void rf510_wsnamedsets()
{
// C r e a t e m o d e l a n d d a t a s e t
// -----------------------------------------------
RooWorkspace* w = new RooWorkspace("w") ;
fillWorkspace(*w) ;
// Exploit convention encoded in named set "parameters" and "observables"
// to use workspace contents w/o need for introspected
RooAbsPdf* model = w->pdf("model") ;
// Generate data from p.d.f. in given observables
RooDataSet* data = model->generate(*w->set("observables"),1000) ;
// Fit model to data
model->fitTo(*data) ;
// Plot fitted model and data on frame of first (only) observable
RooPlot* frame = ((RooRealVar*)w->set("observables")->first())->frame() ;
data->plotOn(frame) ;
model->plotOn(frame) ;
// Overlay plot with model with reference parameters as stored in snapshots
w->loadSnapshot("reference_fit") ;
model->plotOn(frame,LineColor(kRed)) ;
w->loadSnapshot("reference_fit_bkgonly") ;
model->plotOn(frame,LineColor(kRed),LineStyle(kDashed)) ;
// Draw the frame on the canvas
new TCanvas("rf510_wsnamedsets","rf503_wsnamedsets",600,600) ;
gPad->SetLeftMargin(0.15) ; frame->GetYaxis()->SetTitleOffset(1.4) ; frame->Draw() ;
// Print workspace contents
w->Print() ;
// Workspace will remain in memory after macro finishes
gDirectory->Add(w) ;
}
RooAbsData * Tprime::GetPseudoData( void ) {
//
// Generate pseudo data, return a pointer.
// Class member pointer data set to point to the dataset.
// Caller does not take ownership.
//
static int n_toys = 0;
// legend for printouts
std::string legend = "[Tprime::GetPseudoData()]: ";
delete data;
// We will use ToyMCSampler to generate pseudo-data (and test statistic, eventually)
// We are responsible for randomizing nuisances and global observables,
// ToyMCSampler only generates observables (as of ROOT 5.30.00-rc1 and before)
// MC sampler and test statistic
if(n_toys == 0) { // on first entry
// get B model config from workspace
RooStats::ModelConfig * pBModel = (RooStats::ModelConfig *)pWs->obj("BModel");
pBModel->SetWorkspace(*pWs);
// get parameter of interest set
//const RooArgSet * poi = pSbModel->GetParametersOfInterest();
//RooStats::TestStatistic * pTestStatistic = new RooStats::ProfileLikelihoodTestStat(*pBModel->GetPdf());
//RooStats::ToyMCSampler toymcs(*pTestStatistic, 1);
pTestStatistic = new RooStats::ProfileLikelihoodTestStat(*pBModel->GetPdf());
pToyMcSampler = new RooStats::ToyMCSampler(*pTestStatistic, 1);
pToyMcSampler->SetPdf(*pBModel->GetPdf());
pToyMcSampler->SetObservables(*pBModel->GetObservables());
pToyMcSampler->SetParametersForTestStat(*pBModel->GetParametersOfInterest()); // just POI
pToyMcSampler->SetGlobalObservables(*pBModel->GetGlobalObservables());
}
// load parameter point
pWs->loadSnapshot("parametersToGenerateData");
RooArgSet dummySet;
data = pToyMcSampler->GenerateToyData(dummySet);
std::cout << legend << "generated the following background-only pseudo-data:" << std::endl;
data->Print();
// count number of generated toys
++n_toys;
return data;
}
vector<Double_t*> simFit(bool makeSoupFit_ = false,
const string tnp_ = "etoTauMargLooseNoCracks70",
const string category_ = "tauAntiEMVA",
const string bin_ = "abseta<1.5",
const float binCenter_ = 0.75,
const float binWidth_ = 0.75,
const float xLow_=60,
const float xHigh_=120,
bool SumW2_ = false,
bool verbose_ = true){
vector<Double_t*> out;
//return out;
//TFile *test = new TFile( outFile->GetName(),"UPDATE");
// output file
TFile *test = new TFile( Form("EtoTauPlotsFit_%s_%s_%f.root",tnp_.c_str(),category_.c_str(),binCenter_),"RECREATE");
test->mkdir(Form("bin%f",binCenter_));
TCanvas *c = new TCanvas("fitCanvas",Form("fitCanvas_%s_%s",tnp_.c_str(),bin_.c_str()),10,30,650,600);
c->SetGrid(0,0);
c->SetFillStyle(4000);
c->SetFillColor(10);
c->SetTicky();
c->SetObjectStat(0);
TCanvas *c2 = new TCanvas("fitCanvasTemplate",Form("fitCanvasTemplate_%s_%s",tnp_.c_str(),bin_.c_str()),10,30,650,600);
c2->SetGrid(0,0);
c2->SetFillStyle(4000);
c2->SetFillColor(10);
c2->SetTicky();
c2->SetObjectStat(0);
// input files
TFile fsup("/data_CMS/cms/lbianchini/tagAndProbe/trees/38XWcut/testNewWriteFromPAT_soup.root");
TFile fbkg("/data_CMS/cms/lbianchini/tagAndProbe/trees/38XWcut/testNewWriteFromPAT_soup_bkg.root");
TFile fsgn("/data_CMS/cms/lbianchini/tagAndProbe/trees/38XWcut/testNewWriteFromPAT_soup_sgn.root");
TFile fdat("/data_CMS/cms/lbianchini/tagAndProbe/trees/38XWcut/testNewWriteFromPAT_Data.root");
// data from 2iter:
//TFile fdat("/data_CMS/cms/lbianchini/35pb/testNewWriteFromPAT_Data.root");
//********************** signal only tree *************************/
TTree *fullTreeSgn = (TTree*)fsgn.Get((tnp_+"/fitter_tree").c_str());
TH1F* hSall = new TH1F("hSall","",1,0,150);
TH1F* hSPall = new TH1F("hSPall","",1,0,150);
TH1F* hS = new TH1F("hS","",1,0,150);
TH1F* hSP = new TH1F("hSP","",1,0,150);
fullTreeSgn->Draw("mass>>hS",Form("weight*(%s && mass>%f && mass<%f && mcTrue && signalPFChargedHadrCands<1.5)",bin_.c_str(),xLow_,xHigh_));
fullTreeSgn->Draw("mass>>hSall",Form("weight*(%s && mass>%f && mass<%f)",bin_.c_str(),xLow_,xHigh_));
float SGNtrue = hS->Integral();
float SGNall = hSall->Integral();
fullTreeSgn->Draw("mass>>hSP",Form("weight*(%s && %s>0 && mass>%f && mass<%f && mcTrue && signalPFChargedHadrCands<1.5 )",bin_.c_str(),category_.c_str(),xLow_,xHigh_));
fullTreeSgn->Draw("mass>>hSPall",Form("weight*(%s && %s>0 && mass>%f && mass<%f && signalPFChargedHadrCands<1.5 )",bin_.c_str(),category_.c_str(),xLow_,xHigh_));
float SGNtruePass = hSP->Integral();
float SGNallPass = hSPall->Integral();
//********************** background only tree *************************//
TTree *fullTreeBkg = (TTree*)fbkg.Get((tnp_+"/fitter_tree").c_str());
TH1F* hB = new TH1F("hB","",1,0,150);
TH1F* hBP = new TH1F("hBP","",1,0,150);
fullTreeBkg->Draw("mass>>hB",Form("weight*(%s && mass>%f && mass<%f && signalPFChargedHadrCands<1.5 )",bin_.c_str(),xLow_,xHigh_));
float BKG = hB->Integral();
float BKGUnWeighted = hB->GetEntries();
fullTreeBkg->Draw("mass>>hBP",Form("weight*(%s && %s>0 && mass>%f && mass<%f && signalPFChargedHadrCands<1.5 )",bin_.c_str(),category_.c_str(),xLow_,xHigh_));
float BKGPass = hBP->Integral();
float BKGUnWeightedPass = hBP->GetEntries();
float BKGFail = BKG-BKGPass;
cout << "*********** BKGFail " << BKGFail << endl;
//********************** soup tree *************************//
TTree *fullTreeSoup = (TTree*)fsup.Get((tnp_+"/fitter_tree").c_str());
//********************** data tree *************************//
TTree *fullTreeData = (TTree*)fdat.Get((tnp_+"/fitter_tree").c_str());
//********************** workspace ***********************//
RooWorkspace *w = new RooWorkspace("w","w");
// tree variables to be imported
w->factory("mass[30,120]");
w->factory("weight[0,10000]");
w->factory("abseta[0,2.5]");
w->factory("pt[0,200]");
w->factory("mcTrue[0,1]");
w->factory("signalPFChargedHadrCands[0,10]");
w->factory((category_+"[0,1]").c_str());
// background pass pdf for MC
w->factory("RooExponential::McBackgroundPdfP(mass,McCP[0,-10,10])");
// background fail pdf for MC
w->factory("RooExponential::McBackgroundPdfF(mass,McCF[0,-10,10])");
// background pass pdf for Data
w->factory("RooExponential::DataBackgroundPdfP(mass,DataCP[0,-10,10])");
// background fail pdf for Data
w->factory("RooExponential::DataBackgroundPdfF(mass,DataCF[0,-10,10])");
// fit parameters for background
w->factory("McEfficiency[0.04,0,1]");
