F');
//factory->AddVariable("nbjet30csvv2t", "", "", 'F');
//factory->AddVariable("dphijet1met" , "", "", 'F');
//factory->AddVariable("dphijet2met" , "", "", 'F');
//factory->AddVariable("dphijj" , "", "", 'F');
//factory->AddVariable("dphijjmet" , "", "", 'F');
//factory->AddVariable("dphill" , "", "", 'F');
//factory->AddVariable("dphilep1jet1" , "", "", 'F');
//factory->AddVariable("dphilep1jet2" , "", "", 'F');
//factory->AddVariable("dphilep2jet1" , "", "", 'F');
//factory->AddVariable("dphilep2jet2" , "", "", 'F');
//factory->AddVariable("dphilmet1" , "", "", 'F');
//factory->AddVariable("dphilmet2" , "", "", 'F');
factory->AddVariable("dphillmet" , "", "", 'F');
//factory->AddVariable("sphericity" , "", "", 'F');
//factory->AddVariable("alignment" , "", "", 'F');
//factory->AddVariable("planarity" , "", "", 'F');
// Preselection cuts and preparation
//----------------------------------------------------------------------------
//factory->PrepareTrainingAndTestTree(Form("metPfType1>%5.2f&&mt2ll>%5.2f&&newdarkpt>0.", metPfType1_cut, mt2ll_cut), "NormMode=EqualNumEvents:nTrain_Signal=80:nTest_Signal=80:nTrain_Background=400:nTest_Background=400:!V");
factory->PrepareTrainingAndTestTree("mt2ll>100.&&newdarkpt>0.&&metPfType1>80.", "NormMode=EqualNumEvents:nTrain_Signal=0:nTest_Signal=0:nTrain_Background=0:nTest_Background=0:!V");
// Book MVA
//----------------------------------------------------------------------------
factory->BookMethod(TMVA::Types::kMLP, "MLP01",
"H:!V:NeuronType=sigmoid:NCycles=500:VarTransform=Norm:HiddenLayers=6,3:TestRate=1:LearningRate=0.005");
//factory->BookMethod(TMVA::Types::kMLP, "MLP01",
// "H:!V:NeuronType=sigmoid:NCycles=500:VarTransform=Norm:HiddenLayers=4,4:TestRate=3:LearningRate=0.005");
//factory->BookMethod(TMVA::Types::kMLP, "MLP02",
// "H:!V:NeuronType=sigmoid:NCycles=40:VarTransform=Norm:HiddenLayers=20,10:TestRate=3:LearningRate=0.005");
//factory->BookMethod(TMVA::Types::kMLP, "MLP03",
// "H:!V:NeuronType=sigmoid:NCycles=30:VarTransform=Norm:HiddenLayers=20,20:TestRate=3:LearningRate=0.005");
//factory->BookMethod(TMVA::Types::kBDT, "BDT04", "NTrees=50:MaxDepth=2" );
//factory->BookMethod(TMVA::Types::kBDT, "BDT05", "NTrees=50:MaxDepth=3" );
// Train, test and evaluate MVA
//----------------------------------------------------------------------------
factory->TrainAllMethods(); // Train using the set of training events
factory->TestAllMethods(); // Evaluate using the set of test events
factory->EvaluateAllMethods(); // Evaluate and compare performance
// Save the output
//----------------------------------------------------------------------------
outputfile->Close();
delete factory;
}
void TMVAClassification_qgl( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Fisher"] = 0;
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
// --- Boosted Decision Trees
Use["BDTB"] = 0; // decorrelation + Adaptive Boost
Use["BDTG"] = 0;
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 1;
Use["LikelihoodMIX"] = 0;
//
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
// TString outfileName( "TMVA_bjet_new_powheg.root" );
int set_type=1;
TString type[2] = {"_double","_single"};
TString outfileName( "TMVA_qgl"+type[set_type]+"_2jet_1.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
factory->AddVariable( "Jet_pt", "Jet p_{T}", "GeV", 'F' );
factory->AddVariable( "Jet_eta", "Jet #eta", "", 'F' );
factory->AddVariable( "Jet_ptd", "Jet ptd", "", 'F' );
factory->AddVariable( "Jet_axis2", "Jet axis2", "", 'F' );
factory->AddVariable( "Jet_mult", "Jet multiplicity", "", 'I' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
//
TString fname_signal ="/afs/cern.ch/work/n/nchernya/Hbb/qgl_mva/qgl_tmva_tree_VBFHToBB_M-125_13TeV_powheg_v14"+type[set_type]+"_2jets.root";
TString fname_bg ="/afs/cern.ch/work/n/nchernya/Hbb/qgl_mva/qgl_tmva_tree_BTagCSV_v14"+type[set_type]+"_2jets.root";
if (gSystem->AccessPathName( fname_signal )) { // file does not exist in local directory
cout<<"input file "<< fname_signal<<" doesn't exist!"<<endl;
//break;
}
if (gSystem->AccessPathName( fname_bg)) { // file does not exist in local directory
cout<<"input file "<< fname_bg<<" doesn't exist!"<<endl;
//break;
}
// gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *input_signal = TFile::Open( fname_signal );
TFile *input_bg = TFile::Open( fname_bg );
std::cout << "--- TMVAClassification : Using input signal file: " << input_signal->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input bg file: " << input_bg->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)input_signal->Get("QGL_1");
TTree *bg = (TTree*)input_bg->Get("QGL_1");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t bgWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( bg, bgWeight );
