int main( int argc, char** argv )
{
// Select methods (don't look at this code - not of interest)
TString methodList;
for (int i=1; i<argc; i++) {
TString regMethod(argv[i]);
if(regMethod=="-b" || regMethod=="--batch") continue;
if (!methodList.IsNull()) methodList += TString(",");
methodList += regMethod;
}
return TMVAKaggleHiggs(methodList);
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
//TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
//gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
//gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable( "pho_ecalClusterIsoR4", "pho_ecalClusterIsoR4", "units", 'F' );
factory->AddVariable( "pho_hcalRechitIsoR4", "pho_hcalRechitIsoR4", "units", 'F' );
factory->AddVariable( "pho_trackIsoR4PtCut20", "pho_trackIsoR4PtCut20", "units", 'F' );
factory->AddVariable( "phoHoverE", "phoHoverE", "units", 'F' );
factory->AddVariable( "phoSigmaIEtaIEta_2012", "phoSigmaIEtaIEta_2012", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
// TString fname = "./tmva_class_example.root";
TString fname = "/net/hisrv0001/home/juliusbl/alex/cut/cutTree.root";
if (gSystem->AccessPathName( fname )) // file does not exist in local directory
gSystem->Exec("curl -O http://root.cern.ch/files/tmva_class_example.root");
TFile *input = TFile::Open( fname );
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
// --- Register the training and test trees
TTree *signal = (TTree*)input->Get("cutT");
TTree *background = (TTree*)input->Get("cutT");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal, signalWeight );
factory->AddBackgroundTree( background, backgroundWeight );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4], weight;
//
// // Signal
// for (UInt_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2.0) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// // Background (has event weights)
// background->SetBranchAddress( "weight", &weight );
// for (UInt_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (UInt_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (UInt_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight*weight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight*weight );
// }
// --- end ------------------------------------------------------------
//
// --- end of tree registration
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
// factory->SetBackgroundWeightExpression( "weight" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "subid==0"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "subid==1"; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch())
// gROOT->ProcessLine(TString::Format("TMVAGui(\"%s\")", outfileName.Data()));
// efficiencies( TString fin = "TMVA.root", Int_t type = 2, Bool_t useTMVAStyle = kTRUE );
}
//require mumucl>0.6
//opening angle >10
//coplanarity >90
//pang<90
void TMVAClassification_cc1pcoh_bdt_ver6noveract( TString myMethodList = "" )
{
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString thisdir = gSystem->DirName(gInterpreter->GetCurrentMacroName());
gROOT->SetMacroPath(thisdir + ":" + gROOT->GetMacroPath());
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 1;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 1; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 1;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 1;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 1; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 1; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 1; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 1;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 1;
// ---------------------------------------------------------------
// Choose method
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// ---------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVA_cc1pcoh_bdt_ver6noveract.root" );//newchange
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object.
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification_ver6noveract", outputFile,//newchange
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// Add variable
//sprintf(select, "Ntrack==2&&mumucl>0.6&&pmucl>0.25&&pang<90&&muang_t<15 && veract*7.66339869e-2<34");
//factory->AddVariable( "Ntrack", 'F' );
factory->AddVariable( "mumucl", 'F' );
factory->AddVariable( "pmucl", 'F' );
factory->AddVariable( "pang_t", 'F' );//use pang instead of pang_t
factory->AddVariable( "muang_t", 'F' );
//factory->AddVariable( "veract", 'F' );
factory->AddVariable( "ppe", 'F');
factory->AddVariable( "mupe", 'F');
factory->AddVariable( "range", 'F');
factory->AddVariable( "coplanarity", 'F');
factory->AddVariable( "opening", 'F');//newadd
// Add spectator
factory->AddSpectator( "fileIndex", 'I' );
factory->AddSpectator( "nuE", 'F' );
factory->AddSpectator( "inttype", 'I' );
factory->AddSpectator( "norm", 'F' );
factory->AddSpectator( "totcrsne", 'F' );
factory->AddSpectator( "veract", 'F' );
factory->AddSpectator( "pang", 'F' );
factory->AddSpectator( "mupdg", 'I' );
factory->AddSpectator( "ppdg", 'I' );
// ---------------------------------------------------------------
// --- Get weight
TString fratioStr="/home/kikawa/macros/nd34_tuned_11bv3.1_250ka.root";
// ---------------------------------------------------------------
// --- Add sample
TString fsignalStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/pm_merged_ccqe_tot.root";
TString fbarStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/pmbar_merged_ccqe.root";
TString fbkgStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/wall_merged_ccqe_tot.root";
TString fbkg2Str="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmva/ingrid_merged_nd3_ccqe_tot.root";
/*TString fsignalStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/pm_merged_ccqe_tot.root";
TString fbarStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/pmbar_merged_ccqe.root";
TString fbkgStr="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/wall_merged_ccqe_tot.root";
TString fbkg2Str="/home/cvson/cc1picoh/frkikawa/meAna/ip4tmvafix/ingrid_merged_nd3_ccqe_tot.root";*/
TFile *pfileSignal = new TFile(fsignalStr);
TFile *pfileBar = new TFile(fbarStr);
TFile *pfileBkg = new TFile(fbkgStr);
TFile *pfileBkg2 = new TFile(fbkg2Str);
TFile *pfileRatio = new TFile(fratioStr);
TTree *ptree_sig = (TTree*)pfileSignal->Get("tree");
TTree *ptree_bar = (TTree*)pfileBar->Get("tree");
TTree *ptree_bkg = (TTree*)pfileBkg->Get("tree");
TTree *ptree_bkg2 = (TTree*)pfileBkg2->Get("tree");
// POT normalization
const int nmcFile = 3950;
const int nbarFile = 986;
const int nbkgFile = 55546;//(31085+24461);
const int nbkg2File = 7882;//(3941+3941);
// global event weights per tree (see below for setting event-wise weights)
// adding for signal sample
// using this as standard and add other later
Double_t signalWeight_sig = 1.0;
Double_t backgroundWeight_sig = 1.0;
factory->AddSignalTree ( ptree_sig, signalWeight_sig );
factory->AddBackgroundTree( ptree_sig, backgroundWeight_sig );
// Add Numubar sample
//Double_t signalWeight_bar = nmcFile/float(nbarFile);
Double_t backgroundWeight_bar = nmcFile/float(nbarFile);
//factory->AddSignalTree ( ptree_bar, signalWeight_bar );
factory->AddBackgroundTree( ptree_bar, backgroundWeight_bar );
// Add wall background
//Double_t signalWeight_bkg = nmcFile/float(nbkgFile);
Double_t backgroundWeight_bkg = nmcFile/float(nbkgFile);
//factory->AddSignalTree ( ptree_bkg, signalWeight_bkg );
factory->AddBackgroundTree( ptree_bkg, backgroundWeight_bkg );
// Add INGRID background
//Double_t signalWeight_bkg2 = nmcFile/float(nbkg2File);
Double_t backgroundWeight_bkg2 = nmcFile/float(nbkg2File);
//factory->AddSignalTree ( ptree_bkg2, signalWeight_bkg2 );
factory->AddBackgroundTree( ptree_bkg2, backgroundWeight_bkg2 );
//factory->SetSignalWeightExpression ("norm*totcrsne*2.8647e-13");
//factory->SetBackgroundWeightExpression( "norm*totcrsne*2.8647e-13" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "Ntrack==2 && abs(inttype)==16 && fileIndex==1 && pang<90 && mumucl>0.6 && opening>10 && coplanarity>90 && pmucl>0.2"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = "Ntrack==2 && (abs(inttype)!=16 || fileIndex>1) && pang<90 && mumucl>0.6 && opening>10 && coplanarity>90 && pmucl>0.2"; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
/*if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );*/
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
//if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
int main(int argc, char** argv) {
if(argc != 2)
{
std::cerr << ">>>>> analysis.cpp::usage: " << argv[0] << " configFileName MVAconfigFileName" << std::endl ;
return 1;
}
// Parse the config file
parseConfigFile (argv[1]) ;
std::string treeName = gConfigParser -> readStringOption("Input::treeName");
std::string fileSamples = gConfigParser -> readStringOption("Input::fileSamples");
std::string inputDirectory = gConfigParser -> readStringOption("Input::inputDirectory");
std::string inputBeginningFile = "out_NtupleProducer_";
try {
inputBeginningFile = gConfigParser -> readStringOption("Input::inputBeginningFile");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::inputBeginningFile " << inputBeginningFile << std::endl;
double LUMI = gConfigParser -> readDoubleOption("Options::Lumi");
std::vector<std::string> SignalName;
SignalName = gConfigParser -> readStringListOption("Options::SignalName");
for (int iSignalSample=0; iSignalSample<SignalName.size(); iSignalSample++) {
std::cout << " Signal[" << iSignalSample << "] = " << SignalName.at(iSignalSample) << std::endl;
}
std::string nameWeight = "1";
try {
nameWeight = gConfigParser -> readStringOption("Options::nameWeight");
}
catch (char const* exceptionString) {
std::cerr << " exception = " << exceptionString << std::endl;
}
std::cout << ">>>>> Input::nameWeight " << nameWeight << std::endl;
TTree *treeJetLepVect[200];
char *nameSample[1000];
char *nameHumanReadable[1000];
char* xsectionName[1000];
char nameFileIn[1000];
sprintf(nameFileIn,"%s",fileSamples.c_str());
int numberOfSamples = ReadFile(nameFileIn, nameSample, nameHumanReadable, xsectionName);
double Normalization[1000];
double xsection[1000];
for (int iSample=0; iSample<numberOfSamples; iSample++) {
xsection[iSample] = atof(xsectionName[iSample]);
}
for (int iSample=0; iSample<numberOfSamples; iSample++) {
char nameFile[20000];
sprintf(nameFile,"%s/%s%s.root",inputDirectory.c_str(),inputBeginningFile.c_str(),nameSample[iSample]);
TFile* f = new TFile(nameFile, "READ");
treeJetLepVect[iSample] = (TTree*) f->Get(treeName.c_str());
char nameTreeJetLep[100];
sprintf(nameTreeJetLep,"treeJetLep_%d",iSample);
treeJetLepVect[iSample]->SetName(nameTreeJetLep);
double XSection;
XSection = xsection[iSample];
Normalization[iSample] = XSection * LUMI / 1000.;
}
//==== cut
std::string CutFile = gConfigParser -> readStringOption("Selections::CutFile");
std::vector<std::string> vCut;
std::cout << " nCuts = " << ReadFileCut(CutFile, vCut) << std::endl;
std::string Cut;
if (vCut.size() != 0) {
Cut = vCut.at(0);
}
else {
Cut = "1";
}
//==== HiggsMass
std::string HiggsMass = gConfigParser -> readStringOption("Options::HiggsMass");
//==== list of methods
std::vector<std::string> vectorMyMethodList = gConfigParser -> readStringListOption("Options::MVAmethods");
TString myMethodList;
for (int iMVA = 0; iMVA < vectorMyMethodList.size(); iMVA++) {
if (iMVA == 0) myMethodList = Form ("%s",vectorMyMethodList.at(iMVA).c_str());
else myMethodList = Form ("%s,%s",myMethodList.Data(),vectorMyMethodList.at(iMVA).c_str());
}
//==== output
TString outfileName = gConfigParser -> readStringOption("Output::outFileName");
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["MLP"] = 1;
Use["BDTG"] = 1;
Use["FDA_GA"] = 0;
Use["PDEFoam"] = 0;
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return 0;
}
Use[regMethod] = 1;
}
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a new root output file
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "AnalysisType=multiclass:!V:!Silent:!V:Transformations=I;D" );
TMVA::Factory *factory = new TMVA::Factory( "TMVAMulticlass", outputFile, "!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=multiclass" );
factory->AddVariable( "jetpt1" , 'F');
factory->AddVariable( "jetpt2" , 'F');
factory->AddVariable( "mjj" , 'F');
factory->AddVariable( "detajj" , 'F');
factory->AddVariable( "dphilljetjet" , 'F');
factory->AddVariable( "pt1" , 'F');
factory->AddVariable( "pt2" , 'F');
factory->AddVariable( "mll" , 'F');
factory->AddVariable( "dphill" , 'F');
factory->AddVariable( "mth" , 'F');
factory->AddVariable( "dphillmet" , 'F');
factory->AddVariable( "mpmet" , 'F');
factory->AddSpectator( "channel" , 'F');
for (int iSample=0; iSample<numberOfSamples; iSample++) {
int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
if (numEnt != 0) {
if (iSample == 0) factory->AddTree( treeJetLepVect[iSample], "Signal", Normalization[iSample] );
else if (iSample == 1) factory->AddTree( treeJetLepVect[iSample], "Background", Normalization[iSample] );
else factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] , nameWeight.c_str());
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]));
}
}
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
//
// for (int iSample=0; iSample<numberOfSamples; iSample++){
// int numEnt = treeJetLepVect[iSample]->GetEntries(Cut.c_str());
// std::cout << " Sample = " << nameSample[iSample] << " ~ " << nameHumanReadable[iSample] << " --> " << numEnt << std::endl;
// if (numEnt != 0) {
// bool isSig = false;
// for (std::vector<std::string>::const_iterator itSig = SignalName.begin(); itSig != SignalName.end(); itSig++){
// if (nameHumanReadable[iSample] == *itSig) isSig = true;
// }
// if (isSig) {
// // factory->AddTree( treeJetLepVect[iSample], TString("Signal"), Normalization[iSample] ); //---> ci deve essere uno chiamato Signal!
