void FitterUtils::plot_fit_result(string plotsfile, RooAbsPdf &totPdf, RooDataSet dataGenTot)
{
//**************Prepare TFile to save the plots
TFile f2(plotsfile.c_str(), "UPDATE");
//**************Plot the results of the fit
RooArgSet *var_set = totPdf.getObservables(dataGenTot);
TIterator *iter = var_set->createIterator();
RooRealVar *var;
std::vector<RooPlot*> plots;
RooPlot* frame;
while((var = (RooRealVar*) iter->Next()))
{
frame = var->frame();
dataGenTot.plotOn(frame);
totPdf.plotOn(frame, Components("histPdfPartReco"), LineColor(kBlue));
totPdf.plotOn(frame, Components("histPdfSignalZeroGamma"), LineColor(kGreen));
totPdf.plotOn(frame, Components("histPdfSignalOneGamma"), LineColor(kMagenta));
totPdf.plotOn(frame, Components("histPdfSignalTwoGamma"), LineColor(kOrange));
totPdf.plotOn(frame, Components("histPdfJpsiLeak"), LineColor(14));
totPdf.plotOn(frame, Components("combPDF"), LineColor(kBlack));
totPdf.plotOn(frame, LineColor(kRed));
plots.push_back(frame);
}
if (!(plots.size())) return;
TCanvas cFit("cFit", "cFit", 600, 800);
cFit.Divide(1,2);
cFit.cd(1); plots[0]->Draw();
if (plots.size()>1){
cFit.cd(2); plots[1]->Draw();
}
cFit.Write();
f2.Close();
}
void FitterUtilsSimultaneousExpOfPolyTimesX::plot_kemu_fit_result(string plotsfile, RooAbsPdf &totKemuPdf, RooDataSet const& dataGenKemu)
{
//**************Prepare TFile to save the plots
TFile f2(plotsfile.c_str(), "UPDATE");
//**************Plot the results of the fit
RooArgSet *var_set = totKemuPdf.getObservables(dataGenKemu);
TIterator *iter = var_set->createIterator();
RooRealVar *var;
std::vector<RooPlot*> plots;
RooPlot* frame;
while((var = (RooRealVar*) iter->Next()))
{
frame = var->frame();
dataGenKemu.plotOn(frame);
totKemuPdf.plotOn(frame, LineColor(kRed));
plots.push_back(frame);
}
if (!(plots.size())) return;
TCanvas cFit("cKemuFit", "cKemuFit", 600, 800);
cFit.Divide(1,2);
cFit.cd(1); plots[0]->Draw();
if (plots.size()>1){
cFit.cd(2); plots[1]->Draw();
}
cFit.Write();
f2.Close();
}
// internal routine to run the inverter
HypoTestInverterResult *
RooStats::HypoTestInvTool::RunInverter(RooWorkspace * w,
const char * modelSBName, const char * modelBName,
const char * dataName, int type, int testStatType,
bool useCLs, int npoints, double poimin, double poimax,
int ntoys,
bool useNumberCounting,
const char * nuisPriorName ){
std::cout << "Running HypoTestInverter on the workspace " << w->GetName() << std::endl;
w->Print();
RooAbsData * data = w->data(dataName);
if (!data) {
Error("StandardHypoTestDemo","Not existing data %s",dataName);
return 0;
}
else
std::cout << "Using data set " << dataName << std::endl;
if (mUseVectorStore) {
RooAbsData::setDefaultStorageType(RooAbsData::Vector);
data->convertToVectorStore() ;
}
// get models from WS
// get the modelConfig out of the file
ModelConfig* bModel = (ModelConfig*) w->obj(modelBName);
ModelConfig* sbModel = (ModelConfig*) w->obj(modelSBName);
if (!sbModel) {
Error("StandardHypoTestDemo","Not existing ModelConfig %s",modelSBName);
return 0;
}
// check the model
if (!sbModel->GetPdf()) {
Error("StandardHypoTestDemo","Model %s has no pdf ",modelSBName);
return 0;
}
if (!sbModel->GetParametersOfInterest()) {
Error("StandardHypoTestDemo","Model %s has no poi ",modelSBName);
return 0;
}
if (!sbModel->GetObservables()) {
Error("StandardHypoTestInvDemo","Model %s has no observables ",modelSBName);
return 0;
}
if (!sbModel->GetSnapshot() ) {
Info("StandardHypoTestInvDemo","Model %s has no snapshot - make one using model poi",modelSBName);
sbModel->SetSnapshot( *sbModel->GetParametersOfInterest() );
}
// case of no systematics
// remove nuisance parameters from model
if (noSystematics) {
const RooArgSet * nuisPar = sbModel->GetNuisanceParameters();
if (nuisPar && nuisPar->getSize() > 0) {
std::cout << "StandardHypoTestInvDemo" << " - Switch off all systematics by setting them constant to their initial values" << std::endl;
RooStats::SetAllConstant(*nuisPar);
}
if (bModel) {
const RooArgSet * bnuisPar = bModel->GetNuisanceParameters();
if (bnuisPar)
RooStats::SetAllConstant(*bnuisPar);
}
}
if (!bModel || bModel == sbModel) {
Info("StandardHypoTestInvDemo","The background model %s does not exist",modelBName);
Info("StandardHypoTestInvDemo","Copy it from ModelConfig %s and set POI to zero",modelSBName);
bModel = (ModelConfig*) sbModel->Clone();
bModel->SetName(TString(modelSBName)+TString("_with_poi_0"));
RooRealVar * var = dynamic_cast<RooRealVar*>(bModel->GetParametersOfInterest()->first());
if (!var) return 0;
double oldval = var->getVal();
var->setVal(0);
bModel->SetSnapshot( RooArgSet(*var) );
var->setVal(oldval);
}
else {
if (!bModel->GetSnapshot() ) {
Info("StandardHypoTestInvDemo","Model %s has no snapshot - make one using model poi and 0 values ",modelBName);
RooRealVar * var = dynamic_cast<RooRealVar*>(bModel->GetParametersOfInterest()->first());
if (var) {
double oldval = var->getVal();
var->setVal(0);
bModel->SetSnapshot( RooArgSet(*var) );
var->setVal(oldval);
}
else {
Error("StandardHypoTestInvDemo","Model %s has no valid poi",modelBName);
return 0;
}
}
}
// check model has global observables when there are nuisance pdf
// for the hybrid case the globobs are not needed
if (type != 1 ) {
bool hasNuisParam = (sbModel->GetNuisanceParameters() && sbModel->GetNuisanceParameters()->getSize() > 0);
bool hasGlobalObs = (sbModel->GetGlobalObservables() && sbModel->GetGlobalObservables()->getSize() > 0);
if (hasNuisParam && !hasGlobalObs ) {
// try to see if model has nuisance parameters first
RooAbsPdf * constrPdf = RooStats::MakeNuisancePdf(*sbModel,"nuisanceConstraintPdf_sbmodel");
if (constrPdf) {
Warning("StandardHypoTestInvDemo","Model %s has nuisance parameters but no global observables associated",sbModel->GetName());
Warning("StandardHypoTestInvDemo","\tThe effect of the nuisance parameters will not be treated correctly ");
}
}
}
// run first a data fit
const RooArgSet * poiSet = sbModel->GetParametersOfInterest();
RooRealVar *poi = (RooRealVar*)poiSet->first();
std::cout << "StandardHypoTestInvDemo : POI initial value: " << poi->GetName() << " = " << poi->getVal() << std::endl;
// fit the data first (need to use constraint )
TStopwatch tw;
bool doFit = initialFit;
if (testStatType == 0 && initialFit == -1) doFit = false; // case of LEP test statistic
if (type == 3 && initialFit == -1) doFit = false; // case of Asymptoticcalculator with nominal Asimov
double poihat = 0;
if (minimizerType.size()==0) minimizerType = ROOT::Math::MinimizerOptions::DefaultMinimizerType();
else
ROOT::Math::MinimizerOptions::SetDefaultMinimizer(minimizerType.c_str());
Info("StandardHypoTestInvDemo","Using %s as minimizer for computing the test statistic",
ROOT::Math::MinimizerOptions::DefaultMinimizerType().c_str() );
if (doFit) {
// do the fit : By doing a fit the POI snapshot (for S+B) is set to the fit value
// and the nuisance parameters nominal values will be set to the fit value.