w->factory("McNumSgn[0,1000000]");
w->factory("McNumBkgP[0,100000]");
w->factory("McNumBkgF[0,100000]");
w->factory("expr::McNumSgnP('McEfficiency*McNumSgn',McEfficiency,McNumSgn)");
w->factory("expr::McNumSgnF('(1-McEfficiency)*McNumSgn',McEfficiency,McNumSgn)");
w->factory("McPassing[pass=1,fail=0]");
// fit parameters for data
w->factory("DataEfficiency[0.1,0,1]");
w->factory("DataNumSgn[0,1000000]");
w->factory("DataNumBkgP[0,1000000]");
w->factory("DataNumBkgF[0,10000]");
w->factory("expr::DataNumSgnP('DataEfficiency*DataNumSgn',DataEfficiency,DataNumSgn)");
w->factory("expr::DataNumSgnF('(1-DataEfficiency)*DataNumSgn',DataEfficiency,DataNumSgn)");
w->factory("DataPassing[pass=1,fail=0]");
RooRealVar *weight = w->var("weight");
RooRealVar *abseta = w->var("abseta");
RooRealVar *pt = w->var("pt");
RooRealVar *mass = w->var("mass");
mass->setRange(xLow_,xHigh_);
RooRealVar *mcTrue = w->var("mcTrue");
RooRealVar *cut = w->var( category_.c_str() );
RooRealVar *signalPFChargedHadrCands = w->var("signalPFChargedHadrCands");
// build the template for the signal pass sample:
RooDataSet templateP("templateP","dataset for signal-pass template", RooArgSet(*mass,*weight,*abseta,*pt,*cut,*mcTrue,*signalPFChargedHadrCands), Import( *fullTreeSgn ), /*WeightVar( *weight ),*/ Cut( Form("(mcTrue && %s>0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()) ) );
// build the template for the signal fail sample:
RooDataSet templateF("templateF","dataset for signal-fail template", RooArgSet(*mass,*weight,*abseta,*pt,*cut,*mcTrue,*signalPFChargedHadrCands), Import( *fullTreeSgn ), /*WeightVar( *weight ),*/ Cut( Form("(mcTrue && %s<0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()) ) );
mass->setBins(24);
RooDataHist templateHistP("templateHistP","",RooArgSet(*mass), templateP, 1.0);
RooHistPdf TemplateSignalPdfP("TemplateSignalPdfP","",RooArgSet(*mass),templateHistP);
w->import(TemplateSignalPdfP);
mass->setBins(24);
RooDataHist templateHistF("templateHistF","",RooArgSet(*mass),templateF,1.0);
RooHistPdf TemplateSignalPdfF("TemplateSignalPdfF","",RooArgSet(*mass),templateHistF);
w->import(TemplateSignalPdfF);
mass->setBins(10000,"fft");
RooPlot* TemplateFrameP = mass->frame(Bins(24),Title("Template passing"));
templateP.plotOn(TemplateFrameP);
w->pdf("TemplateSignalPdfP")->plotOn(TemplateFrameP);
RooPlot* TemplateFrameF = mass->frame(Bins(24),Title("Template failing"));
templateF.plotOn(TemplateFrameF);
w->pdf("TemplateSignalPdfF")->plotOn(TemplateFrameF);
//w->factory("RooFFTConvPdf::McSignalPdfP(mass,TemplateSignalPdfP,RooTruthModel::McResolModP(mass))");
//w->factory("RooFFTConvPdf::McSignalPdfF(mass,TemplateSignalPdfF,RooTruthModel::McResolModF(mass))");
// FOR GREGORY: PROBLEM WHEN TRY TO USE THE PURE TEMPLATE =>
RooHistPdf McSignalPdfP("McSignalPdfP","McSignalPdfP",RooArgSet(*mass),templateHistP);
RooHistPdf McSignalPdfF("McSignalPdfF","McSignalPdfF",RooArgSet(*mass),templateHistF);
w->import(McSignalPdfP);
w->import(McSignalPdfF);
// FOR GREGORY: FOR DATA, CONVOLUTION IS OK =>
w->factory("RooFFTConvPdf::DataSignalPdfP(mass,TemplateSignalPdfP,RooGaussian::DataResolModP(mass,DataMeanResP[0.0,-5.,5.],DataSigmaResP[0.5,0.,10]))");
w->factory("RooFFTConvPdf::DataSignalPdfF(mass,TemplateSignalPdfF,RooGaussian::DataResolModF(mass,DataMeanResF[-5.,-10.,10.],DataSigmaResF[0.5,0.,10]))");
//w->factory("RooCBShape::DataSignalPdfF(mass,DataMeanF[91.2,88,95.],DataSigmaF[3,0.5,8],DataAlfaF[1.8,0.,10],DataNF[1.0,1e-06,10])");
//w->factory("RooFFTConvPdf::DataSignalPdfF(mass,RooVoigtian::DataVoigF(mass,DataMeanF[85,80,95],DataWidthF[2.49],DataSigmaF[3,0.5,10]),RooCBShape::DataResolModF(mass,DataMeanResF[0.5,0.,10.],DataSigmaResF[0.5,0.,10],DataAlphaResF[0.5,0.,10],DataNResF[1.0,1e-06,10]))");
//w->factory("SUM::DataSignalPdfF(fVBP[0.5,0,1]*RooBifurGauss::bifF(mass,DataMeanResF[91.2,80,95],sigmaLF[10,0.5,40],sigmaRF[0.]), RooVoigtian::voigF(mass, DataMeanResF, widthF[2.49], sigmaVoigF[5,0.1,10]) )" );
// composite model pass for MC
w->factory("SUM::McModelP(McNumSgnP*McSignalPdfP,McNumBkgP*McBackgroundPdfP)");
w->factory("SUM::McModelF(McNumSgnF*McSignalPdfF,McNumBkgF*McBackgroundPdfF)");
// composite model pass for data
w->factory("SUM::DataModelP(DataNumSgnP*DataSignalPdfP,DataNumBkgP*DataBackgroundPdfP)");
w->factory("SUM::DataModelF(DataNumSgnF*DataSignalPdfF,DataNumBkgF*DataBackgroundPdfF)");
// simultaneous fir for MC
w->factory("SIMUL::McModel(McPassing,pass=McModelP,fail=McModelF)");
// simultaneous fir for data
w->factory("SIMUL::DataModel(DataPassing,pass=DataModelP,fail=DataModelF)");
w->Print("V");
w->saveSnapshot("clean", w->allVars());
w->loadSnapshot("clean");
/****************** sim fit to soup **************************/
///////////////////////////////////////////////////////////////
TFile *f = new TFile("dummySoup.root","RECREATE");
TTree* cutTreeSoupP = fullTreeSoup->CopyTree(Form("(%s>0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()));
TTree* cutTreeSoupF = fullTreeSoup->CopyTree(Form("(%s<0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()));
RooDataSet McDataP("McDataP","dataset pass for the soup", RooArgSet(*mass), Import( *cutTreeSoupP ) );
RooDataSet McDataF("McDataF","dataset fail for the soup", RooArgSet(*mass), Import( *cutTreeSoupF ) );
RooDataHist McCombData("McCombData","combined data for the soup", RooArgSet(*mass), Index(*(w->cat("McPassing"))), Import("pass", *(McDataP.createHistogram("histoP",*mass)) ), Import("fail",*(McDataF.createHistogram("histoF",*mass)) ) ) ;
RooPlot* McFrameP = 0;
RooPlot* McFrameF = 0;
RooRealVar* McEffFit = 0;
if(makeSoupFit_){
cout << "**************** N bins in mass " << w->var("mass")->getBins() << endl;
RooFitResult* ResMcCombinedFit = w->pdf("McModel")->fitTo(McCombData, Extended(1), Minos(1), Save(1), SumW2Error( SumW2_ ), Range(xLow_,xHigh_), NumCPU(4) /*, ExternalConstraints( *(w->pdf("ConstrainMcNumBkgF")) )*/ );
test->cd(Form("bin%f",binCenter_));
ResMcCombinedFit->Write("McFitResults_Combined");
RooArgSet McFitParam(ResMcCombinedFit->floatParsFinal());
McEffFit = (RooRealVar*)(&McFitParam["McEfficiency"]);
RooRealVar* McNumSigFit = (RooRealVar*)(&McFitParam["McNumSgn"]);
RooRealVar* McNumBkgPFit = (RooRealVar*)(&McFitParam["McNumBkgP"]);
RooRealVar* McNumBkgFFit = (RooRealVar*)(&McFitParam["McNumBkgF"]);
McFrameP = mass->frame(Bins(24),Title("MC: passing sample"));
McCombData.plotOn(McFrameP,Cut("McPassing==McPassing::pass"));
w->pdf("McModel")->plotOn(McFrameP,Slice(*(w->cat("McPassing")),"pass"), ProjWData(*(w->cat("McPassing")),McCombData), LineColor(kBlue),Range(xLow_,xHigh_));
w->pdf("McModel")->plotOn(McFrameP,Slice(*(w->cat("McPassing")),"pass"), ProjWData(*(w->cat("McPassing")),McCombData), Components("McSignalPdfP"), LineColor(kRed),Range(xLow_,xHigh_));
w->pdf("McModel")->plotOn(McFrameP,Slice(*(w->cat("McPassing")),"pass"), ProjWData(*(w->cat("McPassing")),McCombData), Components("McBackgroundPdfP"), LineColor(kGreen),Range(xLow_,xHigh_));
McFrameF = mass->frame(Bins(24),Title("MC: failing sample"));
McCombData.plotOn(McFrameF,Cut("McPassing==McPassing::fail"));
w->pdf("McModel")->plotOn(McFrameF,Slice(*(w->cat("McPassing")),"fail"), ProjWData(*(w->cat("McPassing")),McCombData), LineColor(kBlue),Range(xLow_,xHigh_));
w->pdf("McModel")->plotOn(McFrameF,Slice(*(w->cat("McPassing")),"fail"), ProjWData(*(w->cat("McPassing")),McCombData), Components("McSignalPdfF"), LineColor(kRed),Range(xLow_,xHigh_));
