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 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 fillWorkspace(RooWorkspace& w) { // C r e a t e m o d e l // ----------------------- // Declare observable x RooRealVar x("x","x",0,10) ; // Create two Gaussian PDFs g1(x,mean1,sigma) anf g2(x,mean2,sigma) and their parameters RooRealVar mean("mean","mean of gaussians",5,0,10) ; RooRealVar sigma1("sigma1","width of gaussians",0.5) ; RooRealVar sigma2("sigma2","width of gaussians",1) ; RooGaussian sig1("sig1","Signal component 1",x,mean,sigma1) ; RooGaussian sig2("sig2","Signal component 2",x,mean,sigma2) ; // Build Chebychev polynomial p.d.f. RooRealVar a0("a0","a0",0.5,0.,1.) ; RooRealVar a1("a1","a1",-0.2,0.,1.) ; RooChebychev bkg("bkg","Background",x,RooArgSet(a0,a1)) ; // Sum the signal components into a composite signal p.d.f. RooRealVar sig1frac("sig1frac","fraction of component 1 in signal",0.8,0.,1.) ; RooAddPdf sig("sig","Signal",RooArgList(sig1,sig2),sig1frac) ; // Sum the composite signal and background RooRealVar bkgfrac("bkgfrac","fraction of background",0.5,0.,1.) ; RooAddPdf model("model","g1+g2+a",RooArgList(bkg,sig),bkgfrac) ; // Import model into p.d.f. w.import(model) ; // E n c o d e d e f i n i t i o n o f p a r a m e t e r s i n w o r k s p a c e // --------------------------------------------------------------------------------------- // Define named sets "parameters" and "observables", which list which variables should be considered // parameters and observables by the users convention // // Variables appearing in sets _must_ live in the workspace already, or the autoImport flag // of defineSet must be set to import them on the fly. Named sets contain only references // to the original variables, therefore the value of observables in named sets already // reflect their 'current' value RooArgSet* params = (RooArgSet*) model.getParameters(x) ; w.defineSet("parameters",*params) ; w.defineSet("observables",x) ; // E n c o d e r e f e r e n c e v a l u e f o r p a r a m e t e r s i n w o r k s p a c e // --------------------------------------------------------------------------------------------------- // Define a parameter 'snapshot' in the p.d.f. // Unlike a named set, a parameter snapshot stores an independent set of values for // a given set of variables in the workspace. The values can be stored and reloaded // into the workspace variable objects using the loadSnapshot() and saveSnapshot() // methods. A snapshot saves the value of each variable, any errors that are stored // with it as well as the 'Constant' flag that is used in fits to determine if a // parameter is kept fixed or not. // Do a dummy fit to a (supposedly) reference dataset here and store the results // of that fit into a snapshot RooDataSet* refData = model.generate(x,10000) ; model.fitTo(*refData,PrintLevel(-1)) ; // The kTRUE flag imports the values of the objects in (*params) into the workspace // If not set, the present values of the workspace parameters objects are stored w.saveSnapshot("reference_fit",*params,kTRUE) ; // Make another fit with the signal componentforced to zero // and save those parameters too bkgfrac.setVal(1) ; bkgfrac.setConstant(kTRUE) ; bkgfrac.removeError() ; model.fitTo(*refData,PrintLevel(-1)) ; w.saveSnapshot("reference_fit_bkgonly",*params,kTRUE) ; }
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; }