// This is relevant when using LEP test statistics
Info( "StandardHypoTestInvDemo"," Doing a first fit to the observed data ");
RooArgSet constrainParams;
if (sbModel->GetNuisanceParameters() ) constrainParams.add(*sbModel->GetNuisanceParameters());
RooStats::RemoveConstantParameters(&constrainParams);
tw.Start();
RooFitResult * fitres = sbModel->GetPdf()->fitTo(*data,InitialHesse(false), Hesse(false),
Minimizer(minimizerType.c_str(),"Migrad"), Strategy(0), PrintLevel(mPrintLevel), Constrain(constrainParams), Save(true) );
if (fitres->status() != 0) {
Warning("StandardHypoTestInvDemo","Fit to the model failed - try with strategy 1 and perform first an Hesse computation");
fitres = sbModel->GetPdf()->fitTo(*data,InitialHesse(true), Hesse(false),Minimizer(minimizerType.c_str(),"Migrad"), Strategy(1), PrintLevel(mPrintLevel+1), Constrain(constrainParams), Save(true) );
}
if (fitres->status() != 0)
Warning("StandardHypoTestInvDemo"," Fit still failed - continue anyway.....");
poihat = poi->getVal();
std::cout << "StandardHypoTestInvDemo - Best Fit value : " << poi->GetName() << " = "
<< poihat << " +/- " << poi->getError() << std::endl;
std::cout << "Time for fitting : "; tw.Print();
//save best fit value in the poi snapshot
sbModel->SetSnapshot(*sbModel->GetParametersOfInterest());
std::cout << "StandardHypoTestInvo: snapshot of S+B Model " << sbModel->GetName()
<< " is set to the best fit value" << std::endl;
}
// print a message in case of LEP test statistics because it affects result by doing or not doing a fit
if (testStatType == 0) {
if (!doFit)
Info("StandardHypoTestInvDemo","Using LEP test statistic - an initial fit is not done and the TS will use the nuisances at the model value");
else
Info("StandardHypoTestInvDemo","Using LEP test statistic - an initial fit has been done and the TS will use the nuisances at the best fit value");
}
// build test statistics and hypotest calculators for running the inverter
SimpleLikelihoodRatioTestStat slrts(*sbModel->GetPdf(),*bModel->GetPdf());
// null parameters must includes snapshot of poi plus the nuisance values
RooArgSet nullParams(*sbModel->GetSnapshot());
if (sbModel->GetNuisanceParameters()) nullParams.add(*sbModel->GetNuisanceParameters());
if (sbModel->GetSnapshot()) slrts.SetNullParameters(nullParams);
RooArgSet altParams(*bModel->GetSnapshot());
if (bModel->GetNuisanceParameters()) altParams.add(*bModel->GetNuisanceParameters());
if (bModel->GetSnapshot()) slrts.SetAltParameters(altParams);
// ratio of profile likelihood - need to pass snapshot for the alt
RatioOfProfiledLikelihoodsTestStat
ropl(*sbModel->GetPdf(), *bModel->GetPdf(), bModel->GetSnapshot());
ropl.SetSubtractMLE(false);
if (testStatType == 11) ropl.SetSubtractMLE(true);
ropl.SetPrintLevel(mPrintLevel);
ropl.SetMinimizer(minimizerType.c_str());
ProfileLikelihoodTestStat profll(*sbModel->GetPdf());
if (testStatType == 3) profll.SetOneSided(true);
if (testStatType == 4) profll.SetSigned(true);
profll.SetMinimizer(minimizerType.c_str());
profll.SetPrintLevel(mPrintLevel);
profll.SetReuseNLL(mOptimize);
slrts.SetReuseNLL(mOptimize);
ropl.SetReuseNLL(mOptimize);
if (mOptimize) {
profll.SetStrategy(0);
ropl.SetStrategy(0);
ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
}
if (mMaxPoi > 0) poi->setMax(mMaxPoi); // increase limit
MaxLikelihoodEstimateTestStat maxll(*sbModel->GetPdf(),*poi);
NumEventsTestStat nevtts;
AsymptoticCalculator::SetPrintLevel(mPrintLevel);
// create the HypoTest calculator class
HypoTestCalculatorGeneric * hc = 0;
if (type == 0) hc = new FrequentistCalculator(*data, *bModel, *sbModel);
else if (type == 1) hc = new HybridCalculator(*data, *bModel, *sbModel);
// else if (type == 2 ) hc = new AsymptoticCalculator(*data, *bModel, *sbModel, false, mAsimovBins);
// else if (type == 3 ) hc = new AsymptoticCalculator(*data, *bModel, *sbModel, true, mAsimovBins); // for using Asimov data generated with nominal values
else if (type == 2 ) hc = new AsymptoticCalculator(*data, *bModel, *sbModel, false );
else if (type == 3 ) hc = new AsymptoticCalculator(*data, *bModel, *sbModel, true ); // for using Asimov data generated with nominal values
else {
Error("StandardHypoTestInvDemo","Invalid - calculator type = %d supported values are only :\n\t\t\t 0 (Frequentist) , 1 (Hybrid) , 2 (Asymptotic) ",type);
return 0;
}
// set the test statistic
TestStatistic * testStat = 0;
if (testStatType == 0) testStat = &slrts;
if (testStatType == 1 || testStatType == 11) testStat = &ropl;
if (testStatType == 2 || testStatType == 3 || testStatType == 4) testStat = &profll;
if (testStatType == 5) testStat = &maxll;
if (testStatType == 6) testStat = &nevtts;
if (testStat == 0) {
Error("StandardHypoTestInvDemo","Invalid - test statistic type = %d supported values are only :\n\t\t\t 0 (SLR) , 1 (Tevatron) , 2 (PLR), 3 (PLR1), 4(MLE)",testStatType);
return 0;
}
ToyMCSampler *toymcs = (ToyMCSampler*)hc->GetTestStatSampler();
if (toymcs && (type == 0 || type == 1) ) {
// look if pdf is number counting or extended
if (sbModel->GetPdf()->canBeExtended() ) {
if (useNumberCounting) Warning("StandardHypoTestInvDemo","Pdf is extended: but number counting flag is set: ignore it ");
}
else {
// for not extended pdf
if (!useNumberCounting ) {
int nEvents = data->numEntries();
Info("StandardHypoTestInvDemo","Pdf is not extended: number of events to generate taken from observed data set is %d",nEvents);
toymcs->SetNEventsPerToy(nEvents);
}
else {
Info("StandardHypoTestInvDemo","using a number counting pdf");
toymcs->SetNEventsPerToy(1);
}
}
toymcs->SetTestStatistic(testStat);
if (data->isWeighted() && !mGenerateBinned) {
Info("StandardHypoTestInvDemo","Data set is weighted, nentries = %d and sum of weights = %8.1f but toy generation is unbinned - it would be faster to set mGenerateBinned to true\n",data->numEntries(), data->sumEntries());
}
toymcs->SetGenerateBinned(mGenerateBinned);
toymcs->SetUseMultiGen(mOptimize);
if (mGenerateBinned && sbModel->GetObservables()->getSize() > 2) {
Warning("StandardHypoTestInvDemo","generate binned is activated but the number of ovservable is %d. Too much memory could be needed for allocating all the bins",sbModel->GetObservables()->getSize() );
}
// set the random seed if needed
if (mRandomSeed >= 0) RooRandom::randomGenerator()->SetSeed(mRandomSeed);
}
// specify if need to re-use same toys
if (reuseAltToys) {
hc->UseSameAltToys();
}
if (type == 1) {
HybridCalculator *hhc = dynamic_cast<HybridCalculator*> (hc);
assert(hhc);
hhc->SetToys(ntoys,ntoys/mNToysRatio); // can use less ntoys for b hypothesis
// remove global observables from ModelConfig (this is probably not needed anymore in 5.32)
bModel->SetGlobalObservables(RooArgSet() );
sbModel->SetGlobalObservables(RooArgSet() );
// check for nuisance prior pdf in case of nuisance parameters
if (bModel->GetNuisanceParameters() || sbModel->GetNuisanceParameters() ) {
// fix for using multigen (does not work in this case)
toymcs->SetUseMultiGen(false);
ToyMCSampler::SetAlwaysUseMultiGen(false);
RooAbsPdf * nuisPdf = 0;
if (nuisPriorName) nuisPdf = w->pdf(nuisPriorName);
// use prior defined first in bModel (then in SbModel)
