void test_dae_mydataset()
{
TMVA::Tools::Instance();
TFile *inputFile = TFile::Open( "../datasets/mydataset.root");
TFile* outputFile = TFile::Open( "mydataset_output.root", "RECREATE" );
TMVA::Factory *factory = new TMVA::Factory("TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar:AnalysisType=Regression" );
TMVA::DataLoader *loader=new TMVA::DataLoader("mydataset");
loader->AddVariable("var0", 'F');
loader->AddVariable("var1", 'F');
loader->AddVariable("var2", 'F');
loader->AddVariable("var3 := var0-var1", 'F');
loader->AddVariable("var4 := var0*var2", 'F');
loader->AddVariable("var5 := var1+var2", 'F');
TTree *tsignal = (TTree*)inputFile->Get("MyMCSig");
TTree *tbackground = (TTree*)inputFile->Get("MyMCBkg");
TCut mycuts = "";
TCut mycutb = "";
loader->AddSignalTree( tsignal, 1.0 );
loader->AddBackgroundTree( tbackground, 1.0 );
loader->PrepareTrainingAndTestTree( mycuts, mycutb,"nTrain_Signal=3000:nTrain_Background=3000:nTest_Signal=1449:nTest_Background=1449:SplitMode=Random:NormMode=NumEvents:!V");
TString layoutString ("Layout=TANH|3,LINEAR");
TString training0 ("LearningRate=1e-1,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-2,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1;
TString nnOptions ("AE(indexLayer=1;pretraining=false;!H:V:ErrorStrategy=SUMOFSQUARES:VarTransform=G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":");
nnOptions.Append (layoutString);
nnOptions.Append (":");
nnOptions.Append (trainingStrategyString);
nnOptions.Append (")");
cout << nnOptions.Data() << endl;
TMVA::DataLoader* newloader = loader->VarTransform(nnOptions);
}
std::pair<TString,TString> TMVAClassification (
TString infilename,
AnalysisType analysisType = AnalysisType::DIRECT,
TString additionalRootFileName = "")
{
TMVA::Tools::Instance();
std::string tmstr (now ());
TString tmstmp (tmstr.c_str ());
std::cout << "==> Start TMVAClassification" << std::endl;
std::cout << "-------------------- open input file ---------------- " << std::endl;
TString fname = infilename; //pathToData + infilename + TString (".root");
if (analysisType != AnalysisType::TRANSFORMED)
fname = pathToData + infilename + TString (".root");
std::cout << "open file " << std::endl << fname.Data () << std::endl;
std::cout << "-------------------- get tree ---------------- " << std::endl;
TString treeName = "data";
if (analysisType == AnalysisType::TRANSFORMED)
treeName = "transformed";
std::cout << "-------------------- create tchain with treeName ---------------- " << std::endl;
std::cout << treeName << std::endl;
TChain* tree = new TChain (treeName);
std::cout << "add file" << std::endl;
std::cout << fname << std::endl;
tree->Add (fname);
TChain* treeFriend (NULL);
if (additionalRootFileName.Length () > 0)
{
std::cout << "-------------------- add additional input file ---------------- " << std::endl;
std::cout << additionalRootFileName << std::endl;
treeFriend = new TChain (treeName);
treeFriend->Add (additionalRootFileName);
tree->AddFriend (treeFriend,"p");
}
// tree->Draw ("mass:prediction");
// return std::make_pair(TString("hallo"),TString ("nix"));
TString outfileName;
if (analysisType == AnalysisType::BACKGROUND)
{
outfileName = TString ("BACK_" + infilename) + tmstmp + TString (".root");
}
else
outfileName += TString ( "TMVA__" ) + tmstmp + TString (".root");
std::cout << "-------------------- open output file ---------------- " << std::endl;
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
std::cout << "-------------------- prepare factory ---------------- " << std::endl;
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassification", outputFile,
"AnalysisType=Classification:Transformations=I:!V" );
std::cout << "-------------------- add variables ---------------- " << std::endl;
for (auto varname : variableNames)
{
factory->AddVariable (varname.c_str (), 'F');
}
for (auto varname : spectatorNames)
{
factory->AddSpectator (varname.c_str (), 'F');
}
std::cout << "-------------------- add trees ---------------- " << std::endl;
TCut signalCut ("signal==1");
TCut backgroundCut ("signal==0");
if (analysisType == AnalysisType::TRANSFORMED)
{
