// 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;
}
示例#2
0
void splitws(string inFolderName, double mass, string channel) {
  cout << "Splitting workspace in " << channel << endl;

  int flatInterpCode = 4;
  int shapeInterpCode = 4;

  bool do2011 = 0;

  if (inFolderName.find("2011") != string::npos) do2011 = 1;

  bool conditionalAsimov = 0;
  bool doData = 1;
  //if (inFolderName.find("_blind_") != string::npos) {
    //conditionalAsimov = 0;
  //}
  //else {
    //conditionalAsimov = 1;
  //}

  set<string> channelNames;

  if (channel == "01j") {
    channelNames.insert("em_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));

    channelNames.insert("em_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "0j") {
    channelNames.insert("em_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));
  }
  else if (channel == "1j") {
    channelNames.insert("em_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "OF01j") {
    channelNames.insert("em_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_sscr_0j"+string(!do2011?"_2012":""));

    channelNames.insert("em_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_sscr_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "OF0j") {
    channelNames.insert("em_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_sscr_0j"+string(!do2011?"_2012":""));
  }
  else if (channel == "OF1j") {
    channelNames.insert("em_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_sscr_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "SF01j") {
    channelNames.insert("SF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));

    channelNames.insert("SF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "SF0j") {
    channelNames.insert("SF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));
  }
  else if (channel == "SF1j") {
    channelNames.insert("SF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));
  }
  else if (channel == "2j") {
    channelNames.insert("em_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("ee_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_topbox_2j"+string(!do2011?"_2012":""));
  }
  else if (channel == "OF2j") {
    channelNames.insert("em_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_topbox_2j"+string(!do2011?"_2012":""));
  }
  else if (channel == "SF2j") {
    channelNames.insert("ee_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_topbox_2j"+string(!do2011?"_2012":""));
  }
  else if (channel == "OF") {
    channelNames.insert("em_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_0j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));

    channelNames.insert("em_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("em_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike1_1j"+string(!do2011?"_2012":""));
    channelNames.insert("me_signalLike2_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));

    channelNames.insert("em_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_topbox_2j"+string(!do2011?"_2012":""));
  }
  else if (channel == "SF") {
    channelNames.insert("SF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_0j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_0j"+string(!do2011?"_2012":""));

    channelNames.insert("SF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_AfrecSR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_ASR_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CfrecZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_CZpeak_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_mainControl_1j"+string(!do2011?"_2012":""));
    channelNames.insert("OF_topbox_1j"+string(!do2011?"_2012":""));

    channelNames.insert("ee_signalLike1_2j"+string(!do2011?"_2012":""));
    channelNames.insert("SF_topbox_2j"+string(!do2011?"_2012":""));
  }
  else {
    cout << "Channel " << channel << " not defined. Please check!" << endl;
    exit(1);
  }

  // bool fix = 1;
  stringstream inFileName;

  inFileName << "workspaces/" << inFolderName << "/" << mass << ".root";
  TFile f(inFileName.str().c_str());
  
  RooWorkspace* w = (RooWorkspace*)f.Get("combWS");
  if (!w) w = (RooWorkspace*)f.Get("combined");
  
  RooDataSet* data = (RooDataSet*)w->data("combData");
  if (!data) data = (RooDataSet*)w->data("obsData");
  
  ModelConfig* mc = (ModelConfig*)w->obj("ModelConfig");
  
  RooRealVar* weightVar = w->var("weightVar");
  
  RooRealVar* mu = (RooRealVar*)mc->GetParametersOfInterest()->first();
  if (!mu) mu = w->var("SigXsecOverSM");

  const RooArgSet* mc_obs = mc->GetObservables();
  const RooArgSet* mc_nuis = mc->GetNuisanceParameters();
  const RooArgSet* mc_globs = mc->GetGlobalObservables();
  const RooArgSet* mc_poi = mc->GetParametersOfInterest();

  RooArgSet nuis = *mc_nuis;
  RooArgSet antiNuis = *mc_nuis;

  RooArgSet globs = *mc_globs;
  RooArgSet antiGlobs = *mc_globs;

