void TMVAMulticlassApplication( TString myMethodList = "" )
{
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 1;
Use["BDTG"] = 1;
Use["FDA_GA"] = 0;
Use["PDEFoam"] = 0;
//---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAMulticlassApplication" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " " << std::endl;
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// create the Reader object
TMVA::Reader *reader = new TMVA::Reader( "!Color:!Silent" );
// create a set of variables and declare them to the reader
// - the variable names must corresponds in name and type to
// those given in the weight file(s) that you use
Float_t var1, var2, var3, var4;
reader->AddVariable( "var1", &var1 );
reader->AddVariable( "var2", &var2 );
reader->AddVariable( "var3", &var3 );
reader->AddVariable( "var4", &var4 );
// book the MVA methods
TString dir = "dataset/weights/";
TString prefix = "TMVAMulticlass";
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) {
if (it->second) {
TString methodName = TString(it->first) + TString(" method");
TString weightfile = dir + prefix + TString("_") + TString(it->first) + TString(".weights.xml");
reader->BookMVA( methodName, weightfile );
}
}
// book output histograms
UInt_t nbin = 100;
TH1F *histMLP_signal(0), *histBDTG_signal(0), *histFDAGA_signal(0), *histPDEFoam_signal(0);
if (Use["MLP"])
histMLP_signal = new TH1F( "MVA_MLP_signal", "MVA_MLP_signal", nbin, 0., 1.1 );
if (Use["BDTG"])
histBDTG_signal = new TH1F( "MVA_BDTG_signal", "MVA_BDTG_signal", nbin, 0., 1.1 );
if (Use["FDA_GA"])
histFDAGA_signal = new TH1F( "MVA_FDA_GA_signal", "MVA_FDA_GA_signal", nbin, 0., 1.1 );
if (Use["PDEFoam"])
histPDEFoam_signal = new TH1F( "MVA_PDEFoam_signal", "MVA_PDEFoam_signal", nbin, 0., 1.1 );
TFile *input(0);
TString fname = "./tmva_example_multiple_background.root";
if (!gSystem->AccessPathName( fname )) {
input = TFile::Open( fname ); // check if file in local directory exists
}
if (!input) {
std::cout << "ERROR: could not open data file, please generate example data first!" << std::endl;
exit(1);
}
std::cout << "--- TMVAMulticlassApp : Using input file: " << input->GetName() << std::endl;
// prepare the tree
// - here the variable names have to corresponds to your tree
// - you can use the same variables as above which is slightly faster,
// but of course you can use different ones and copy the values inside the event loop
TTree* theTree = (TTree*)input->Get("TreeS");
std::cout << "--- Select signal sample" << std::endl;
theTree->SetBranchAddress( "var1", &var1 );
theTree->SetBranchAddress( "var2", &var2 );
theTree->SetBranchAddress( "var3", &var3 );
theTree->SetBranchAddress( "var4", &var4 );
std::cout << "--- Processing: " << theTree->GetEntries() << " events" << std::endl;
TStopwatch sw;
sw.Start();
for (Long64_t ievt=0; ievt<theTree->GetEntries();ievt++) {
if (ievt%1000 == 0){
std::cout << "--- ... Processing event: " << ievt << std::endl;
}
theTree->GetEntry(ievt);
if (Use["MLP"])
histMLP_signal->Fill((reader->EvaluateMulticlass( "MLP method" ))[0]);
if (Use["BDTG"])
histBDTG_signal->Fill((reader->EvaluateMulticlass( "BDTG method" ))[0]);
if (Use["FDA_GA"])
histFDAGA_signal->Fill((reader->EvaluateMulticlass( "FDA_GA method" ))[0]);
if (Use["PDEFoam"])
histPDEFoam_signal->Fill((reader->EvaluateMulticlass( "PDEFoam method" ))[0]);