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTG"]) //
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=120:MinNodeSize=6%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=3:NegWeightTreatment=IgnoreNegWeightsInTraining" );
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVARegression( int optimIndex, int Cat=0, TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVARegression.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 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 TMVARegression" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TString outfileName( Form("TMVAoutput/TMVAReg_%i.root",optimIndex) );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( Form("TMVARegression_%i_Cat%i",optimIndex,Cat), outputFile,
"!V:!Silent:!Color:!DrawProgressBar:Transformations=I:AnalysisType=Regression" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "jet_eta", "jet_eta", "units", 'F' );
factory->AddVariable( "jet_emfrac", "jet_emfrac", "units", 'F' );
factory->AddVariable( "jet_hadfrac", "jet_hadfrac", "units", 'F' );
factory->AddVariable( "jet_nconstituents", "jet_nconst", "units", 'F' );
factory->AddVariable( "jet_vtx3dL", "jet_vtx3dL", "units", 'F' );
factory->AddVariable( "MET", "MET", "units", 'F' );
factory->AddVariable( "jet_dPhiMETJet", "jet_dPhiMETJet", "units", 'F' );
//factory->AddVariable( "hJet_vtxPt", "hJet_vtxPt", "units", 'F' );
//factory->AddVariable( "hJet_JECUnc", "hJet_JECUnc", "units", 'F' );
//factory->AddVariable( "hJet_ptLeadTrack", "hJet_ptLeadTrack", "units", 'F' );
//factory->AddVariable( "hJet_SoftLeptPtCut:=(hJet_SoftLeptIdlooseMu>0. || hJet_SoftLeptId95>0.) ? (hJet_SoftLeptPt) : (-99)", "hJet_SoftLeptPt", "units", 'F' );
//factory->AddVariable( "hJet_En", "hJet_En", "units", 'F' );
//factory->AddVariable( "hJet_Et", "hJet_Et", "units", 'F' );
//factory->AddVariable( "hJet_Mt", "hJet_Mt", "units", 'F' );
//factory->AddVariable( "hJet_nch", "hJet_nch", "units", 'F' );
//factory->AddVariable( "hJet_vtx3deL", "hJet_vtx3deL", "units", 'F' );
//factory->AddVariable( "hJet_vtxMass", "hJet_vtxMass", "units", 'F' );
//factory->AddVariable( "hJet_ptRaw", "hJet_ptRaw", "units", 'F' );
//factory->AddVariable( "hJet_EnRaw", "hJet_EnRaw", "units", 'F' );
//factory->AddVariable( "hJet_SoftLeptptRelCut:=(hJet_SoftLeptIdlooseMu>0. || hJet_SoftLeptId95>0.) ? (hJet_SoftLeptptRel) : (-99)", "hJet_SoftLeptptRel", "units", 'F' );
//factory->AddVariable( "hJet_SoftLeptdRCut:=(hJet_SoftLeptIdlooseMu>0. || hJet_SoftLeptId95>0.) ? (hJet_SoftLeptdR) : (-99)", "hJet_SoftLeptdR", "units", 'F' );
//factory->AddVariable( "rho25", "rho25", "units", 'F' );
//factory->AddVariable( "dPhiMETJet", "dPhiMETJet", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// Add the variable carrying the regression target
//factory->AddTarget( "jet_genPt" );
factory->AddTarget( "jet_genJetPt/jet_pt" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// Read training and test data (see TMVAClassification for reading ASCII files)
// load the signal and background event samples from ROOT trees
/* TFile *input(0);
TString fname = "./tmva_reg_example.root";
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_reg_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
// --- Register the regression tree
TTree *regTree = (TTree*)input->Get("TreeR");
*/
TChain chainTraining("Events");
chainTraining.Add("TrainingFiles/training.root");
TTree *regTreeTraining = (TTree*) chainTraining;
TChain chainTesting("Events");
chainTesting.Add("TrainingFiles/testing.root");
TTree *regTreeTesting = (TTree*) chainTesting;
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddTree( regTreeTraining, "Regression", regWeight, "", "training" );
factory->AddTree( regTreeTesting, "Regression", regWeight, "", "test" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = "hJet_pt[0]>20. && hJet_pt[1]>20. && fabs(hJet_eta[0])<2.5 && fabs(hJet_eta[1])<2.5 && hJet_csv[0]>0. && hJet_csv[1]>0. && hJet_ptLeadTrack[0]<1500. && hJet_ptLeadTrack[1]<1500. && hJet_genJetPt[0]>0. && hJet_genJetPt[1]>0. && hJet_puJetIdL[0]>0.0 && hJet_puJetIdL[1]>0.0";
TCut testingCut = "hJet_pt[0]>20. && hJet_pt[1]>20. && abs(hJet_eta[0])<2.5 && abs(hJet_eta[1])<2.5";
TCut mjjCut = "sqrt(pow(hJet_pt[0]*cos(hJet_phi[0])+hJet_pt[1]*cos(hJet_phi[1]),2)+pow(hJet_pt[0]*sin(hJet_phi[0])+hJet_pt[1]*sin(hJet_phi[1]),2)) < 110";
if(Cat==1) mjjCut = "sqrt(pow(hJet_pt[0]*cos(hJet_phi[0])+hJet_pt[1]*cos(hJet_phi[1]),2)+pow(hJet_pt[0]*sin(hJet_phi[0])+hJet_pt[1]*sin(hJet_phi[1]),2)) > 110";
TCut jetPtCut="jet_pt>90";
if(Cat==1) jetPtCut="jet_pt>90";
//TCut trainingCut = "hJet_pt[0]>20. && hJet_pt[1]>20. && abs(hJet_eta[0])<2.5 && abs(hJet_eta[1])<2.5 && hJet_genJetPt[0]>0. && hJet_genJetPt[1]>0. && hJet_csv[0]>0.0 && hJet_csv[1]>0.0 && hJet_ptLeadTrack[0]<1500. && hJet_ptLeadTrack[1]<1500.";