// }
// else {
// factory->AddTree( treeJetLepVect[iSample], TString(nameHumanReadable[iSample]), Normalization[iSample] );
// }
// }
// }
std::cerr << " AAAAAAAAAAAAAAAAAAAAAAAAAAAAA " << std::endl;
TCut mycuts = Cut.c_str();
// factory->SetWeightExpression( nameWeight.c_str() );
// factory->SetBackgroundWeightExpression( nameWeight.c_str() );
// factory->SetSignalWeightExpression ( nameWeight.c_str() );
std::cerr << " BBBBBBBBBBBBBBBBBBBBBBBBBBBBB " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts ,"SplitMode=Random:NormMode=None:!V");
// factory->PrepareTrainingAndTestTree( "" ,"SplitMode=Random:NormMode=None:!V");
std::cerr << " CCCCCCCCCCCCCCCCCCCCCCCCCCCCC " << std::endl;
// gradient boosted decision trees
// if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
if (Use["BDTG"]) factory->BookMethod( TMVA::Types::kBDT, "BDTG", "!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.50:nCuts=20:NNodesMax=8");
// neural network
if (Use["MLP"]) factory->BookMethod( TMVA::Types::kMLP, "MLP", "!H:!V:NeuronType=tanh:NCycles=1000:HiddenLayers=N+5,5:TestRate=5:EstimatorType=MSE");
// functional discriminant with GA minimizer
if (Use["FDA_GA"]) factory->BookMethod( TMVA::Types::kFDA, "FDA_GA", "H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
// PDE-Foam approach
if (Use["PDEFoam"]) factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam", "!H:!V:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
//==== Optimize parameters in MVA methods
// factory->OptimizeAllMethods();
// factory->OptimizeAllMethods("ROCIntegral","Scan");
//==== Train MVAs using the set of training events ====
factory->TrainAllMethods();
//==== Evaluate all MVAs using the set of test events ====
factory->TestAllMethods();
//==== Evaluate and compare performance of all configured MVAs ====
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAnalysis is done!" << std::endl;
delete factory;
//==== change position of weights file
std::string toDo;
toDo = "rm -r Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
toDo = "mv weights Weights-MVA-MultiClass/weights_" + HiggsMass + "_testVariables";
std::cerr << "toDo = " << toDo << std::endl;
system (toDo.c_str());
// Launch the GUI for the root macros
// if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString eventsToTrain = "0", const TString & region = "barrel", const TString index = "", TString myMethodList = "BDT")
{
std::cout << "running classification for " << region << " for " << myMethodList << std::endl;
if( region != "barrel" && region != "endcaps" ) {
std::cout << "Error, region can only be barrel or endcaps. Selected region was: " << region << std::endl;
exit(1);
}
if( index != "" && index != "0" && index != "1" && index != "2" ) {
std::cout << "Error, index can only be \"\", \"0\", \"1\" or \"2\". Selected index was: " << index << std::endl;
exit(1);
}
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
std::exit(2);
}
Use[regMethod] = 1;
}
}
// Input and output file names
TString fnameTrainS = "BsMC12_barrel_preselection";
TString fnameTrainB = "Barrel_preselection";
TString fnameTestS = "BsMC12_barrel_preselection";
TString fnameTestB = "Barrel_preselection";
TString outputFileName = "TMVA_barrel";
TString weightDirName = "barrel";
if( region == "endcaps" ) {
fnameTrainS = "BsMC12_endcaps_preselection";
fnameTrainB = "Endcaps_preselection";
fnameTestS = "BsMC12_endcaps_preselection";
fnameTestB = "Endcaps_preselection";
outputFileName = "TMVA_endcaps";
weightDirName = "endcaps";
}
if( index != "" ) {
fnameTrainS += "_"+index;
fnameTrainB += "_"+index;
TString indexTest = "";
// The test index is the train index +1 (2+1 -> 0)
if( index == "0" ) indexTest = "1";
else if( index == "1" ) indexTest = "2";
else if( index == "2" ) indexTest = "0";
fnameTestS += "_"+indexTest;
fnameTestB += "_"+indexTest;
outputFileName += "_"+index;
weightDirName += index;
}
fnameTrainS = rootDir + fnameTrainS + ".root";
fnameTrainB = rootDir + fnameTrainB + ".root";
fnameTestS = rootDir + fnameTestS + ".root";
fnameTestB = rootDir + fnameTestB + ".root";
outputFileName = rootDir + outputFileName + ".root";
weightDirName = weightsDir + weightDirName + "Weights";
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName(outputFileName);
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// (TMVA::gConfig().GetIONames()).fWeightFileDir = outputFileName;
(TMVA::gConfig().GetIONames()).fWeightFileDir = weightDirName;
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
bool useNewMuonID = false;
factory->AddVariable( "fls3d", "fls3d", "", 'F' );
factory->AddVariable( "alpha", "alpha", "", 'F' );
factory->AddVariable( "pvips", "pvips", "", 'F' );
factory->AddVariable( "iso", "iso", "", 'F' );
factory->AddVariable( "m1iso", "m1iso", "", 'F' );
factory->AddVariable( "m2iso", "m2iso", "", 'F' );
factory->AddVariable( "chi2dof", "chi2/dof", "", 'F' );
if( region == "barrel" ) {
factory->AddVariable( "eta", "eta", "", 'F' );
factory->AddVariable( "maxdoca", "maxdoca", "cm", 'F' );
}
else {
factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
factory->AddVariable( "pvip", "pvip", "cm", 'F' );
}
factory->AddVariable( "docatrk", "docatrk", "cm", 'F' );
// factory->AddVariable( "pt", "pt", "GeV/c", 'F' );
// factory->AddVariable( "closetrk", "closetrk", "", 'I' );
// factory->AddVariable( "y", "y", "", 'F' );
// factory->AddVariable( "l3d", "l3d", "cm", 'F' );
// factory->AddVariable( "cosAlphaXY", "cosAlphaXY", "", 'F' );
// factory->AddVariable( "mu1_dxy", "mu1_dxy", "cm", 'F' );
// factory->AddVariable( "mu2_dxy", "mu2_dxy", "cm", 'F' );
if( useNewMuonID ) {
// New Muon-id
factory->AddVariable( "mu1_MVAMuonID", "mu1_MVAMuonID", "", 'F');
factory->AddVariable( "mu2_MVAMuonID", "mu2_MVAMuonID", "", 'F');
}
// Extra variables
// factory->AddVariable( "mu1_pt", "mu1_pt", "GeV/c", 'F' );
// factory->AddVariable( "mu2_pt", "mu2_pt", "GeV/c", 'F' );
// factory->AddVariable( "pvw8", "pvw8", "", 'F' );
// factory->AddVariable( "cosAlpha3D", "cosAlpha3D", "", 'F' );
// factory->AddVariable( "countTksOfPV", "countTksOfPV", "", 'I' );
// factory->AddVariable( "ctauErrPV", "ctauErrPV", "", 'F' );
// factory->AddVariable( "ctauPV", "ctauPV", "", 'F' );
// factory->AddVariable( "dcaxy", "dcaxy", "", 'F' );
// factory->AddVariable( "mu1_glbTrackProb", "mu1_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu1_nChi2", "mu1_nChi2", "", 'F' );
// factory->AddVariable( "mu1_nMuSegs", "mu1_nMuSegs", "", 'F' );
// factory->AddVariable( "mu1_nMuSegsCln", "mu1_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu1_nPixHits", "mu1_nPixHits", "", 'F' );
// factory->AddVariable( "mu1_nTrHits", "mu1_nTrHits", "", 'F' );
// factory->AddVariable( "mu1_segComp", "mu1_segComp", "", 'F' );
// factory->AddVariable( "mu1_trkEHitsOut", "mu1_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu1_trkVHits", "mu1_trkVHits", "", 'F' );
// factory->AddVariable( "mu1_validFrac", "mu1_validFrac", "", 'F' );
// factory->AddVariable( "mu1_chi2LocMom", "mu1_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu1_chi2LocPos", "mu1_chi2LocPos", "", 'F' );
// factory->AddVariable( "mu2_glbTrackProb", "mu2_glbTrackProb", "", 'F' );
// factory->AddVariable( "mu2_nChi2", "mu2_nChi2", "", 'F' );
// factory->AddVariable( "mu2_nMuSegs", "mu2_nMuSegs", "", 'F' );
// factory->AddVariable( "mu2_nMuSegsCln", "mu2_nMuSegsCln", "", 'F' );
// factory->AddVariable( "mu2_nPixHits", "mu2_nPixHits", "", 'F' );
// factory->AddVariable( "mu2_nTrHits", "mu2_nTrHits", "", 'F' );
// factory->AddVariable( "mu2_segComp", "mu2_segComp", "", 'F' );
// factory->AddVariable( "mu2_trkEHitsOut", "mu2_trkEHitsOut", "", 'F' );
// factory->AddVariable( "mu2_trkVHits", "mu2_trkVHits", "", 'F' );
// factory->AddVariable( "mu2_validFrac", "mu2_validFrac", "", 'F' );
// factory->AddVariable( "mu2_chi2LocMom", "mu2_chi2LocMom", "", 'F' );
// factory->AddVariable( "mu2_chi2LocPos", "mu2_chi2LocPos", "", 'F' );
// factory->AddVariable( "l3d := ctauPV*pt/mass", "l3d", "cm", 'F' );
// factory->AddVariable( "l3dSig := ctauPV/ctauErrPV", "l3dSig", "", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1 := mass*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2 := mass*3", "Spectator 2", "units", 'F' );
factory->AddSpectator( "mass", "mass", "GeV/c^{2}", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
if (gSystem->AccessPathName( fnameTrainS )) { // file does not exist in local directory
std::cout << "Did not access " << fnameTrainS << " exiting." << std::endl;
std::exit(4);
}
//gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *inputTrainS = TFile::Open( fnameTrainS );
TFile *inputTrainB = TFile::Open( fnameTrainB );
TFile *inputTestS = TFile::Open( fnameTestS );
TFile *inputTestB = TFile::Open( fnameTestB );
// --- Register the training and test trees
TTree *signalTrainTree = (TTree*)inputTrainS->Get("probe_tree");
TTree *backgroundTrainTree = (TTree*)inputTrainB->Get("probe_tree");
TTree *signalTestTree = (TTree*)inputTestS->Get("probe_tree");
TTree *backgroundTestTree = (TTree*)inputTestB->Get("probe_tree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalTrainWeight = 1.0;
Double_t backgroundTrainWeight = 1.0;
Double_t signalTestWeight = 1.0;
Double_t backgroundTestWeight = 1.0;
// Decide if using the split and mixing or the full trees
if( fnameTrainS == fnameTestS ) {
if( fnameTrainB != fnameTestB ) {
std::cout << "This macro cannot handle cases where the same signal sample is used for training and testing, but different background samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << std::endl;
// You can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signalTrainTree, signalTrainWeight );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight );
}
else {
if( fnameTrainB == fnameTestB ) {
std::cout << "This macro cannot handle cases where the same background sample is used for training and testing, but different signal samples are used.";
exit(1);
}
std::cout << "--- TMVAClassification : Using input file: " << inputTrainS->GetName() << std::endl;
std::cout << "--- and file: " << inputTrainB->GetName() << " for training and" << std::endl;
std::cout << "--- input file: " << inputTestS->GetName() << std::endl;
std::cout << "--- and file: " << inputTestB->GetName() << " for testing." << std::endl;
// To give different trees for training and testing, do as follows:
factory->AddSignalTree( signalTrainTree, signalTrainWeight, "Training" );
factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
factory->AddBackgroundTree( backgroundTrainTree, backgroundTrainWeight, "Training" );
factory->AddBackgroundTree( backgroundTestTree, backgroundTestWeight, "Test" );
}
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal="+eventsToTrain+":nTrain_Background="+eventsToTrain+":SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "nTrain_Signal=3000:nTrain_Background=3000:nTest_Signal=3000:nTest_Background=3000:SplitMode=Random:NormMode=NumEvents:!V" );
// factory->PrepareTrainingAndTestTree( mycuts, mycutb,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
// factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+8:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=800:nEventsMin=50:MaxDepth=2:BoostType=AdaBoost:AdaBoostBeta=1:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:NNodesMax=5" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:nEventsMin=150:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","GA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
std::cout << "Training all methods" << std::endl;
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
std::cout << "Testing all methods" << std::endl;
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
std::cout << "Evaluating all methods" << std::endl;
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileName );
}
void TMVAClassification( TString myMethodList = "" , TString myModel = "")
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
//---------------------------------------------------------------
// This loads the library
TMVA::Tools::Instance();
// to get access to the GUI and all tmva macros
TString tmva_dir(TString(gRootDir) + "/tmva");
if(gSystem->Getenv("TMVASYS"))
tmva_dir = TString(gSystem->Getenv("TMVASYS"));
gROOT->SetMacroPath(tmva_dir + "/test/:" + gROOT->GetMacroPath() );
gROOT->ProcessLine(".L TMVAGui.C");
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 1;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 0; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
Use["BDTF"] = 0; // allow usage of fisher discriminant for node splitting
//
// --- Friedman's RuleFit method, ie, an optimised series of cuts ("rules")
Use["RuleFit"] = 0;
// ---------------------------------------------------------------
// Default model to be trained + tested
std::map<std::string,int> Model;
// --- Cut optimisation
Model[ "MM" ] = 0; // Mass mechanism
Model[ "RHC_L" ] = 0; // Right Handed Current
Model[ "RHC_E" ] = 0; // Right Handed Current
Model[ "M1" ] = 0; // Majoron
Model[ "M2" ] = 0; // Majoron
Model[ "M3" ] = 0; // Majoron
Model[ "M7" ] = 0; // Majoron
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
if(myModel != "") {
std::string regModel(myModel);
if( Model.find(regModel) == Model.end() ){
std::cout << "Model \"" << myModel << "\" not known in under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Model.begin(); it != Model.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Model[regModel] = 1;
} else {
std::cout << "No signal model as been specified. You must choose one among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Model.begin(); it != Model.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
// --------------------------------------------------------------------------------------------------
// --- Here the preparation phase begins
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName;
outfileName.Form( "TMVA_%s.root", myModel.Data() );
//TString outfileDir( "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_FINAL_TECHNOTE_20150921/TMVA/" );
TString outfileDir( "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_UPDATE_TECHNOTE_20160429/TMVA/" );
TFile* outputFile = TFile::Open( outfileDir + outfileName , "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory is
// the only TMVA object you have to interact with
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TString weightBaseName;
weightBaseName.Form("TMVAClassification_%s", myModel.Data());
TMVA::Factory *factory = new TMVA::Factory( weightBaseName , outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
//factory->AddVariable( "myvar1 := var1+var2", 'F' );
//factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
//factory->AddVariable( "var3", "Variable 3", "units", 'F' );
//factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable( "min_el_en" , 'F' );
factory->AddVariable( "max_el_en" , 'F' );
factory->AddVariable( "el_en_asym := (max_el_en-min_el_en)/(min_el_en+max_el_en)" , 'F' );
factory->AddVariable( "el_en_sum := min_el_en+max_el_en" , 'F' );
factory->AddVariable( "cos_theta" , 'F' );
factory->AddVariable( "prob_int" , 'F' );
factory->AddVariable( "min_el_track_len" , 'F' );
factory->AddVariable( "max_el_track_len" , 'F' );
//factory->AddVariable( "min_el_curv := min_el_track_r*min_el_sign" , 'F' );
//factory->AddVariable( "max_el_curv := max_el_track_r*max_el_sign" , 'F' );
//factory->AddVariable( "max_vertex_s" , 'F' );
//factory->AddVariable( "max_vertex_z" , 'F' );
//factory->AddVariable( "min_vertex_s" , 'F' );
//factory->AddVariable( "min_vertex_z" , 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
//factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
//factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Read training and test data
// (it is also possible to use ASCII format as input -> see TMVA Users Guide)
//TString fdir = "/sps/nemo/scratch/remoto/nemo3/plot/plot_FINAL_TECHNOTE_20150921/";
TString fdir = "/Users/alberto/Software/SuperNEMO/work/nemo3/plot/plot_UPDATE_TECHNOTE_20160429/";
TString fname = "TwoElectronIntTree.root";
TFile *input = TFile::Open( fdir + fname , "READ");
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree * sig_tree = 0;
Double_t sig_weight = 1.;
if ( Model[ "MM" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m1_tree" ) ;
if ( Model[ "RHC_L" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m2_tree" ) ;
if ( Model[ "RHC_E" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m18_tree" ) ;
if ( Model[ "M1" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m5_tree" ) ;
if ( Model[ "M2" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m15_tree" ) ;
if ( Model[ "M3" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m6_tree" ) ;
if ( Model[ "M7" ] ) sig_tree = (TTree*) input->Get( "Cd116_2b0n_m7_tree" ) ;
factory->AddSignalTree( sig_tree , sig_weight );
//Double_t Cd116_2b0n_m1_weight = 1.;
//TTree * Cd116_2b0n_m1_tree = (TTree*) input->Get("Cd116_2b0n_m1_tree" ) ;
//factory->AddSignalTree( Cd116_2b0n_m1_tree , Cd116_2b0n_m1_weight );
TTree * Cd116_Tl208_tree = (TTree*) input->Get("Cd116_Tl208_tree" ) ; Double_t Cd116_Tl208_weight = 6.52838 ; if( Cd116_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Tl208_tree , Cd116_Tl208_weight ); };
TTree * Cd116_Ac228_tree = (TTree*) input->Get("Cd116_Ac228_tree" ) ; Double_t Cd116_Ac228_weight = 7.62351 ; if( Cd116_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Ac228_tree , Cd116_Ac228_weight ); };
TTree * Cd116_Bi212_tree = (TTree*) input->Get("Cd116_Bi212_tree" ) ; Double_t Cd116_Bi212_weight = 3.00708 ; if( Cd116_Bi212_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Bi212_tree , Cd116_Bi212_weight ); };
TTree * Cd116_Bi214_tree = (TTree*) input->Get("Cd116_Bi214_tree" ) ; Double_t Cd116_Bi214_weight = 18.1504 ; if( Cd116_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Bi214_tree , Cd116_Bi214_weight ); };
TTree * Cd116_Pb214_tree = (TTree*) input->Get("Cd116_Pb214_VT_tree" ) ; Double_t Cd116_Pb214_weight = 0.186417 ; if( Cd116_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Pb214_tree , Cd116_Pb214_weight ); };
TTree * Mylar_Bi214_tree = (TTree*) input->Get("Mylar_Bi214_tree" ) ; Double_t Mylar_Bi214_weight = 11.1346 ; if( Mylar_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Mylar_Bi214_tree , Mylar_Bi214_weight ); };
TTree * Mylar_Pb214_tree = (TTree*) input->Get("Mylar_Pb214_tree" ) ; Double_t Mylar_Pb214_weight = 0.496238 ; if( Mylar_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Mylar_Pb214_tree , Mylar_Pb214_weight ); };
TTree * Cd116_K40_tree = (TTree*) input->Get("Cd116_K40_tree" ) ; Double_t Cd116_K40_weight = 8.9841+25.8272 ; if( Cd116_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_K40_tree , Cd116_K40_weight ); };
TTree * Cd116_Pa234m_tree = (TTree*) input->Get("Cd116_Pa234m_tree" ) ; Double_t Cd116_Pa234m_weight = 27.9307+72.4667 ; if( Cd116_Pa234m_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_Pa234m_tree , Cd116_Pa234m_weight ); };
TTree * SFoil_Bi210_tree = (TTree*) input->Get("SFoil_Bi210_tree" ) ; Double_t SFoil_Bi210_weight = 0+23.2438 ; if( SFoil_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Bi210_tree , SFoil_Bi210_weight ); };
TTree * SWire_Bi210_tree = (TTree*) input->Get("SWire_Bi210_tree" ) ; Double_t SWire_Bi210_weight = 0.136147+0.624187 ; if( SWire_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Bi210_tree , SWire_Bi210_weight ); };
TTree * SScin_Bi210_tree = (TTree*) input->Get("SScin_Bi210_tree" ) ; Double_t SScin_Bi210_weight = 1.75641 ; if( SScin_Bi210_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Bi210_tree , SScin_Bi210_weight ); };
TTree * SScin_Bi214_tree = (TTree*) input->Get("SScin_Bi214_tree" ) ; Double_t SScin_Bi214_weight = 0.0510754 ; if( SScin_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Bi214_tree , SScin_Bi214_weight ); };
TTree * SScin_Pb214_tree = (TTree*) input->Get("SScin_Pb214_tree" ) ; Double_t SScin_Pb214_weight = 0 ; if( SScin_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SScin_Pb214_tree , SScin_Pb214_weight ); };
TTree * SWire_Tl208_tree = (TTree*) input->Get("SWire_Tl208_tree" ) ; Double_t SWire_Tl208_weight = 0.217623+1.07641 ; if( SWire_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Tl208_tree , SWire_Tl208_weight ); };
TTree * SWire_Bi214_P1_tree = (TTree*) input->Get("SWire_Bi214_tree" ) ; Double_t SWire_Bi214_weight = 21.4188+17.8236 ; if( SWire_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Bi214_tree , SWire_Bi214_weight ); };
TTree * SFoil_Bi214_tree = (TTree*) input->Get("SFoil_Bi214_tree" ) ; Double_t SFoil_Bi214_weight = 5.83533+2.80427 ; if( SFoil_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Bi214_tree , SFoil_Bi214_weight ); };