w->pdf("McModel")->plotOn(McFrameF,Slice(*(w->cat("McPassing")),"fail"), ProjWData(*(w->cat("McPassing")),McCombData), Components("McBackgroundPdfF"), LineColor(kGreen),Range(xLow_,xHigh_));
}
///////////////////////////////////////////////////////////////
/****************** sim fit to data **************************/
///////////////////////////////////////////////////////////////
TFile *f2 = new TFile("dummyData.root","RECREATE");
TTree* cutTreeDataP = fullTreeData->CopyTree(Form("(%s>0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()));
TTree* cutTreeDataF = fullTreeData->CopyTree(Form("(%s<0.5 && %s && signalPFChargedHadrCands<1.5)",category_.c_str(),bin_.c_str()));
RooDataSet DataDataP("DataDataP","dataset pass for the soup", RooArgSet(*mass), Import( *cutTreeDataP ) );
RooDataSet DataDataF("DataDataF","dataset fail for the soup", RooArgSet(*mass), Import( *cutTreeDataF ) );
RooDataHist DataCombData("DataCombData","combined data for the soup", RooArgSet(*mass), Index(*(w->cat("DataPassing"))), Import("pass",*(DataDataP.createHistogram("histoDataP",*mass))),Import("fail",*(DataDataF.createHistogram("histoDataF",*mass)))) ;
RooFitResult* ResDataCombinedFit = w->pdf("DataModel")->fitTo(DataCombData, Extended(1), Minos(1), Save(1), SumW2Error( SumW2_ ), Range(xLow_,xHigh_), NumCPU(4));
test->cd(Form("bin%f",binCenter_));
ResDataCombinedFit->Write("DataFitResults_Combined");
RooArgSet DataFitParam(ResDataCombinedFit->floatParsFinal());
RooRealVar* DataEffFit = (RooRealVar*)(&DataFitParam["DataEfficiency"]);
RooRealVar* DataNumSigFit = (RooRealVar*)(&DataFitParam["DataNumSgn"]);
RooRealVar* DataNumBkgPFit = (RooRealVar*)(&DataFitParam["DataNumBkgP"]);
RooRealVar* DataNumBkgFFit = (RooRealVar*)(&DataFitParam["DataNumBkgF"]);
RooPlot* DataFrameP = mass->frame(Bins(24),Title("Data: passing sample"));
DataCombData.plotOn(DataFrameP,Cut("DataPassing==DataPassing::pass"));
w->pdf("DataModel")->plotOn(DataFrameP,Slice(*(w->cat("DataPassing")),"pass"), ProjWData(*(w->cat("DataPassing")),DataCombData), LineColor(kBlue),Range(xLow_,xHigh_));
w->pdf("DataModel")->plotOn(DataFrameP,Slice(*(w->cat("DataPassing")),"pass"), ProjWData(*(w->cat("DataPassing")),DataCombData), Components("DataSignalPdfP"), LineColor(kRed),Range(xLow_,xHigh_));
w->pdf("DataModel")->plotOn(DataFrameP,Slice(*(w->cat("DataPassing")),"pass"), ProjWData(*(w->cat("DataPassing")),DataCombData), Components("DataBackgroundPdfP"), LineColor(kGreen),LineStyle(kDashed),Range(xLow_,xHigh_));
RooPlot* DataFrameF = mass->frame(Bins(24),Title("Data: failing sample"));
DataCombData.plotOn(DataFrameF,Cut("DataPassing==DataPassing::fail"));
w->pdf("DataModel")->plotOn(DataFrameF,Slice(*(w->cat("DataPassing")),"fail"), ProjWData(*(w->cat("DataPassing")),DataCombData), LineColor(kBlue),Range(xLow_,xHigh_));
w->pdf("DataModel")->plotOn(DataFrameF,Slice(*(w->cat("DataPassing")),"fail"), ProjWData(*(w->cat("DataPassing")),DataCombData), Components("DataSignalPdfF"), LineColor(kRed),Range(xLow_,xHigh_));
w->pdf("DataModel")->plotOn(DataFrameF,Slice(*(w->cat("DataPassing")),"fail"), ProjWData(*(w->cat("DataPassing")),DataCombData), Components("DataBackgroundPdfF"), LineColor(kGreen),LineStyle(kDashed),Range(xLow_,xHigh_));
///////////////////////////////////////////////////////////////
if(makeSoupFit_) c->Divide(2,2);
else c->Divide(2,1);
c->cd(1);
DataFrameP->Draw();
c->cd(2);
DataFrameF->Draw();
if(makeSoupFit_){
c->cd(3);
McFrameP->Draw();
c->cd(4);
McFrameF->Draw();
}
c->Draw();
test->cd(Form("bin%f",binCenter_));
c->Write();
c2->Divide(2,1);
c2->cd(1);
TemplateFrameP->Draw();
c2->cd(2);
TemplateFrameF->Draw();
c2->Draw();
test->cd(Form("bin%f",binCenter_));
c2->Write();
// MINOS errors, otherwise HESSE quadratic errors
float McErrorLo = 0;
float McErrorHi = 0;
if(makeSoupFit_){
McErrorLo = McEffFit->getErrorLo()<0 ? McEffFit->getErrorLo() : (-1)*McEffFit->getError();
McErrorHi = McEffFit->getErrorHi()>0 ? McEffFit->getErrorHi() : McEffFit->getError();
}
float DataErrorLo = DataEffFit->getErrorLo()<0 ? DataEffFit->getErrorLo() : (-1)*DataEffFit->getError();
float DataErrorHi = DataEffFit->getErrorHi()>0 ? DataEffFit->getErrorHi() : DataEffFit->getError();
float BinomialError = TMath::Sqrt(SGNtruePass/SGNtrue*(1-SGNtruePass/SGNtrue)/SGNtrue);
Double_t* truthMC = new Double_t[6];
Double_t* tnpMC = new Double_t[6];
Double_t* tnpData = new Double_t[6];
truthMC[0] = binCenter_;
truthMC[1] = binWidth_;
truthMC[2] = binWidth_;
truthMC[3] = SGNtruePass/SGNtrue;
truthMC[4] = BinomialError;
truthMC[5] = BinomialError;
if(makeSoupFit_){
tnpMC[0] = binCenter_;
tnpMC[1] = binWidth_;
tnpMC[2] = binWidth_;
tnpMC[3] = McEffFit->getVal();
tnpMC[4] = (-1)*McErrorLo;
tnpMC[5] = McErrorHi;
}
tnpData[0] = binCenter_;
tnpData[1] = binWidth_;
tnpData[2] = binWidth_;
tnpData[3] = DataEffFit->getVal();
tnpData[4] = (-1)*DataErrorLo;
tnpData[5] = DataErrorHi;
out.push_back(truthMC);
out.push_back(tnpData);
if(makeSoupFit_) out.push_back(tnpMC);
test->Close();
//delete c; delete c2;
if(verbose_) cout << "returning from bin " << bin_ << endl;
return out;
}
void compute_p0(const char* inFileName,
const char* wsName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData",
const char* asimov1DataName = "asimovData_1",
const char* conditional1Snapshot = "conditionalGlobs_1",
const char* nominalSnapshot = "nominalGlobs",
string smass = "130",
string folder = "test")
{
double mass;
stringstream massStr;
massStr << smass;
massStr >> mass;
double mu_profile_value = 1; // mu value to profile the obs data at wbefore generating the expected
bool doConditional = 1; // do conditional expected data
bool remakeData = 0; // handle unphysical pdf cases in H->ZZ->4l
bool doUncap = 1; // uncap p0
bool doInj = 0; // setup the poi for injection study (zero is faster if you're not)
bool doObs = 1; // compute median significance
bool doMedian = 1; // compute observed significance
TStopwatch timer;
timer.Start();
TFile f(inFileName);
RooWorkspace* ws = (RooWorkspace*)f.Get(wsName);
if (!ws)
{
cout << "ERROR::Workspace: " << wsName << " doesn't exist!" << endl;
return;
}
ModelConfig* mc = (ModelConfig*)ws->obj(modelConfigName);
if (!mc)
{
cout << "ERROR::ModelConfig: " << modelConfigName << " doesn't exist!" << endl;
return;
}
RooDataSet* data = (RooDataSet*)ws->data(dataName);
if (!data)
{
cout << "ERROR::Dataset: " << dataName << " doesn't exist!" << endl;
return;
}
mc->GetNuisanceParameters()->Print("v");
ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
ROOT::Math::MinimizerOptions::SetDefaultPrintLevel(1);
cout << "Setting max function calls" << endl;
ws->loadSnapshot("conditionalNuis_0");
RooArgSet nuis(*mc->GetNuisanceParameters());
RooRealVar* mu = (RooRealVar*)mc->GetParametersOfInterest()->first();
RooAbsPdf* pdf = mc->GetPdf();
string condSnapshot(conditional1Snapshot);
RooArgSet nuis_tmp2 = *mc->GetNuisanceParameters();
RooNLLVar* obs_nll = doObs ? (RooNLLVar*)pdf->createNLL(*data, Constrain(nuis_tmp2)) : NULL;
RooDataSet* asimovData1 = (RooDataSet*)ws->data(asimov1DataName);
RooRealVar* emb = (RooRealVar*)mc->GetNuisanceParameters()->find("ATLAS_EMB");
if (!asimovData1 || (string(inFileName).find("ic10") != string::npos && emb))
{
if (emb) emb->setVal(0.7);
cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
