int main (int argc, char *argv[]){
gROOT->SetBatch();
OptionParser(argc,argv);
TFile *outFile = new TFile(outfilename_.c_str(),"RECREATE");
RooRealVar *intLumi = new RooRealVar("IntLumi","IntLumi",lumi_*1000,0.,10.e5);
WSTFileWrapper * inWS = new WSTFileWrapper(infilename_,"wsig_13TeV");
RooWorkspace *saveWS = new RooWorkspace();
RooWorkspace *tmpWS = new RooWorkspace();
//saveWS->import((inWS->allVars()),RecycleConflictNodes());
//saveWS->import((inWS->allFunctions()),RecycleConflictNodes());
for (int i=0 ; i < inWS->getWsList().size() ; i++){
inWS->getWsList()[i]->Print();
if (i==0) tmpWS = (RooWorkspace*) inWS->getWsList()[i]->Clone();
if (!tmpWS){ std::cout << "EXIT" << std::endl; exit(1);}
if (i !=0) {
//tmpWS->merge(*(inWS->getWsList()[i]));
tmpWS->import(inWS->getWsList()[i]->allVars(),RecycleConflictNodes());
tmpWS->import(inWS->getWsList()[i]->allFunctions(),RecycleConflictNodes());
inWS->getWsList()[i]->allFunctions().Print();
tmpWS->import(inWS->getWsList()[i]->allPdfs(),RecycleConflictNodes());
inWS->getWsList()[i]->allPdfs().Print();
std::list<RooAbsData*> data = (inWS->getWsList()[i]->allData()) ;
for (std::list<RooAbsData*>::const_iterator iterator = data.begin(), end = data.end(); iterator != end; ++iterator ) {
tmpWS->import(**iterator);
}
std::list<TObject*> stuff = (inWS->getWsList()[i]->allGenericObjects()) ;
for (std::list<TObject*>::const_iterator iterator = stuff.begin(), end = stuff.end(); iterator != end; ++iterator ) {
tmpWS->import(**iterator);
}
};
}
WSTFileWrapper *mergedWS = new WSTFileWrapper(tmpWS);
saveWS->SetName("wsig_13TeV");
ncats_= flashggCats_.size();
cout << "[INFO] Starting to combine fits..." << endl;
// this guy packages everything up
RooWorkspace *mergeWS = 0;
Packager packager(mergedWS, saveWS ,procs_,ncats_,mhLow_,mhHigh_,skipMasses_,/*sqrts*/13,/*skipPlots_*/false,plotDir_,mergeWS,cats_,flashggCats_);
cout << "[INFO] Finished initalising packager." << endl;
packager.packageOutput(/*split*/ false);
cout << "[INFO] Combination complete." << endl;
cout << "[INFO] cd to output file" << endl;
outFile->cd();
cout << "[INFO] write saveWS " << endl;
saveWS->Write();
cout << "[INFO] close output file " << endl;
outFile->Close();
return 0;
}
void buildModel(int sel_i, TFile *fin, TDirectory *fout){
// Define outputs
RooWorkspace *wout = new RooWorkspace();
wout->SetName(Form("normalization_cat%d",sel_i));
fout->cd();
// Input to this is TTrees
// Setup the "x" variable and weights
RooRealVar mvamet("metRaw","metRaw",200,1200);
//RooRealVar mvamet("jet1mprune","jet1mprune",0,200);
//RooRealVar mvamet("jet1tau2o1","jet1tau2o1",0,1);
wout->import(mvamet);
// TH1F Base Style
std::string lName = "basehist";
//const int numberofBins = 18;
//double myBins[numberofBins+1] = {200,210,220,230,240,250,260,270,280,290,300,310,320,330,350,380,430,500,1200};
//TH1F *lMet = new TH1F(lName.c_str(),lName.c_str(),numberofBins,myBins);
TH1F *lMet = new TH1F(lName.c_str(),lName.c_str(),20,200,1200);
//TH1F *lMet = new TH1F(lName.c_str(),lName.c_str(),20,0,1);
// Make Datasets
makeAndImportDataSets(fin,wout,mvamet);
// ==========================================================================================================
const int nProcs = 27;
std::string procnames[nProcs];
procnames[0] = "DY";
procnames[1] = "RDY";
procnames[2] = "W";
procnames[3] = "WHT";
procnames[4] = "TT";
procnames[5] = "T";
procnames[6] = "ZZ";
procnames[7] = "WW";
procnames[8] = "WZ";
procnames[9] = "WH0";
procnames[10] = "ZH0";
procnames[11] = "GGH0";
procnames[12] = "VBFH0";