TTree * SWire_Pb214_tree = (TTree*) input->Get("SWire_Pb214_tree" ) ; Double_t SWire_Pb214_weight = 0.458486+0.649167 ; if( SWire_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SWire_Pb214_tree , SWire_Pb214_weight ); };
TTree * SFoil_Pb214_tree = (TTree*) input->Get("SFoil_Pb214_tree" ) ; Double_t SFoil_Pb214_weight = 0.218761+0.195287 ; if( SFoil_Pb214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( SFoil_Pb214_tree , SFoil_Pb214_weight ); };
TTree * FeShield_Bi214_tree = (TTree*) input->Get("FeShield_Bi214_tree" ) ; Double_t FeShield_Bi214_weight = 50.7021 ; if( FeShield_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Bi214_tree , FeShield_Bi214_weight ); };
TTree * FeShield_Tl208_tree = (TTree*) input->Get("FeShield_Tl208_tree" ) ; Double_t FeShield_Tl208_weight = 0.859465 ; if( FeShield_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Tl208_tree , FeShield_Tl208_weight ); };
TTree * FeShield_Ac228_tree = (TTree*) input->Get("FeShield_Ac228_tree" ) ; Double_t FeShield_Ac228_weight = 0.126868 ; if( FeShield_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( FeShield_Ac228_tree , FeShield_Ac228_weight ); };
TTree * CuTower_Co60_tree = (TTree*) input->Get("CuTower_Co60_tree" ) ; Double_t CuTower_Co60_weight = 3.9407 ; if( CuTower_Co60_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( CuTower_Co60_tree , CuTower_Co60_weight ); };
TTree * Air_Bi214_P1_tree = (TTree*) input->Get("Air_Bi214_tree" ) ; Double_t Air_Bi214_P1_weight = 4.19744 ; if( Air_Bi214_P1_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Air_Bi214_P1_tree , Air_Bi214_P1_weight ); };
TTree * Air_Tl208_P1_tree = (TTree*) input->Get("Air_Tl208_tree" ) ; Double_t Air_Tl208_P1_weight = 0 ; if( Air_Tl208_P1_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Air_Tl208_P1_tree , Air_Tl208_P1_weight ); };
TTree * PMT_Bi214_tree = (TTree*) input->Get("PMT_Bi214_tree" ) ; Double_t PMT_Bi214_weight = 27.9661 ; if( PMT_Bi214_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Bi214_tree , PMT_Bi214_weight ); };
TTree * PMT_Tl208_tree = (TTree*) input->Get("PMT_Tl208_tree" ) ; Double_t PMT_Tl208_weight = 22.923 ; if( PMT_Tl208_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Tl208_tree , PMT_Tl208_weight ); };
TTree * PMT_Ac228_tree = (TTree*) input->Get("PMT_Ac228_tree" ) ; Double_t PMT_Ac228_weight = 3.60712 ; if( PMT_Ac228_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_Ac228_tree , PMT_Ac228_weight ); };
TTree * PMT_K40_tree = (TTree*) input->Get("PMT_K40_tree" ) ; Double_t PMT_K40_weight = 16.813 ; if( PMT_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( PMT_K40_tree , PMT_K40_weight ); };
TTree * ScintInn_K40_tree = (TTree*) input->Get("ScintInn_K40_tree" ) ; Double_t ScintInn_K40_weight = 0.333988 ; if( ScintInn_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintInn_K40_tree , ScintInn_K40_weight ); };
TTree * ScintOut_K40_tree = (TTree*) input->Get("ScintOut_K40_tree" ) ; Double_t ScintOut_K40_weight = 0.601178 ; if( ScintOut_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintOut_K40_tree , ScintOut_K40_weight ); };
TTree * ScintPet_K40_tree = (TTree*) input->Get("ScintPet_K40_tree" ) ; Double_t ScintPet_K40_weight = 1.00195 ; if( ScintPet_K40_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( ScintPet_K40_tree , ScintPet_K40_weight ); };
TTree * MuMetal_Pa234m_tree = (TTree*) input->Get("MuMetal_Pa234m_tree" ) ; Double_t MuMetal_Pa234m_weight = 0.739038 ; if( MuMetal_Pa234m_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( MuMetal_Pa234m_tree , MuMetal_Pa234m_weight ); };
TTree * Cd116_2b2n_m14_tree = (TTree*) input->Get("Cd116_2b2n_m14_tree" ) ; Double_t Cd116_2b2n_m14_weight = 4977.55 ; if( Cd116_2b2n_m14_tree -> GetEntriesFast() > 0. ) {factory->AddBackgroundTree( Cd116_2b2n_m14_tree , Cd116_2b2n_m14_weight ); };
// --- end of tree registration
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
factory->SetBackgroundWeightExpression( "weight" );
// Apply additional cuts on the signal and background samples (can be different)
// Apply cut on charge
//TCut mycuts = "min_el_sign < 0 && max_el_sign < 0.";
//TCut mycutb = "min_el_sign < 0 && max_el_sign < 0.";
// Apply cut on vertex
//TCut mycuts = "((max_vertex_x - min_vertex_x)**2 + (max_vertex_y - min_vertex_y)**2 <= 4**2)&&((max_vertex_z-min_vertex_z)**2<8**2)";
//TCut mycutb = "((max_vertex_x - min_vertex_x)**2 + (max_vertex_y - min_vertex_y)**2 <= 4**2)&&((max_vertex_z-min_vertex_z)**2<8**2)";
TCut mycuts = "";
TCut mycutb = "";
// Tell the factory how to use the training and testing events
//
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// ---- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V:VarTransform=None" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2:!Boost_DetailedMonitoring" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20:MaxDepth=2" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=400:MinNodeSize=5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate" );
if (Use["BDTF"]) // Allow Using Fisher discriminant in node splitting for (strong) linearly correlated variables
factory->BookMethod( TMVA::Types::kBDT, "BDTMitFisher",
"!H:!V:NTrees=50:MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=-1" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier usage, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// ---- STILL EXPERIMENTAL and only implemented for BDT's !
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("ROCIntegral","FitGA");
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVAGui( outfileDir + outfileName );
}
void TMVAClassification( TString myMethodList = "" )
{
// TString curDynamicPath( gSystem->GetDynamicPath() );
// gSystem->SetDynamicPath( "/usr/local/bin/root/bin:" + curDynamicPath );
// TString curIncludePath(gSystem->GetIncludePath());
// gSystem->SetIncludePath( " -I /usr/local/bin/root/include " + curIncludePath );
// // load TMVA shared library created in local release: for MAC OSX
// if (TString(gSystem->GetBuildArch()).Contains("macosx") ) gSystem->Load( "libTMVA.so" );
// gSystem->Load( "libTMVA" );
// TMVA::Tools::Instance();
// // welcome the user
// TMVA::gTools().TMVAWelcomeMessage();
// TMVAGlob::SetTMVAStyle();
// // this loads the library
// TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 1;
// Use["Likelihood"] = 1;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
factory->AddVariable("deltaEta := deta", 'F');
factory->AddVariable("deltaPhi := dphi", 'F');
factory->AddVariable("sigmaIetaIeta := sieie", 'F');
factory->AddVariable("HoverE := hoe", 'F');
factory->AddVariable("trackIso := trackiso", 'F');
factory->AddVariable("ecalIso := ecaliso", 'F');
factory->AddVariable("hcalIso := hcaliso", 'F');
//factory->AddVariable("nMissingHits := misshits", 'I');
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
factory->AddSpectator( "et", 'F' );
factory->AddSpectator( "eta", 'F' );
factory->AddSpectator( "phi", 'F' );
// read training and test data
TFile *input = TFile::Open( "SigElectrons.root" );
TFile *inputB = TFile::Open( "BkgElectrons.root" );
std::cout << "--- TMVAClassification : Using input file: " << input->GetName() << std::endl;
TTree *signal = (TTree*)input->Get("ntuple");
TTree *background = (TTree*)inputB->Get("ntuple");
factory->AddSignalTree ( signal, 1.0 );
factory->AddBackgroundTree( background, 1.0 );
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
//factory->SetBackgroundWeightExpression("weight");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "";
TCut mycutb = "";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/correlations.C");
gROOT->ProcessLine(".x /usr/local/bin/root/tmva/test/variables.C");
}
void TMVAClassification( TString myMethodList = "" )
{
// The explicit loading of the shared libTMVA is done in TMVAlogon.C, defined in .rootrc
// if you use your private .rootrc, or run from a different directory, please copy the
// corresponding lines from .rootrc
// methods to be processed can be given as an argument; use format:
//
// mylinux~> root -l TMVAClassification.C\(\"myMethod1,myMethod2,myMethod3\"\)
//
// if you like to use a method via the plugin mechanism, we recommend using
//
// mylinux~> root -l TMVAClassification.C\(\"P_myMethod\"\)
// (an example is given for using the BDT as plugin (see below),
// but of course the real application is when you write your own
// method based)
// this loads the library
TMVA::Tools::Instance();
//---------------------------------------------------------------
// default MVA methods to be trained + tested
std::map<std::string,int> Use;
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
Use["Likelihood"] = 1;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
// ---
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDERSkNN"] = 0; // depreciated until further notice
Use["PDEFoam"] = 0;
// --
Use["KNN"] = 0;
// ---
Use["HMatrix"] = 0;
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0;
Use["LD"] = 0;
// ---
Use["FDA_GA"] = 0;
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
// ---
Use["MLP"] = 0; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["MLPBNN"] = 0; // recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // *** missing
Use["TMlpANN"] = 0;
// ---
Use["SVM"] = 0;
// ---
Use["BDT"] = 1;
Use["BDTD"] = 0;
Use["BDTG"] = 0;
Use["BDTB"] = 0;
// ---
Use["RuleFit"] = 0;
// ---
Use["Plugin"] = 0;
// ---------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVAClassification" << std::endl;
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 0;
}
}
// Create a new root output file.
TString outfileName( "TMVA.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weight/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
// factory->AddVariable( "myvar1 := var1+var2", 'F' );
// factory->AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' );
// factory->AddVariable( "var3", "Variable 3", "units", 'F' );
// factory->AddVariable( "var4", "Variable 4", "units", 'F' );
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
// factory->AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' );
// factory->AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' );
// read training and test data
factory->AddVariable("CScostheta",'F');
factory->AddVariable("ZRapidity",'F');
factory->AddVariable("REDmet",'F');
if (ReadDataFromAsciiIFormat) {
// load the signal and background event samples from ascii files
// format in file must be:
// var1/F:var2/F:var3/F:var4/F
// 0.04551 0.59923 0.32400 -0.19170
// ...