bool fitCharmoniaMassModel( RooWorkspace& myws, // Local Workspace const RooWorkspace& inputWorkspace, // Workspace with all the input RooDatasets struct KinCuts& cut, // Variable containing all kinematic cuts map<string, string>& parIni, // Variable containing all initial parameters struct InputOpt& opt, // Variable with run information (kept for legacy purpose) string outputDir, // Path to output directory // Select the type of datasets to fit string DSTAG, // Specifies the type of datasets: i.e, DATA, MCJPSINP, ... bool isPbPb = false, // isPbPb = false for pp, true for PbPb bool importDS = true, // Select if the dataset is imported in the local workspace // Select the type of object to fit bool incJpsi = true, // Includes Jpsi model bool incPsi2S = true, // Includes Psi(2S) model bool incBkg = true, // Includes Background model // Select the fitting options bool doFit = true, // Flag to indicate if we want to perform the fit bool cutCtau = false, // Apply prompt ctau cuts bool doConstrFit = false, // Do constrained fit bool doSimulFit = false, // Do simultaneous fit bool wantPureSMC = false, // Flag to indicate if we want to fit pure signal MC const char* applyCorr ="", // Flag to indicate if we want corrected dataset and which correction uint loadFitResult = false, // Load previous fit results string inputFitDir = "", // Location of the fit results int numCores = 2, // Number of cores used for fitting // Select the drawing options bool setLogScale = true, // Draw plot with log scale bool incSS = false, // Include Same Sign data bool zoomPsi = false, // Zoom Psi(2S) peak on extra pad double binWidth = 0.05, // Bin width used for plotting bool getMeanPT = false // Compute the mean PT (NEED TO FIX) ) { if (DSTAG.find("_")!=std::string::npos) DSTAG.erase(DSTAG.find("_")); // Check if input dataset is MC bool isMC = false; if (DSTAG.find("MC")!=std::string::npos) { if (incJpsi && incPsi2S) { cout << "[ERROR] We can only fit one type of signal using MC" << endl; return false; } isMC = true; } wantPureSMC = (isMC && wantPureSMC); bool cutSideBand = (incBkg && (!incPsi2S && !incJpsi)); bool applyWeight_Corr = ( strcmp(applyCorr,"") ); // Define the mass range setMassCutParameters(cut, incJpsi, incPsi2S, isMC); parIni["invMassNorm"] = Form("RooFormulaVar::%s('( -1.0 + 2.0*( @0 - @1 )/( @2 - @1) )', {%s, mMin[%.6f], mMax[%.6f]})", "invMassNorm", "invMass", cut.dMuon.M.Min, cut.dMuon.M.Max ); // Apply the ctau cuts to reject non-prompt charmonia if (cutCtau) { setCtauCuts(cut, isPbPb); } string COLL = (isPbPb ? "PbPb" : "PP" ); string plotLabelPbPb, plotLabelPP; if (doSimulFit || !isPbPb) { // Set models based on initial parameters struct OniaModel model; if (!setMassModel(model, parIni, false, incJpsi, incPsi2S, incBkg)) { return false; } // Import the local datasets double numEntries = 1000000; string label = ((DSTAG.find("PP")!=std::string::npos) ? DSTAG.c_str() : Form("%s_%s", DSTAG.c_str(), "PP")); if (wantPureSMC) label += "_NoBkg"; if (applyWeight_Corr) label += Form("_%s",applyCorr); string dsName = Form("dOS_%s", label.c_str()); if (importDS) { if ( !(myws.data(dsName.c_str())) ) { int importID = importDataset(myws, inputWorkspace, cut, label, cutSideBand); if (importID<0) { return false; } else if (importID==0) { doFit = false; } } numEntries = myws.data(dsName.c_str())->sumEntries(); if (numEntries<=0) { doFit = false; } } else if (doFit && !(myws.data(dsName.c_str()))) { cout << "[ERROR] No local dataset was found to perform the fit!" << endl; return false; } if (myws.data(dsName.c_str())) numEntries = myws.data(dsName.c_str())->sumEntries(); // Set global parameters setMassGlobalParameterRange(myws, parIni, cut, incJpsi, incPsi2S, incBkg, wantPureSMC); // Build the Fit Model if (!buildCharmoniaMassModel(myws, model.PP, parIni, false, doConstrFit, doSimulFit, incBkg, incJpsi, incPsi2S, numEntries)) { return false; } // Define plot names if (incJpsi) { plotLabelPP += Form("_Jpsi_%s", parIni["Model_Jpsi_PP"].c_str()); } if (incPsi2S) { plotLabelPP += Form("_Psi2S_%s", parIni["Model_Psi2S_PP"].c_str()); } if (incBkg) { plotLabelPP += Form("_Bkg_%s", parIni["Model_Bkg_PP"].c_str()); } if (wantPureSMC) plotLabelPP +="_NoBkg"; if (applyWeight_Corr) plotLabelPP +=Form("_%s",applyCorr); } if (doSimulFit || isPbPb) { // Set models based on initial parameters struct OniaModel model; if (!setMassModel(model, parIni, true, incJpsi, incPsi2S, incBkg)) { return false; } // Import the local datasets double numEntries = 1000000; string label = ((DSTAG.find("PbPb")!