TCut trainingCut = "jet_pt>20. && abs(jet_eta)<2.5 && jet_genJetPt>0. && jet_dRJetGenJet < 0.4 && (jet_partonID)==5";
// for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// tell the factory to use all remaining events in the trees after training for testing:
// factory->PrepareTrainingAndTestTree(mycut, "nTrain_Regression=600000:nTest_Regression=600000:SplitMode=Random:NormMode=NumEvents:!V");
//factory->PrepareTrainingAndTestTree(mycut, "nTrain_Regression=337500:nTest_Regression=337500:SplitMode=Random:NormMode=NumEvents:!V");
// factory->PrepareTrainingAndTestTree(mycut, "nTrain_Regression=158393:nTest_Regression=158393:SplitMode=Random:NormMode=NumEvents:!V");
//factory->PrepareTrainingAndTestTree(mycut, "nTrain_Regression=14197:nTest_Regression=14197:SplitMode=Random:NormMode=NumEvents:!V");
factory->PrepareTrainingAndTestTree(trainingCut+jetPtCut, "!V");
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=40:NEventsMax=60:VarTransform=None" );
// And the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:MultiTargetRegression=F:TargetSelection=Mpv:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Compress=T:Kernel=None:Nmin=10:VarTransform=None" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// Linear discriminant
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD",
"!H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=MC:SampleSize=100000:Sigma=0.1:VarTransform=D" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options) .. the formula of this example is good for parabolas
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:PopSize=100:Cycles=3:Steps=30:Trim=True:SaveBestGen=1:VarTransform=Norm" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
// Neural network (MLP)
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=20000:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
//100, 5
// Boosted Decision Tree //100,5 nCuts=-1
if (Use["BDT"])
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=100:nEventsMin=4:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=-1:PruneMethod=CostComplexity:PruneStrength=30" );
const bool doScan1=0;
int ntreesArray[8] = {100,200,300,400,500,600,700,800};
float shrinkageArray[3] = {0.1,0.2,0.3};
float gradbaggingfracArray[3] = {0.7,0.8,0.9};
int maxdepthArray[3] = {2,3,4};
int nnodesmaxArray[3] = {5,10,15};
if(!doScan1) shrinkageArray[2]=1.0;
int nnodesmaxIndex=-1,maxdepthIndex=-1,gradbaggingfracIndex=-1,shrinkageIndex=-1,ntreesIndex=-1;
if(doScan1){
nnodesmaxIndex = optimIndex/216;
maxdepthIndex = (optimIndex-nnodesmaxIndex*216)/72;
gradbaggingfracIndex = (optimIndex-nnodesmaxIndex*216-maxdepthIndex*72)/24;
shrinkageIndex = (optimIndex-nnodesmaxIndex*216-maxdepthIndex*72-gradbaggingfracIndex*24)/8;
ntreesIndex = (optimIndex-nnodesmaxIndex*216-maxdepthIndex*72-gradbaggingfracIndex*24-shrinkageIndex*8);
}
else{
nnodesmaxIndex = optimIndex/72;
maxdepthIndex = (optimIndex-nnodesmaxIndex*72)/24;
shrinkageIndex = (optimIndex-nnodesmaxIndex*72-maxdepthIndex*24)/8;
ntreesIndex = (optimIndex-nnodesmaxIndex*72-maxdepthIndex*24-shrinkageIndex*8);
}
if (Use["BDTG"]){
if(doScan1)
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
Form("!H:!V:NTrees=%i::BoostType=Grad:Shrinkage=%.1f:UseBaggedGrad:GradBaggingFraction=%.1f:nCuts=200:MaxDepth=%i:NNodesMax=%i",ntreesArray[ntreesIndex],shrinkageArray[shrinkageIndex],gradbaggingfracArray[gradbaggingfracIndex],maxdepthArray[maxdepthIndex],nnodesmaxArray[nnodesmaxIndex]) );
else
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
Form("!H:!V:IgnoreNegWeights:NTrees=%i::BoostType=Grad:Shrinkage=%.1f:nCuts=200:MaxDepth=%i:NNodesMax=%i",ntreesArray[ntreesIndex],shrinkageArray[shrinkageIndex],maxdepthArray[maxdepthIndex],nnodesmaxArray[nnodesmaxIndex]) );
}
if(doScan1)
cout << Form("!H:!V:NTrees=%i::BoostType=Grad:Shrinkage=%.2f:UseBaggedGrad:GradBaggingFraction=%.2f:nCuts=200:MaxDepth=%i:NNodesMax=%i",ntreesArray[ntreesIndex],shrinkageArray[shrinkageIndex],gradbaggingfracArray[gradbaggingfracIndex],maxdepthArray[maxdepthIndex],nnodesmaxArray[nnodesmaxIndex])<<endl;
else
cout << Form("!H:!V:IgnoreNegWeights:NTrees=%i::BoostType=Grad:Shrinkage=%.1f:nCuts=200:MaxDepth=%i:NNodesMax=%i",ntreesArray[ntreesIndex],shrinkageArray[shrinkageIndex],maxdepthArray[maxdepthIndex],nnodesmaxArray[nnodesmaxIndex]) << endl;
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVARegGui( outfileName );
}
void TMVAClassification_cc1pcoh_bdt_verFF( TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
// Choose method
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// ---------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA_cc1pcoh_bdt_verFF.root" );//newchange
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object.