TString datFileS = "tmva_example_sig.dat";
TString datFileB = "tmva_example_bkg.dat";
factory->SetInputTrees( datFileS, datFileB );
}
else {
// load the signal and background event samples from ROOT trees
TString fname = "./tmva_class_example.root";
TString fname_Data7TeV_DoubleElectron2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_0.root";
TString fname_Data7TeV_MuEG2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_0.root";
TString fname_ZH125 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH125.root";
TString fname_SingleT_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_tW.root";
TString fname_SingleT_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_s.root";
TString fname_Data7TeV_DoubleMu2011B_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_0.root";
TString fname_Data7TeV_DoubleElectron2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_0.root";
TString fname_ZH135 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH135.root";
TString fname_DYJetsToLL = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//DYJetsToLL.root";
TString fname_ZH115 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH115.root";
TString fname_SingleTbar_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_t.root";
TString fname_Data7TeV_DoubleElectron2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011B_1.root";
TString fname_Data7TeV_DoubleMu2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_1.root";
TString fname_Data7TeV_MuEG2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_1.root";
TString fname_TTJets = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//TTJets.root";
TString fname_SingleTbar_s = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_s.root";
TString fname_WJetsToLNu = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WJetsToLNu.root";
TString fname_Data7TeV_DoubleElectron2011A_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleElectron2011A_1.root";
TString fname_ZZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZZ.root";
TString fname_ZH150 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH150.root";
TString fname_Data7TeV_MuEG2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011B_1.root";
TString fname_WW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WW.root";
TString fname_ZH105 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH105.root";
TString fname_Data7TeV_DoubleMu2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011A_0.root";
TString fname_SingleTbar_tW = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleTbar_tW.root";
TString fname_WZ = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//WZ.root";
TString fname_Data7TeV_MuEG2011A_0 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_MuEG2011A_0.root";
TString fname_Data7TeV_DoubleMu2011B_1 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//Data7TeV_DoubleMu2011B_1.root";
TString fname_ZH145 = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//ZH145.root";
TString fname_SingleT_t = "/tmp/chasco/INIT/HADD/TMVA/Trees_FUSION2/ZZ_vs_nonZZ//SingleT_t.root";
if (gSystem->AccessPathName( fname )) // file does not exist in local directory
gSystem->Exec("wget http://root.cern.ch/files/tmva_class_example.root");
TFile *input_Data7TeV_DoubleElectron2011B_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_0 );
TFile *input_Data7TeV_MuEG2011B_0 = TFile::Open( fname_Data7TeV_MuEG2011B_0 );
TFile *input_ZH125 = TFile::Open( fname_ZH125 );
TFile *input_SingleT_tW = TFile::Open( fname_SingleT_tW );
TFile *input_SingleT_s = TFile::Open( fname_SingleT_s );
TFile *input_Data7TeV_DoubleMu2011B_0 = TFile::Open( fname_Data7TeV_DoubleMu2011B_0 );
TFile *input_Data7TeV_DoubleElectron2011A_0 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_0 );
TFile *input_ZH135 = TFile::Open( fname_ZH135 );
TFile *input_DYJetsToLL = TFile::Open( fname_DYJetsToLL );
TFile *input_ZH115 = TFile::Open( fname_ZH115 );
TFile *input_SingleTbar_t = TFile::Open( fname_SingleTbar_t );
TFile *input_Data7TeV_DoubleElectron2011B_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011B_1 );
TFile *input_Data7TeV_DoubleMu2011A_1 = TFile::Open( fname_Data7TeV_DoubleMu2011A_1 );
TFile *input_Data7TeV_MuEG2011A_1 = TFile::Open( fname_Data7TeV_MuEG2011A_1 );
TFile *input_TTJets = TFile::Open( fname_TTJets );
TFile *input_SingleTbar_s = TFile::Open( fname_SingleTbar_s );
TFile *input_WJetsToLNu = TFile::Open( fname_WJetsToLNu );
TFile *input_Data7TeV_DoubleElectron2011A_1 = TFile::Open( fname_Data7TeV_DoubleElectron2011A_1 );
TFile *input_ZZ = TFile::Open( fname_ZZ );
TFile *input_ZH150 = TFile::Open( fname_ZH150 );
TFile *input_Data7TeV_MuEG2011B_1 = TFile::Open( fname_Data7TeV_MuEG2011B_1 );
TFile *input_WW = TFile::Open( fname_WW );
TFile *input_ZH105 = TFile::Open( fname_ZH105 );
TFile *input_Data7TeV_DoubleMu2011A_0 = TFile::Open( fname_Data7TeV_DoubleMu2011A_0 );
TFile *input_SingleTbar_tW = TFile::Open( fname_SingleTbar_tW );
TFile *input_WZ = TFile::Open( fname_WZ );
TFile *input_Data7TeV_MuEG2011A_0 = TFile::Open( fname_Data7TeV_MuEG2011A_0 );
TFile *input_Data7TeV_DoubleMu2011B_1 = TFile::Open( fname_Data7TeV_DoubleMu2011B_1 );
TFile *input_ZH145 = TFile::Open( fname_ZH145 );
TFile *input_SingleT_t = TFile::Open( fname_SingleT_t );
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_0 file: " << input_Data7TeV_DoubleElectron2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_0 file: " << input_Data7TeV_MuEG2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH125 file: " << input_ZH125->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_tW file: " << input_SingleT_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_s file: " << input_SingleT_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_0 file: " << input_Data7TeV_DoubleMu2011B_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_0 file: " << input_Data7TeV_DoubleElectron2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH135 file: " << input_ZH135->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_DYJetsToLL file: " << input_DYJetsToLL->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH115 file: " << input_ZH115->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_t file: " << input_SingleTbar_t->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011B_1 file: " << input_Data7TeV_DoubleElectron2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_1 file: " << input_Data7TeV_DoubleMu2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_1 file: " << input_Data7TeV_MuEG2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_TTJets file: " << input_TTJets->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_s file: " << input_SingleTbar_s->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WJetsToLNu file: " << input_WJetsToLNu->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleElectron2011A_1 file: " << input_Data7TeV_DoubleElectron2011A_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZZ file: " << input_ZZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH150 file: " << input_ZH150->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011B_1 file: " << input_Data7TeV_MuEG2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WW file: " << input_WW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH105 file: " << input_ZH105->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011A_0 file: " << input_Data7TeV_DoubleMu2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleTbar_tW file: " << input_SingleTbar_tW->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_WZ file: " << input_WZ->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_MuEG2011A_0 file: " << input_Data7TeV_MuEG2011A_0->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_Data7TeV_DoubleMu2011B_1 file: " << input_Data7TeV_DoubleMu2011B_1->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_ZH145 file: " << input_ZH145->GetName() << std::endl;
std::cout << "--- TMVAClassification : Using input_SingleT_t file: " << input_SingleT_t->GetName() << std::endl;
TTree *signal_ZH145 = (TTree*)input_ZH145->Get("tmvatree");
TTree *background_ZZ = (TTree*)input_ZZ->Get("tmvatree");
// global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// ====== register trees ====================================================
//
// the following method is the prefered one:
// you can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal_ZH145, 1.0 );
factory->AddBackgroundTree( background_ZZ, 1.0 );
// To give different trees for training and testing, do as follows:
// factory->AddSignalTree( signal_ZH145TrainingTree, signal_ZH145TrainWeight, "Training" );
// factory->AddSignalTree( signal_ZH145TestTree, signal_ZH145TestWeight, "Test" );
// Use the following code instead of the above two or four lines to add signal and background
// training and test events "by hand"
// NOTE that in this case one should not give expressions (such as "var1+var2") in the input
// variable definition, but simply compute the expression before adding the event
//
// // --- begin ----------------------------------------------------------
// std::vector<Double_t> vars( 4 ); // vector has size of number of input variables
// Float_t treevars[4];
// for (Int_t ivar=0; ivar<4; ivar++) signal->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<signal->GetEntries(); i++) {
// signal->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < signal->GetEntries()/2) factory->AddSignalTrainingEvent( vars, signalWeight );
// else factory->AddSignalTestEvent ( vars, signalWeight );
// }
//
// for (Int_t ivar=0; ivar<4; ivar++) background->SetBranchAddress( Form( "var%i", ivar+1 ), &(treevars[ivar]) );
// for (Int_t i=0; i<background->GetEntries(); i++) {
// background->GetEntry(i);
// for (Int_t ivar=0; ivar<4; ivar++) vars[ivar] = treevars[ivar];
// // add training and test events; here: first half is training, second is testing
// // note that the weight can also be event-wise
// if (i < background->GetEntries()/2) factory->AddBackgroundTrainingEvent( vars, backgroundWeight );
// else factory->AddBackgroundTestEvent ( vars, backgroundWeight );
// }
// // --- end ------------------------------------------------------------
//
// ====== end of register trees ==============================================
}
// This would set individual event weights (the variables defined in the
// expression need to exist in the original TTree)
// for signal : factory->SetSignalWeightExpression("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("weight1*weight2");
factory->SetBackgroundWeightExpression("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
factory->SetSignalWeightExpression("Eweight*XS*BR*LUM*(1/NGE)*(B2/B3)*CUT");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = "(CUT>2)";
TCut mycutb = "(CUT>2)";
// tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycuts, "SplitMode=random:!V" );
// "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// If no numbers of events are given, half of the events in the tree are used for training, and
// the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
// To also specify the number of testing events, use:
// factory->PrepareTrainingAndTestTree( mycut,
// "NSigTrain=3000:NBkgTrain=3000:NSigTest=3000:NBkgTest=3000:SplitMode=Random:!V" );
// ---- Book MVA methods
//
// please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// Cut optimisation
if (Use["Cuts"])
factory->BookMethod( TMVA::Types::kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" );
if (Use["CutsD"])
factory->BookMethod( TMVA::Types::kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" );
if (Use["CutsPCA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" );
if (Use["CutsGA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsGA",
"H:!V:FitMethod=GA:Seed=0:EffSel:Steps=50:Cycles=3:PopSize=1000:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// test the decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// test the new kernel density estimator
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// test the mixed splines and kernel density estimator (depending on which variable)
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSkNN"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSkNN",
"!H:!V:VolumeRangeMode=kNN:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:CutNmin=T:Nmin=100:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Fisher discriminant
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=60:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher", "H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2");
// Linear discriminant (same as Fisher)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
if (Use["MLPBFGS"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" );
if (Use["MLPBNN"])
factory->BookMethod( TMVA::Types::kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ); // BFGS training with bayesian regulators
// CF(Clermont-Ferrand)ANN
if (Use["CFMlpANN"])
factory->BookMethod( TMVA::Types::kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ); // n_cycles:#nodes:#nodes:...
// Tmlp(Root)ANN
if (Use["TMlpANN"])
factory->BookMethod( TMVA::Types::kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ); // n_cycles:#nodes:#nodes:...