if (!nuisPdf) {
Info("StandardHypoTestInvDemo","No nuisance pdf given for the HybridCalculator - try to deduce pdf from the model");
if (bModel->GetPdf() && bModel->GetObservables() )
nuisPdf = RooStats::MakeNuisancePdf(*bModel,"nuisancePdf_bmodel");
else
nuisPdf = RooStats::MakeNuisancePdf(*sbModel,"nuisancePdf_sbmodel");
}
if (!nuisPdf ) {
if (bModel->GetPriorPdf()) {
nuisPdf = bModel->GetPriorPdf();
Info("StandardHypoTestInvDemo","No nuisance pdf given - try to use %s that is defined as a prior pdf in the B model",nuisPdf->GetName());
}
else {
Error("StandardHypoTestInvDemo","Cannnot run Hybrid calculator because no prior on the nuisance parameter is specified or can be derived");
return 0;
}
}
assert(nuisPdf);
Info("StandardHypoTestInvDemo","Using as nuisance Pdf ... " );
nuisPdf->Print();
const RooArgSet * nuisParams = (bModel->GetNuisanceParameters() ) ? bModel->GetNuisanceParameters() : sbModel->GetNuisanceParameters();
RooArgSet * np = nuisPdf->getObservables(*nuisParams);
if (np->getSize() == 0) {
Warning("StandardHypoTestInvDemo","Prior nuisance does not depend on nuisance parameters. They will be smeared in their full range");
}
delete np;
hhc->ForcePriorNuisanceAlt(*nuisPdf);
hhc->ForcePriorNuisanceNull(*nuisPdf);
}
}
else if (type == 2 || type == 3) {
if (testStatType == 3) ((AsymptoticCalculator*) hc)->SetOneSided(true);
if (testStatType != 2 && testStatType != 3)
Warning("StandardHypoTestInvDemo","Only the PL test statistic can be used with AsymptoticCalculator - use by default a two-sided PL");
}
else if (type == 0 || type == 1)
((FrequentistCalculator*) hc)->SetToys(ntoys,ntoys/mNToysRatio);
// Get the result
RooMsgService::instance().getStream(1).removeTopic(RooFit::NumIntegration);
HypoTestInverter calc(*hc);
calc.SetConfidenceLevel(0.95);
calc.UseCLs(useCLs);
calc.SetVerbose(true);
// can speed up using proof-lite
if (mUseProof && mNWorkers > 1) {
ProofConfig pc(*w, mNWorkers, "", kFALSE);
toymcs->SetProofConfig(&pc); // enable proof
}
if (npoints > 0) {
if (poimin > poimax) {
// if no min/max given scan between MLE and +4 sigma
poimin = int(poihat);
poimax = int(poihat + 4 * poi->getError());
}
std::cout << "Doing a fixed scan in interval : " << poimin << " , " << poimax << std::endl;
calc.SetFixedScan(npoints,poimin,poimax);
}
else {
//poi->setMax(10*int( (poihat+ 10 *poi->getError() )/10 ) );
std::cout << "Doing an automatic scan in interval : " << poi->getMin() << " , " << poi->getMax() << std::endl;
}
tw.Start();
HypoTestInverterResult * r = calc.GetInterval();
std::cout << "Time to perform limit scan \n";
tw.Print();
if (mRebuild) {
calc.SetCloseProof(1);
tw.Start();
SamplingDistribution * limDist = calc.GetUpperLimitDistribution(true,mNToyToRebuild);
std::cout << "Time to rebuild distributions " << std::endl;
tw.Print();
if (limDist) {
std::cout << "expected up limit " << limDist->InverseCDF(0.5) << " +/- "
<< limDist->InverseCDF(0.16) << " "
<< limDist->InverseCDF(0.84) << "\n";
//update r to a new updated result object containing the rebuilt expected p-values distributions
// (it will not recompute the expected limit)
if (r) delete r; // need to delete previous object since GetInterval will return a cloned copy
r = calc.GetInterval();
}
else
std::cout << "ERROR : failed to re-build distributions " << std::endl;
}
return r;
}
//put very small data entries in a binned dataset to avoid unphysical pdfs, specifically for H->ZZ->4l
RooDataSet* makeData(RooDataSet* orig, RooSimultaneous* simPdf, const RooArgSet* observables, RooRealVar* firstPOI, double mass, double& mu_min)
{
double max_soverb = 0;
mu_min = -10e9;
map<string, RooDataSet*> data_map;
firstPOI->setVal(0);
RooCategory* cat = (RooCategory*)&simPdf->indexCat();
TList* datalist = orig->split(*(RooAbsCategory*)cat, true);
TIterator* dataItr = datalist->MakeIterator();
RooAbsData* ds;
RooRealVar* weightVar = new RooRealVar("weightVar","weightVar",1);
while ((ds = (RooAbsData*)dataItr->Next()))
{
string typeName(ds->GetName());
cat->setLabel(typeName.c_str());
RooAbsPdf* pdf = simPdf->getPdf(typeName.c_str());
cout << "pdf: " << pdf << endl;
RooArgSet* obs = pdf->getObservables(observables);
cout << "obs: " << obs << endl;
RooArgSet obsAndWeight(*obs, *weightVar);
obsAndWeight.add(*cat);
stringstream datasetName;
datasetName << "newData_" << typeName;
RooDataSet* thisData = new RooDataSet(datasetName.str().c_str(),datasetName.str().c_str(), obsAndWeight, WeightVar(*weightVar));
RooRealVar* firstObs = (RooRealVar*)obs->first();
//int ibin = 0;
int nrEntries = ds->numEntries();
for (int ib=0;ib<nrEntries;ib++)
{
const RooArgSet* event = ds->get(ib);
const RooRealVar* thisObs = (RooRealVar*)event->find(firstObs->GetName());
firstObs->setVal(thisObs->getVal());
firstPOI->setVal(0);
double b = pdf->expectedEvents(*firstObs)*pdf->getVal(obs);
firstPOI->setVal(1);
double s = pdf->expectedEvents(*firstObs)*pdf->getVal(obs) - b;
if (s > 0)
{
mu_min = max(mu_min, -b/s);
double soverb = s/b;
if (soverb > max_soverb)
{
max_soverb = soverb;
cout << "Found new max s/b: " << soverb << " in pdf " << pdf->GetName() << " at m = " << thisObs->getVal() << endl;
}
}
if (b == 0 && s != 0)
{
cout << "Expecting non-zero signal and zero bg at m=" << firstObs->getVal() << " in pdf " << pdf->GetName() << endl;
}
if (s+b <= 0)
{
cout << "expecting zero" << endl;
continue;
}
double weight = ds->weight();
if ((typeName.find("ATLAS_H_4mu") != string::npos ||
typeName.find("ATLAS_H_4e") != string::npos ||
typeName.find("ATLAS_H_2mu2e") != string::npos ||
typeName.find("ATLAS_H_2e2mu") != string::npos) && fabs(firstObs->getVal() - mass) < 10 && weight == 0)
{
cout << "adding event: " << firstObs->getVal() << endl;
thisData->add(*event, pow(10., -9.));
}
else
{
//weight = max(pow(10.0, -9), weight);
thisData->add(*event, weight);
}
}
data_map[string(ds->GetName())] = (RooDataSet*)thisData;
}
RooDataSet* newData = new RooDataSet("newData","newData",RooArgSet(*observables, *weightVar),
Index(*cat), Import(data_map), WeightVar(*weightVar));
orig->Print();
newData->Print();
//newData->tree()->Scan("*");
return newData;
}
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 StandardHypoTestDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelSBName = "ModelConfig",
const char* modelBName = "",
const char* dataName = "obsData",
int calcType = 0, // 0 freq 1 hybrid, 2 asymptotic
int testStatType = 3, // 0 LEP, 1 TeV, 2 LHC, 3 LHC - one sided
int ntoys = 5000,
bool useNC = false,
const char * nuisPriorName = 0)
{
/*
Other Parameter to pass in tutorial
apart from standard for filename, ws, modelconfig and data
type = 0 Freq calculator
type = 1 Hybrid calculator
type = 2 Asymptotic calculator
testStatType = 0 LEP
= 1 Tevatron
= 2 Profile Likelihood
= 3 Profile Likelihood one sided (i.e. = 0 if mu < mu_hat)
ntoys: number of toys to use
useNumberCounting: set to true when using number counting events
nuisPriorName: name of prior for the nnuisance. This is often expressed as constraint term in the global model
It is needed only when using the HybridCalculator (type=1)
If not given by default the prior pdf from ModelConfig is used.