//procnames[12] = "DY_control_bkg_mc";
procnames[13] = "Zvv_control_mc";
procnames[14] = "T_control_bkg_mc";
procnames[15] = "TT_control_bkg_mc";
procnames[16] = "WW_control_bkg_mc";
procnames[17] = "WZ_control_bkg_mc";
procnames[18] = "ZZ_control_bkg_mc";
procnames[19] = "Wlv_control_mc_1";
procnames[20] = "Wlv_control_mc_2";
procnames[21] = "T_sl_control_bkg_mc";
procnames[22] = "TT_sl_control_bkg_mc";
procnames[23] = "WW_sl_control_bkg_mc";
procnames[24] = "WZ_sl_control_bkg_mc";
procnames[25] = "ZZ_sl_control_bkg_mc";
procnames[26] = "DY_sl_control_bkg_mc";
// Fill TF1s which do not need corrections
for (int p0=0;p0<nProcs;p0++){
std::cout << "Filling hist for " << procnames[p0] << std::endl;;
TH1F *hist_ = (TH1F*)generateTemplate(lMet, (TTree*)fin->Get(procnames[p0].c_str()), mvamet.GetName(), "weight",cutstring); // standard processes are TTrees
hist_->Write();
}
std::cout << "Filling hist for " << "data_obs" << std::endl;;
TH1F *hist_ = (TH1F*)generateTemplate(lMet, (TTree*)fin->Get("data_obs"), mvamet.GetName(), "",cutstring); // standard processes are TTrees
hist_->Write();
std::cout << "Filling hist for " << "Zvv_control" << std::endl;;
hist_ = (TH1F*)generateTemplate(lMet, (TTree*)fin->Get("Zvv_control"), mvamet.GetName(), "",cutstring); // standard processes are TTrees
hist_->Write();
std::cout << "Filling hist for " << "Wlv_control" << std::endl;;
hist_ = (TH1F*)generateTemplate(lMet, (TTree*)fin->Get("Wlv_control"), mvamet.GetName(), "",cutstring); // standard processes are TTrees
hist_->Write();
// ==========================================================================================================
// Fit backgrounds to produce fit model
#ifdef RUN_CORRECTION
buildAndFitModels(fout,wout,mvamet,"Zvv");
buildAndFitModels(fout,wout,mvamet,"Wlv");
double mcyield = wout->data("DY")->sumEntries();
double datayield = wout->var("num_Zvv")->getVal(); // post fit number of data Z->mumu in control
std::cout << "sfactor" << brscaleFactorZvv*datayield/mcyield << std::endl;
TH1F *hist_zvv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("ratio_Zvv") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("DY")
//TH1F *hist_zvv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("DY")
, 1 /*run correction*/
, 1 /*brscaleFactorZvv*datayield/mcyield*/ /*additional weight*/);
hist_zvv->Write();
std::cout << " DataCardInfo ---------------- " << std::endl;
std::cout << Form(" Zvv_norm gmN %d %g ",(int)datayield,hist_zvv->Integral()/datayield) << std::endl;
std::cout << " ----------------------------- " << std::endl;
// Also correct normalization data why not?
hist_zvv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("ratio_Zvv") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("Zvv_control_mc")
, 1 /*run correction*/
, 1. /*additional weight*/);
hist_zvv->Write();
// Single muon
mcyield = wout->data("W")->sumEntries();
datayield = wout->var("num_Wlv")->getVal(); // post fit number of data W->munu in control
std::cout << "sfactor" << brscaleFactorWlv*datayield/mcyield << std::endl;
TH1F *hist_wlv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("ratio_Wlv") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("W")
, 1 /*run correction*/
, 1./*brscaleFactorWlv*datayield/mcyield*/ /*additional weight*/);
hist_wlv->Write();
std::cout << " DataCardInfo ---------------- " << std::endl;
std::cout << Form(" Wlv_norm gmN %d %g ",(int)datayield,hist_wlv->Integral()/datayield) << std::endl;
std::cout << " ----------------------------- " << std::endl;
// Also correct normalization data why not?