  RooArgSet allParams;

  RooSimultaneous* simPdf = (RooSimultaneous*)mc->GetPdf();
  RooCategory* cat = (RooCategory*)&simPdf->indexCat();

  RooArgSet nuis_tmp = nuis;
  RooArgSet fullConstraints = *simPdf->getAllConstraints(*mc_obs,nuis_tmp,false);

  vector<string> foundChannels;
  vector<string> skippedChannels;  

  cout << "Getting constraints" << endl;
  map<string, RooDataSet*> data_map;
  map<string, RooAbsPdf*> pdf_map;
  RooCategory* decCat = new RooCategory("dec_channel","dec_channel");
  // int i = 0;
  TIterator* catItr = cat->typeIterator();
  RooCatType* type;
  RooArgSet allConstraints;
  while ((type = (RooCatType*)catItr->Next())) {
    RooAbsPdf* pdf =  simPdf->getPdf(type->GetName());

    string typeName(type->GetName());
    if (channelNames.size() && channelNames.find(typeName) == channelNames.end())  {
      skippedChannels.push_back(typeName);
      continue;
    }
    cout << "On channel " << type->GetName() << endl;
    foundChannels.push_back(typeName);

    decCat->defineType(type->GetName());
    // pdf->getParameters(*data)->Print("v");

    RooArgSet nuis_tmp1 = nuis;
    RooArgSet nuis_tmp2 = nuis;
    RooArgSet* constraints = pdf->getAllConstraints(*mc_obs, nuis_tmp1, true);
    constraints->Print();
    allConstraints.add(*constraints);
  }

  catItr->Reset();

  while ((type = (RooCatType*)catItr->Next())) {
    RooAbsPdf* pdf =  simPdf->getPdf(type->GetName());

    string typeName(type->GetName());
    cout << "Considering type " << typeName << endl;
    if (channelNames.size() && channelNames.find(typeName) == channelNames.end()) continue;
    cout << "On channel " << type->GetName() << endl;

    RooArgSet nuis_tmp1 = nuis;
    RooArgSet nuis_tmp2 = nuis;
    RooArgSet* constraints = pdf->getAllConstraints(*mc_obs, nuis_tmp1, true);

    cout << "Adding pdf to map: " << typeName << " = " << pdf->GetName() << endl;
    pdf_map[typeName] = pdf;

    RooProdPdf prod("prod","prod",*constraints);

    RooArgSet* params = pdf->getParameters(*data);
    antiNuis.remove(*params);
    antiGlobs.remove(*params);

    allParams.add(*params);
    // cout << type->GetName() << endl;
  }
  // return;

  RooArgSet decNuis;
  TIterator* nuiItr = mc_nuis->createIterator();
  TIterator* parItr = allParams.createIterator();
  RooAbsArg* nui, *par;
  while ((par = (RooAbsArg*)parItr->Next())) {
    nuiItr->Reset();
    while ((nui = (RooAbsArg*)nuiItr->Next())) {
      if (par == nui) decNuis.add(*nui);
    }
  }

  RooArgSet decGlobs;
  TIterator* globItr = mc_globs->createIterator();
  parItr->Reset();
  RooAbsArg* glob;
  while ((par = (RooAbsArg*)parItr->Next())) {
    globItr->Reset();
    while ((glob = (RooAbsArg*)globItr->Next())) {
      if (par == glob) decGlobs.add(*glob);
    }
  }

  // antiNuis.Print();

  // nuis.Print();
  // globs.Print();

  // i = 0;
  TList* datalist = data->split(*cat, true);
  TIterator* dataItr = datalist->MakeIterator();
  RooAbsData* ds;
  while ((ds = (RooAbsData*)dataItr->Next())) {
    string typeName(ds->GetName());
    if (channelNames.size() && channelNames.find(typeName) == channelNames.end()) continue;

    cout << "Adding dataset to map: " << ds->GetName() << endl;
    data_map[string(ds->GetName())] = (RooDataSet*)ds;

    cout << ds->GetName() << endl;
  }

  RooSimultaneous* decPdf = new RooSimultaneous("decPdf","decPdf",pdf_map,*decCat); 
  RooArgSet decObs = *decPdf->getObservables(data);
  // decObs.add(*(RooAbsArg*)weightVar);
  decObs.add(*(RooAbsArg*)decCat);
  decObs.Print();

  nuis.remove(antiNuis);
  globs.remove(antiGlobs);
  // nuis.Print("v");