string mu_str, mu_prof_str;
asimovData1 = makeAsimovData(mc, doConditional, ws, obs_nll, 1, &mu_str, &mu_prof_str, mu_profile_value, true);
condSnapshot="conditionalGlobs"+mu_prof_str;
}
if (!doUncap) mu->setRange(0, 40);
else mu->setRange(-40, 40);
RooAbsPdf* pdf = mc->GetPdf();
RooArgSet nuis_tmp1 = *mc->GetNuisanceParameters();
RooNLLVar* asimov_nll = (RooNLLVar*)pdf->createNLL(*asimovData1, Constrain(nuis_tmp1));
//do asimov
mu->setVal(1);
mu->setConstant(0);
if (!doInj) mu->setConstant(1);
int status,sign;
double med_sig=0,obs_sig=0,asimov_q0=0,obs_q0=0;
if (doMedian)
{
ws->loadSnapshot(condSnapshot.c_str());
if (doInj) ws->loadSnapshot("conditionalNuis_inj");
else ws->loadSnapshot("conditionalNuis_1");
mc->GetGlobalObservables()->Print("v");
mu->setVal(0);
mu->setConstant(1);
status = minimize(asimov_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov_nll_cond = asimov_nll->getVal();
mu->setVal(1);
if (doInj) ws->loadSnapshot("conditionalNuis_inj");
else ws->loadSnapshot("conditionalNuis_1");
if (doInj) mu->setConstant(0);
status = minimize(asimov_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov_nll_min = asimov_nll->getVal();
asimov_q0 = 2*(asimov_nll_cond - asimov_nll_min);
if (doUncap && mu->getVal() < 0) asimov_q0 = -asimov_q0;
sign = int(asimov_q0 != 0 ? asimov_q0/fabs(asimov_q0) : 0);
med_sig = sign*sqrt(fabs(asimov_q0));
ws->loadSnapshot(nominalSnapshot);
}
if (doObs)
{
ws->loadSnapshot("conditionalNuis_0");
mu->setVal(0);
mu->setConstant(1);
status = minimize(obs_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(obs_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double obs_nll_cond = obs_nll->getVal();
mu->setConstant(0);
status = minimize(obs_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(obs_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double obs_nll_min = obs_nll->getVal();
obs_q0 = 2*(obs_nll_cond - obs_nll_min);
if (doUncap && mu->getVal() < 0) obs_q0 = -obs_q0;
sign = int(obs_q0 == 0 ? 0 : obs_q0 / fabs(obs_q0));
if (!doUncap && (obs_q0 < 0 && obs_q0 > -0.1 || mu->getVal() < 0.001)) obs_sig = 0;
else obs_sig = sign*sqrt(fabs(obs_q0));
}
// Report results
cout << "obs: " << obs_sig << endl;
cout << "Observed significance: " << obs_sig << endl;
cout << "Corresponding to a p-value of " << (1-ROOT::Math::gaussian_cdf( obs_sig )) << endl;
if (med_sig)
{
cout << "Median test stat val: " << asimov_q0 << endl;
cout << "Median significance: " << med_sig << endl;
}
f.Close();
stringstream fileName;
fileName << "root-files/" << folder << "/" << mass << ".root";
system(("mkdir -vp root-files/" + folder).c_str());
TFile f2(fileName.str().c_str(),"recreate");
TH1D* h_hypo = new TH1D("hypo","hypo",2,0,2);
h_hypo->SetBinContent(1, obs_sig);
h_hypo->SetBinContent(2, med_sig);
f2.Write();
f2.Close();
timer.Stop();
timer.Print();
}
void computeLimits(
const char* ACTag, // ACTag: where to look for combined workspaces in Limits/CombinedWorkspaces/
bool doSyst= false,
double CL=0.95, // Confidence Level for limits computation
int calculatorType = 2,
int testStatType = 2,
bool useCLs = false
)
// define calc type and test stat type:
//
// calculatorType = 0 Freq calculator
// calculatorType = 1 Hybrid calculator
// calculatorType = 2 Asymptotic calculator
// calculatorType = 3 Asymptotic calculator using nominal Asimov data sets (not using fitted parameter values but nominal ones)
//
// testStatType = 0 LEP
// = 1 Tevatron
// = 2 Profile Likelihood two sided
// = 3 Profile Likelihood one sided (i.e. = 0 if mu < mu_hat)
// = 4 Profile Likelihood signed ( pll = -pll if mu < mu_hat)
// = 5 Max Likelihood Estimate as test statistic
// = 6 Number of observed event as test statistic
//
// 0,3,true for frequentist CLs; 2,3,true for asymptotic CLs; 0,2,false for FC
{
// list of files
vector<TString> theFiles = combFileList(ACTag, doSyst ? "wSyst" : "woSyst");
if ( theFiles.empty() )
{
cout << "# [Error]: No combined workspaces found" << endl;
return;
}
// File to save results
ostringstream strs;
strs << CL;
string str = strs.str();
TString sCL(str);
sCL.Remove(0,sCL.First('.')+1);
string limitsFileName = string("csv/") + "cLimits_" + string(sCL) + "_" + string(ACTag);
if ( calculatorType == 0 ) limitsFileName = limitsFileName + "_Freq";
else if ( calculatorType == 1 ) limitsFileName = limitsFileName + "_Hybr";
else if ( calculatorType == 2 ) limitsFileName = limitsFileName + "_Asym";
else if ( calculatorType == 3 ) limitsFileName = limitsFileName + "_AsymAsi";
if ( testStatType == 0 ) limitsFileName = limitsFileName + "_LEP";
else if ( testStatType == 1 ) limitsFileName = limitsFileName + "_Tev";
else if ( testStatType == 2 ) limitsFileName = limitsFileName + "_2SPL";
else if ( testStatType == 3 ) limitsFileName = limitsFileName + "_1SPL";
else if ( testStatType == 4 ) limitsFileName = limitsFileName + "_SPL";
else if ( testStatType == 5 ) limitsFileName = limitsFileName + "_MaxL";
else if ( testStatType == 6 ) limitsFileName = limitsFileName + "_NOE";
if ( doSyst ) limitsFileName = limitsFileName + "_wSyst.csv";
else limitsFileName = limitsFileName + "_woSyst.csv";
ofstream file(limitsFileName.c_str());
file << CL << endl;
// Confidence interval computation
int cnt=1;
for (vector<TString>::const_iterator it=theFiles.begin(); it!=theFiles.end(); it++)
{
cout << ">>>>>>> Computing " << CL*100 << "% " << "limits for analysis bin " << cnt << endl;
cout << "Using combined PbPb-PP workspace " << cnt << " / " << theFiles.size() << ": " << *it << endl;
anabin thebin = binFromFile(*it);
// if (thebin != anabin(1.6,2.4,3,30,40,80)) continue;
if (!usebatch) {
pair<double,double> lims = runLimit_RaaNS_Workspace(*it, "RFrac2Svs1S_PbPbvsPP_P", "simPdf", "workspace", "dOS_DATA", ACTag, CL, calculatorType, testStatType, useCLs);
file << thebin.rapbin().low() << ", " << thebin.rapbin().high() << ", "
<< thebin.ptbin().low() << ", " << thebin.ptbin().high() << ", "
<< thebin.centbin().low() << ", " << thebin.centbin().high() << ", "
<< lims.first << ", " << lims.second << endl;
} else {
TString exports;
exports += Form("export it=%s; ",it->Data());
exports += Form("export ACTag=%s; ",ACTag);
exports += Form("export CL=%f; ",CL);
exports += Form("export calculatorType=%i; ",calculatorType);
exports += Form("export testStatType=%i; ",testStatType);
exports += Form("export useCLs=%i; ",useCLs);
exports += Form("export pwd_=%s; ", gSystem->pwd());
if (calculatorType==0) {
// special case of frequentist limits: submit more jobs
TFile *f = TFile::Open(*it);
RooWorkspace *ws = (RooWorkspace*) f->Get("workspace");
ws->loadSnapshot("SbHypo_poiAndNuisance_snapshot");
RooRealVar *theVar = (RooRealVar*) ws->var("RFrac2Svs1S_PbPbvsPP_P");
double val = theVar->getVal();
double err = theVar->getError();
f->Close(); if (ws) delete ws;
double nsigma = sqrt(2)*TMath::ErfcInverse(1-CL);
// double poimin = max(0.,0.5*(val - nsigma*err));
// double poimax = 1.5*(val + nsigma*err);
double poimin = max(0.,val + 0.9*nsigma*err);
double poimax = val + 1.1*nsigma*err;
int npoints = 5;
double dpoi = (poimax-poimin)/npoints;
for (int ipoi=0; ipoi<npoints; ipoi++)
for (int irnd=0; irnd<50; irnd++) {
TString exports2 = exports + Form("export poival=%f; ",poimin+ipoi*dpoi);
exports2 += Form("export rndseed=%i; ",irnd+1);
TString command("qsub -k oe -q cms@llrt3 -p -500 "); // -p option: lower the priority since we're submitting many jobs...