hist_wlv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("ratio_Wlv") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("Wlv_control_mc")
, 1 /*run correction*/
, 1. /*additional weight*/);
hist_wlv->Write();
//buildAndFitModels(fout,wout,mvamet,"Wlv");
//TH1F *hist_wlv = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("ratio_Wlv"), &mvamet, (RooDataSet*) wout->data(""));
//hist_wlv->Write();
#endif
// Since the W came in 2 parts, we can make the histogram based on the dataset (called uncorrected)
TH1F *hist_wlv_uc = (TH1F*)generateTemplate(lMet, (RooFormulaVar*)wout->function("") , *(wout->var(mvamet.GetName())), (RooDataSet*) wout->data("W")
, 1 /*run correction forwards*/
, 1./*brscaleFactorWlv*datayield/mcyield*/ /*additional weight*/);
hist_wlv_uc->Write();
#ifdef RUN_BKGSYS
// Load and run systematics from fit model
std::vector<TH1F> v_th1f_Z;
generateVariations(lMet,(RooFitResult*)fout->Get("fitResult_Zvv_control"),(RooFormulaVar*)wout->function("ratio_Zvv"),wout->var(mvamet.GetName()),v_th1f_Z,wout,"DY");
std::vector<TH1F> v_th1f_W;
generateVariations(lMet,(RooFitResult*)fout->Get("fitResult_Wlv_control"),(RooFormulaVar*)wout->function("ratio_Wlv"),wout->var(mvamet.GetName()),v_th1f_W,wout,"W");
// Nice plots
hist_zvv = (TH1F*)fout->Get("th1f_corrected_DY");
hist_wlv = (TH1F*)fout->Get("th1f_corrected_W");
double norm = hist_zvv->Integral();
int colit=2, styleit=1;
TCanvas *can_zvv_systs = new TCanvas("can_zvv_systs","can_zvv_systs",800,600);
TLegend *leg = new TLegend(0.6,0.4,0.89,0.89); leg->SetFillColor(0); leg->SetTextFont(42);
hist_zvv->SetLineColor(1);hist_zvv->SetLineWidth(3); hist_zvv->Draw();
for (std::vector<TH1F>::iterator hit=v_th1f_Z.begin();hit!=v_th1f_Z.end();hit++){
hit->SetLineColor(colit);
hit->SetLineWidth(3);
hit->SetLineStyle(styleit%2+1);
leg->AddEntry(&(*hit),hit->GetName(),"L");
hit->Scale(norm/hit->Integral());
hit->Draw("same");
hit->Write();
styleit++;
if (styleit%2==1) colit++;
}
leg->Draw();
can_zvv_systs->Write();
norm = hist_wlv->Integral();
styleit=1; colit=2;
TCanvas *can_wlv_systs = new TCanvas("can_wlv_systs","can_wlv_systs",800,600);
TLegend *leg_2 = new TLegend(0.6,0.4,0.89,0.89); leg_2->SetFillColor(0); leg_2->SetTextFont(42);
hist_wlv->SetLineColor(1);hist_wlv->SetLineWidth(3); hist_wlv->Draw();
for (std::vector<TH1F>::iterator hit=v_th1f_W.begin();hit!=v_th1f_W.end();hit++){
hit->SetLineColor(colit);
hit->SetLineWidth(3);
hit->SetLineStyle(styleit%2+1);
leg_2->AddEntry(&(*hit),hit->GetName(),"L");
hit->Scale(norm/hit->Integral());
hit->Draw("same");
hit->Write();
styleit++;
if (styleit%2==1) colit++;
}
leg_2->Draw();
can_wlv_systs->Write();
#endif
// Save the work
fout->cd();
wout->Write();
// Done!