}
// get elapsed time
sw.Stop();
std::cout << "--- End of event loop: "; sw.Print();
TFile *target = new TFile( "TMVAMulticlassApp.root","RECREATE" );
if (Use["MLP"])
histMLP_signal->Write();
if (Use["BDTG"])
histBDTG_signal->Write();
if (Use["FDA_GA"])
histFDAGA_signal->Write();
if (Use["PDEFoam"])
histPDEFoam_signal->Write();
target->Close();
std::cout << "--- Created root file: \"TMVMulticlassApp.root\" containing the MVA output histograms" << std::endl;
delete reader;
std::cout << "==> TMVAClassificationApplication is done!" << std::endl << std::endl;
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName" << std::endl ;
return 1;
}
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString){
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
//==== list of methods
std::string MVADirectory = gConfigParser -> readStringOption ("Options::MVADirectory");
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
std::vector<std::string> vectorMyMethodMassList = gConfigParser -> readStringListOption("Options::MVAmethodsMass");
std::string outputDirectory = gConfigParser -> readStringOption("Output::outputDirectory");
//---- variables
float jetpt1;
float jetpt2;
float mjj;
float detajj;
float dphilljetjet;
float pt1;
float pt2;
float mll;
float dphill;
float mth;
float dphillmet;
float mpmet;
float channel;
//~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
TFile* outputRootFile[500];
TTree* cloneTreeJetLepVect[500];
TTree *treeJetLepVect[500];
TFile* file[500];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++){
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
file[iSample] = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) file[iSample]->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
treeJetLepVect[iSample] -> SetBranchAddress("jetpt1", &jetpt1);
treeJetLepVect[iSample] -> SetBranchAddress("jetpt2", &jetpt2);
treeJetLepVect[iSample] -> SetBranchAddress("mjj", &mjj);
treeJetLepVect[iSample] -> SetBranchAddress("detajj", &detajj);
treeJetLepVect[iSample] -> SetBranchAddress("dphilljetjet", &dphilljetjet);
treeJetLepVect[iSample] -> SetBranchAddress("pt1", &pt1);
treeJetLepVect[iSample] -> SetBranchAddress("pt2", &pt2);
treeJetLepVect[iSample] -> SetBranchAddress("mll", &mll);
treeJetLepVect[iSample] -> SetBranchAddress("dphill", &dphill);
treeJetLepVect[iSample] -> SetBranchAddress("mth", &mth);
treeJetLepVect[iSample] -> SetBranchAddress("dphillmet", &dphillmet);
treeJetLepVect[iSample] -> SetBranchAddress("mpmet", &mpmet);
treeJetLepVect[iSample] -> SetBranchAddress("channel", &channel);
sprintf(nameFile,"%s/%s%s.root",outputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
outputRootFile[iSample] = new TFile ( nameFile, "RECREATE") ;
outputRootFile[iSample] -> cd () ;
cloneTreeJetLepVect[iSample] = treeJetLepVect[iSample] -> CloneTree (0) ;
}
/**
* cycle on MVA (method-mass)
* * cycle on samples
* * * cycle on events
*/
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
std::cout << " vectorMyMethodList[" << iMVA << "] = " << vectorMyMethodList.at(iMVA) << std::endl;
TString myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
for (int iMVAMass = 0; iMVAMass < vectorMyMethodMassList.size(); iMVAMass++) {
std::cout << " vectorMyMethodMassList[" << iMVAMass << "] = " << vectorMyMethodMassList.at(iMVAMass) << std::endl;