command += Form("-N limits_bin%i_ipoi%i_%i ",cnt,ipoi,irnd+1);
command += "-V ";
command += Form("-o %s ", gSystem->pwd());
command += Form("-v it,ACTag,CL,calculatorType,testStatType,useCLs,pwd_,poival,rndseed ");
command += "runbatch_limits_4WS.sh";
TString command_full = exports2 + command;
cout << command_full.Data() << endl;
int njobs = atoi(exec("qstat -u $USER cms@llrt3 | wc -l").c_str());
int njobs_queue = atoi(exec("qstat cms@llrt3 | grep \" Q \" | wc -l").c_str());
while (njobs_queue>0 && njobs >= maxjobs) {
system("sleep 60");
njobs = atoi(exec("qstat -u $USER cms@llrt3 | wc -l").c_str());
njobs_queue = atoi(exec("qstat cms@llrt3 | grep \" Q \" | wc -l").c_str());
}
system(command_full.Data());
}
} else {
exports += Form("export poival=%f; ",-1.);
exports += Form("export rndseed=%i; ",-1);
TString command("qsub -k oe -q cms@llrt3 -l nodes=1:ppn=23 ");
command += Form("-N limits_bin%i ",cnt);
command += "-V ";
command += Form("-o %s ", gSystem->pwd());
command += Form("-v it,ACTag,CL,calculatorType,testStatType,useCLs,pwd_,poival,rndseed ");
command += "runbatch_limits_4WS.sh";
TString command_full = exports + command;
cout << command_full.Data() << endl;
system(command_full.Data());
}
system("sleep 1");
}
cnt++;
} // loop on the files
file.close();
cout << "Closed " << limitsFileName << endl << endl;
}
void OneSidedFrequentistUpperLimitWithBands(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData") {
double confidenceLevel=0.95;
int nPointsToScan = 20;
int nToyMC = 200;
// -------------------------------------------------------
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
const char* filename = "";
if (!strcmp(infile,"")) {
filename = "results/example_combined_GaussExample_model.root";
bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
// if file does not exists generate with histfactory
if (!fileExist) {
#ifdef _WIN32
cout << "HistFactory file cannot be generated on Windows - exit" << endl;
return;
#endif
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
}
else
filename = infile;
// Try to open the file
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file ){
cout <<"StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
return;
}
// -------------------------------------------------------
// Now get the data and workspace
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !mc){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
// -------------------------------------------------------
// Now get the POI for convenience
// you may want to adjust the range of your POI
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
/* firstPOI->setMin(0);*/
/* firstPOI->setMax(10);*/
// --------------------------------------------
// Create and use the FeldmanCousins tool
// to find and plot the 95% confidence interval
// on the parameter of interest as specified
// in the model config
// REMEMBER, we will change the test statistic
// so this is NOT a Feldman-Cousins interval
FeldmanCousins fc(*data,*mc);
fc.SetConfidenceLevel(confidenceLevel);
/* fc.AdditionalNToysFactor(0.25); // degrade/improve sampling that defines confidence belt*/
/* fc.UseAdaptiveSampling(true); // speed it up a bit, don't use for expected limits*/
fc.SetNBins(nPointsToScan); // set how many points per parameter of interest to scan
fc.CreateConfBelt(true); // save the information in the belt for plotting
// -------------------------------------------------------
// Feldman-Cousins is a unified limit by definition
// but the tool takes care of a few things for us like which values
// of the nuisance parameters should be used to generate toys.
// so let's just change the test statistic and realize this is
// no longer "Feldman-Cousins" but is a fully frequentist Neyman-Construction.
/* ProfileLikelihoodTestStatModified onesided(*mc->GetPdf());*/
/* fc.GetTestStatSampler()->SetTestStatistic(&onesided);*/
/* ((ToyMCSampler*) fc.GetTestStatSampler())->SetGenerateBinned(true); */
ToyMCSampler* toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler();
ProfileLikelihoodTestStat* testStat = dynamic_cast<ProfileLikelihoodTestStat*>(toymcsampler->GetTestStatistic());
testStat->SetOneSided(true);
// Since this tool needs to throw toy MC the PDF needs to be
// extended or the tool needs to know how many entries in a dataset
// per pseudo experiment.
// In the 'number counting form' where the entries in the dataset
// are counts, and not values of discriminating variables, the
// datasets typically only have one entry and the PDF is not
// extended.
if(!mc->GetPdf()->canBeExtended()){
if(data->numEntries()==1)
fc.FluctuateNumDataEntries(false);
else
cout <<"Not sure what to do about this model" <<endl;
}
// We can use PROOF to speed things along in parallel
// However, the test statistic has to be installed on the workers
// so either turn off PROOF or include the modified test statistic
// in your `$ROOTSYS/roofit/roostats/inc` directory,
// add the additional line to the LinkDef.h file,
// and recompile root.
if (useProof) {
ProofConfig pc(*w, nworkers, "", false);
toymcsampler->SetProofConfig(&pc); // enable proof
}
if(mc->GetGlobalObservables()){
cout << "will use global observables for unconditional ensemble"<<endl;
mc->GetGlobalObservables()->Print();
toymcsampler->SetGlobalObservables(*mc->GetGlobalObservables());
}
// Now get the interval
PointSetInterval* interval = fc.GetInterval();
ConfidenceBelt* belt = fc.GetConfidenceBelt();
// print out the interval on the first Parameter of Interest
cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
interval->LowerLimit(*firstPOI) << ", "<<
interval->UpperLimit(*firstPOI) <<"] "<<endl;
// get observed UL and value of test statistic evaluated there
RooArgSet tmpPOI(*firstPOI);
double observedUL = interval->UpperLimit(*firstPOI);
firstPOI->setVal(observedUL);
double obsTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*data,tmpPOI);
// Ask the calculator which points were scanned
RooDataSet* parameterScan = (RooDataSet*) fc.GetPointsToScan();
RooArgSet* tmpPoint;
// make a histogram of parameter vs. threshold
TH1F* histOfThresholds = new TH1F("histOfThresholds","",
parameterScan->numEntries(),
firstPOI->getMin(),
firstPOI->getMax());
histOfThresholds->GetXaxis()->SetTitle(firstPOI->GetName());
histOfThresholds->GetYaxis()->SetTitle("Threshold");
// loop through the points that were tested and ask confidence belt
// what the upper/lower thresholds were.
// For FeldmanCousins, the lower cut off is always 0
for(Int_t i=0; i<parameterScan->numEntries(); ++i){
tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
//cout <<"get threshold"<<endl;
double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
double poiVal = tmpPoint->getRealValue(firstPOI->GetName()) ;
histOfThresholds->Fill(poiVal,arMax);
}
TCanvas* c1 = new TCanvas();
c1->Divide(2);
c1->cd(1);
histOfThresholds->SetMinimum(0);
histOfThresholds->Draw();
c1->cd(2);
// -------------------------------------------------------
// Now we generate the expected bands and power-constraint
// First: find parameter point for mu=0, with conditional MLEs for nuisance parameters
RooAbsReal* nll = mc->GetPdf()->createNLL(*data);
RooAbsReal* profile = nll->createProfile(*mc->GetParametersOfInterest());
firstPOI->setVal(0.);
profile->getVal(); // this will do fit and set nuisance parameters to profiled values
RooArgSet* poiAndNuisance = new RooArgSet();
if(mc->GetNuisanceParameters())
poiAndNuisance->add(*mc->GetNuisanceParameters());
poiAndNuisance->add(*mc->GetParametersOfInterest());
w->saveSnapshot("paramsToGenerateData",*poiAndNuisance);
RooArgSet* paramsToGenerateData = (RooArgSet*) poiAndNuisance->snapshot();
cout << "\nWill use these parameter points to generate pseudo data for bkg only" << endl;
paramsToGenerateData->Print("v");
RooArgSet unconditionalObs;
unconditionalObs.add(*mc->GetObservables());
unconditionalObs.add(*mc->GetGlobalObservables()); // comment this out for the original conditional ensemble
double CLb=0;
double CLbinclusive=0;
// Now we generate background only and find distribution of upper limits
TH1F* histOfUL = new TH1F("histOfUL","",100,0,firstPOI->getMax());
histOfUL->GetXaxis()->SetTitle("Upper Limit (background only)");
histOfUL->GetYaxis()->SetTitle("Entries");
for(int imc=0; imc<nToyMC; ++imc){
// set parameters back to values for generating pseudo data
// cout << "\n get current nuis, set vals, print again" << endl;
w->loadSnapshot("paramsToGenerateData");
// poiAndNuisance->Print("v");
RooDataSet* toyData = 0;
// now generate a toy dataset
if(!mc->GetPdf()->canBeExtended()){
if(data->numEntries()==1)
toyData = mc->GetPdf()->generate(*mc->GetObservables(),1);
else
cout <<"Not sure what to do about this model" <<endl;
} else{
// cout << "generating extended dataset"<<endl;
toyData = mc->GetPdf()->generate(*mc->GetObservables(),Extended());
}
// generate global observables