extra options are available as global paramwters of the macro. They major ones are:
generateBinned generate binned data sets for toys (default is false) - be careful not to activate with
a too large (>=3) number of observables
nToyRatio ratio of S+B/B toys (default is 2)
printLevel
*/
// disable - can cause some problems
//ToyMCSampler::SetAlwaysUseMultiGen(true);
SimpleLikelihoodRatioTestStat::SetAlwaysReuseNLL(true);
ProfileLikelihoodTestStat::SetAlwaysReuseNLL(true);
RatioOfProfiledLikelihoodsTestStat::SetAlwaysReuseNLL(true);
//RooRandom::randomGenerator()->SetSeed(0);
// to change minimizers
// ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
// ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
// ROOT::Math::MinimizerOptions::SetDefaultTolerance(1);
/////////////////////////////////////////////////////////////
// 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;
}
/////////////////////////////////////////////////////////////
// Tutorial starts here
////////////////////////////////////////////////////////////
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
w->Print();
// get the modelConfig out of the file
ModelConfig* sbModel = (ModelConfig*) w->obj(modelSBName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !sbModel){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
// make b model
ModelConfig* bModel = (ModelConfig*) w->obj(modelBName);
// case of no systematics
// remove nuisance parameters from model
if (noSystematics) {
const RooArgSet * nuisPar = sbModel->GetNuisanceParameters();
if (nuisPar && nuisPar->getSize() > 0) {
std::cout << "StandardHypoTestInvDemo" << " - Switch off all systematics by setting them constant to their initial values" << std::endl;
RooStats::SetAllConstant(*nuisPar);
}
if (bModel) {
const RooArgSet * bnuisPar = bModel->GetNuisanceParameters();
if (bnuisPar)
RooStats::SetAllConstant(*bnuisPar);
}
}
if (!bModel ) {
Info("StandardHypoTestInvDemo","The background model %s does not exist",modelBName);
Info("StandardHypoTestInvDemo","Copy it from ModelConfig %s and set POI to zero",modelSBName);
bModel = (ModelConfig*) sbModel->Clone();
bModel->SetName(TString(modelSBName)+TString("B_only"));
RooRealVar * var = dynamic_cast<RooRealVar*>(bModel->GetParametersOfInterest()->first());
if (!var) return;
double oldval = var->getVal();
var->setVal(0);
//bModel->SetSnapshot( RooArgSet(*var, *w->var("lumi")) );
bModel->SetSnapshot( RooArgSet(*var) );
var->setVal(oldval);
}
if (!sbModel->GetSnapshot() || poiValue > 0) {
Info("StandardHypoTestDemo","Model %s has no snapshot - make one using model poi",modelSBName);
RooRealVar * var = dynamic_cast<RooRealVar*>(sbModel->GetParametersOfInterest()->first());
if (!var) return;
double oldval = var->getVal();
if (poiValue > 0) var->setVal(poiValue);
//sbModel->SetSnapshot( RooArgSet(*var, *w->var("lumi") ) );
sbModel->SetSnapshot( RooArgSet(*var) );
if (poiValue > 0) var->setVal(oldval);
//sbModel->SetSnapshot( *sbModel->GetParametersOfInterest() );
}
// part 1, hypothesis testing
SimpleLikelihoodRatioTestStat * slrts = new SimpleLikelihoodRatioTestStat(*bModel->GetPdf(), *sbModel->GetPdf());
// null parameters must includes snapshot of poi plus the nuisance values
RooArgSet nullParams(*bModel->GetSnapshot());
if (bModel->GetNuisanceParameters()) nullParams.add(*bModel->GetNuisanceParameters());
slrts->SetNullParameters(nullParams);
RooArgSet altParams(*sbModel->GetSnapshot());
if (sbModel->GetNuisanceParameters()) altParams.add(*sbModel->GetNuisanceParameters());
slrts->SetAltParameters(altParams);
ProfileLikelihoodTestStat * profll = new ProfileLikelihoodTestStat(*bModel->GetPdf());
RatioOfProfiledLikelihoodsTestStat *
ropl = new RatioOfProfiledLikelihoodsTestStat(*bModel->GetPdf(), *sbModel->GetPdf(), sbModel->GetSnapshot());
ropl->SetSubtractMLE(false);
if (testStatType == 3) profll->SetOneSidedDiscovery(1);
profll->SetPrintLevel(printLevel);
// profll.SetReuseNLL(mOptimize);
// slrts.SetReuseNLL(mOptimize);
// ropl.SetReuseNLL(mOptimize);
AsymptoticCalculator::SetPrintLevel(printLevel);
HypoTestCalculatorGeneric * hypoCalc = 0;
// note here Null is B and Alt is S+B
if (calcType == 0) hypoCalc = new FrequentistCalculator(*data, *sbModel, *bModel);
else if (calcType == 1) hypoCalc= new HybridCalculator(*data, *sbModel, *bModel);
else if (calcType == 2) hypoCalc= new AsymptoticCalculator(*data, *sbModel, *bModel);
if (calcType == 0)
((FrequentistCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
if (calcType == 1)
((HybridCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
if (calcType == 2 ) {
if (testStatType == 3) ((AsymptoticCalculator*) hypoCalc)->SetOneSidedDiscovery(true);
if (testStatType != 2 && testStatType != 3)
Warning("StandardHypoTestDemo","Only the PL test statistic can be used with AsymptoticCalculator - use by default a two-sided PL");
}
// check for nuisance prior pdf in case of nuisance parameters
if (calcType == 1 && (bModel->GetNuisanceParameters() || sbModel->GetNuisanceParameters() )) {
RooAbsPdf * nuisPdf = 0;
if (nuisPriorName) nuisPdf = w->pdf(nuisPriorName);
// use prior defined first in bModel (then in SbModel)
if (!nuisPdf) {
Info("StandardHypoTestDemo","No nuisance pdf given for the HybridCalculator - try to deduce pdf from the model");
if (bModel->GetPdf() && bModel->GetObservables() )
nuisPdf = RooStats::MakeNuisancePdf(*bModel,"nuisancePdf_bmodel");
else
nuisPdf = RooStats::MakeNuisancePdf(*sbModel,"nuisancePdf_sbmodel");
}
if (!nuisPdf ) {
if (bModel->GetPriorPdf()) {
nuisPdf = bModel->GetPriorPdf();
Info("StandardHypoTestDemo","No nuisance pdf given - try to use %s that is defined as a prior pdf in the B model",nuisPdf->GetName());
}
else {
Error("StandardHypoTestDemo","Cannnot run Hybrid calculator because no prior on the nuisance parameter is specified or can be derived");