TMVA::Reader *TMVAreader = new TMVA::Reader( "!Color:!Silent" );
// TMVAreader->AddVariable("jetpt1", &jetpt1);
// TMVAreader->AddVariable("jetpt2", &jetpt2);
// TMVAreader->AddVariable("mjj", &mjj);
// TMVAreader->AddVariable("detajj", &detajj);
// TMVAreader->AddVariable("dphilljetjet", &dphilljetjet);
// TMVAreader->AddVariable("pt1", &pt1);
// TMVAreader->AddVariable("pt2", &pt2);
// TMVAreader->AddVariable("mll", &mll);
// TMVAreader->AddVariable("dphill", &dphill);
// TMVAreader->AddVariable("mth", &mth);
// TMVAreader->AddVariable("dphillmet", &dphillmet);
// TMVAreader->AddVariable("mpmet", &mpmet);
Float_t input_variables[1000];
// float input_variables[1000];
// TMVAreader->AddVariable("jetpt1", &(input_variables[0]));
// TMVAreader->AddVariable("jetpt2", &(input_variables[1]));
// TMVAreader->AddVariable("mjj", &(input_variables[2]));
// TMVAreader->AddVariable("detajj", &(input_variables[3]));
// TMVAreader->AddVariable("dphilljetjet", &(input_variables[4]));
// TMVAreader->AddVariable("pt1", &(input_variables[5]));
// TMVAreader->AddVariable("pt2", &(input_variables[6]));
// TMVAreader->AddVariable("mll", &(input_variables[7]));
// TMVAreader->AddVariable("dphill", &(input_variables[8]));
// TMVAreader->AddVariable("mth", &(input_variables[9]));
// TMVAreader->AddVariable("dphillmet", &(input_variables[10]));
// TMVAreader->AddVariable("mpmet", &(input_variables[11]));
TMVAreader->AddVariable("jetpt1", &input_variables[0]);
TMVAreader->AddVariable("jetpt2", &input_variables[1]);
TMVAreader->AddVariable("mjj", &input_variables[2]);
TMVAreader->AddVariable("detajj", &input_variables[3]);
TMVAreader->AddVariable("dphilljetjet", &input_variables[4]);
TMVAreader->AddVariable("pt1", &input_variables[5]);
TMVAreader->AddVariable("pt2", &input_variables[6]);
TMVAreader->AddVariable("mll", &input_variables[7]);
TMVAreader->AddVariable("dphill", &input_variables[8]);
TMVAreader->AddVariable("mth", &input_variables[9]);
TMVAreader->AddVariable("dphillmet", &input_variables[10]);
TMVAreader->AddVariable("mpmet", &input_variables[11]);
TMVAreader->AddSpectator("channel", &input_variables[12]);
TString myMethodMassList = Form ("%s",vectorMyMethodMassList.at(iMVAMass).c_str());
TString weightfile = Form ("%s/weights_%s_testVariables/TMVAMulticlass_%s.weights.xml",MVADirectory.c_str(),myMethodMassList.Data(),myMethodList.Data());
std::cout << " myMethodList = " << myMethodList.Data() << std::endl;
std::cout << " weightfile = " << weightfile.Data() << std::endl;
// TString myMethodListBook = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
// TMVAreader->BookMVA( myMethodListBook, weightfile );
TMVAreader->BookMVA( myMethodList, weightfile );
for (int iSample=0; iSample<numberOfSamples; iSample++){
std::cout << " iSample = " << iSample << " :: " << numberOfSamples << std::endl;
file[iSample] -> cd();
Double_t MVA_Value;
TBranch *newBranch;
TString methodName4Tree = Form ("%s_%s_MVAHiggs",myMethodList.Data(),myMethodMassList.Data());
TString methodName4Tree2 = Form ("%s_%s_MVAHiggs/D",myMethodList.Data(),myMethodMassList.Data());
newBranch = cloneTreeJetLepVect[iSample]->Branch(methodName4Tree,&MVA_Value,methodName4Tree2);
// newBranch = treeJetLepVect[iSample]->Branch(methodName4Tree,&MVA_Value,methodName4Tree2);