signalCut = "(signal_original==1 && signal_in==0)";
backgroundCut = "(signal_original==0 && signal_in==0)";
}
if (analysisType == AnalysisType::BACKGROUND)
{
signalCut = TString("(signal==0) * (prediction > 0.7)");
backgroundCut = TString("(signal==0) * (prediction < 0.4)");
}
//tree->Draw ("prediction",signalCut);
//return std::make_pair(TString("hallo"),TString ("nix"));
factory->AddTree(tree, "Signal", 1.0, baseCut + signalCut, "TrainingTesting");
factory->AddTree(tree, "Background", 1.0, baseCut + backgroundCut, "TrainingTesting");
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
/* // Set individual event weights (the variables must exist in the original TTree) */
if (analysisType == AnalysisType::BACKGROUND)
{
factory->SetSignalWeightExpression ("prediction");
factory->SetBackgroundWeightExpression ("1");
}
std::cout << "-------------------- prepare ---------------- " << std::endl;
factory->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:nTest_Signal=0:nTest_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
TString methodName ("");
if (analysisType == AnalysisType::BACKGROUND)
methodName = TString ("TONBKG_") + tmstmp;
if (false)
{
// gradient boosting training
methodName += TString("GBDT");
factory->BookMethod(TMVA::Types::kBDT, methodName,
"NTrees=40:BoostType=Grad:Shrinkage=0.01:MaxDepth=7:UseNvars=6:nCuts=20:MinNodeSize=10");
}
if (false)
{
methodName += TString("Likelihood");
factory->BookMethod( TMVA::Types::kLikelihood, methodName,
"H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
}
if (false)
{
TString layoutString ("Layout=TANH|100,LINEAR");
TString training0 ("LearningRate=1e-1,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-2,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-2,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-3,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNgauss");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (false)
{
TString layoutString ("Layout=TANH|200,TANH|70,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=300,BatchSize=20,TestRepetitions=15,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.5,Repetitions=1,ConvergenceSteps=300,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.3,Repetitions=1,ConvergenceSteps=300,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.1,Repetitions=1,ConvergenceSteps=200,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2 + "|" + training3;
// trainingStrategyString += training0 + "|" + training2;
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CROSSENTROPY");
TString nnOptions ("!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=N:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName = TString("NNnormalized");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
if (true)
{
TString layoutString ("Layout=TANH|100,TANH|50,LINEAR");
TString training0 ("LearningRate=1e-2,Momentum=0.0,Repetitions=1,ConvergenceSteps=100,BatchSize=20,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE,DropConfig=0.0+0.5+0.5+0.5,DropRepetitions=1,Multithreading=True");
TString training1 ("LearningRate=1e-3,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=30,TestRepetitions=7,WeightDecay=0.001,Regularization=L2,Multithreading=True,DropConfig=0.0+0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=40,TestRepetitions=7,WeightDecay=0.0001,Regularization=L2,Multithreading=True");
TString training3 ("LearningRate=1e-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=30,BatchSize=70,TestRepetitions=7,WeightDecay=0.0001,Regularization=NONE,Multithreading=True");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 + "|" + training3;
TString nnOptions ("!H:!V:ErrorStrategy=CROSSENTROPY:VarTransform=P+G:WeightInitialization=XAVIERUNIFORM");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
methodName += TString("NNPG");
factory->BookMethod( TMVA::Types::kNN, methodName, nnOptions ); // NN
}
factory->TrainAllMethods();
// return std::make_pair(TString("hallo"),TString ("nix"));
factory->TestAllMethods();
factory->EvaluateAllMethods();
//input->Close();
outputFile->Close();
// TMVA::TMVAGui (outfileName);
delete factory;
delete tree;
switch (analysisType)