=std::string::npos) ? DSTAG.c_str() : Form("%s_%s", DSTAG.c_str(), "PbPb")); if (wantPureSMC) label += "_NoBkg"; if (applyWeight_Corr) label += Form("_%s",applyCorr); string dsName = Form("dOS_%s", label.c_str()); if (importDS) { if ( !(myws.data(dsName.c_str())) ) { int importID = importDataset(myws, inputWorkspace, cut, label, cutSideBand); if (importID<0) { return false; } else if (importID==0) { doFit = false; } } numEntries = myws.data(dsName.c_str())->sumEntries(); if (numEntries<=0) { doFit = false; } } else if (doFit && !(myws.data(dsName.c_str()))) { cout << "[ERROR] No local dataset was found to perform the fit!" << endl; return false; } if (myws.data(dsName.c_str())) numEntries = myws.data(dsName.c_str())->sumEntries(); // Set global parameters setMassGlobalParameterRange(myws, parIni, cut, incJpsi, incPsi2S, incBkg, wantPureSMC); // Build the Fit Model if (!buildCharmoniaMassModel(myws, model.PbPb, parIni, true, doConstrFit, doSimulFit, incBkg, incJpsi, incPsi2S, numEntries)) { return false; } // Define plot names if (incJpsi) { plotLabelPbPb += Form("_Jpsi_%s", parIni["Model_Jpsi_PbPb"].c_str()); } if (incPsi2S) { plotLabelPbPb += Form("_Psi2S_%s", parIni["Model_Psi2S_PbPb"].c_str()); } if (incBkg) { plotLabelPbPb += Form("_Bkg_%s", parIni["Model_Bkg_PbPb"].c_str()); } if (wantPureSMC) plotLabelPbPb += "_NoBkg"; if (applyWeight_Corr) plotLabelPbPb += Form("_%s",applyCorr); } if (doSimulFit) { // Create the combided datasets RooCategory* sample = new RooCategory("sample","sample"); sample->defineType("PbPb"); sample->defineType("PP"); RooDataSet* combData = new RooDataSet("combData","combined data", *myws.var("invMass"), Index(*sample), Import("PbPb", *((RooDataSet*)myws.data("dOS_DATA_PbPb"))), Import("PP", *((RooDataSet*)myws.data("dOS_DATA_PP"))) ); myws.import(*sample); // Create the combided models RooSimultaneous* simPdf = new RooSimultaneous("simPdf", "simultaneous pdf", *sample); simPdf->addPdf(*myws.pdf("pdfMASS_Tot_PbPb"), "PbPb"); simPdf->addPdf(*myws.pdf("pdfMASS_Tot_PP"), "PP"); myws.import(*simPdf); // check if we have already done this fit. If yes, do nothing and return true. string FileName = ""; setMassFileName(FileName, (inputFitDir=="" ? outputDir : inputFitDir), DSTAG, (plotLabelPP + plotLabelPbPb), cut, isPbPb, cutSideBand, doSimulFit); if (gSystem->AccessPathName(FileName.c_str()) && inputFitDir!="") { cout << "[WARNING] User Input File : " << FileName << " was not found!" << endl; if (loadFitResult) return false; setMassFileName(FileName, outputDir, DSTAG, (plotLabelPP + plotLabelPbPb), cut, isPbPb, cutSideBand, doSimulFit); } bool found = true; bool skipFit = !doFit; RooArgSet *newpars = myws.pdf("simPdf")->getParameters(*(myws.var("invMass"))); myws.saveSnapshot("simPdf_parIni", *newpars, kTRUE); found = found && isFitAlreadyFound(newpars, FileName, "simPdf"); if (loadFitResult) { if ( loadPreviousFitResult(myws, FileName, DSTAG, false, (!isMC && !cutSideBand && loadFitResult==1), loadFitResult==1) ) { skipFit = true; } else { skipFit = false; } if ( loadPreviousFitResult(myws, FileName, DSTAG, true, (!isMC && !cutSideBand && loadFitResult==1), loadFitResult==1) ) { skipFit = true; } else { skipFit = false; } if (skipFit) { cout << "[INFO] This simultaneous mass fit was already done, so I'll load the fit results." << endl; } myws.saveSnapshot("simPdf_parLoad", *newpars, kTRUE); } else if (found) { cout << "[INFO] This simultaneous mass fit was already done, so I'll just