///==== loop ====
Long64_t nentries = treeJetLepVect[iSample]->GetEntries();
for (Long64_t iEntry = 0; iEntry < nentries; iEntry++){
if((iEntry%1000) == 0) std::cout << ">>>>> analysis::GetEntry " << iEntry << " : " << nentries << std::endl;
treeJetLepVect[iSample]->GetEntry(iEntry);
input_variables[0] = static_cast<Float_t>(jetpt1);
input_variables[1] = static_cast<Float_t>(jetpt2);
input_variables[2] = static_cast<Float_t>(mjj);
input_variables[3] = static_cast<Float_t>(detajj);
input_variables[4] = static_cast<Float_t>(dphilljetjet);
input_variables[5] = static_cast<Float_t>(pt1);
input_variables[6] = static_cast<Float_t>(pt2);
input_variables[7] = static_cast<Float_t>(mll);
input_variables[8] = static_cast<Float_t>(dphill);
input_variables[9] = static_cast<Float_t>(mth);
input_variables[10] = static_cast<Float_t>(dphillmet);
input_variables[11] = static_cast<Float_t>(mpmet);
input_variables[12] = static_cast<Float_t>(channel);
int num = TMVAreader->EvaluateMulticlass(myMethodList).size();
double max = -1e9;
double tempmax;
int numsel = -1;
for (int inum = 0; inum<(num-2); inum++) { // il -2 รจ dovuto a Sig e Bkg che mi salva il training! Uffi!
tempmax = (TMVAreader->EvaluateMulticlass(myMethodList))[inum];
if (tempmax > max) {
max = tempmax;
numsel = inum;
}
}
MVA_Value = max + 3*numsel;
// newBranch -> Fill();
cloneTreeJetLepVect[iSample] -> Fill () ;
}
}
}
}
for (int iSample=0; iSample<numberOfSamples; iSample++){
// save only the new version of the tree
// treeJetLepVect[iSample]->Write("", TObject::kOverwrite);
cloneTreeJetLepVect[iSample] -> SetName (treeName.c_str());
cloneTreeJetLepVect[iSample] -> AutoSave () ;
outputRootFile[iSample] -> Close () ;
}
}
int testPyGTBMulticlass(){
// Get data file
std::cout << "Get test data..." << std::endl;
TString fname = "./tmva_example_multiple_background.root";
if (gSystem->AccessPathName(fname)){ // file does not exist in local directory
std::cout << "Create multiclass test data..." << std::endl;
TString createDataMacro = TString(gROOT->GetTutorialsDir()) + "/tmva/createData.C";
gROOT->ProcessLine(TString::Format(".L %s",createDataMacro.Data()));
gROOT->ProcessLine("create_MultipleBackground(200)");
std::cout << "Created " << fname << " for tests of the multiclass features" << std::endl;
}
TFile *input = TFile::Open(fname);
// Setup PyMVA and factory
std::cout << "Setup TMVA..." << std::endl;
TMVA::PyMethodBase::PyInitialize();
TFile* outputFile = TFile::Open("ResultsTestPyGTBMulticlass.root", "RECREATE");
TMVA::Factory *factory = new TMVA::Factory("testPyGTBMulticlass", outputFile,
"!V:Silent:Color:!DrawProgressBar:AnalysisType=multiclass");
// Load data
TMVA::DataLoader *dataloader = new TMVA::DataLoader("datasetTestPyGTBMulticlass");
TTree *signal = (TTree*)input->Get("TreeS");
TTree *background0 = (TTree*)input->Get("TreeB0");
TTree *background1 = (TTree*)input->Get("TreeB1");
TTree *background2 = (TTree*)input->Get("TreeB2");
dataloader->AddTree(signal, "Signal");
dataloader->AddTree(background0, "Background_0");
dataloader->AddTree(background1, "Background_1");
dataloader->AddTree(background2, "Background_2");
dataloader->AddVariable("var1");
dataloader->AddVariable("var2");
dataloader->AddVariable("var3");
dataloader->AddVariable("var4");
dataloader->PrepareTrainingAndTestTree("",