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification_verFF", outputFile,//newchange
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// Add variable
//sprintf(select, "Ntrack==2&&mumucl>0.6&&pmucl>0.25&&pang<90&&muang_t<15 && veract*7.66339869e-2<34");
factory->AddVariable( "mumucl", 'F' );
factory->AddVariable( "pmucl", 'F' );
factory->AddVariable( "pang_t", 'F' );//this is fixed with backward
factory->AddVariable( "muang_t", 'F' );
factory->AddVariable( "ppe", 'F');
factory->AddVariable( "mupe", 'F');
factory->AddVariable( "rangetot", 'F');//total range in PM and INGRID
factory->AddVariable( "prangetot", 'F');//total range in PM and INGRID
factory->AddVariable( "coplanarity", 'F');
factory->AddVariable( "opening", 'F');//newadd
// Add spectator
factory->AddSpectator( "fileIndex", 'I' );
factory->AddSpectator( "nuE", 'F' );
factory->AddSpectator( "inttype", 'I' );
factory->AddSpectator( "norm", 'F' );
factory->AddSpectator( "totcrsne", 'F' );
factory->AddSpectator( "veract", 'F' );
// ---------------------------------------------------------------
// --- Get weight
TString fratioStr="/home/kikawa/macros/nd34_tuned_11bv3.1_250ka.root";
// ---------------------------------------------------------------
// --- Add sample
TString fsignalStr="/home/cvson/cc1picoh/dataProcess/fix20150420/pm_merged_ccqe_tot.root";
TString fbarStr="/home/cvson/cc1picoh/dataProcess/fix20150420/pmbar_merged_ccqe.root";
TString fbkgStr="/home/cvson/cc1picoh/dataProcess/fix20150420/wall_merged_ccqe_tot.root";
TString fbkg2Str="/home/cvson/cc1picoh/dataProcess/fix20150420/ingrid_merged_nd3_ccqe_tot.root";
TFile *pfileSignal = new TFile(fsignalStr);
TFile *pfileBar = new TFile(fbarStr);
TFile *pfileBkg = new TFile(fbkgStr);
TFile *pfileBkg2 = new TFile(fbkg2Str);
TFile *pfileRatio = new TFile(fratioStr);
TTree *ptree_sig = (TTree*)pfileSignal->Get("tree");
TTree *ptree_bar = (TTree*)pfileBar->Get("tree");
TTree *ptree_bkg = (TTree*)pfileBkg->Get("tree");
TTree *ptree_bkg2 = (TTree*)pfileBkg2->Get("tree");
// POT normalization
const int nmcFile = 3950;
const int nbarFile = 986;
const int nbkgFile = 55546;//(31085+24461);
const int nbkg2File = 7882;//(3941+3941);
// global event weights per tree (see below for setting event-wise weights)
// adding for signal sample
// using this as standard and add other later
Double_t signalWeight_sig = 1.0;
Double_t backgroundWeight_sig = 1.0;
factory->AddSignalTree ( ptree_sig, signalWeight_sig );
factory->AddBackgroundTree( ptree_sig, backgroundWeight_sig );
// Add Numubar sample
//Double_t signalWeight_bar = nmcFile/float(nbarFile);
Double_t backgroundWeight_bar = nmcFile/float(nbarFile);
//factory->AddSignalTree ( ptree_bar, signalWeight_bar );
factory->AddBackgroundTree( ptree_bar, backgroundWeight_bar );
// Add wall background
//Double_t signalWeight_bkg = nmcFile/float(nbkgFile);
Double_t backgroundWeight_bkg = nmcFile/float(nbkgFile);
//factory->AddSignalTree ( ptree_bkg, signalWeight_bkg );
factory->AddBackgroundTree( ptree_bkg, backgroundWeight_bkg );
// Add INGRID background
//Double_t signalWeight_bkg2 = nmcFile/float(nbkg2File);
Double_t backgroundWeight_bkg2 = nmcFile/float(nbkg2File);
//factory->AddSignalTree ( ptree_bkg2, signalWeight_bkg2 );
factory->AddBackgroundTree( ptree_bkg2, backgroundWeight_bkg2 );
//factory->SetSignalWeightExpression ("norm*totcrsne*2.8647e-13");
//factory->SetBackgroundWeightExpression( "norm*totcrsne*2.8647e-13" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "Ntrack==2 && abs(inttype)==16 && fileIndex==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "Ntrack==2 && (abs(inttype)!=16 || fileIndex>1)"; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
/*if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );*/
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void tmva_test_lite(const int sigreg = true){
const string outfileName("TMVA.root");
TFile* outputFile = TFile::Open(outfileName.c_str(),"RECREATE");
string name;
if(!sigreg) name = string("MVAnalysisLite");
else name = string("MVAnalysis_sig_Lite");
TMVA::Factory *factory = new TMVA::Factory(name.c_str(),outputFile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification");
TFile *inputSig = TFile::Open("/home/vitaly/B0toDh0/Tuples/fil_b2dh_sigmc.root");
TFile *inputBack = TFile::Open("/home/vitaly/B0toDh0/Tuples/fil_b2dh_cont.root");
// TFile *tfile = new TFile("","RECREATE");
TTree* insigtree = (TTree*)inputSig->Get("TEventTr");
TTree* inbacktree = (TTree*)inputBack->Get("TEventTr");
factory->AddVariable("abs(cos_b0)");
// factory->AddVariable("p_ks");
factory->AddVariable("log(chi2_ndf_D0)");
// factory->AddVariable("log(chi2_ndf_B0)");
// factory->AddVariable("log(chi2_tag_vtx/ndf_tag_vtx)");
factory->AddVariable("abs(cos_thr)");
factory->AddVariable("thr_sig");
factory->AddVariable("thr_oth");
factory->AddVariable("log(tag_LH_err)");
// factory->AddVariable("log(dzerr)");
// factory->AddVariable("log(pi0_chi2)");
// factory->AddVariable("log(egamma)");
// factory->AddVariable("log(ptgamma)");
factory->AddVariable("k1mm2");
factory->AddVariable("k1et");
factory->AddVariable("k1hso00");
// factory->AddVariable("k1hso01");
factory->AddVariable("k1hso02");
// factory->AddVariable("k1hso03");
factory->AddVariable("k1hso04");
factory->AddVariable("k1hso10");
factory->AddVariable("k1hso12");
factory->AddVariable("k1hso14");
factory->AddVariable("k1hso20");
factory->AddVariable("k1hso22");
factory->AddVariable("k1hso24");
factory->AddVariable("k1hoo0");
factory->AddVariable("k1hoo1");
factory->AddVariable("k1hoo2");
factory->AddVariable("k1hoo3");
factory->AddVariable("k1hoo4");
// factory->AddVariable("k0mm2");
// factory->AddVariable("k0et");
// factory->AddVariable("k0hso00");
// factory->AddVariable("k0hso02");