{
case AnalysisType::BACKGROUND:
std::cout << "DONE BACKGROUND" << std::endl;
break;
case AnalysisType::DIRECT:
std::cout << "DONE DIRECT" << std::endl;
break;
case AnalysisType::TRANSFORMED:
std::cout << "DONE TRANSFORMED" << std::endl;
break;
};
std::cout << "classification, return : " << outfileName << " , " << methodName << std::endl;
return std::make_pair (outfileName, methodName);
}
TString autoencoder (std::string inputFileName)
{
std::string tmstr (now ());
TString tmstmp (tmstr.c_str ());
std::cout << "==> Start Autoencoder " << std::endl;
std::cout << "-------------------- open input file ---------------- " << std::endl;
TString fname = pathToData + TString (inputFileName.c_str ()) + TString (".root");
TFile *input = TFile::Open( fname );
std::cout << "-------------------- get tree ---------------- " << std::endl;
TTree *tree = (TTree*)input->Get("data");
TString outfileName( "TMVAAutoEnc__" );
outfileName += TString (inputFileName.c_str ()) + TString ("__") + tmstmp + TString (".root");
std::cout << "-------------------- open output file ---------------- " << std::endl;
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
std::cout << "-------------------- prepare factory ---------------- " << std::endl;
TMVA::Factory *factory = new TMVA::Factory( "TMVAAutoencoder", outputFile,
"AnalysisType=Regression:Color:DrawProgressBar" );
std::cout << "-------------------- add variables ---------------- " << std::endl;
for (auto varname : variableNames+additionalVariableNames)
{
factory->AddVariable (varname.c_str (), 'F');
factory->AddTarget (varname.c_str (), 'F');
}
std::cout << "-------------------- add tree ---------------- " << std::endl;
// global event weights per tree (see below for setting event-wise weights)
Double_t regWeight = 1.0;
factory->AddRegressionTree (tree, regWeight);
std::cout << "-------------------- prepare ---------------- " << std::endl;
TCut mycut = ""; // for example: TCut mycut = "abs(var1)<0.5 && abs(var2-0.5)<1";
factory->PrepareTrainingAndTestTree( mycut,
"nTrain_Regression=0:nTest_Regression=0:SplitMode=Random:NormMode=NumEvents:!V" );
/* // This would set individual event weights (the variables defined in the */
/* // expression need to exist in the original TTree) */
/* factory->SetWeightExpression( "var1", "Regression" ); */
if (true)
{
TString layoutString ("Layout=TANH|100,TANH|20,TANH|40,LINEAR");
TString training0 ("LearningRate=1e-5,Momentum=0.5,Repetitions=1,ConvergenceSteps=500,BatchSize=50,TestRepetitions=7,WeightDecay=0.01,Regularization=NONE,DropConfig=0.5+0.5+0.5+0.5,DropRepetitions=2");
TString training1 ("LearningRate=1e-5,Momentum=0.9,Repetitions=1,ConvergenceSteps=500,BatchSize=30,TestRepetitions=7,WeightDecay=0.01,Regularization=L2,DropConfig=0.1+0.1+0.1,DropRepetitions=1");
TString training2 ("LearningRate=1e-4,Momentum=0.3,Repetitions=1,ConvergenceSteps=10,BatchSize=40,TestRepetitions=7,WeightDecay=0.1,Regularization=L2");
TString training3 ("LearningRate=1e-5,Momentum=0.1,Repetitions=1,ConvergenceSteps=10,BatchSize=10,TestRepetitions=7,WeightDecay=0.001,Regularization=NONE");
TString trainingStrategyString ("TrainingStrategy=");
trainingStrategyString += training0 + "|" + training1 + "|" + training2 ; //+ "|" + training3;
// TString trainingStrategyString ("TrainingStrategy=LearningRate=1e-1,Momentum=0.3,Repetitions=3,ConvergenceSteps=20,BatchSize=30,TestRepetitions=7,WeightDecay=0.0,L1=false,DropFraction=0.0,DropRepetitions=5");
TString nnOptions ("!H:V:ErrorStrategy=SUMOFSQUARES:VarTransform=N:WeightInitialization=XAVIERUNIFORM");
// TString nnOptions ("!H:V:VarTransform=Normalize:ErrorStrategy=CHECKGRADIENTS");
nnOptions.Append (":"); nnOptions.Append (layoutString);
nnOptions.Append (":"); nnOptions.Append (trainingStrategyString);
factory->BookMethod( TMVA::Types::kNN, TString("NN_")+tmstmp, nnOptions ); // NN
}
// --------------------------------------------------------------------------------------------------
factory->TrainAllMethods();
factory->TestAllMethods();
factory->EvaluateAllMethods();
outputFile->Close();
// TMVA::TMVARegGui (outfileName);
delete factory;
return TString("NN_")+tmstmp;
}