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDTG"]) // Gradient Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" );
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=1000:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=1000:nEventsMin=400:MaxDepth=6:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" );
// RuleFit -- TMVA implementation of Friedman's method
if (Use["RuleFit"])
factory->BookMethod( TMVA::Types::kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" );
// For an example of the category classifier, see: TMVAClassificationCategory
// --------------------------------------------------------------------------------------------------
// As an example how to use the ROOT plugin mechanism, book BDT via
// plugin mechanism
if (Use["Plugin"]) {
//
// first the plugin has to be defined, which can happen either through the following line in the local or global .rootrc:
//
// # plugin handler plugin name(regexp) class to be instanciated library constructor format
// Plugin.TMVA@@MethodBase: ^BDT TMVA::MethodBDT TMVA.1 "MethodBDT(TString,TString,DataSet&,TString)"
//
// or by telling the global plugin manager directly
gPluginMgr->AddHandler("TMVA@@MethodBase", "BDT", "TMVA::MethodBDT", "TMVA.1", "MethodBDT(TString,TString,DataSet&,TString)");
factory->BookMethod( TMVA::Types::kPlugins, "BDT",
"!H:!V:NTrees=1000:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=CostComplexity:PruneStrength=50" );
}
// --------------------------------------------------------------------------------------------------
// ---- Now you can tell the factory to train, test, and evaluate the MVAs
// Train MVAs using the set of training events
factory->TrainAllMethods();
// ---- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// ----- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassification is done!" << std::endl;
delete factory;
// Launch the GUI for the root macros
gROOT->ProcessLine(".q;");
}
////////////////////////////////////////////////////////////////////////////////
/// Main ///
////////////////////////////////////////////////////////////////////////////////
void TrainRegressionFJ(TString myMethodList="")
{
gROOT->SetBatch(1);
gROOT->LoadMacro("HelperFunctions.h" ); // make functions visible to TTreeFormula
if (!TString(gROOT->GetVersion()).Contains("5.34")) {
std::cout << "INCORRECT ROOT VERSION! Please use 5.34:" << std::endl;
std::cout << "source /uscmst1/prod/sw/cms/slc5_amd64_gcc462/lcg/root/5.34.02-cms/bin/thisroot.csh" << std::endl;
std::cout << "Return without doing anything." << std::endl;
return;
}
//TString curDynamicPath( gSystem->GetDynamicPath() );
//gSystem->SetDynamicPath( "../lib:" + curDynamicPath );
//TString curIncludePath(gSystem->GetIncludePath());
//gSystem->SetIncludePath( " -I../include " + curIncludePath );
// Load the library
TMVA::Tools::Instance();
//--------------------------------------------------------------------------
// Default MVA methods to be trained + tested
std::map<std::string, int> Use;
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDEFoam"] = 1;
Use["KNN"] = 1;
//
// --- Linear Discriminant Analysis
Use["LD"] = 1;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 1;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
//
// --- Neural Network
Use["MLP"] = 1;
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1;
Use["BDT1"] = 0;
Use["BDTG"] = 0;
Use["BDTG1"] = 0;
//--------------------------------------------------------------------------
std::cout << std::endl;
std::cout << "==> Start TMVARegression" << std::endl;
// Select methods (don't look at this code - not of interest)
if (myMethodList != "") {
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) it->second = 0;
std::vector<TString> mlist = TMVA::gTools().SplitString( myMethodList, ',' );
for (UInt_t i=0; i<mlist.size(); i++) {
std::string regMethod(mlist[i]);
if (Use.find(regMethod) == Use.end()) {
std::cout << "Method \"" << regMethod << "\" not known in TMVA under this name. Choose among the following:" << std::endl;
for (std::map<std::string,int>::iterator it = Use.begin(); it != Use.end(); it++) std::cout << it->first << " ";
std::cout << std::endl;
return;
}
Use[regMethod] = 1;
}
}
//--------------------------------------------------------------------------
// Create a ROOT output file where TMVA will store ntuples, histograms, etc.
TString outfileName( "TMVARegFJ.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object. Later you can choose the methods
// whose performance you'd like to investigate. The factory will
// then run the performance analysis for you.
//
// The first argument is the base of the name of all the
// weightfiles in the directory weights/
//
// The second argument is the output file for the training results
// All TMVA output can be suppressed by removing the "!" (not) in
// front of the "Silent" argument in the option string
TMVA::Factory *factory = new TMVA::Factory( "TMVARegressionFJ", outputFile,
"!V:!Silent:!Color:!DrawProgressBar:Transformations=I:AnalysisType=Regression" );
// If you wish to modify default settings
// (please check "src/Config.h" to see all available global options)
// (TMVA::gConfig().GetVariablePlotting()).fTimesRMS = 8.0;
// (TMVA::gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory";
const std::vector<std::string> & inputExpressions = GetInputExpressionsFJReg();
const std::vector<std::string> & inputExpressionLabels = GetInputExpressionLabelsFJReg();
assert(inputExpressions.size() == inputExpressionLabels.size());
// Define the input variables that shall be used for the MVA training
// note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
// [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
//factory->AddVariable( "var1", "Variable 1", "units", 'F' );
//factory->AddVariable( "var2", "Variable 2", "units", 'F' );
for (UInt_t iexpr=0; iexpr!=inputExpressions.size(); iexpr++){
Label label = MakeLabel(inputExpressionLabels.at(iexpr));
TString expr = inputExpressions.at(iexpr);
factory->AddVariable(expr, label.xlabel, label.unit, label.type);
}
// You can add so-called "Spectator variables", which are not used in the MVA training,
// but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
// input variables, the response values of all trained MVAs, and the spectator variables
//factory->AddSpectator( "spec1 := var1*2", "Spectator 1", "units", 'F' );
//factory->AddSpectator( "spec2 := var1*3", "Spectator 2", "units", 'F' );
// Add the variable carrying the regression target
//factory->AddTarget( "fvalue" );
factory->AddTarget( "fathFilterJets_genPt" );
// It is also possible to declare additional targets for multi-dimensional regression, ie:
// -- factory->AddTarget( "fvalue2" );
// BUT: this is currently ONLY implemented for MLP
//--------------------------------------------------------------------------
// Read training and test data
TFile *input(0);
TString dirname = "skim_ZnnH_regression_fj/";
TString prefix = "skim_";
TString suffix = ".root";
TTree *regTrainTree(0), *regTestTree(0);
std::vector<std::string> processes;
processes.push_back("ZnnH110");
processes.push_back("ZnnH115");
processes.push_back("ZnnH120");
processes.push_back("ZnnH125");
processes.push_back("ZnnH130");
processes.push_back("ZnnH135");
processes.push_back("ZnnH140");
processes.push_back("ZnnH145");
processes.push_back("ZnnH150");
#ifdef USE_WH
processes.push_back("WlnH110");
processes.push_back("WlnH115");
processes.push_back("WlnH120");
processes.push_back("WlnH125");
processes.push_back("WlnH130");
processes.push_back("WlnH135");
processes.push_back("WlnH140");
processes.push_back("WlnH145");
processes.push_back("WlnH150");
#endif
std::vector<TFile *> files;
for (UInt_t i=0; i<processes.size(); i++){
std::string process = processes.at(i);
input = (TFile*) TFile::Open(dirname + prefix + process + suffix, "READ");
if (!input) {
std::cout << "ERROR: Could not open input file." << std::endl;
exit(1);
}
std::cout << "--- TMVARegression : Using input file: " << input->GetName() << std::endl;
files.push_back(input);
// --- Register the regression tree
regTrainTree = (TTree*) input->Get("tree_train");
regTestTree = (TTree*) input->Get("tree_test");
// Global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
// You can add an arbitrary number of regression trees
factory->AddRegressionTree(regTrainTree, regWeight, TMVA::Types::kTraining);
factory->AddRegressionTree(regTestTree , regWeight, TMVA::Types::kTesting );
}
// Set individual event weights (the variables must exist in the original TTree)
//factory->SetWeightExpression( "var1", "Regression" );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycut = "fathFilterJets_genPt>10 && fathFilterJets_pt>15 && abs(fathFilterJets_eta)<2.5"; // this is to avoid 3rd filter jet without gen match
//TCut mycut = "hJet_genPt[0] > 0. && hJet_genPt[1] > 0. && hJet_csv[0] > 0. && hJet_csv[1] > 0. && hJet_pt[0] > 20. && hJet_pt[1] > 20. && abs(hJet_eta[0])<2.5 && abs(hJet_eta[1])<2.5";
// Tell the factory to use all remaining events in the trees after training for testing:
factory->PrepareTrainingAndTestTree( mycut, "V:nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents" );
// If no numbers of events are given, half of the events in the tree are used
// for training, and the other half for testing:
// factory->PrepareTrainingAndTestTree( mycut, "SplitMode=Random:!V" );
// --- Book MVA methods
//
// Please lookup the various method configuration options in the corresponding cxx files, eg:
// src/MethodCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
// it is possible to preset ranges in the option string in which the cut optimisation should be done:
// "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
// PDE - RS method
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=40:NEventsMax=60:VarTransform=None" );
// And the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"!H:!V:MultiTargetRegression=F:TargetSelection=Mpv:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Compress=T:Kernel=None:Nmin=10:VarTransform=None" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// Linear discriminant
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD",
"!H:!V:VarTransform=None" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=MC:SampleSize=100000:Sigma=0.1:VarTransform=D" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options) .. the formula of this example is good for parabolas
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:PopSize=100:Cycles=3:Steps=30:Trim=True:SaveBestGen=1:VarTransform=Norm" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"!H:!V:Formula=(0)+(1)*x0+(2)*x1:ParRanges=(-100,100);(-100,100);(-100,100):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
// Neural network (MLP)
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP",
"!H:!V:VarTransform=Norm:NeuronType=tanh:NCycles=20000:HiddenLayers=N+20:TestRate=6:TrainingMethod=BFGS:Sampling=0.3:SamplingEpoch=0.8:ConvergenceImprove=1e-6:ConvergenceTests=15:!UseRegulator" );
// Support Vector Machine
if (Use["SVM"])
factory->BookMethod( TMVA::Types::kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" );
// Boosted Decision Trees
if (Use["BDT"])
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"!H:V:NTrees=100:nEventsMin=30:NodePurityLimit=0.5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
//"!H:V:NTrees=60:nEventsMin=20:NodePurityLimit=0.5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30:DoBoostMonitor" );
if (Use["BDT1"])
factory->BookMethod( TMVA::Types::kBDT, "BDT1",
"!H:V:NTrees=100:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" );
if (Use["BDTG"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG",
"!H:V:NTrees=2000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.7:nCuts=200:MaxDepth=3:NNodesMax=15" );
if (Use["BDTG1"])
factory->BookMethod( TMVA::Types::kBDT, "BDTG1",
"!H:V:NTrees=1000:BoostType=Grad:Shrinkage=0.10:UseBaggedGrad:GradBaggingFraction=0.5:nCuts=20:MaxDepth=3:NNodesMax=15" );
//--------------------------------------------------------------------------
// Train MVAs using the set of training events
factory->TrainAllMethods();
// --- Evaluate all MVAs using the set of test events
factory->TestAllMethods();
// --- Evaluate and compare performance of all configured MVAs
factory->EvaluateAllMethods();
//--------------------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVARegression is done!" << std::endl;
for (UInt_t i=0; i<files.size(); i++)
files.at(i)->Close();
delete outputFile;
delete factory;
// Launch the GUI for the root macros
//gROOT->SetMacroPath( "$ROOTSYS/tmva/macros/" );
//gROOT->Macro( "$ROOTSYS/tmva/macros/TMVAlogon.C" );
//gROOT->LoadMacro( "$ROOTSYS/tmva/macros/TMVAGui.C" );
//if (!gROOT->IsBatch()) TMVARegGui( outfileName );
}
void 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 );
}
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 TMVAClassification( std::string selectionName, std::string charge, 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"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