// factory->AddVariable("k0hso04");
// factory->AddVariable("k0hso10");
// factory->AddVariable("k0hso12");
// factory->AddVariable("k0hso14");
// factory->AddVariable("k0hso20");
// factory->AddVariable("k0hso22");
// factory->AddVariable("k0hso24");
// factory->AddVariable("k0hoo0");
// factory->AddVariable("k0hoo1");
// factory->AddVariable("k0hoo2");
// factory->AddVariable("k0hoo4");
factory->AddSignalTree(insigtree,1.0);
factory->AddBackgroundTree(inbacktree,1.0);
// string Common_precuts("mbc>5.271 && mbc<5.289 && de<0.08 && de>-0.1 && chi2_ndf_B0<1000 && abs(mks_raw-0.4975)<0.009 && abs(md0_raw-1.865)<0.015 && abs(mpi0_raw-0.135)<0.012");
string Common_precuts("chi2_ndf_B0<1000 && de<0.1 && de>-0.1 && mbc>5.25 && mbc<5.289");
if(sigreg) Common_precuts += string(" && mbc>5.271 && mbc<5.289 && de<0.08 && de>-0.1");
string sig_cuts = Common_precuts;// + string("");
string back_cuts = Common_precuts;// + string(" && abs(md0_raw-1.865)<0.030 && abs(mpi0_raw-0.135)<0.030");
TCut cutsig(sig_cuts.c_str());
TCut cutback(back_cuts.c_str());
factory->PrepareTrainingAndTestTree(cutsig,cutback,"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// factory->BookMethod( TMVA::Types::kCuts, "Cuts","!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
// factory->BookMethod(TMVA::Types::kBDT,"BDTG","!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggedFraction=0.6:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrenght=50:NNodesMax=5");
factory->BookMethod(TMVA::Types::kBDT,"BDTG","!H:!V:NTrees=800:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:NNodesMax=5");
factory->BookMethod(TMVA::Types::kBDT,"BDT","!H:!V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName.c_str() );
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 1;
Use["CutsGA"] = 1;
Use["CutsSA"] = 1;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 1; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 1;
Use["LikelihoodMIX"] = 1;
// ---
Use["PDERS"] = 1;
Use["PDERSD"] = 1;
Use["PDERSPCA"] = 1;
Use["PDERSkNN"] = 1; // depreciated until further notice
Use["PDEFoam"] = 1;
// --
Use["KNN"] = 1;
// ---
Use["HMatrix"] = 1;
Use["Fisher"] = 1;
Use["FisherG"] = 1;
Use["BoostedFisher"] = 1;
Use["LD"] = 1;
// ---
Use["FDA_GA"] = 1;
Use["FDA_SA"] = 1;
Use["FDA_MC"] = 1;
Use["FDA_MT"] = 1;
Use["FDA_GAMT"] = 1;
Use["FDA_MCMT"] = 1;
// ---
Use["MLP"] = 1; // this is the recommended ANN
Use["MLPBFGS"] = 1; // recommended ANN with optional training method
Use["CFMlpANN"] = 1; // *** missing
Use["TMlpANN"] = 1;
// ---
Use["SVM"] = 1;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 1;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 1;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "myvar1 := var1+var2", 'F' );
factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
factory->AddVariable( "var3", "Variable 3", "units", 'F' );
factory->AddVariable( "var4", "Variable 4", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// read training and test data
if (ReadDataFromAsciiIFormat) {
// load the signal and background event samples from ascii files
// format in file must be:
// var1/F:var2/F:var3/F:var4/F
// 0.04551 0.59923 0.32400 -0.19170
// ...
TString datFileS = "tmva_example_sig.dat";
TString datFileB = "tmva_example_bkg.dat";
factory->SetInputTrees( datFileS, datFileB );
}
else {
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = "../macros/tmva_example.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
else {
input = TFile::Open( "http://root.cern.ch/files/tmva_class_example.root" ); // if not: download from ROOT server
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS" );
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=400:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethodsForClassification();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void Boost2(){
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString tmva_dir(TString(gRootDir) + "/tmva");
if(gSystem->Getenv("TMVASYS"))
tmva_dir = TString(gSystem->Getenv("TMVASYS"));
gROOT->SetMacroPath(tmva_dir + "/test/:" + gROOT->GetMacroPath() );
gROOT->ProcessLine(".L TMVAGui.C");
TString outfileName = "boost.root";
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
factory->AddVariable( "var0", 'F' );
factory->AddVariable( "var1", 'F' );
TFile *input(0);
TString fname = "./circledata.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find data.root in the local directory
std::cout << "--- BOOST : Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
else {
gROOT->LoadMacro( "./createData.C");
create_fullcirc(20000);
cout << " created circledata.root with data and circle arranged in circles"<<endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
gROOT->cd( outfileName+TString(":/") );
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
factory->PrepareTrainingAndTestTree( "", "",
"nTrain_Signal=10000:nTrain_Background=10000:SplitMode=Random:NormMode=NumEvents:!V" );
TString fisher="!H:!V";
factory->BookMethod( TMVA::Types::kFisher, "Fisher", fisher );
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher", "!H:V:NTrees=150:NCuts=101:MaxDepth=1:UseFisherCuts:UseExclusiveVars:MinLinCorrForFisher=0." );
// factory->BookMethod( TMVA::Types::kFisher, "FisherBS", fisher+":Boost_Num=100:Boost_Type=Bagging:Boost_Transform=step" );
factory->BookMethod( TMVA::Types::kFisher, "FisherS", fisher+":Boost_Num=150:Boost_Type=AdaBoost:Boost_Transform=step" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void trainMVACat()
{
char name[1000];
float XSEC[6] = {3.67e+5,2.94e+4,6.524e+03,1.064e+03,121.5,2.542e+01};
float NORM[6];
TCut preselectionCut = "ht>400 && jetPt[5]>40 && (triggerBit[0] || triggerBit[2]) && nBJets>1 && nLeptons==0";
TFile *bkgSrc[6];
bkgSrc[0] = TFile::Open("flatTree_QCD_HT300to500.root");