// need to be careful for simpdf
// RooDataSet* globalData = mc->GetPdf()->generate(*mc->GetGlobalObservables(),1);
RooSimultaneous* simPdf = dynamic_cast<RooSimultaneous*>(mc->GetPdf());
if(!simPdf){
RooDataSet *one = mc->GetPdf()->generate(*mc->GetGlobalObservables(), 1);
const RooArgSet *values = one->get();
RooArgSet *allVars = mc->GetPdf()->getVariables();
*allVars = *values;
delete allVars;
delete values;
delete one;
} else {
//try fix for sim pdf
TIterator* iter = simPdf->indexCat().typeIterator() ;
RooCatType* tt = NULL;
while((tt=(RooCatType*) iter->Next())) {
// Get pdf associated with state from simpdf
RooAbsPdf* pdftmp = simPdf->getPdf(tt->GetName()) ;
// Generate only global variables defined by the pdf associated with this state
RooArgSet* globtmp = pdftmp->getObservables(*mc->GetGlobalObservables()) ;
RooDataSet* tmp = pdftmp->generate(*globtmp,1) ;
// Transfer values to output placeholder
*globtmp = *tmp->get(0) ;
// Cleanup
delete globtmp ;
delete tmp ;
}
}
// globalData->Print("v");
// unconditionalObs = *globalData->get();
// mc->GetGlobalObservables()->Print("v");
// delete globalData;
// cout << "toy data = " << endl;
// toyData->get()->Print("v");
// get test stat at observed UL in observed data
firstPOI->setVal(observedUL);
double toyTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
// toyData->get()->Print("v");
// cout <<"obsTSatObsUL " <<obsTSatObsUL << "toyTS " << toyTSatObsUL << endl;
if(obsTSatObsUL < toyTSatObsUL) // not sure about <= part yet
CLb+= (1.)/nToyMC;
if(obsTSatObsUL <= toyTSatObsUL) // not sure about <= part yet
CLbinclusive+= (1.)/nToyMC;
// loop over points in belt to find upper limit for this toy data
double thisUL = 0;
for(Int_t i=0; i<parameterScan->numEntries(); ++i){
tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
// double thisTS = profile->getVal();
double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
// cout << "poi = " << firstPOI->getVal()
// << " max is " << arMax << " this profile = " << thisTS << endl;
// cout << "thisTS = " << thisTS<<endl;
if(thisTS<=arMax){
thisUL = firstPOI->getVal();
} else{
break;
}
}
/*
// loop over points in belt to find upper limit for this toy data
double thisUL = 0;
for(Int_t i=0; i<histOfThresholds->GetNbinsX(); ++i){
tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
cout <<"---------------- "<<i<<endl;
tmpPoint->Print("v");
cout << "from hist " << histOfThresholds->GetBinCenter(i+1) <<endl;
double arMax = histOfThresholds->GetBinContent(i+1);
// cout << " threhold from Hist = aMax " << arMax<<endl;
// double arMax2 = belt->GetAcceptanceRegionMax(*tmpPoint);
// cout << "from scan arMax2 = "<< arMax2 << endl; // not the same due to TH1F not TH1D
// cout << "scan - hist" << arMax2-arMax << endl;
firstPOI->setVal( histOfThresholds->GetBinCenter(i+1));
// double thisTS = profile->getVal();
double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
// cout << "poi = " << firstPOI->getVal()
// << " max is " << arMax << " this profile = " << thisTS << endl;
// cout << "thisTS = " << thisTS<<endl;
// NOTE: need to add a small epsilon term for single precision vs. double precision
if(thisTS<=arMax + 1e-7){
thisUL = firstPOI->getVal();
} else{
break;
}
}
*/
histOfUL->Fill(thisUL);
// for few events, data is often the same, and UL is often the same
// cout << "thisUL = " << thisUL<<endl;
delete toyData;
}
histOfUL->Draw();
c1->SaveAs("one-sided_upper_limit_output.pdf");
// if you want to see a plot of the sampling distribution for a particular scan point:
/*
SamplingDistPlot sampPlot;
int indexInScan = 0;
tmpPoint = (RooArgSet*) parameterScan->get(indexInScan)->clone("temp");
firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
toymcsampler->SetParametersForTestStat(tmpPOI);
SamplingDistribution* samp = toymcsampler->GetSamplingDistribution(*tmpPoint);
sampPlot.AddSamplingDistribution(samp);
sampPlot.Draw();
*/
// Now find bands and power constraint
Double_t* bins = histOfUL->GetIntegral();
TH1F* cumulative = (TH1F*) histOfUL->Clone("cumulative");
cumulative->SetContent(bins);
double band2sigDown, band1sigDown, bandMedian, band1sigUp,band2sigUp;
for(int i=1; i<=cumulative->GetNbinsX(); ++i){
if(bins[i]<RooStats::SignificanceToPValue(2))
band2sigDown=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(1))
band1sigDown=cumulative->GetBinCenter(i);
if(bins[i]<0.5)
bandMedian=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(-1))
band1sigUp=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(-2))
band2sigUp=cumulative->GetBinCenter(i);
}
cout << "-2 sigma band " << band2sigDown << endl;
cout << "-1 sigma band " << band1sigDown << " [Power Constraint)]" << endl;
cout << "median of band " << bandMedian << endl;
cout << "+1 sigma band " << band1sigUp << endl;
cout << "+2 sigma band " << band2sigUp << endl;
// print out the interval on the first Parameter of Interest
cout << "\nobserved 95% upper-limit "<< interval->UpperLimit(*firstPOI) <<endl;
cout << "CLb strict [P(toy>obs|0)] for observed 95% upper-limit "<< CLb <<endl;
cout << "CLb inclusive [P(toy>=obs|0)] for observed 95% upper-limit "<< CLbinclusive <<endl;
delete profile;
delete nll;
}
void OneSidedFrequentistUpperLimitWithBands_intermediate(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData"){
double confidenceLevel=0.95;
// degrade/improve number of pseudo-experiments used to define the confidence belt.
// value of 1 corresponds to default number of toys in the tail, which is 50/(1-confidenceLevel)
double additionalToysFac = 1.;
int nPointsToScan = 30; // number of steps in the parameter of interest
int nToyMC = 100; // number of toys used to define the expected limit and band
TStopwatch t;
t.Start();
/////////////////////////////////////////////////////////////
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
////////////////////////////////////////////////////////////
const char* filename = "";
if (!strcmp(infile,""))
filename = "results/example_combined_GaussExample_model.root";
else
filename = infile;
// Check if example input file exists
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file && strcmp(infile,"")){
cout <<"file not found" << endl;
return;
}
// if default file not found, try to create it
if(!file ){
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
// now try to access the file again
file = TFile::Open(filename);
if(!file){
// if it is still not there, then we can't continue
cout << "Not able to run hist2workspace to create example input" <<endl;
return;
}
/////////////////////////////////////////////////////////////
// Now get the data and workspace
////////////////////////////////////////////////////////////
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !mc){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
cout << "Found data and ModelConfig:" <<endl;
mc->Print();
/////////////////////////////////////////////////////////////
// Now get the POI for convenience
// you may want to adjust the range of your POI
////////////////////////////////////////////////////////////
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
// firstPOI->setMin(0);
// firstPOI->setMax(10);
/////////////////////////////////////////////
// create and use the FeldmanCousins tool
// to find and plot the 95% confidence interval
// on the parameter of interest as specified
// in the model config
// REMEMBER, we will change the test statistic
// so this is NOT a Feldman-Cousins interval
FeldmanCousins fc(*data,*mc);
fc.SetConfidenceLevel(confidenceLevel);
fc.AdditionalNToysFactor(additionalToysFac); // improve sampling that defines confidence belt
// fc.UseAdaptiveSampling(true); // speed it up a bit, but don't use for expectd limits
fc.SetNBins(nPointsToScan); // set how many points per parameter of interest to scan
fc.CreateConfBelt(true); // save the information in the belt for plotting
/////////////////////////////////////////////
// Feldman-Cousins is a unified limit by definition
// but the tool takes care of a few things for us like which values
// of the nuisance parameters should be used to generate toys.
// so let's just change the test statistic and realize this is
// no longer "Feldman-Cousins" but is a fully frequentist Neyman-Construction.
// ProfileLikelihoodTestStatModified onesided(*mc->GetPdf());
// fc.GetTestStatSampler()->SetTestStatistic(&onesided);
// ((ToyMCSampler*) fc.GetTestStatSampler())->SetGenerateBinned(true);
ToyMCSampler* toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler();
ProfileLikelihoodTestStat* testStat = dynamic_cast<ProfileLikelihoodTestStat*>(toymcsampler->GetTestStatistic());
testStat->SetOneSided(true);
// test speedups:
testStat->SetReuseNLL(true);
// toymcsampler->setUseMultiGen(true); // not fully validated
// Since this tool needs to throw toy MC the PDF needs to be
// extended or the tool needs to know how many entries in a dataset
// per pseudo experiment.