// ---
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
// ---
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDERSkNN"] = 0; // depreciated until further notice
Use["PDEFoam"] = 0;
// --
Use["KNN"] = 0;
// ---
Use["HMatrix"] = 0;
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0;
Use["LD"] = 0;
// ---
Use["FDA_GA"] = 0;
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
// ---
Use["MLP"] = 0; // this is the recommended ANN
Use["MLPBFGS"] = 0; // recommended ANN with optional training method
Use["CFMlpANN"] = 0; // *** missing
Use["TMlpANN"] = 0;
// ---
Use["SVM"] = 0;
// ---
Use["BDT"] = 0;
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" );
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( "MET" , "ME_{T}", "GeV", 'F');
//factory->AddVariable( "TMath::Max(pT1,pT2)" , "Lead Lepton p_{T}", "GeV", 'F');
factory->AddVariable( "HT" , "H_{T}", "GeV", 'F');
//factory->AddVariable( "M3" , "M_{3}", "GeV", 'F');
factory->AddVariable( "TMath::Min(pT1,pT2)" , "Sublead Lepton p_{T}", "GeV", 'F');
//factory->AddVariable( "NbJ" , "N B Jets", "", 'I');
//factory->AddVariable( "NbJmed" , "N B Jets (medium)", "", 'I');
//factory->AddVariable( "NJ" , "N Jets", "", '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
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";
//TString fname = "opt_ttW_Apr10_Iso005_NoZVeto_jet20.root";
TString fname = "opt_ttW_Nov20_muDetIso0p05_elDetIso0p05_jet20_withZveto_optimization.root";
//TString fname = "opt_ttW_" + selectionName + ".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* opt_tree = (TTree*)input->Get("tree_opt");
TFile* signalFile = TFile::Open("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/TTbarW_Yields.root");
TTree *signal = (TTree*)signalFile->Get("SigEvents");
TChain* background = new TChain("SigEvents");
background->Add("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/TTJets_Yields.root");
background->Add("/shome/mdunser/workspace/CMSSW_5_2_5/src/DiLeptonAnalysis/NTupleProducer/macros/plots/Nov26_muPFIso0p05_elPFIso0p05_jet20_withZveto/WZTo3LNu_Yields.root");
//TTree *background = (TTree*)opt_tree->CopyTree("SName==\"TTJets\" || SName==\"DYJets\" || SName==\"WZTo3LNu\"");
//TTree *background = (TTree*)opt_tree->CopyTree("SName==\"DYJets\"");
// 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->SetSignalWeightExpression("eventWeight");
factory->SetBackgroundWeightExpression("1./SLumi");
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts;
TCut mycutb;
if( charge == "plus" ) {
mycuts = "Charge==1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = "Charge==1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else if( charge == "minus" ) {
mycuts = "Charge==-1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = "Charge==-1 && SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else if( charge == "all" ) {
mycuts = " SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = " SystFlag==0 && NJ>=3 && pT1>20. && pT2>20. && NbJmed>0 && TLCat==0 && Flavor<3 && PassZVeto==1"; // for example: TCut mycutb = "abs(var1)<0.5";
} else {
std::cout << "only 'plus' and 'minus' and 'all' are allowed for charge." <<std::endl;
return;
}
//if( btagMed_presel_ ) {
// mycuts += "NbJmed>0"; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
// mycutb += "NbJmed>0"; // 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"]) {
std::string bookConditions;
bookConditions = "H:!V:FitMethod=MC";
bookConditions += ":VarProp[0]=FMax"; //HT
bookConditions += ":VarProp[1]=FMax"; //pt2
bookConditions += ":EffSel:SampleSize=500000000";
//bookConditions += ":EffSel:SampleSize=50000";
factory->BookMethod( TMVA::Types::kCuts, "Cuts", bookConditions.c_str() );
//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();
if (Use["Cuts"]) {
for( unsigned iEff=1; iEff<11; ++iEff ) {
TMVA::IMethod* method = (TMVA::IMethod*)factory->GetMethod("Cuts");
TMVA::MethodCuts* cuts = dynamic_cast<TMVA::MethodCuts*>(method);
std::string optcutsdir = "optcuts_" + selectionName + "_" + charge;
std::string mkdir_command = "mkdir -p " + optcutsdir;
system(mkdir_command.c_str());
char cutsFileName[500];
sprintf( cutsFileName, "%s/cuts_Seff%d.txt", optcutsdir.c_str(), 10*iEff );
ofstream ofs(cutsFileName);
std::vector<Double_t> cutsMin, cutsMax;
cuts->GetCuts((float)iEff*0.10, cutsMin, cutsMax);
bool found_pT1 = false;
bool found_pT2 = false;
bool found_NJ = false;
bool found_NbJ = false;
bool found_NbJmed = false;
for( unsigned iCut=0; iCut<cutsMin.size(); ++iCut) {
TString varName = factory->DefaultDataSetInfo().GetVariableInfo(iCut).GetInternalName();
if( varName=="TMath_Min_pT1,pT2_") {
ofs << "pT1 " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
ofs << "pT2 " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
found_pT1 = true;
found_pT2 = true;
} else {
ofs << varName << " " << cutsMin[iCut] << " " << cutsMax[iCut] << std::endl;
}
if( varName=="pT1" ) found_pT1 = true;
if( varName=="pT2" ) found_pT2 = true;
if( varName=="NJ" ) found_NJ = true;
if( varName=="NbJ" ) found_NbJ = true;
if( varName=="NbJmed" ) found_NbJmed = true;
}
// preselection cuts (if not optimized):
if( !found_pT1 ) ofs << "pT1 20. 100000." << std::endl;
if( !found_pT2 ) ofs << "pT2 20. 100000." << std::endl;
if( !found_NJ ) ofs << "NJ 3 100000." << std::endl;
if( !found_NbJ ) ofs << "NbJ 1 100000." << std::endl;
if( !found_NbJmed && btagMed_presel_ ) ofs << "NbJmed 1 100000." << std::endl;
if( charge=="plus" )
ofs << "Charge 1 10" << std::endl;
else if( charge=="minus" )
ofs << "Charge -10 0" << std::endl;
ofs.close();
} // for eff
} // if cuts
// --------------------------------------------------------------
// 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 mytmvaClass( 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\(\"P_myMethod\"\)
//--------------------------------
TMVA::Tools::Instance();
// Default MVA methods to be trained + tested
std::map<std::string,int> Use;
// --- Cut optimisation
Use["Cuts"] = 0;
Use["CutsD"] = 0;
Use["CutsPCA"] = 0;
Use["CutsGA"] = 0;
Use["CutsSA"] = 0;
//
// --- 1-dimensional likelihood ("naive Bayes estimator")
Use["Likelihood"] = 0;
Use["LikelihoodD"] = 0; // the "D" extension indicates decorrelated input variables (see option strings)
Use["LikelihoodPCA"] = 0; // the "PCA" extension indicates PCA-transformed input variables (see option strings)
Use["LikelihoodKDE"] = 0;
Use["LikelihoodMIX"] = 0;
//
// --- Mutidimensional likelihood and Nearest-Neighbour methods
Use["PDERS"] = 0;
Use["PDERSD"] = 0;
Use["PDERSPCA"] = 0;
Use["PDEFoam"] = 0;
Use["PDEFoamBoost"] = 0; // uses generalised MVA method boosting
Use["KNN"] = 0; // k-nearest neighbour method
//
// --- Linear Discriminant Analysis
Use["LD"] = 0; // Linear Discriminant identical to Fisher
Use["Fisher"] = 0;
Use["FisherG"] = 0;
Use["BoostedFisher"] = 0; // uses generalised MVA method boosting
Use["HMatrix"] = 0;
//
// --- Function Discriminant analysis
Use["FDA_GA"] = 0; // minimisation of user-defined function using Genetics Algorithm
Use["FDA_SA"] = 0;
Use["FDA_MC"] = 0;
Use["FDA_MT"] = 0;
Use["FDA_GAMT"] = 0;
Use["FDA_MCMT"] = 0;
//
// --- Neural Networks (all are feed-forward Multilayer Perceptrons)
Use["MLP"] = 0; // Recommended ANN
Use["MLPBFGS"] = 0; // Recommended ANN with optional training method
Use["MLPBNN"] = 0; // Recommended ANN with BFGS training method and bayesian regulator
Use["CFMlpANN"] = 0; // Depreciated ANN from ALEPH
Use["TMlpANN"] = 0; // ROOT's own ANN
//
// --- Support Vector Machine
Use["SVM"] = 0;
//
// --- Boosted Decision Trees
Use["BDT"] = 1; // uses Adaptive Boost
Use["BDTG"] = 0; // uses Gradient Boost
Use["BDTB"] = 0; // uses Bagging
Use["BDTD"] = 0; // decorrelation + Adaptive Boost
//
// --- 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 (Not of much 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)"
//Syntax --> "factory->AddVariable( "VarName", "UserDefinedLabel", "units", 'VarType' );" //Where VarType refers to float, int etc.
Float_t nhiggsJetSubjets;
Float_t njets;
Float_t deltaPhiWH;
Float_t jetPt[11];
Float_t jetEta[11];
Float_t jetPhi[11];
Float_t jetE[11];
Float_t higgsJetSubjetEta[3];
Float_t higgsJetSubjetPhi[3];
Float_t higgsJetSubjetPt[3];
Float_t higgsJetSubjetE[3];
Float_t Wphi;
Float_t fatjetPt[15];
Float_t fatjetEta[15];
Float_t fatjetPhi[15];
Float_t fatjetE[15];
Float_t DeltaPhiWH;
TLorentzVector fatjet(0,0,0,0);
TLorentzVector subjet1(0,0,0,0);
TLorentzVector subjet2(0,0,0,0);
TLorentzVector subjet3(0,0,0,0);
TLorentzVector akt[15];
fatjet.SetPtEtaPhiE(fatjetPt[0],fatjetEta[0],fatjetPhi[0], fatjetE[0]);
// deltaPhiWH = std::fabs(Wphi-fatjetPhi[0]);
// if(deltaPhiWH>TMath::Pi()){ std::fabs(deltaPhiWH = 2*TMath::Pi()-deltaPhiWH);}
factory->AddVariable( "deltaPhiWH", "deltaPhiWH", "", 'F' );
factory->AddVariable( "jetPt.array[0]", "jetPt.array[0]", "", 'F' );
factory->AddVariable( "fatjetPt[0].array[0]", "fatjetPt.array[0]", "", 'F' );
//factory->AddVariable( "DeltaR[3][13]", "DeltaR[3][13]", "", 'F' );
// factory->AddSpectator( "nhiggsJetSubjets", "nhiggsJetSubjets", "", 'F');
// factory->AddSpectator( "njets", "", "njets", 'I');
// factory->AddSpectator( "jetPt[0]", "jetPt[0]", "", 'F');
// factory->AddSpectator( "jetPt[1]", "jetPt[1]", "", 'F');
// factory->AddSpectator( "jetPt[2]", "jetPt[2]", "", 'F');
// factory->AddSpectator( "jetPt[3]", "jetPt[3]", "", 'F');
// factory->AddSpectator( "jetPt[4]", "jetPt[4]", "", 'F');
// factory->AddSpectator( "jetPt[5]", "jetPt[5]", "", 'F');
// factory->AddSpectator( "jetPt[6]", "jetPt[6]", "", 'F');
// factory->AddSpectator( "jetPt[7]", "jetPt[7]", "", 'F');
// factory->AddSpectator( "jetPt[8]", "jetPt[8]", "", 'F');
// factory->AddSpectator( "jetPt[9]", "jetPt[9]", "", 'F');
// factory->AddSpectator( "jetPt[10]", "jetPt[10]", "", 'F');
// factory->AddSpectator( "jetEta[0]", "jetEta[0]", "", 'F');
// factory->AddSpectator( "jetEta[1]", "jetEta[1]", "", 'F');
// factory->AddSpectator( "jetEta[2]", "jetEta[2]", "", 'F');
// factory->AddSpectator( "jetEta[3]", "jetEta[3]", "", 'F');
// factory->AddSpectator( "jetEta[4]", "jetEta[4]", "", 'F');
// factory->AddSpectator( "jetEta[5]", "jetEta[5]", "", 'F');
// factory->AddSpectator( "jetEta[6]", "jetEta[6]", "", 'F');
// factory->AddSpectator( "jetEta[7]", "jetEta[7]", "", 'F');
// factory->AddSpectator( "jetEta[8]", "jetEta[8]", "", 'F');
// factory->AddSpectator( "jetEta[9]", "jetEta[9]", "", 'F');
// factory->AddSpectator( "jetEta[10]", "jetEta[10]", "", 'F');
// factory->AddSpectator( "jetPhi[0]", "jetPhi[0]", "", 'F');
// factory->AddSpectator( "jetPhi[1]", "jetPhi[1]", "", 'F');
// factory->AddSpectator( "jetPhi[2]", "jetPhi[2]", "", 'F');
// factory->AddSpectator( "jetPhi[3]", "jetPhi[3]", "", 'F');
// factory->AddSpectator( "jetPhi[4]", "jetPhi[4]", "", 'F');
// factory->AddSpectator( "jetPhi[5]", "jetPhi[5]", "", 'F');
// factory->AddSpectator( "jetPhi[6]", "jetPhi[6]", "", 'F');
// factory->AddSpectator( "jetPhi[7]", "jetPhi[7]", "", 'F');
// factory->AddSpectator( "jetPhi[8]", "jetPhi[8]", "", 'F');
// factory->AddSpectator( "jetPhi[9]", "jetPhi[9]", "", 'F');
// factory->AddSpectator( "jetPhi[10]", "jetPhi[10]", "", 'F');
// factory->AddSpectator("jetE[0]", "jetE[0]", "", 'F');
// factory->AddSpectator("jetE[1]", "jetE[1]", "", 'F');
// factory->AddSpectator("jetE[2]", "jetE[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[0]","higgsJetSubjetEta[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[1]","higgsJetSubjetEta[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetEta[2]","higgsJetSubjetEta[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[0]","higgsJetSubjetPhi[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[1]","higgsJetSubjetPhi[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPhi[2]","higgsJetSubjetPhi[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[0]","higgsJetSubjetPt[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[1]","higgsJetSubjetPt[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetPt[2]","higgsJetSubjetPt[2]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[0]","higgsJetSubjetE[0]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[1]","higgsJetSubjetE[1]", "", 'F');
// factory->AddSpectator("higgsJetSubjetE[2]","higgsJetSubjetE[2]", "", 'F');
// factory->AddSpectator("Wphi", "Wphi", "" , 'F');
// factory->AddVariable("fatjetPt[0]", "fatjetPt[0]", "", 'F');
// factory->AddSpectator("fatjetPhi[0]", "fatjetPhi[0]", "", 'F');
// factory->AddSpectator("fatjetEta[0]", "fatjetEta[0]", "", 'F');
// factory->AddSpectator("fatjetE[0]", "fatjetE[0]", "", 'F');
// //if(std::fabs(Wphi-fatjetPhi[0])<TMath::Pi()){
// factory->AddVariable("abs(Wphi-fatjetPhi[0])", "DeltaPhiWH", "", 'F');
// //}
// if ((abs(Wphi-fatjetPhi[0])>TMath::Pi())){
// factory->AddVariable("(abs(DeltaPhiWH = 2*(TMath::Pi())-DeltaPhiWH))", "DeltaPhiWH", "", 'F');
// }
// Here, we add the lepton flag as a spectator so we can cut (further down) on lep == 0 for muons only or lep == 1 for electrons only.