bkgSrc[1] = TFile::Open("flatTree_QCD_HT500to700.root");
bkgSrc[2] = TFile::Open("flatTree_QCD_HT700to1000.root");
bkgSrc[3] = TFile::Open("flatTree_QCD_HT1000to1500.root");
bkgSrc[4] = TFile::Open("flatTree_QCD_HT1500to2000.root");
bkgSrc[5] = TFile::Open("flatTree_QCD_HT2000toInf.root");
TFile *sigSrc = TFile::Open("flatTree_ttHJetTobb_M125.root");
//TFile *sigSrc = TFile::Open("flatTree_TT.root");
TTree *sigTree = (TTree*)sigSrc->Get("hadtop/events");
TTree *bkgTree[6];
TFile *outf = new TFile("mva_Cat_QCD.root","RECREATE");
TMVA::Factory* factory = new TMVA::Factory("factory_mva_Cat_QCD_",outf,"!V:!Silent:Color:DrawProgressBar:Transformations=I;G:AnalysisType=Classification");
factory->AddSignalTree(sigTree);
for(int k=0;k<6;k++) {
NORM[k] = ((TH1F*)bkgSrc[k]->Get("hadtop/pileup"))->GetEntries();
bkgTree[k] = (TTree*)bkgSrc[k]->Get("hadtop/events");
factory->AddBackgroundTree(bkgTree[k],XSEC[k]/NORM[k]);
}
//int N_SIG(sigTree->GetEntries(preselectionCut));
//int N_BKG0(bkgTree[0]->GetEntries(preselectionCut));
//int N_BKG1(bkgTree[1]->GetEntries(preselectionCut));
//int N_BKG2(bkgTree[2]->GetEntries(preselectionCut));
//int N_BKG3(bkgTree[3]->GetEntries(preselectionCut));
//float N_BKG_EFF = N_BKG0*XSEC[0]/NORM[0]+N_BKG1*XSEC[1]/NORM[1]+N_BKG2*XSEC[2]/NORM[2]+N_BKG3*XSEC[3]/NORM[3];
//int N = TMath::Min((float)N_SIG,N_BKG_EFF);
//cout<<N_SIG<<" "<<N_BKG_EFF<<endl;
const int NVAR = 21;
TString VAR[NVAR] = {
"nJets",
//"nBJets",
"ht",
"jetPt[0]","jetPt[1]","jetPt[2]","jetPt[3]","jetPt[4]","jetPt[5]",
"mbbMin","dRbbMin",
//"dRbbAve","mbbAve",
//"btagAve","btagMax","btagMin",
//"qglAve","qglMin","qglMedian",
"sphericity","aplanarity","foxWolfram[0]","foxWolfram[1]","foxWolfram[2]","foxWolfram[3]",
"mTop[0]","ptTTbar","mTTbar","dRbbTop","chi2"
};
char TYPE[NVAR] = {
'I',
//'I',
'F',
'F','F','F','F','F','F',
'F','F',
//'F','F',
//'F','F','F',
//'F','F','F',
'F','F','F','F','F','F',
'F','F','F','F','F'
};
for(int i=0;i<NVAR;i++) {
factory->AddVariable(VAR[i],TYPE[i]);
}
factory->AddSpectator("status",'I');
factory->AddSpectator("nBJets",'I');
sprintf(name,"nTrain_Signal=%d:nTrain_Background=%d:nTest_Signal=%d:nTest_Background=%d",-1,-1,-1,-1);
factory->PrepareTrainingAndTestTree(preselectionCut,name);
TMVA::IMethod* BDT_Category = factory->BookMethod( TMVA::Types::kCategory,"BDT_Category");
TMVA::MethodCategory* mcategory_BDT = dynamic_cast<TMVA::MethodCategory*>(BDT_Category);
mcategory_BDT->AddMethod("status == 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kBDT,
"BDT_Cat1",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status == 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kBDT,
"BDT_Cat2",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status < 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kBDT,
"BDT_Cat3",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
mcategory_BDT->AddMethod("status < 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kBDT,
"BDT_Cat4",
"NTrees=2000:BoostType=Grad:Shrinkage=0.1");
TMVA::IMethod* Fisher_Category = factory->BookMethod( TMVA::Types::kCategory,"Fisher_Category");
TMVA::MethodCategory* mcategory_Fisher = dynamic_cast<TMVA::MethodCategory*>(Fisher_Category);
mcategory_Fisher->AddMethod("status == 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kFisher,
"Fisher_Cat1","H:!V:Fisher");
mcategory_Fisher->AddMethod("status == 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:mTop[0]:ptTTbar:mTTbar:dRbbTop:chi2:",
TMVA::Types::kFisher,
"Fisher_Cat2","H:!V:Fisher");
mcategory_Fisher->AddMethod("status < 0 && nBJets == 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kFisher,
"Fisher_Cat3","H:!V:Fisher");
mcategory_Fisher->AddMethod("status < 0 && nBJets > 2",
"nJets:ht:jetPt[0]:jetPt[1]:jetPt[2]:jetPt[3]:jetPt[4]:jetPt[5]:mbbMin:dRbbMin:sphericity:aplanarity:foxWolfram[0]:foxWolfram[1]:foxWolfram[2]:foxWolfram[3]:",
TMVA::Types::kFisher,
"Fisher_Cat4","H:!V:Fisher");
// specify the training methods
//factory->BookMethod(TMVA::Types::kFisher,"Fisher");
//factory->BookMethod(TMVA::Types::kBDT,"BDT_GRAD_2000","NTrees=2000:BoostType=Grad:Shrinkage=0.1");
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outf->Close();
}
void Training_BDT(TString channel, bool isZHvsOther, TString cat){
TString name;
if (isZHvsOther) name="ZHvsOther";
else name="TTvsDY";
if (channel=="Mu") name=name+"_Mu";
else name=name+"_El";
if (cat=="2j")name=name+"_2j";
else if(cat=="2j") name=name+"_3j";
else name=name+"_noCat";
TMVA::Tools::Instance();
TFile* outputFile = TFile::Open( "outputtrainning"+name+".root", "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "BDT_NN_trainning"+name, outputFile,"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );;
//TFile *input = TFile::Open( "study_histo.root" );
TFile *inputTT = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/TTFullLept_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputDYM10 = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/DYjets_M10to50_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputDY = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/DYjets_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputZZ = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/ZZ_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputZH = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/ZH125_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputWW = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/WW_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputWZ = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/WZ_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputWt = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/Wt_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputWtbar = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/Wtbar_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TFile *inputTTSemi = TFile::Open( "/home/fynu/cbeluffi/storage/RDS/5320_JP_Skimmed_V5/llbbX/TTSemiLept_Summer12_final_skimed_llbbX_withWeights_V3.root" );