}
void rs101_limitexample()
{
// --------------------------------------
// An example of setting a limit in a number counting experiment with uncertainty on background and signal
// to time the macro
TStopwatch t;
t.Start();
// --------------------------------------
// The Model building stage
// --------------------------------------
RooWorkspace* wspace = new RooWorkspace();
wspace->factory("Poisson::countingModel(obs[150,0,300], sum(s[50,0,120]*ratioSigEff[1.,0,3.],b[100]*ratioBkgEff[1.,0.,3.]))"); // counting model
// wspace->factory("Gaussian::sigConstraint(ratioSigEff,1,0.05)"); // 5% signal efficiency uncertainty
// wspace->factory("Gaussian::bkgConstraint(ratioBkgEff,1,0.1)"); // 10% background efficiency uncertainty
wspace->factory("Gaussian::sigConstraint(gSigEff[1,0,3],ratioSigEff,0.05)"); // 5% signal efficiency uncertainty
wspace->factory("Gaussian::bkgConstraint(gSigBkg[1,0,3],ratioBkgEff,0.2)"); // 10% background efficiency uncertainty
wspace->factory("PROD::modelWithConstraints(countingModel,sigConstraint,bkgConstraint)"); // product of terms
wspace->Print();
RooAbsPdf* modelWithConstraints = wspace->pdf("modelWithConstraints"); // get the model
RooRealVar* obs = wspace->var("obs"); // get the observable
RooRealVar* s = wspace->var("s"); // get the signal we care about
RooRealVar* b = wspace->var("b"); // get the background and set it to a constant. Uncertainty included in ratioBkgEff
b->setConstant();
RooRealVar* ratioSigEff = wspace->var("ratioSigEff"); // get uncertain parameter to constrain
RooRealVar* ratioBkgEff = wspace->var("ratioBkgEff"); // get uncertain parameter to constrain
RooArgSet constrainedParams(*ratioSigEff, *ratioBkgEff); // need to constrain these in the fit (should change default behavior)
RooRealVar * gSigEff = wspace->var("gSigEff"); // global observables for signal efficiency
RooRealVar * gSigBkg = wspace->var("gSigBkg"); // global obs for background efficiency
gSigEff->setConstant();
gSigBkg->setConstant();
// Create an example dataset with 160 observed events
obs->setVal(160.);
RooDataSet* data = new RooDataSet("exampleData", "exampleData", RooArgSet(*obs));
data->add(*obs);
RooArgSet all(*s, *ratioBkgEff, *ratioSigEff);
// not necessary
modelWithConstraints->fitTo(*data, RooFit::Constrain(RooArgSet(*ratioSigEff, *ratioBkgEff)));
// Now let's make some confidence intervals for s, our parameter of interest
RooArgSet paramOfInterest(*s);
ModelConfig modelConfig(wspace);
modelConfig.SetPdf(*modelWithConstraints);
modelConfig.SetParametersOfInterest(paramOfInterest);
modelConfig.SetNuisanceParameters(constrainedParams);
modelConfig.SetObservables(*obs);
modelConfig.SetGlobalObservables( RooArgSet(*gSigEff,*gSigBkg));
modelConfig.SetName("ModelConfig");
wspace->import(modelConfig);
wspace->import(*data);
wspace->SetName("w");
wspace->writeToFile("rs101_ws.root");
// First, let's use a Calculator based on the Profile Likelihood Ratio
//ProfileLikelihoodCalculator plc(*data, *modelWithConstraints, paramOfInterest);
ProfileLikelihoodCalculator plc(*data, modelConfig);
plc.SetTestSize(.05);
ConfInterval* lrinterval = plc.GetInterval(); // that was easy.
// Let's make a plot
TCanvas* dataCanvas = new TCanvas("dataCanvas");
dataCanvas->Divide(2,1);
dataCanvas->cd(1);
LikelihoodIntervalPlot plotInt((LikelihoodInterval*)lrinterval);
plotInt.SetTitle("Profile Likelihood Ratio and Posterior for S");
plotInt.Draw();
// Second, use a Calculator based on the Feldman Cousins technique
FeldmanCousins fc(*data, modelConfig);
fc.UseAdaptiveSampling(true);
fc.FluctuateNumDataEntries(false); // number counting analysis: dataset always has 1 entry with N events observed
fc.SetNBins(100); // number of points to test per parameter
fc.SetTestSize(.05);
// fc.SaveBeltToFile(true); // optional
ConfInterval* fcint = NULL;
fcint = fc.GetInterval(); // that was easy.