return;
}
}
assert(nuisPdf);
Info("StandardHypoTestDemo","Using as nuisance Pdf ... " );
nuisPdf->Print();
const RooArgSet * nuisParams = (bModel->GetNuisanceParameters() ) ? bModel->GetNuisanceParameters() : sbModel->GetNuisanceParameters();
RooArgSet * np = nuisPdf->getObservables(*nuisParams);
if (np->getSize() == 0) {
Warning("StandardHypoTestDemo","Prior nuisance does not depend on nuisance parameters. They will be smeared in their full range");
}
delete np;
((HybridCalculator*)hypoCalc)->ForcePriorNuisanceAlt(*nuisPdf);
((HybridCalculator*)hypoCalc)->ForcePriorNuisanceNull(*nuisPdf);
}
// hypoCalc->ForcePriorNuisanceAlt(*sbModel->GetPriorPdf());
// hypoCalc->ForcePriorNuisanceNull(*bModel->GetPriorPdf());
ToyMCSampler * sampler = (ToyMCSampler *)hypoCalc->GetTestStatSampler();
if (sampler && (calcType == 0 || calcType == 1) ) {
// look if pdf is number counting or extended
if (sbModel->GetPdf()->canBeExtended() ) {
if (useNC) Warning("StandardHypoTestDemo","Pdf is extended: but number counting flag is set: ignore it ");
}
else {
// for not extended pdf
if (!useNC) {
int nEvents = data->numEntries();
Info("StandardHypoTestDemo","Pdf is not extended: number of events to generate taken from observed data set is %d",nEvents);
sampler->SetNEventsPerToy(nEvents);
}
else {
Info("StandardHypoTestDemo","using a number counting pdf");
sampler->SetNEventsPerToy(1);
}
}
if (data->isWeighted() && !generateBinned) {
Info("StandardHypoTestDemo","Data set is weighted, nentries = %d and sum of weights = %8.1f but toy generation is unbinned - it would be faster to set generateBinned to true\n",data->numEntries(), data->sumEntries());
}
if (generateBinned) sampler->SetGenerateBinned(generateBinned);
// set the test statistic
if (testStatType == 0) sampler->SetTestStatistic(slrts);
if (testStatType == 1) sampler->SetTestStatistic(ropl);
if (testStatType == 2 || testStatType == 3) sampler->SetTestStatistic(profll);
}
HypoTestResult * htr = hypoCalc->GetHypoTest();
htr->SetPValueIsRightTail(true);
htr->SetBackgroundAsAlt(false);
htr->Print(); // how to get meaningfull CLs at this point?
delete sampler;
delete slrts;
delete ropl;
delete profll;
if (calcType != 2) {
HypoTestPlot * plot = new HypoTestPlot(*htr,100);
plot->SetLogYaxis(true);
plot->Draw();
}
else {
std::cout << "Asymptotic results " << std::endl;
}
// look at expected significances
// found median of S+B distribution
if (calcType != 2) {
SamplingDistribution * altDist = htr->GetAltDistribution();
HypoTestResult htExp("Expected Result");
htExp.Append(htr);
// find quantiles in alt (S+B) distribution
double p[5];
double q[5];
for (int i = 0; i < 5; ++i) {
double sig = -2 + i;
p[i] = ROOT::Math::normal_cdf(sig,1);
}
std::vector<double> values = altDist->GetSamplingDistribution();
TMath::Quantiles( values.size(), 5, &values[0], q, p, false);
for (int i = 0; i < 5; ++i) {
htExp.SetTestStatisticData( q[i] );
double sig = -2 + i;
std::cout << " Expected p -value and significance at " << sig << " sigma = "
<< htExp.NullPValue() << " significance " << htExp.Significance() << " sigma " << std::endl;
}
}
else {
// case of asymptotic calculator
for (int i = 0; i < 5; ++i) {
double sig = -2 + i;
// sigma is inverted here
double pval = AsymptoticCalculator::GetExpectedPValues( htr->NullPValue(), htr->AlternatePValue(), -sig, false);
std::cout << " Expected p -value and significance at " << sig << " sigma = "
<< pval << " significance " << ROOT::Math::normal_quantile_c(pval,1) << " sigma " << std::endl;
}
}
}
void StandardHistFactoryPlotsWithCategories(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData"){
double nSigmaToVary=5.;
double muVal=0;
bool doFit=false;
// -------------------------------------------------------
// 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;
}
// -------------------------------------------------------
// Tutorial starts here
// -------------------------------------------------------
// 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 use the profile inspector
RooRealVar* obs = (RooRealVar*)mc->GetObservables()->first();
TList* list = new TList();
RooRealVar * firstPOI = dynamic_cast<RooRealVar*>(mc->GetParametersOfInterest()->first());
firstPOI->setVal(muVal);
// firstPOI->setConstant();
if(doFit){
mc->GetPdf()->fitTo(*data);
}
// -------------------------------------------------------
mc->GetNuisanceParameters()->Print("v");
int nPlotsMax = 1000;
cout <<" check expectedData by category"<<endl;
RooDataSet* simData=NULL;
RooSimultaneous* simPdf = NULL;
if(strcmp(mc->GetPdf()->ClassName(),"RooSimultaneous")==0){
cout <<"Is a simultaneous PDF"<<endl;
simPdf = (RooSimultaneous *)(mc->GetPdf());
} else {
cout <<"Is not a simultaneous PDF"<<endl;
}
if(doFit) {
RooCategory* channelCat = (RooCategory*) (&simPdf->indexCat());
TIterator* iter = channelCat->typeIterator() ;
RooCatType* tt = NULL;
tt=(RooCatType*) iter->Next();
RooAbsPdf* pdftmp = ((RooSimultaneous*)mc->GetPdf())->getPdf(tt->GetName()) ;
RooArgSet* obstmp = pdftmp->getObservables(*mc->GetObservables()) ;
obs = ((RooRealVar*)obstmp->first());
RooPlot* frame = obs->frame();
cout <<Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())<<endl;
cout << tt->GetName() << " " << channelCat->getLabel() <<endl;
data->plotOn(frame,MarkerSize(1),Cut(Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())),DataError(RooAbsData::None));
Double_t normCount = data->sumEntries(Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())) ;
pdftmp->plotOn(frame,LineWidth(2.),Normalization(normCount,RooAbsReal::NumEvent)) ;
frame->Draw();
cout <<"expected events = " << mc->GetPdf()->expectedEvents(*data->get()) <<endl;
return;
}
int nPlots=0;
if(!simPdf){
TIterator* it = mc->GetNuisanceParameters()->createIterator();
RooRealVar* var = NULL;