//factory->AddSpectator( "lepType[0]", "lepType[0]", "units", '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 fsig_name_WH = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/mc11_7TeV.128034.HerwigppPowHeg_Boosted_WH125lnubb.merge.NTUP_HSG5WH.Output_PreCuts-Original.root";
TString fback_name_TT = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/TT_NewBranch2.output_MERGE_PreCuts-Original.root";
TString fback_name_Wbb = "/Disk/speyside7/Grid/grid-files/rsmith/SummerProject/OverlapperInputFiles/PreCutsApplied/mc11_7TeV.128861.SherpaWbb2J_lnu_Wpt100GeV_PreCuts-Original.root";
TFile *sig_input_WH = TFile::Open( fsig_name_WH );
TFile *back_input_TT = TFile::Open( fback_name_TT );
TFile *back_input_Wbb = TFile::Open( fback_name_Wbb);
// --- Register the training and test trees
TTree *signal_WH = (TTree*)sig_input_WH->Get("OutputTree");
TTree *background_TT = (TTree*)back_input_TT->Get("OutputTree");
TTree * background_Wbb = (TTree*)back_input_Wbb->Get("OutputTree");
// --- global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight_WH = 1;
Double_t backgroundWeight_TT = 1;
Double_t backgroundWeight_Wbb= 1;
// --- Here can add an arbitrary number of signal or background trees
factory->AddSignalTree ( signal_WH, signalWeight_WH );
factory->AddBackgroundTree( background_TT, backgroundWeight_TT );
factory->AddBackgroundTree( background_Wbb, backgroundWeight_Wbb);
Float_t nhiggsJetSubjets;
Float_t njets;
Float_t deltaPhiWH;
Float_t jetPt[11];
Float_t jetEta[11];
Float_t jetPhi[11];
Float_t jetE[11];
Float_t higgsJetSubjetEta[3];
Float_t higgsJetSubjetPhi[3];
Float_t higgsJetSubjetPt[3];
Float_t higgsJetSubjetE[3];
Float_t Wphi;
Float_t fatjetPt[15];
Float_t fatjetEta[15];
Float_t fatjetPhi[15];
Float_t fatjetE[15];
TLorentzVector fatjet(0,0,0,0);
TLorentzVector subjet1(0,0,0,0);
TLorentzVector subjet2(0,0,0,0);
TLorentzVector subjet3(0,0,0,0);
TLorentzVector akt[15];
fatjet.SetPtEtaPhiE(fatjetPt[0],fatjetEta[0],fatjetPhi[0], fatjetE[0]);
deltaPhiWH = std::fabs(Wphi-fatjetPhi[0]);
if(deltaPhiWH>TMath::Pi()){ std::fabs(deltaPhiWH = 2*TMath::Pi()-deltaPhiWH);}
float deltaEta[3][11];
float deltaPhi[3][11];
float DeltaR[3][13];
for(int j = 0; j<nhiggsJetSubjets; j++){
for(int i = 0; i<njets; i++){
deltaEta[j][i] = std::fabs(higgsJetSubjetEta[j]-jetEta[i]);
deltaPhi[j][i] = std::fabs(higgsJetSubjetPhi[j]-jetPhi[i]);
DeltaR[j][i] = std::sqrt(deltaEta[j][i]*deltaEta[j][i]+deltaPhi[j][i]*deltaPhi[j][i]);
}
}
for (int i=0; i < njets; i++) {
akt[i].SetPtEtaPhiE(jetPt[i],jetEta[i],jetPhi[i], jetE[i]);
}
subjet1.SetPtEtaPhiE(higgsJetSubjetPt[0],higgsJetSubjetEta[0],higgsJetSubjetPhi[0], higgsJetSubjetE[0]);
subjet2.SetPtEtaPhiE(higgsJetSubjetPt[1],higgsJetSubjetEta[1],higgsJetSubjetPhi[1], higgsJetSubjetE[1]);
FatHiggs = subjet1 + subjet2;
if (nhiggsJetSubjets>2){
subjet3.SetPtEtaPhiE(higgsJetSubjetPt[2],higgsJetSubjetEta[2],higgsJetSubjetPhi[2], higgsJetSubjetE[2]);
}
// To give different trees for training and testing, do:
// factory->AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" );
// factory->AddSignalTree( signalTestTree, signalTestWeight, "Test" );
// Set individual event weights (the variables must exist in the original TTree)
// for signal : factory->SetSignalWeightExpression ("weight1*weight2");
// for background: factory->SetBackgroundWeightExpression("wei
// --- Apply additional cuts on the signal and background samples (can be different)
// PLEASE NOTE: If no cuts are required, do NOT leave any spaces between quotation marks, otherwise an error will occur.
TCut mycuts = "deltaPhiWH>-800"; //Signal Tree Cuts
TCut mycutb = "deltaPhiWH>-800"; //Background Tree Cuts
//cout << "DeltaPhiWH: " << deltaPhiWH << endl;
// 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:!V:NormMode=NumEvents");
// ---- 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[1]=0:CutRangeMax[1]=450:VarProp[1]=FMax:EffSel:Steps=60:Cycles=3:PopSize=2000:SC_steps=10:SC_rate=5:SC_factor=0.95" );
if (Use["CutsSA"])
factory->BookMethod( TMVA::Types::kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
// Likelihood ("naive Bayes estimator")
if (Use["Likelihood"])
factory->BookMethod( TMVA::Types::kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// Decorrelated likelihood
if (Use["LikelihoodD"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" );
// PCA-transformed likelihood
if (Use["LikelihoodPCA"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" );
// Use a kernel density estimator to approximate the PDFs
if (Use["LikelihoodKDE"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" );
// Use a variable-dependent mix of splines and kernel density estimator
if (Use["LikelihoodMIX"])
factory->BookMethod( TMVA::Types::kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" );
// Test the multi-dimensional probability density estimator
// here are the options strings for the MinMax and RMS methods, respectively:
// "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
// "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if (Use["PDERS"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" );
if (Use["PDERSD"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" );
if (Use["PDERSPCA"])
factory->BookMethod( TMVA::Types::kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" );
// Multi-dimensional likelihood estimator using self-adapting phase-space binning
if (Use["PDEFoam"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoam",
"H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0333:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" );
if (Use["PDEFoamBoost"])
factory->BookMethod( TMVA::Types::kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" );
// K-Nearest Neighbour classifier (KNN)
if (Use["KNN"])
factory->BookMethod( TMVA::Types::kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" );
// H-Matrix (chi2-squared) method
if (Use["HMatrix"])
factory->BookMethod( TMVA::Types::kHMatrix, "HMatrix", "!H:!V" );
// Linear discriminant (same as Fisher discriminant)
if (Use["LD"])
factory->BookMethod( TMVA::Types::kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher discriminant (same as LD)
if (Use["Fisher"])
factory->BookMethod( TMVA::Types::kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" );
// Fisher with Gauss-transformed input variables
if (Use["FisherG"])
factory->BookMethod( TMVA::Types::kFisher, "FisherG", "H:!V:VarTransform=Gauss" );
// Composite classifier: ensemble (tree) of boosted Fisher classifiers
if (Use["BoostedFisher"])
factory->BookMethod( TMVA::Types::kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2" );
// Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if (Use["FDA_MC"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if (Use["FDA_GA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if (Use["FDA_SA"]) // can also use Simulated Annealing (SA) algorithm (see Cuts_SA options])
factory->BookMethod( TMVA::Types::kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if (Use["FDA_MT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if (Use["FDA_GAMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if (Use["FDA_MCMT"])
factory->BookMethod( TMVA::Types::kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1);(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
// TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if (Use["MLP"])
factory->BookMethod( TMVA::Types::kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" );
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=350:nEventsMin=100:MaxDepth=3:BoostType=Grad:Shrinkage=0.05:UseBaggedGrad:GradBaggingFraction=0.51:nCuts=65:PruneStrength=2:PruneMethod=ExpectedError:NNodesMax=7" );
//"!H:!V:NTrees=350:nEventsMin=100:MaxDepth=3:BoostType=Grad:Shrinkage=0.05:UseBaggedGrad:GradBaggingFraction=0.55:nCuts=50:PruneStrength=2:PruneMethod=ExpectedError:NNodesMax=10" ); //nCuts=20 && no pruning originally
if (Use["BDT"]) // Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDT",
"NTrees=550:nEventsMin=110:MaxDepth=5.5:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=10:PruneStrength=6:PruneMethod=ExpectedError");
if (Use["BDTB"]) // Bagging
factory->BookMethod( TMVA::Types::kBDT, "BDTB",
"!H:!V:NTrees=950:nEventsMin=20:MaxDepth=10:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" );
if (Use["BDTD"]) // Decorrelation + Adaptive Boost
factory->BookMethod( TMVA::Types::kBDT, "BDTD",
"!H:!V:NTrees=300:nEventsMin=20:MaxDepth=10:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=10:PruneStrength=6:PruneMethod=ExpectedError: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" );
// --------------------------------------------------------------------------------------------------
// ---- Now you can optimize the setting (configuration) of the MVAs using the set of training events
// factory->OptimizeAllMethods("SigEffAt001","Scan");
// factory->OptimizeAllMethods("SigEffAt001","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 );
}