RooFitResult* fit = modelWithConstraints->fitTo(*data, Save(true));
// Third, use a Calculator based on Markov Chain monte carlo
// Before configuring the calculator, let's make a ProposalFunction
// that will achieve a high acceptance rate
ProposalHelper ph;
ph.SetVariables((RooArgSet&)fit->floatParsFinal());
ph.SetCovMatrix(fit->covarianceMatrix());
ph.SetUpdateProposalParameters(true);
ph.SetCacheSize(100);
ProposalFunction* pdfProp = ph.GetProposalFunction(); // that was easy
MCMCCalculator mc(*data, modelConfig);
mc.SetNumIters(20000); // steps to propose in the chain
mc.SetTestSize(.05); // 95% CL
mc.SetNumBurnInSteps(40); // ignore first N steps in chain as "burn in"
mc.SetProposalFunction(*pdfProp);
mc.SetLeftSideTailFraction(0.5); // find a "central" interval
MCMCInterval* mcInt = (MCMCInterval*)mc.GetInterval(); // that was easy
// Get Lower and Upper limits from Profile Calculator
cout << "Profile lower limit on s = " << ((LikelihoodInterval*) lrinterval)->LowerLimit(*s) << endl;
cout << "Profile upper limit on s = " << ((LikelihoodInterval*) lrinterval)->UpperLimit(*s) << endl;
// Get Lower and Upper limits from FeldmanCousins with profile construction
if (fcint != NULL) {
double fcul = ((PointSetInterval*) fcint)->UpperLimit(*s);
double fcll = ((PointSetInterval*) fcint)->LowerLimit(*s);
cout << "FC lower limit on s = " << fcll << endl;
cout << "FC upper limit on s = " << fcul << endl;
TLine* fcllLine = new TLine(fcll, 0, fcll, 1);
TLine* fculLine = new TLine(fcul, 0, fcul, 1);
fcllLine->SetLineColor(kRed);
fculLine->SetLineColor(kRed);
fcllLine->Draw("same");
fculLine->Draw("same");
dataCanvas->Update();
}
// Plot MCMC interval and print some statistics
MCMCIntervalPlot mcPlot(*mcInt);
mcPlot.SetLineColor(kMagenta);
mcPlot.SetLineWidth(2);
mcPlot.Draw("same");
double mcul = mcInt->UpperLimit(*s);
double mcll = mcInt->LowerLimit(*s);
cout << "MCMC lower limit on s = " << mcll << endl;
cout << "MCMC upper limit on s = " << mcul << endl;
cout << "MCMC Actual confidence level: "
<< mcInt->GetActualConfidenceLevel() << endl;
// 3-d plot of the parameter points
dataCanvas->cd(2);
// also plot the points in the markov chain
RooDataSet * chainData = mcInt->GetChainAsDataSet();
assert(chainData);
std::cout << "plotting the chain data - nentries = " << chainData->numEntries() << std::endl;
TTree* chain = RooStats::GetAsTTree("chainTreeData","chainTreeData",*chainData);
assert(chain);
chain->SetMarkerStyle(6);
chain->SetMarkerColor(kRed);
chain->Draw("s:ratioSigEff:ratioBkgEff","nll_MarkovChain_local_","box"); // 3-d box proportional to posterior
// the points used in the profile construction
RooDataSet * parScanData = (RooDataSet*) fc.GetPointsToScan();
assert(parScanData);
std::cout << "plotting the scanned points used in the frequentist construction - npoints = " << parScanData->numEntries() << std::endl;
// getting the tree and drawing it -crashes (very strange....);
// TTree* parameterScan = RooStats::GetAsTTree("parScanTreeData","parScanTreeData",*parScanData);
// assert(parameterScan);
// parameterScan->Draw("s:ratioSigEff:ratioBkgEff","","goff");
TGraph2D *gr = new TGraph2D(parScanData->numEntries());
for (int ievt = 0; ievt < parScanData->numEntries(); ++ievt) {
const RooArgSet * evt = parScanData->get(ievt);
double x = evt->getRealValue("ratioBkgEff");
double y = evt->getRealValue("ratioSigEff");
double z = evt->getRealValue("s");
gr->SetPoint(ievt, x,y,z);
// std::cout << ievt << " " << x << " " << y << " " << z << std::endl;
}
gr->SetMarkerStyle(24);
gr->Draw("P SAME");
delete wspace;
delete lrinterval;
delete mcInt;
delete fcint;
delete data;
// print timing info
t.Stop();
t.Print();
}