while( (var = (RooRealVar*) it->Next()) != NULL){
RooPlot* frame = obs->frame();
frame->SetYTitle(var->GetName());
data->plotOn(frame,MarkerSize(1));
var->setVal(0);
mc->GetPdf()->plotOn(frame,LineWidth(1.));
var->setVal(1);
mc->GetPdf()->plotOn(frame,LineColor(kRed),LineStyle(kDashed),LineWidth(1));
var->setVal(-1);
mc->GetPdf()->plotOn(frame,LineColor(kGreen),LineStyle(kDashed),LineWidth(1));
list->Add(frame);
var->setVal(0);
}
} else {
RooCategory* channelCat = (RooCategory*) (&simPdf->indexCat());
// TIterator* iter = simPdf->indexCat().typeIterator() ;
TIterator* iter = channelCat->typeIterator() ;
RooCatType* tt = NULL;
while(nPlots<nPlotsMax && (tt=(RooCatType*) iter->Next())) {
cout << "on type " << tt->GetName() << " " << endl;
// Get pdf associated with state from simpdf
RooAbsPdf* pdftmp = simPdf->getPdf(tt->GetName()) ;
// Generate observables defined by the pdf associated with this state
RooArgSet* obstmp = pdftmp->getObservables(*mc->GetObservables()) ;
// obstmp->Print();
obs = ((RooRealVar*)obstmp->first());
TIterator* it = mc->GetNuisanceParameters()->createIterator();
RooRealVar* var = NULL;
while(nPlots<nPlotsMax && (var = (RooRealVar*) it->Next())){
TCanvas* c2 = new TCanvas("c2");
RooPlot* frame = obs->frame();
frame->SetName(Form("frame%d",nPlots));
frame->SetYTitle(var->GetName());
cout <<Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())<<endl;
cout << tt->GetName() << " " << channelCat->getLabel() <<endl;
data->plotOn(frame,MarkerSize(1),Cut(Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())),DataError(RooAbsData::None));
Double_t normCount = data->sumEntries(Form("%s==%s::%s",channelCat->GetName(),channelCat->GetName(),tt->GetName())) ;
if(strcmp(var->GetName(),"Lumi")==0){
cout <<"working on lumi"<<endl;
var->setVal(w->var("nominalLumi")->getVal());
var->Print();
} else{
var->setVal(0);
}
// w->allVars().Print("v");
// mc->GetNuisanceParameters()->Print("v");
// pdftmp->plotOn(frame,LineWidth(2.));
// mc->GetPdf()->plotOn(frame,LineWidth(2.),Slice(*channelCat,tt->GetName()),ProjWData(*data));
//pdftmp->plotOn(frame,LineWidth(2.),Slice(*channelCat,tt->GetName()),ProjWData(*data));
normCount = pdftmp->expectedEvents(*obs);
pdftmp->plotOn(frame,LineWidth(2.),Normalization(normCount,RooAbsReal::NumEvent)) ;
if(strcmp(var->GetName(),"Lumi")==0){
cout <<"working on lumi"<<endl;
var->setVal(w->var("nominalLumi")->getVal()+0.05);
var->Print();
} else{
var->setVal(nSigmaToVary);
}
// pdftmp->plotOn(frame,LineColor(kRed),LineStyle(kDashed),LineWidth(2));
// mc->GetPdf()->plotOn(frame,LineColor(kRed),LineStyle(kDashed),LineWidth(2.),Slice(*channelCat,tt->GetName()),ProjWData(*data));
//pdftmp->plotOn(frame,LineColor(kRed),LineStyle(kDashed),LineWidth(2.),Slice(*channelCat,tt->GetName()),ProjWData(*data));
normCount = pdftmp->expectedEvents(*obs);
pdftmp->plotOn(frame,LineWidth(2.),LineColor(kRed),LineStyle(kDashed),Normalization(normCount,RooAbsReal::NumEvent)) ;
if(strcmp(var->GetName(),"Lumi")==0){
cout <<"working on lumi"<<endl;
var->setVal(w->var("nominalLumi")->getVal()-0.05);
var->Print();
} else{
var->setVal(-nSigmaToVary);
}
// pdftmp->plotOn(frame,LineColor(kGreen),LineStyle(kDashed),LineWidth(2));
// mc->GetPdf()->plotOn(frame,LineColor(kGreen),LineStyle(kDashed),LineWidth(2),Slice(*channelCat,tt->GetName()),ProjWData(*data));
//pdftmp->plotOn(frame,LineColor(kGreen),LineStyle(kDashed),LineWidth(2),Slice(*channelCat,tt->GetName()),ProjWData(*data));
normCount = pdftmp->expectedEvents(*obs);
pdftmp->plotOn(frame,LineWidth(2.),LineColor(kGreen),LineStyle(kDashed),Normalization(normCount,RooAbsReal::NumEvent)) ;
// set them back to normal
if(strcmp(var->GetName(),"Lumi")==0){
cout <<"working on lumi"<<endl;
var->setVal(w->var("nominalLumi")->getVal());
var->Print();
} else{
var->setVal(0);
}
list->Add(frame);
// quit making plots
++nPlots;
frame->Draw();
c2->SaveAs(Form("%s_%s_%s.pdf",tt->GetName(),obs->GetName(),var->GetName()));
delete c2;
}
}
}
// -------------------------------------------------------
// now make plots
TCanvas* c1 = new TCanvas("c1","ProfileInspectorDemo",800,200);
if(list->GetSize()>4){
double n = list->GetSize();
int nx = (int)sqrt(n) ;
int ny = TMath::CeilNint(n/nx);
nx = TMath::CeilNint( sqrt(n) );
c1->Divide(ny,nx);
} else
c1->Divide(list->GetSize());
for(int i=0; i<list->GetSize(); ++i){
c1->cd(i+1);
list->At(i)->Draw();
}
}
void ptBestFit(float BIN_SIZE=5.0,bool BLIND=false,TString MASS,TString NAME)
{
gROOT->ProcessLine(".x ../../common/styleCMSTDR.C");
gSystem->Load("libHiggsAnalysisCombinedLimit.so");
gROOT->ForceStyle();
gStyle->SetOptStat(0);
gStyle->SetOptTitle(0);
gROOT->SetBatch(1);
gStyle->SetPadRightMargin(0.04);
gStyle->SetPadLeftMargin(0.16);
gStyle->SetPadTopMargin(0.06);
gStyle->SetPadBottomMargin(0.10);
gStyle->SetTitleFont(42,"XY");
gStyle->SetTitleSize(0.0475,"XY");
gStyle->SetTitleOffset(0.9,"X");
gStyle->SetTitleOffset(1.5,"Y");
gStyle->SetLabelSize(0.0375,"XY");
RooMsgService::instance().setSilentMode(kTRUE);
for(int i=0;i<2;i++) {
RooMsgService::instance().setStreamStatus(i,kFALSE);
}
float XMIN = 80;
float XMAX = 200;
TFile *f1 = TFile::Open("datacards/datacard_m"+MASS+"_"+NAME+".root");
TFile *f2 = TFile::Open("combine/mlfit.vbfHbb_"+NAME+"_mH"+MASS+".root");
TFile *f3 = TFile::Open("root/sig_shapes_workspace_B80-200.root");
TFile *f4 = TFile::Open("root/data_shapes_workspace_"+NAME+".root");
RooWorkspace *w = (RooWorkspace*)f1->Get("w");
//w->Print();
RooAbsPdf *bkg_model = (RooAbsPdf*)w->pdf("model_s");
RooFitResult *res_s = (RooFitResult*)f2->Get("fit_s");
RooFitResult *res_b = (RooFitResult*)f2->Get("fit_b");
RooRealVar *rFit = dynamic_cast<RooRealVar *>(res_s->floatParsFinal()).find("r");
RooDataSet *data = (RooDataSet*)w->data("data_obs");
int nparS=0,nparB=0;