TTree *signal = (TTree*)inputZH->Get("rds_zbb");
TTree *backgroundDY = (TTree*)inputDY->Get("rds_zbb");
TTree *backgroundZZ = (TTree*)inputZZ->Get("rds_zbb");
TTree *backgroundTT = (TTree*)inputTT->Get("rds_zbb");
TTree *backgroundDYM10 = (TTree*)inputDYM10->Get("rds_zbb");
TTree *backgroundWW = (TTree*)inputWW->Get("rds_zbb");
TTree *backgroundWZ = (TTree*)inputWZ->Get("rds_zbb");
TTree *backgroundWt = (TTree*)inputWt->Get("rds_zbb");
TTree *backgroundWtbar = (TTree*)inputWtbar->Get("rds_zbb");
TTree *backgroundTTSemi = (TTree*)inputTTSemi->Get("rds_zbb");
if (isZHvsOther ){
factory->AddSignalTree( signal , 1.2);
factory->AddBackgroundTree( backgroundDY, 0.54);
factory->AddBackgroundTree( backgroundZZ, 0.1);
factory->AddBackgroundTree( backgroundDYM10, 0.02);
factory->AddBackgroundTree( backgroundTT, 0.3);
factory->AddBackgroundTree(backgroundWW , 0.005);
factory->AddBackgroundTree(backgroundWZ , 0.005);
factory->AddBackgroundTree(backgroundWt , 0.01);
factory->AddBackgroundTree(backgroundWtbar ,0.01 );
factory->AddBackgroundTree(backgroundTTSemi ,0.01 );
}
else{
factory->AddSignalTree( backgroundDY , 1.0);
factory->AddBackgroundTree( backgroundTT, 1.0);
}
if (isZHvsOther ){
factory->AddVariable("MinusLogW_ZH_cor3", 'F');
factory->AddVariable("MinusLogW_ZH_cor0", 'F');
factory->AddVariable("MinusLogW_ZZ_cor3", 'F');
factory->AddVariable("MinusLogW_ZZ_cor0", 'F');
factory->AddVariable("MinusLogW_TT", 'F');
factory->AddVariable("MinusLogW_gg_Zbb", 'F');
factory->AddVariable("MinusLogW_qq_Zbb", 'F');
}
else{
factory->AddVariable("MinusLogW_TT", 'F');
factory->AddVariable("MinusLogW_gg_Zbb", 'F');
factory->AddVariable("MinusLogW_qq_Zbb", 'F');
}
TCut mycuts, mycutb;
if(isZHvsOther){
if(channel=="Mu"){
if(cat=="2j"){
mycuts = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj==2 && (eventSelectiondijetM_inc > 80 && eventSelectiondijetM_inc < 150))";
mycutb = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj==2 && (eventSelectiondijetM_inc > 80 && eventSelectiondijetM_inc < 150))";
}
else{
mycuts = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj>2 && (eventSelectiondijetM_inc > 50 && eventSelectiondijetM_inc < 150))";
mycutb = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj>2 && (eventSelectiondijetM_inc > 50 && eventSelectiondijetM_inc < 150))";
}
}
else {
if(cat=="2j"){
mycuts = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj==2 && (eventSelectiondijetM_inc > 80 && eventSelectiondijetM_inc < 150))";
mycutb = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj==2 && (eventSelectiondijetM_inc > 80 && eventSelectiondijetM_inc < 150))";
}
else{
mycuts = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj>2 && (eventSelectiondijetM_inc > 50 && eventSelectiondijetM_inc < 150))";
mycutb = "(MinusLogW_ZH_cor3 > 2 && MinusLogW_ZH_cor0 > 2 &&MinusLogW_ZZ_cor0> 2 &&MinusLogW_ZZ_cor3> 2 &&MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_ZH_cor3<50 && MinusLogW_ZH_cor0<50 &&MinusLogW_ZZ_cor0<50 &&MinusLogW_ZZ_cor3<50 &&MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 76 && eventSelectiondilepM_inc < 106 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30&& jetmetnj>2 && (eventSelectiondijetM_inc > 50 && eventSelectiondijetM_inc < 150))";
}
}
}
else{
if(channel=="Mu"){
mycuts = "(MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 60 && eventSelectiondilepM_inc < 120 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30)";
mycutb = "(MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_6_idx && eventSelectionmu1pt_inc>20 && eventSelectionmu2pt_inc>20 && eventSelectiondilepM_inc > 60 && eventSelectiondilepM_inc < 120 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30)";
}
else {
mycuts = "(MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 60 && eventSelectiondilepM_inc < 120 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30)";
mycutb = "(MinusLogW_TT> 2 &&MinusLogW_gg_Zbb> 2 &&MinusLogW_qq_Zbb> 2)&&(MinusLogW_TT<50 &&MinusLogW_gg_Zbb<50 &&MinusLogW_qq_Zbb<50)&& (rc_stage_16_idx && eventSelectionel1pt_inc>20 && eventSelectionel2pt_inc>20 && eventSelectiondilepM_inc > 60 && eventSelectiondilepM_inc < 120 && jetmetMETsignificance<10 && jetmetbjet1pt>30 && jetmetbjet2pt>30)";
}
}
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
if (isZHvsOther)factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=40:nEventsMin=600:MaxDepth=10:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
else factory->BookMethod( TMVA::Types::kBDT, "BDT", "!H:!V:NTrees=50:nEventsMin=1000:MaxDepth=20:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (isZHvsOther)factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=1000:HiddenLayers=N+6:TestRate=5:!UseRegulator" );
else factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=500:HiddenLayers=N+2:TestRate=5:!UseRegulator" );
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch() ) TMVAGui( "outputtrainning"+name+".root" );
}
void TMVARegression( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVARegression.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 1;
Use["KNN"] = 1;
//
// --- Linear Discriminant Analysis
Use["LD"] = 1;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 1;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0;
Use["BDTG"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TString outfileName( "TMVAReg.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory->AddVariable( "var1", "Variable 1", "units", 'F' );
factory->AddVariable( "var2", "Variable 2", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