go to the next one." << endl; return true; } // Do the simultaneous fit if (skipFit==false) { RooFitResult* fitResult = simPdf->fitTo(*combData, Offset(kTRUE), Extended(kTRUE), NumCPU(numCores), Range("MassWindow"), Save()); //, Minimizer("Minuit2","Migrad") fitResult->Print("v"); myws.import(*fitResult, "fitResult_simPdf"); // Create the output files int nBins = min(int( round((cut.dMuon.M.Max - cut.dMuon.M.Min)/binWidth) ), 1000); drawMassPlot(myws, outputDir, opt, cut, parIni, plotLabelPP, DSTAG, false, incJpsi, incPsi2S, incBkg, cutCtau, doSimulFit, false, setLogScale, incSS, zoomPsi, nBins, getMeanPT); drawMassPlot(myws, outputDir, opt, cut, parIni, plotLabelPbPb, DSTAG, true, incJpsi, incPsi2S, incBkg, cutCtau, doSimulFit, false, setLogScale, incSS, zoomPsi, nBins, getMeanPT); // Save the results string FileName = ""; setMassFileName(FileName, outputDir, DSTAG, (plotLabelPP + plotLabelPbPb), cut, isPbPb, cutSideBand, doSimulFit); myws.saveSnapshot("simPdf_parFit", *newpars, kTRUE); saveWorkSpace(myws, Form("%smass%s/%s/result", outputDir.c_str(), (cutSideBand?"SB":""), DSTAG.c_str()), FileName); // Delete the objects used during the simultaneous fit delete sample; delete combData; delete simPdf; } } else { // Define pdf and plot names string pdfName = Form("pdfMASS_Tot_%s", COLL.c_str()); string plotLabel = (isPbPb ? plotLabelPbPb : plotLabelPP); // Import the local datasets string label = ((DSTAG.find(COLL.c_str())!=std::string::npos) ? DSTAG.c_str() : Form("%s_%s", DSTAG.c_str(), COLL.c_str())); if (wantPureSMC) label += "_NoBkg"; if (applyWeight_Corr) label += Form("_%s",applyCorr); string dsName = Form("dOS_%s", label.c_str()); // check if we have already done this fit. If yes, do nothing and return true. string FileName = ""; setMassFileName(FileName, (inputFitDir=="" ? outputDir : inputFitDir), DSTAG, plotLabel, cut, isPbPb, cutSideBand); if (gSystem->AccessPathName(FileName.c_str()) && inputFitDir!="") { cout << "[WARNING] User Input File : " << FileName << " was not found!" << endl; if (loadFitResult) return false; setMassFileName(FileName, outputDir, DSTAG, plotLabel, cut, isPbPb, cutSideBand); } bool found = true; bool skipFit = !doFit; RooArgSet *newpars = myws.pdf(pdfName.c_str())->getParameters(*(myws.var("invMass"))); found = found && isFitAlreadyFound(newpars, FileName, pdfName.c_str()); if (loadFitResult) { if ( loadPreviousFitResult(myws, FileName, DSTAG, isPbPb, (!isMC && !cutSideBand && loadFitResult==1), loadFitResult==1) ) { skipFit = true; } else { skipFit = false; } if (skipFit) { cout << "[INFO] This mass fit was already done, so I'll load the fit results." << endl; } myws.saveSnapshot(Form("%s_parLoad", pdfName.c_str()), *newpars, kTRUE); } else if (found) { cout << "[INFO] This mass fit was already done, so I'll just go to the next one." << endl; return true; } // Fit the Datasets if (skipFit==false) { bool isWeighted = myws.data(dsName.c_str())->isWeighted(); RooFitResult* fitResult(0x0); if (doConstrFit) { cout << "[INFO] Performing constrained fit" << endl; if (isPbPb) { cout << "[INFO] Constrained variables: alpha, n, ratio of sigmas" << endl; fitResult = myws.pdf(pdfName.c_str())->fitTo(*myws.data(dsName.c_str()), Extended(kTRUE), SumW2Error(isWeighted), Range(cutSideBand ? parIni["BkgMassRange_FULL_Label"].c_str() : "MassWindow"), ExternalConstraints(RooArgSet(*(myws.pdf("sigmaAlphaConstr")),*(myws.pdf("sigmaNConstr")),*(myws.pdf("sigmaRSigmaConstr")))), NumCPU(numCores), Save()); } else { cout << "[INFO] Constrained variables: alpha, n, ratio of sigmas" << endl; fitResult = myws.pdf(pdfName.c_str())->fitTo(*myws.data(dsName.c_str()), Extended(kTRUE), SumW2Error(isWeighted), Range(cutSideBand ? parIni["BkgMassRange_FULL_Label"].c_str() : "MassWindow"), ExternalConstraints(RooArgSet(*(myws.pdf("sigmaAlphaConstr")),*(myws.pdf("sigmaNConstr")))), NumCPU(numCores), Save()); } } else { fitResult = myws.pdf(pdfName.c_str())->fitTo(*myws.data(dsName.c_str()), Extended(kTRUE), SumW2Error(isWeighted), Range(cutSideBand ? parIni["BkgMassRange_FULL_Label"].c_str() : "MassWindow"), NumCPU(numCores), Save()); } fitResult->Print("v"); myws.import(*fitResult, Form("fitResult_%s", pdfName.c_str())); // Create the output files int nBins = min(int( round((cut.dMuon.M.Max - cut.dMuon.M.Min)/binWidth) ), 1000); drawMassPlot(myws, outputDir, opt, cut, parIni, plotLabel, DSTAG, isPbPb, incJpsi, incPsi2S, incBkg, cutCtau, doSimulFit, wantPureSMC, setLogScale, incSS, zoomPsi, nBins, getMeanPT); // Save the results string FileName = ""; setMassFileName(FileName, outputDir, DSTAG, plotLabel, cut, isPbPb, cutSideBand); myws.saveSnapshot(Form("%s_parFit", pdfName.c_str()), *newpars, kTRUE); saveWorkSpace(myws, Form("%smass%s/%s/result", outputDir.c_str(), (cutSideBand?"SB":""), DSTAG.c_str()), FileName); } } return true; };
Int_t Tprime::SetParameterPoints( std::string sbModelName, std::string bModelName ) { // // Fit the data with S+B model. // Make a snapshot of the S+B parameter point. // Profile with POI=0. // Make a snapshot of the B parameter point // (B model is the S+B model with POI=0 // Double_t poi_value_for_b_model = 0.0; // get S+B model config from workspace RooStats::ModelConfig * pSbModel = (RooStats::ModelConfig *)pWs->obj(sbModelName.c_str()); pSbModel->SetWorkspace(*pWs); // get parameter of interest set const RooArgSet * poi = pSbModel->GetParametersOfInterest(); // get B model config from workspace RooStats::ModelConfig * pBModel = (RooStats::ModelConfig *)pWs->obj(bModelName.c_str()); pBModel->SetWorkspace(*pWs); // make sure that data has been loaded if (!data) return -1; // find parameter point for global maximum with the S+B model, // with conditional MLEs for nuisance parameters // and save the parameter point snapshot in the Workspace RooAbsReal * nll = pSbModel->GetPdf()->createNLL(*data); RooAbsReal * profile = nll->createProfile(RooArgSet()); profile->getVal(); // this will do fit and set POI and nuisance parameters to fitted values RooArgSet * poiAndNuisance = new RooArgSet(); if(pSbModel->GetNuisanceParameters()) poiAndNuisance->add(*pSbModel->GetNuisanceParameters()); poiAndNuisance->add(*pSbModel->GetParametersOfInterest()); pWs->defineSet("SPlusBModelParameters", *poiAndNuisance); pWs->saveSnapshot("SPlusBFitParameters",*poiAndNuisance); pSbModel->SetSnapshot(*poi); RooArgSet * sbModelFitParams = (RooArgSet *)poiAndNuisance->snapshot(); cout << "\nWill save these parameter points that correspond to the fit to data" << endl; sbModelFitParams->Print("v"); delete profile; delete nll; delete poiAndNuisance; delete sbModelFitParams; // // Find a parameter point for generating pseudo-data // with the background-only data. // Save the parameter point snapshot in the Workspace nll = pBModel->GetPdf()->createNLL(*data); profile = nll->createProfile(*poi); ((RooRealVar *)poi->first())->setVal(poi_value_for_b_model); profile->getVal(); // this will do fit and set nuisance parameters to profiled values poiAndNuisance = new RooArgSet(); if(pBModel->GetNuisanceParameters()) poiAndNuisance->add(*pBModel->GetNuisanceParameters()); poiAndNuisance->add(*pBModel->GetParametersOfInterest()); pWs->defineSet("parameterPointToGenerateData", *poiAndNuisance); pWs->saveSnapshot("parametersToGenerateData",*poiAndNuisance); pBModel->SetSnapshot(*poi); RooArgSet * paramsToGenerateData = (RooArgSet *)poiAndNuisance->snapshot(); cout << "\nShould use these parameter points to generate pseudo data for bkg only" << endl; paramsToGenerateData->Print("v"); delete profile; delete nll; delete poiAndNuisance; delete paramsToGenerateData; return 0; }