cout << res_s->floatParsFinal().getSize() << endl;
cout << res_b->floatParsFinal().getSize() << endl;
nparS = res_s->floatParsFinal().getSize();
nparB = res_b->floatParsFinal().getSize();
float chi2sumS = 0.;
float chi2sumB = 0.;
int nparsum = 0;
// if (BLIND) {
// res_b->Print();
// }
// else {
// res_s->Print();
// }
w->allVars().assignValueOnly(res_s->floatParsFinal());
// w->Print();
// w->allVars()->Print();
RooWorkspace *wSig = (RooWorkspace*)f3->Get("w");
RooWorkspace *wDat = (RooWorkspace*)f4->Get("w");
const RooSimultaneous *sim = dynamic_cast<const RooSimultaneous *> (bkg_model);
const RooAbsCategoryLValue &cat = (RooAbsCategoryLValue &) sim->indexCat();
TList *datasets = data->split(cat,true);
TIter next(datasets);
//int count = 0;
for(RooAbsData *ds = (RooAbsData*)next();ds != 0; ds = (RooAbsData*)next()) {
//if (count > 0) return 0;
//count++;
RooAbsPdf *pdfi = sim->getPdf(ds->GetName());
RooArgSet *obs = (RooArgSet*)pdfi->getObservables(ds);
RooRealVar *x = dynamic_cast<RooRealVar *>(obs->first());
RooRealVar *yield_vbf = (RooRealVar*)wSig->var("yield_signalVBF_mass"+MASS+"_"+TString(ds->GetName()));
RooRealVar *yield_gf = (RooRealVar*)wSig->var("yield_signalGF_mass"+MASS+"_"+TString(ds->GetName()));
TString ds_name(ds->GetName());
//----- get the QCD normalization -----------
RooRealVar *qcd_norm_final = dynamic_cast<RooRealVar *>(res_s->floatParsFinal()).find("CMS_vbfbb_qcd_norm_"+ds_name);
RooRealVar *qcd_yield = (RooRealVar*)wDat->var("yield_data_"+ds_name);
float Nqcd = exp(log(1.5)*qcd_norm_final->getVal())*qcd_yield->getVal();
float eNqcd = log(1.5)*qcd_norm_final->getError()*Nqcd;
cout<<"QCD normalization = "<<Nqcd<<" +/- "<<eNqcd<<endl;
TH1 *hCoarse = (TH1*)ds->createHistogram("coarseHisto_"+ds_name,*x);
float norm = hCoarse->Integral();
int rebin = BIN_SIZE/hCoarse->GetBinWidth(1);
hCoarse->Rebin(rebin);
float MIN_VAL = TMath::Max(0.9*hCoarse->GetBinContent(hCoarse->GetMinimumBin()),1.0);
float MAX_VAL = 1.3*hCoarse->GetBinContent(hCoarse->GetMaximumBin());
RooDataHist ds_coarse("ds_coarse_"+ds_name,"ds_coarse_"+ds_name,*x,hCoarse);
TH1F *hBlind = (TH1F*)hCoarse->Clone("blindHisto_"+ds_name);
for(int i=0;i<hBlind->GetNbinsX();i++) {
double x0 = hBlind->GetBinCenter(i+1);
if (x0 > 100 && x0 < 150) {
hBlind->SetBinContent(i+1,0);
hBlind->SetBinError(i+1,0);
}
}
RooDataHist ds_blind("ds_blind_"+ds_name,"ds_blind_"+ds_name,*x,hBlind);
RooHist *hresid,*hresid0;
RooPlot *frame1 = x->frame();
RooPlot *frame2 = x->frame();
if (BLIND) {
//cout << "Blind case: " << ds_coarse.GetName() << endl;
ds_coarse.plotOn(frame1,LineColor(0),MarkerColor(0));
pdfi->plotOn(frame1,Components("shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name),VisualizeError(*res_s,1,kTRUE),FillColor(0),MoveToBack());
pdfi->plotOn(frame1,Components("shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name),LineWidth(2),LineStyle(3));
ds_blind.plotOn(frame1);
hresid = frame1->residHist();
frame2->addPlotable(hresid,"pE1");
}
else {
//cout << "Non-blind case: " << ds_coarse.GetName() << endl;
ds_coarse.plotOn(frame1);
pdfi->plotOn(frame1);
//cout << pdfi->getParameters(ds_coarse)->selectByAttrib("Constant",kFALSE)->getSize() << endl;
cout<<"chi2/ndof (bkg+sig) = "<<frame1->chiSquare()<<endl;
cout << ds_coarse.numEntries() << endl;
chi2sumS += frame1->chiSquare()*ds_coarse.numEntries();
nparsum += ds_coarse.numEntries();
//hresid0 = frame1->residHist();
//pdfi->plotOn(frame1,VisualizeError(*res_s,1,kTRUE),FillColor(0),MoveToBack());
pdfi->plotOn(frame1,Components("shapeBkg_qcd_"+ds_name),LineWidth(2),LineStyle(5),LineColor(kGreen+2));
pdfi->plotOn(frame1,Components("shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name),LineWidth(2),LineStyle(2),LineColor(kBlack));
cout<<"chi2/ndof (bkg) = "<<frame1->chiSquare()<<endl;
chi2sumB += frame1->chiSquare()*ds_coarse.numEntries();
pdfi->plotOn(frame1,Components("shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name),LineWidth(2),LineStyle(2),LineColor(kBlack),VisualizeError(*res_s,1,kTRUE),FillColor(0),MoveToBack());
hresid = frame1->residHist();
frame2->addPlotable(hresid,"pE1");
float yield_sig = rFit->getValV()*(yield_vbf->getValV()+yield_gf->getValV());
RooAbsPdf *signal_pdf = (RooAbsPdf*)w->pdf("shapeSig_qqH_"+ds_name);
signal_pdf->plotOn(frame2,LineWidth(2),LineColor(kRed),Normalization(yield_sig,RooAbsReal::NumEvent),MoveToBack());
}
// hresid0->Print();
// hresid->Print();
// double x2,y2;
// for (int i=0; i<3; ++i) {
// hresid0->GetPoint(i,x2,y2);
// cout << "BKG+SIG\t" << x2 << "\t" << y2 << endl;
// hresid->GetPoint(i,x2,y2);
// cout << "BKG\t" << x2 << "\t" << y2 << endl;
// ds_coarse.get(i);
// cout << ds_coarse.weightError(RooAbsData::SumW2) << endl;
// cout << endl;
// }
TCanvas* canFit = new TCanvas("Higgs_fit_"+ds_name,"Higgs_fit_"+ds_name,900,750);
canFit->cd(1)->SetBottomMargin(0.4);
frame1->SetMinimum(MIN_VAL);
frame1->SetMaximum(MAX_VAL);
frame1->GetYaxis()->SetNdivisions(510);
frame1->GetXaxis()->SetTitleSize(0);
frame1->GetXaxis()->SetLabelSize(0);
frame1->GetYaxis()->SetTitle(TString::Format("Events / %1.1f GeV",BIN_SIZE));
frame1->Draw();
gPad->Update();
TList *list = (TList*)gPad->GetListOfPrimitives();
//list->Print();
TH1F *hUncH = new TH1F("hUncH"+ds_name,"hUncH"+ds_name,(XMAX-XMIN)/BIN_SIZE,XMIN,XMAX);
TH1F *hUncL = new TH1F("hUncL"+ds_name,"hUncL"+ds_name,(XMAX-XMIN)/BIN_SIZE,XMIN,XMAX);
TH1F *hUnc2H = new TH1F("hUnc2H"+ds_name,"hUnc2H"+ds_name,(XMAX-XMIN)/BIN_SIZE,XMIN,XMAX);
TH1F *hUnc2L = new TH1F("hUnc2L"+ds_name,"hUnc2L"+ds_name,(XMAX-XMIN)/BIN_SIZE,XMIN,XMAX);
TH1F *hUncC = new TH1F("hUncC"+ds_name,"hUncC"+ds_name,(XMAX-XMIN)/BIN_SIZE,XMIN,XMAX);
RooCurve *errorBand,*gFit,*gQCDFit,*gBkgFit;
//list->Print();
if (BLIND) {
errorBand = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]_errorband_Comp[shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name+"]");