factory->AddTarget( "fvalue" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
// Read training and test data (see TMVAClassification for reading ASCII files)
// load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = "./tmva_reg_example.root";
if (!gSystem->AccessPathName( fname ))
input = TFile::Open( fname ); // check if file in local directory exists
else
input = TFile::Open( "http://root.cern.ch/files/tmva_reg_example.root" ); // if not: download from ROOT server
if (!input) {
std::cout << "ERROR: could not open data file" << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
// --- Register the regression tree
TTree *regTree = (TTree*)input->Get("TreeR");
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddRegressionTree( regTree, regWeight );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
factory->SetWeightExpression( "var1", "Regression" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = ""; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=40:NEventsMax=60:VarTransform=None" );
// And the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:MultiTargetRegression=F:TargetSelection=Mpv:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Compress=T:Kernel=None:Nmin=10:VarTransform=None" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// Linear discriminant
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD",
"!H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=MC:SampleSize=100000:Sigma=0.1:VarTransform=D" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options) .. the formula of this example is good for parabolas
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:PopSize=100:Cycles=3:Steps=30:Trim=True:SaveBestGen=1:VarTransform=Norm" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
// Neural network (MLP)
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=20000:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDT"])
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=100:MinNodeSize=1.0%:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
if (Use["BDTG"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000::BoostType=Grad:Shrinkage=0.1:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=3:MaxDepth=4" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVARegGui( outfileName );
}
void ZTMVAClassification_norm( TString myMethodList = "" ) {
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 1; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// ADD IN OUR VARIABLES HERE
factory->AddVariable("log(kaon_IPCHI2_OWNPV)", "log(kaon_IPCHI2_OWNPV)", "", 'D');
factory->AddVariable("kaon_TRACK_GhostProb", "kaon_TRACK_GhostProb", "", 'D');
factory->AddVariable("kaon_PT", "kaon_PT", "", 'D');
factory->AddVariable("log(proton_IPCHI2_OWNPV)", "log(proton_IPCHI2_OWNPV)", "", 'D');
factory->AddVariable("proton_TRACK_GhostProb", "proton_TRACK_GhostProb", "", 'D');
factory->AddVariable("proton_PT", "proton_PT", "", 'D');
factory->AddVariable("muminus_ProbNNmu", "muminus_ProbNNmu", "", 'D');
factory->AddVariable("muminus_TRACK_GhostProb", "muminus_TRACK_GhostProb", "", 'D');
factory->AddVariable("muplus_ProbNNmu", "muplus_ProbNNmu", "", 'D');
factory->AddVariable("muplus_TRACK_GhostProb", "muplus_TRACK_GhostProb", "", 'D');
factory->AddVariable("Lambda_b0_DTF_CHI2NDOF", "Lambda_b0_DTF_CHI2NDOF", "", 'D');
factory->AddVariable("log(Lambda_b0_IPCHI2_OWNPV)", "log(Lambda_b0_IPCHI2_OWNPV)", "", 'D');
factory->AddVariable("Lambda_b0_PT", "Lambda_b0_PT", "", 'D');
factory->AddVariable("Lambda_b0_FDS", "Lambda_b0_FDS", "", 'D');
// TFile * input_Background = new TFile("../back.root");
TFile * input_Signal = new TFile("/afs/cern.ch/work/a/apmorris/private/cern/ntuples/new_tuples/normalisation_samples/reduced_Lb2JpsipK_MC_2011_2012_norm.root");
TFile * input_Background = new TFile("/afs/cern.ch/work/a/apmorris/private/cern/ntuples/new_tuples/normalisation_samples/background.root");
std::cout << "--- TMVAClassification : Using input file for signal : " << input_Signal->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input file for background : " << input_Background->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)input_Signal->Get("DecayTree");
TTree *background = (TTree*)input_Background->Get("DecayTree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"]){
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
//factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=Norm:NCycles=600:HiddenLayers=N+5:TestRate=5" );
// factory->BookMethod( TMVA::Types::kMLP, "MLPCE", "H:!V:NeuronType=sigmoid:VarTransform=Norm:NCycles=600:HiddenLayers=N+5:TestRate=5:EstimatorType=CE" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=sigmoid:VarTransform=Norm:NCycles=600:HiddenLayers=9:TestRate=5:EstimatorType=CE" );
// factory->BookMethod( TMVA::Types::kMLP, "MLPCE83", "H:!V:NeuronType=tanh:VarTransform=Norm:NCycles=600:HiddenLayers=8,3:TestRate=5:EstimatorType=CE" );
}
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) { // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTGI",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5:SeparationType=GiniIndexWithLaplace" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG6",
// "!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
//factory->BookMethod( TMVA::Types::kBDT, "BDTG2",
// "!H:!V:NTrees=800:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
factory->BookMethod( TMVA::Types::kBDT, "BDTG3",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG4",
// "!H:!V:NTrees=1200:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=6" );
// factory->BookMethod( TMVA::Types::kBDT, "BDTG5",
// "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.4:nCuts=20:NNodesMax=5" );
}
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}