// In the 'number counting form' where the entries in the dataset
// are counts, and not values of discriminating variables, the
// datasets typically only have one entry and the PDF is not
// extended.
if(!mc->GetPdf()->canBeExtended()){
if(data->numEntries()==1)
fc.FluctuateNumDataEntries(false);
else
cout <<"Not sure what to do about this model" <<endl;
}
// We can use PROOF to speed things along in parallel
ProofConfig pc(*w, 4, "",false);
if(mc->GetGlobalObservables()){
cout << "will use global observables for unconditional ensemble"<<endl;
mc->GetGlobalObservables()->Print();
toymcsampler->SetGlobalObservables(*mc->GetGlobalObservables());
}
toymcsampler->SetProofConfig(&pc); // enable proof
// Now get the interval
PointSetInterval* interval = fc.GetInterval();
ConfidenceBelt* belt = fc.GetConfidenceBelt();
// print out the iterval on the first Parameter of Interest
cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
interval->LowerLimit(*firstPOI) << ", "<<
interval->UpperLimit(*firstPOI) <<"] "<<endl;
// get observed UL and value of test statistic evaluated there
RooArgSet tmpPOI(*firstPOI);
double observedUL = interval->UpperLimit(*firstPOI);
firstPOI->setVal(observedUL);
double obsTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*data,tmpPOI);
// Ask the calculator which points were scanned
RooDataSet* parameterScan = (RooDataSet*) fc.GetPointsToScan();
RooArgSet* tmpPoint;
// make a histogram of parameter vs. threshold
TH1F* histOfThresholds = new TH1F("histOfThresholds","",
parameterScan->numEntries(),
firstPOI->getMin(),
firstPOI->getMax());
histOfThresholds->GetXaxis()->SetTitle(firstPOI->GetName());
histOfThresholds->GetYaxis()->SetTitle("Threshold");
// loop through the points that were tested and ask confidence belt
// what the upper/lower thresholds were.
// For FeldmanCousins, the lower cut off is always 0
for(Int_t i=0; i<parameterScan->numEntries(); ++i){
tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
double poiVal = tmpPoint->getRealValue(firstPOI->GetName()) ;
histOfThresholds->Fill(poiVal,arMax);
}
TCanvas* c1 = new TCanvas();
c1->Divide(2);
c1->cd(1);
histOfThresholds->SetMinimum(0);
histOfThresholds->Draw();
c1->cd(2);
/////////////////////////////////////////////////////////////
// Now we generate the expected bands and power-constriant
////////////////////////////////////////////////////////////
// First: find parameter point for mu=0, with conditional MLEs for nuisance parameters
RooAbsReal* nll = mc->GetPdf()->createNLL(*data);
RooAbsReal* profile = nll->createProfile(*mc->GetParametersOfInterest());
firstPOI->setVal(0.);
profile->getVal(); // this will do fit and set nuisance parameters to profiled values
RooArgSet* poiAndNuisance = new RooArgSet();
if(mc->GetNuisanceParameters())
poiAndNuisance->add(*mc->GetNuisanceParameters());
poiAndNuisance->add(*mc->GetParametersOfInterest());
w->saveSnapshot("paramsToGenerateData",*poiAndNuisance);
RooArgSet* paramsToGenerateData = (RooArgSet*) poiAndNuisance->snapshot();
cout << "\nWill use these parameter points to generate pseudo data for bkg only" << endl;
paramsToGenerateData->Print("v");
double CLb=0;
double CLbinclusive=0;
// Now we generate background only and find distribution of upper limits
TH1F* histOfUL = new TH1F("histOfUL","",100,0,firstPOI->getMax());
histOfUL->GetXaxis()->SetTitle("Upper Limit (background only)");
histOfUL->GetYaxis()->SetTitle("Entries");
for(int imc=0; imc<nToyMC; ++imc){
// set parameters back to values for generating pseudo data
w->loadSnapshot("paramsToGenerateData");
// in 5.30 there is a nicer way to generate toy data & randomize global obs
RooAbsData* toyData = toymcsampler->GenerateToyData(*paramsToGenerateData);
// get test stat at observed UL in observed data
firstPOI->setVal(observedUL);
double toyTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
// toyData->get()->Print("v");
// cout <<"obsTSatObsUL " <<obsTSatObsUL << "toyTS " << toyTSatObsUL << endl;
if(obsTSatObsUL < toyTSatObsUL) // (should be checked)
CLb+= (1.)/nToyMC;
if(obsTSatObsUL <= toyTSatObsUL) // (should be checked)
CLbinclusive+= (1.)/nToyMC;
// loop over points in belt to find upper limit for this toy data
double thisUL = 0;
for(Int_t i=0; i<parameterScan->numEntries(); ++i){
tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
if(thisTS<=arMax){
thisUL = firstPOI->getVal();
} else{
break;
}
}
histOfUL->Fill(thisUL);
delete toyData;
}
histOfUL->Draw();
c1->SaveAs("one-sided_upper_limit_output.pdf");
// if you want to see a plot of the sampling distribution for a particular scan point:
// Now find bands and power constraint
Double_t* bins = histOfUL->GetIntegral();
TH1F* cumulative = (TH1F*) histOfUL->Clone("cumulative");
cumulative->SetContent(bins);
double band2sigDown=0, band1sigDown=0, bandMedian=0, band1sigUp=0,band2sigUp=0;
for(int i=1; i<=cumulative->GetNbinsX(); ++i){
if(bins[i]<RooStats::SignificanceToPValue(2))
band2sigDown=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(1))
band1sigDown=cumulative->GetBinCenter(i);
if(bins[i]<0.5)
bandMedian=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(-1))
band1sigUp=cumulative->GetBinCenter(i);
if(bins[i]<RooStats::SignificanceToPValue(-2))
band2sigUp=cumulative->GetBinCenter(i);
}
t.Stop();
t.Print();
cout << "-2 sigma band " << band2sigDown << endl;
cout << "-1 sigma band " << band1sigDown << endl;
cout << "median of band " << bandMedian << " [Power Constriant)]" << endl;
cout << "+1 sigma band " << band1sigUp << endl;
cout << "+2 sigma band " << band2sigUp << endl;
// print out the iterval on the first Parameter of Interest
cout << "\nobserved 95% upper-limit "<< interval->UpperLimit(*firstPOI) <<endl;
cout << "CLb strict [P(toy>obs|0)] for observed 95% upper-limit "<< CLb <<endl;
cout << "CLb inclusive [P(toy>=obs|0)] for observed 95% upper-limit "<< CLbinclusive <<endl;
delete profile;
delete nll;
}
void runQ(const char* inFileName,
const char* wsName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData",
const char* asimov0DataName = "asimovData_0",
const char* conditional0Snapshot = "conditionalGlobs_0",
const char* asimov1DataName = "asimovData_1",
const char* conditional1Snapshot = "conditionalGlobs_1",
const char* nominalSnapshot = "nominalGlobs",
string smass = "130",
string folder = "test")
{
double mass;
stringstream massStr;
massStr << smass;
massStr >> mass;
bool errFast = 0;
bool goFast = 1;
bool remakeData = 1;
bool doRightSided = 1;
bool doInj = 0;
bool doObs = 1;
bool doMedian = 1;
TStopwatch timer;
timer.Start();
TFile f(inFileName);
RooWorkspace* ws = (RooWorkspace*)f.Get(wsName);
if (!ws)
{
cout << "ERROR::Workspace: " << wsName << " doesn't exist!" << endl;
return;
}
ModelConfig* mc = (ModelConfig*)ws->obj(modelConfigName);
if (!mc)
{
cout << "ERROR::ModelConfig: " << modelConfigName << " doesn't exist!" << endl;
return;
}
RooDataSet* data = (RooDataSet*)ws->data(dataName);
if (!data)
{
cout << "ERROR::Dataset: " << dataName << " doesn't exist!" << endl;
return;
}
mc->GetNuisanceParameters()->Print("v");
RooNLLVar::SetIgnoreZeroEntries(1);
ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
ROOT::Math::MinimizerOptions::SetDefaultPrintLevel(1);
cout << "Setting max function calls" << endl;
//ROOT::Math::MinimizerOptions::SetDefaultMaxFunctionCalls(20000);
RooMinimizer::SetMaxFunctionCalls(10000);
ws->loadSnapshot("conditionalNuis_0");
RooArgSet nuis(*mc->GetNuisanceParameters());
RooRealVar* mu = (RooRealVar*)mc->GetParametersOfInterest()->first();
if (string(mc->GetPdf()->ClassName()) == "RooSimultaneous" && remakeData)
{
RooSimultaneous* simPdf = (RooSimultaneous*)mc->GetPdf();
double min_mu;
data = makeData(data, simPdf, mc->GetObservables(), mu, mass, min_mu);
}
RooDataSet* asimovData0 = (RooDataSet*)ws->data(asimov0DataName);
if (!asimovData0)
{
cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
makeAsimovData(mc, true, ws, mc->GetPdf(), data, 1);
ws->Print();
asimovData0 = (RooDataSet*)ws->data("asimovData_0");
}
RooDataSet* asimovData1 = (RooDataSet*)ws->data(asimov1DataName);
if (!asimovData1)
{
cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