gFit = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]"+"_Comp[shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name+"]");
}
else {
//errorBand = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]_errorband");
errorBand = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]_errorband_Comp[shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name+"]");
gFit = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]");
}
gQCDFit = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]"+"_Comp[shapeBkg_qcd_"+ds_name+"]");
gBkgFit = (RooCurve*)list->FindObject("pdf_bin"+ds_name+"_Norm[mbbReg_"+ds_name+"]"+"_Comp[shapeBkg_qcd_"+ds_name+",shapeBkg_top_"+ds_name+",shapeBkg_zjets_"+ds_name+"]");
for(int i=0;i<hUncH->GetNbinsX();i++) {
double x0 = hUncH->GetBinCenter(i+1);
double e1 = fabs(errorBand->Eval(x0)-gBkgFit->Eval(x0));
//double e1 = fabs(errorBand->Eval(x0)-gFit->Eval(x0));
double e2 = eNqcd/hUncH->GetNbinsX();
hUncH->SetBinContent(i+1,sqrt(pow(e2,2)+pow(e1,2)));
hUnc2H->SetBinContent(i+1,2*sqrt(pow(e2,2)+pow(e1,2)));
hUncL->SetBinContent(i+1,-sqrt(pow(e2,2)+pow(e1,2)));
hUnc2L->SetBinContent(i+1,-2*sqrt(pow(e2,2)+pow(e1,2)));
hUncC->SetBinContent(i+1,0.);
}
TPad* pad = new TPad("pad", "pad", 0., 0., 1., 1.);
pad->SetTopMargin(0.63);
pad->SetFillColor(0);
pad->SetFillStyle(0);
pad->Draw();
pad->cd(0);
hUnc2H->GetXaxis()->SetTitle("m_{bb} (GeV)");
hUnc2H->GetYaxis()->SetTitle("Data - Bkg");
//hUnc2H->GetYaxis()->SetTitle("Data - Fit");
double YMAX = 1.1*frame2->GetMaximum();
double YMIN = -1.1*frame2->GetMaximum();
hUnc2H->GetYaxis()->SetRangeUser(YMIN,YMAX);
hUnc2H->GetYaxis()->SetNdivisions(507);
// hUnc2H->GetXaxis()->SetTitleOffset(0.9);
// hUnc2H->GetYaxis()->SetTitleOffset(1.0);
hUnc2H->GetYaxis()->SetTickLength(0.0);
// hUnc2H->GetYaxis()->SetTitleSize(0.05);
// hUnc2H->GetYaxis()->SetLabelSize(0.04);
hUnc2H->GetYaxis()->CenterTitle(kTRUE);
hUnc2H->SetFillColor(kGreen);
hUnc2L->SetFillColor(kGreen);
hUncH->SetFillColor(kYellow);
hUncL->SetFillColor(kYellow);
hUncC->SetLineColor(kBlack);
hUncC->SetLineStyle(7);
hUnc2H->Draw("HIST");
hUnc2L->Draw("same HIST");
hUncH->Draw("same HIST");
hUncL->Draw("same HIST");
hUncC->Draw("same HIST");
frame2->GetYaxis()->SetTickLength(0.03/0.4);
frame2->Draw("same");
TList *list1 = (TList*)gPad->GetListOfPrimitives();
//list1->Print();
RooCurve *gSigFit = (RooCurve*)list1->FindObject("shapeSig_qqH_"+ds_name+"_Norm[mbbReg_"+ds_name+"]");
TLegend *leg = new TLegend(0.70,0.61,0.94,1.-gStyle->GetPadTopMargin()-0.01);
leg->SetTextFont(42);
leg->SetFillStyle(-1);
//leg->SetHeader(ds_name+" (m_{H}="+MASS+")");
leg->SetHeader(TString::Format("Category %d",atoi(ds_name(3,1).Data())+1));
leg->AddEntry(hBlind,"Data","P");
if (!BLIND) {
leg->AddEntry(gSigFit,"Fitted signal","L");
}
TLine *gEmpty = new TLine(0.0,0.0,0.0,0.0);
gEmpty->SetLineWidth(0);
TLegendEntry *l1 = leg->AddEntry(gEmpty,"(m_{H} = "+MASS+" GeV)","");
l1->SetTextSize(0.038*0.97*0.85);
leg->AddEntry(gFit,"Bkg. + signal","L");
leg->AddEntry(gBkgFit,"Bkg.","L");
leg->AddEntry(gQCDFit,"QCD","L");
leg->AddEntry(hUnc2H,"2#sigma bkg. unc.","F");
leg->AddEntry(hUncH,"1#sigma bkg. unc.","F");
leg->SetFillColor(0);
leg->SetBorderSize(0);
leg->SetTextFont(42);
leg->SetTextSize(0.038*0.98);
leg->Draw();
leg->SetY1(leg->GetY2()-leg->GetNRows()*0.045*0.96);
TPaveText *paveCMS = new TPaveText(gStyle->GetPadLeftMargin()+0.02,0.7,gStyle->GetPadLeftMargin()+0.15,1.-gStyle->GetPadTopMargin()-0.01,"NDC");
paveCMS->SetTextFont(62);
paveCMS->SetTextSize(gStyle->GetPadTopMargin()*3./4.);
paveCMS->SetBorderSize(0);
paveCMS->SetFillStyle(-1);
paveCMS->SetTextAlign(12);
paveCMS->AddText("CMS");
paveCMS->Draw();
gPad->Update();
paveCMS->SetY1NDC(paveCMS->GetY2NDC()-paveCMS->GetListOfLines()->GetSize()*gStyle->GetPadTopMargin());
TPaveText *paveLumi = new TPaveText(0.5,1.-gStyle->GetPadTopMargin(),0.98,1.00,"NDC");
paveLumi->SetTextFont(42);
paveLumi->SetTextSize(gStyle->GetPadTopMargin()*3./4.);
paveLumi->SetBorderSize(0);
paveLumi->SetFillStyle(-1);
paveLumi->SetTextAlign(32);
paveLumi->AddText(TString::Format("%.1f fb^{-1} (8TeV)",(atoi(ds_name(3,1).Data())<4 ? 19.8 : 18.3)).Data());//+ 18.2 ;
paveLumi->Draw();
TString path=".";
//TString path="BiasV10_limit_BRN5p4_dX0p1_B80-200_CAT0-6/output/";
system(TString::Format("[ ! -d %s/plot ] && mkdir %s/plot",path.Data(),path.Data()).Data());
system(TString::Format("[ ! -d %s/plot/fits ] && mkdir %s/plot/fits",path.Data(),path.Data()).Data());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s.pdf",path.Data(),MASS.Data(),ds_name.Data()).Data());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s.png",path.Data(),MASS.Data(),ds_name.Data()).Data());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s.eps",path.Data(),MASS.Data(),ds_name.Data()).Data());
TText *l = (TText*)paveCMS->AddText("Preliminary");
l->SetTextFont(52);
paveCMS->Draw();
gPad->Update();
paveCMS->SetY1NDC(paveCMS->GetY2NDC()-paveCMS->GetListOfLines()->GetSize()*gStyle->GetPadTopMargin());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s_prelim.pdf",path.Data(),MASS.Data(),ds_name.Data()).Data());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s_prelim.png",path.Data(),MASS.Data(),ds_name.Data()).Data());
canFit->SaveAs(TString::Format("%s/plot/fits/Fit_mH%s_%s_prelim.eps",path.Data(),MASS.Data(),ds_name.Data()).Data());
delete ds;
}
cout << "chi2sumS: " << chi2sumS << endl;
cout << "chi2sumB: " << chi2sumB << endl;
cout << "nparS: " << nparS << endl;
cout << "nparB: " << nparB << endl;
cout << "nbinsum: " << nparsum << endl;
cout << "chi2sumS/(nbinsum - nparS): " << chi2sumS / (float)(nparsum - nparS) << endl;
cout << "chi2sumB/(nbinsum - nparB): " << chi2sumB / (float)(nparsum - nparB) << endl;
delete datasets;
}