"SplitMode=Random:NormMode=NumEvents:!V");
// Book and train method
factory->BookMethod(dataloader, TMVA::Types::kPyGTB, "PyGTB",
"!H:!V:VarTransform=None:NEstimators=100:Verbose=0");
std::cout << "Train classifier..." << std::endl;
factory->TrainAllMethods();
// Clean-up
delete factory;
delete dataloader;
delete outputFile;
// Setup reader
UInt_t numEvents = 100;
std::cout << "Run reader and classify " << numEvents << " events..." << std::endl;
TMVA::Reader *reader = new TMVA::Reader("!Color:Silent");
Float_t vars[4];
reader->AddVariable("var1", vars+0);
reader->AddVariable("var2", vars+1);
reader->AddVariable("var3", vars+2);
reader->AddVariable("var4", vars+3);
reader->BookMVA("PyGTB", "datasetTestPyGTBMulticlass/weights/testPyGTBMulticlass_PyGTB.weights.xml");
// Get mean response of method on signal and background events
signal->SetBranchAddress("var1", vars+0);
signal->SetBranchAddress("var2", vars+1);
signal->SetBranchAddress("var3", vars+2);
signal->SetBranchAddress("var4", vars+3);
background0->SetBranchAddress("var1", vars+0);
background0->SetBranchAddress("var2", vars+1);
background0->SetBranchAddress("var3", vars+2);
background0->SetBranchAddress("var4", vars+3);
background1->SetBranchAddress("var1", vars+0);
background1->SetBranchAddress("var2", vars+1);
background1->SetBranchAddress("var3", vars+2);
background1->SetBranchAddress("var4", vars+3);
background2->SetBranchAddress("var1", vars+0);
background2->SetBranchAddress("var2", vars+1);
background2->SetBranchAddress("var3", vars+2);
background2->SetBranchAddress("var4", vars+3);
Float_t meanMvaSignal = 0;
Float_t meanMvaBackground0 = 0;
Float_t meanMvaBackground1 = 0;
Float_t meanMvaBackground2 = 0;
for(UInt_t i=0; i<numEvents; i++){
signal->GetEntry(i);
meanMvaSignal += reader->EvaluateMulticlass("PyGTB")[0];
background0->GetEntry(i);
meanMvaBackground0 += reader->EvaluateMulticlass("PyGTB")[1];
background1->GetEntry(i);
meanMvaBackground1 += reader->EvaluateMulticlass("PyGTB")[2];
background2->GetEntry(i);
meanMvaBackground2 += reader->EvaluateMulticlass("PyGTB")[3];
}
meanMvaSignal = meanMvaSignal/float(numEvents);
meanMvaBackground0 = meanMvaBackground0/float(numEvents);
meanMvaBackground1 = meanMvaBackground1/float(numEvents);
meanMvaBackground2 = meanMvaBackground2/float(numEvents);
// Check whether the response is obviously better than guessing
std::cout << "Mean MVA response on signal: " << meanMvaSignal << std::endl;
if(meanMvaSignal < 0.3){
std::cout << "[ERROR] Mean response on signal is " << meanMvaSignal << " (<0.3)" << std::endl;
return 1;
}
std::cout << "Mean MVA response on background 0: " << meanMvaBackground0 << std::endl;
if(meanMvaBackground0 < 0.3){
std::cout << "[ERROR] Mean response on background 0 is " << meanMvaBackground0 << " (<0.3)" << std::endl;
return 1;
}
std::cout << "Mean MVA response on background 1: " << meanMvaBackground1 << std::endl;
if(meanMvaBackground0 < 0.3){
std::cout << "[ERROR] Mean response on background 1 is " << meanMvaBackground1 << " (<0.3)" << std::endl;
return 1;
}
std::cout << "Mean MVA response on background 2: " << meanMvaBackground2 << std::endl;
if(meanMvaBackground0 < 0.3){
std::cout << "[ERROR] Mean response on background 2 is " << meanMvaBackground2 << " (<0.3)" << std::endl;
return 1;
}
return 0;
}