makeAsimovData(mc, true, ws, mc->GetPdf(), data, 0);
ws->Print();
asimovData1 = (RooDataSet*)ws->data("asimovData_1");
}
if (!doRightSided) mu->setRange(0, 40);
else mu->setRange(-40, 40);
bool old = false;
if (old)
{
mu->setVal(0);
RooArgSet poi(*mu);
ProfileLikelihoodTestStat_modified asimov_testStat_sig(*mc->GetPdf());
asimov_testStat_sig.SetRightSided(doRightSided);
asimov_testStat_sig.SetNuis(&nuis);
if (!doInj) asimov_testStat_sig.SetDoAsimov(true, 1);
asimov_testStat_sig.SetWorkspace(ws);
ProfileLikelihoodTestStat_modified testStat(*mc->GetPdf());
testStat.SetRightSided(doRightSided);
testStat.SetNuis(&nuis);
testStat.SetWorkspace(ws);
//RooMinimizerFcn::SetOverrideEverything(true);
double med_sig = 0;
double med_testStat_val = 0;
//gRandom->SetSeed(1);
//RooRandom::randomGenerator()->SetSeed(1);
RooNLLVar::SetIgnoreZeroEntries(1);
if (asimov1DataName != "" && doMedian)
{
mu->setVal(0);
if (!doInj) mu->setRange(0, 2);
ws->loadSnapshot("conditionalNuis_0");
asimov_testStat_sig.SetLoadUncondSnapshot("conditionalNuis_1");
if (string(conditional1Snapshot) != "") ws->loadSnapshot(conditional1Snapshot);
med_testStat_val = 2*asimov_testStat_sig.Evaluate(*asimovData1, poi);
if (med_testStat_val < 0 && !doInj)
{
mu->setVal(0);
med_testStat_val = 2*asimov_testStat_sig.Evaluate(*asimovData1, poi); // just try again
}
int sign = med_testStat_val != 0 ? med_testStat_val/fabs(med_testStat_val) : 0;
med_sig = sign*sqrt(fabs(med_testStat_val));
if (string(nominalSnapshot) != "") ws->loadSnapshot(nominalSnapshot);
if (!doRightSided) mu->setRange(0, 40);
else mu->setRange(-40, 40);
}
RooNLLVar::SetIgnoreZeroEntries(0);
//gRandom->SetSeed(1);
//RooRandom::randomGenerator()->SetSeed(1);
//RooMinimizerFcn::SetOverrideEverything(false);
cout << "med test stat: " << med_testStat_val << endl;
ws->loadSnapshot("nominalGlobs");
ws->loadSnapshot("conditionalNuis_0");
mu->setVal(0);
testStat.SetWorkspace(ws);
testStat.SetLoadUncondSnapshot("ucmles");
double obsTestStat_val = doObs ? 2*testStat.Evaluate(*data, poi) : 0;
cout << "obs test stat: " << obsTestStat_val << endl;
// obsTestStat_val = 2*testStat.Evaluate(*data, poi);
// cout << "obs test stat: " << obsTestStat_val << endl;
// obsTestStat_val = 2*testStat.Evaluate(*data, poi);
// cout << "obs test stat: " << obsTestStat_val << endl;
double obs_sig;
int sign = obsTestStat_val == 0 ? 0 : obsTestStat_val / fabs(obsTestStat_val);
if (!doRightSided && (obsTestStat_val < 0 && obsTestStat_val > -0.1 || mu->getVal() < 0.001)) obs_sig = 0;
else obs_sig = sign*sqrt(fabs(obsTestStat_val));
if (obs_sig != obs_sig) //nan, do by hand
{
cout << "Obs test stat gave nan: try by hand" << endl;
mu->setVal(0);
mu->setConstant(1);
mc->GetPdf()->fitTo(*data, Hesse(0), Minos(0), PrintLevel(-1), Constrain(*mc->GetNuisanceParameters()));
mu->setConstant(0);
double L_0 = mc->GetPdf()->getVal();
//mu->setVal(0);
//mu->setConstant(1);
mc->GetPdf()->fitTo(*data, Hesse(0), Minos(0), PrintLevel(-1), Constrain(*mc->GetNuisanceParameters()));
//mu->setConstant(0);
double L_muhat = mc->GetPdf()->getVal();
cout << "L_0: " << L_0 << ", L_muhat: " << L_muhat << endl;
obs_sig = sqrt(-2*TMath::Log(L_0/L_muhat));
//still nan
if (obs_sig != obs_sig && fabs(L_0 - L_muhat) < 0.000001) obs_sig = 0;
}
cout << "obs: " << obs_sig << endl;
cout << "Observed significance: " << obs_sig << endl;
if (med_sig)
{
cout << "Median test stat val: " << med_testStat_val << endl;
cout << "Median significance: " << med_sig << endl;
}
f.Close();
stringstream fileName;
fileName << "root_files/" << folder << "/" << mass << ".root";
system(("mkdir -vp root_files/" + folder).c_str());
TFile f2(fileName.str().c_str(),"recreate");
// stringstream fileName;
// fileName << "results_sig/" << mass << ".root";
// system("mkdir results_sig");
// TFile f(fileName.str().c_str(),"recreate");
TH1D* h_hypo = new TH1D("hypo","hypo",2,0,2);
h_hypo->SetBinContent(1, obs_sig);
h_hypo->SetBinContent(2, med_sig);
f2.Write();
f2.Close();
//mc->GetPdf()->fitTo(*data, PrintLevel(0));
timer.Stop();
timer.Print();
}
else
{
RooAbsPdf* pdf = mc->GetPdf();
RooArgSet nuis_tmp1 = *mc->GetNuisanceParameters();
RooNLLVar* asimov_nll0 = (RooNLLVar*)pdf->createNLL(*asimovData0, Constrain(nuis_tmp1));
RooArgSet nuis_tmp2 = *mc->GetNuisanceParameters();
RooNLLVar* asimov_nll1 = (RooNLLVar*)pdf->createNLL(*asimovData1, Constrain(nuis_tmp2));
RooArgSet nuis_tmp3 = *mc->GetNuisanceParameters();
RooNLLVar* obs_nll = (RooNLLVar*)pdf->createNLL(*data, Constrain(nuis_tmp3));
//do asimov
int status;
//get sigma_b
ws->loadSnapshot(conditional0Snapshot);
status = ws->loadSnapshot("conditionalNuis_0");
if (status != 0 && goFast) errFast = 1;
mu->setVal(0);
mu->setConstant(1);
status = goFast ? 0 : minimize(asimov_nll0, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll0, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov0_nll0 = asimov_nll0->getVal();
mu->setVal(1);
ws->loadSnapshot("conditionalNuis_1");
status = minimize(asimov_nll0, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll0, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov0_nll1 = asimov_nll0->getVal();
double asimov0_q = 2*(asimov0_nll1 - asimov0_nll0);
double sigma_b = sqrt(1./asimov0_q);
ws->loadSnapshot(nominalSnapshot);
//get sigma_sb
ws->loadSnapshot(conditional1Snapshot);
ws->loadSnapshot("conditionalNuis_0");
mu->setVal(0);
mu->setConstant(1);
status = minimize(asimov_nll1, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll1, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov1_nll0 = asimov_nll1->getVal();
mu->setVal(1);
status = ws->loadSnapshot("conditionalNuis_1");
if (status != 0 && goFast) errFast = 1;
status = goFast ? 0 : minimize(asimov_nll1, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll1, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov1_nll1 = asimov_nll1->getVal();
double asimov1_q = 2*(asimov1_nll1 - asimov1_nll0);
double sigma_sb = sqrt(-1./asimov1_q);
ws->loadSnapshot(nominalSnapshot);
//do obs
mu->setVal(0);
status = ws->loadSnapshot("conditionalNuis_0");
if (status != 0 && goFast) errFast = 1;
mu->setConstant(1);
status = goFast ? 0 : minimize(obs_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(obs_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double obs_nll0 = obs_nll->getVal();
status = ws->loadSnapshot("conditionalNuis_1");
if (status != 0 && goFast) errFast = 1;
mu->setVal(1);
status = goFast ? 0 : minimize(obs_nll, ws);
if (status < 0)
{
cout << "Retrying with conditional snapshot at mu=1" << endl;
ws->loadSnapshot("conditionalNuis_0");
status = minimize(obs_nll, ws);
if (status >= 0) cout << "Success!" << endl;
}
double obs_nll1 = obs_nll->getVal();
double obs_q = 2*(obs_nll1 - obs_nll0);
double Zobs = (1./sigma_b/sigma_b - obs_q) / (2./sigma_b);
double Zexp = (1./sigma_b/sigma_b - asimov1_q) / (2./sigma_b);
double pb_obs = 1-ROOT::Math::gaussian_cdf(Zobs);
double pb_exp = 1-ROOT::Math::gaussian_cdf(Zexp);
cout << "asimov0_q = " << asimov0_q << endl;
cout << "asimov1_q = " << asimov1_q << endl;
cout << "obs_q = " << obs_q << endl;
cout << "sigma_b = " << sigma_b << endl;
cout << "sigma_sb = " << sigma_sb << endl;
cout << "Z obs = " << Zobs << endl;
cout << "Z exp = " << Zexp << endl;
f.Close();
stringstream fileName;
fileName << "root_files/" << folder << "/" << mass << ".root";
system(("mkdir -vp root_files/" + folder).c_str());
TFile f2(fileName.str().c_str(),"recreate");
TH1D* h_hypo = new TH1D("hypo_tev","hypo_tev",2,0,2);
h_hypo->SetBinContent(1, pb_obs);
h_hypo->SetBinContent(2, pb_exp);
f2.Write();
f2.Close();
stringstream fileName3;
fileName3 << "root_files/" << folder << "_llr/" << mass << ".root";
system(("mkdir -vp root_files/" + folder + "_llr").c_str());
TFile f3(fileName3.str().c_str(),"recreate");
TH1D* h_hypo3 = new TH1D("hypo_llr","hypo_llr",7,0,7);
h_hypo3->SetBinContent(1, -obs_q);
h_hypo3->SetBinContent(2, -asimov1_q);
h_hypo3->SetBinContent(3, -asimov0_q);
h_hypo3->SetBinContent(4, -asimov0_q-2*2/sigma_b);
h_hypo3->SetBinContent(5, -asimov0_q-1*2/sigma_b);
h_hypo3->SetBinContent(6, -asimov0_q+1*2/sigma_b);
h_hypo3->SetBinContent(7, -asimov0_q+2*2/sigma_b);
f3.Write();
f3.Close();
timer.Stop();
timer.Print();
}
}