  RooDataSet* decData = new RooDataSet("obsData","obsData",RooArgSet(decObs,*(RooAbsArg*)weightVar),Index(*decCat),Import(data_map),WeightVar(*weightVar));

  decData->Print();

  RooArgSet poi(*(RooAbsArg*)mu);
  RooWorkspace decWS("combined");
  ModelConfig decMC("ModelConfig",&decWS);
  decMC.SetPdf(*decPdf);
  decMC.SetObservables(decObs);
  decMC.SetNuisanceParameters(decNuis);
  decMC.SetGlobalObservables(decGlobs);
  decMC.SetParametersOfInterest(poi);

  decMC.Print();
  decWS.import(*decPdf);
  decWS.import(decMC);
  decWS.import(*decData);
  // decWS.Print();

  ModelConfig* mcInWs = (ModelConfig*)decWS.obj("ModelConfig");
  decPdf = (RooSimultaneous*)mcInWs->GetPdf();

  // setup(mcInWs);
  // return;

  mcInWs->GetNuisanceParameters()->Print("v");
  mcInWs->GetGlobalObservables()->Print("v");
  // decData->tree()->Scan("*");

  // Make asimov data
  RooArgSet funcs = decWS.allFunctions();
  TIterator* it = funcs.createIterator();
  TObject* tempObj = 0;
  while((tempObj=it->Next()))
  {
    FlexibleInterpVar* flex = dynamic_cast<FlexibleInterpVar*>(tempObj);
    if(flex) {
      flex->setAllInterpCodes(flatInterpCode);
    }
    PiecewiseInterpolation* piece = dynamic_cast<PiecewiseInterpolation*>(tempObj);
    if(piece) {
      piece->setAllInterpCodes(shapeInterpCode);
    }
  }

  RooDataSet* dataInWs = (RooDataSet*)decWS.data("obsData");
  makeAsimovData(mcInWs, conditionalAsimov && doData, &decWS, mcInWs->GetPdf(), dataInWs, 0);
  makeAsimovData(mcInWs, conditionalAsimov && doData, &decWS, mcInWs->GetPdf(), dataInWs, 1);
  makeAsimovData(mcInWs, conditionalAsimov && doData, &decWS, mcInWs->GetPdf(), dataInWs, 2);

  system(("mkdir -vp workspaces/"+inFolderName+"_"+channel).c_str());
  stringstream outFileName;
  outFileName << "workspaces/" << inFolderName << "_" << channel << "/" << mass << ".root";
  cout << "Exporting" << endl;

  decWS.writeToFile(outFileName.str().c_str());

  cout << "\nIncluded the following channels: " << endl;
  for (int i=0;i<(int)foundChannels.size();i++) {
    cout << "-> " << foundChannels[i] << endl;
  }

  cout << "\nSkipping the following channels: " << endl;
  
  for (int i=0;i<(int)skippedChannels.size();i++) {
    cout << "-> " << skippedChannels[i] << endl;
  }

  cout << "Done" << endl;

  // decPdf->fitTo(*decData, Hesse(0), Minos(0), PrintLevel(0));
}
示例#3
0
void compute_p0(const char* inFileName,
	    const char* wsName = "combined",
	    const char* modelConfigName = "ModelConfig",
	    const char* dataName = "obsData",
	    const char* asimov1DataName = "asimovData_1",
	    const char* conditional1Snapshot = "conditionalGlobs_1",
	    const char* nominalSnapshot = "nominalGlobs",
	    string smass = "130",
	    string folder = "test")
{
  double mass;
  stringstream massStr;
  massStr << smass;
  massStr >> mass;

  double mu_profile_value = 1; // mu value to profile the obs data at wbefore generating the expected
  bool doConditional      = 1; // do conditional expected data
  bool remakeData         = 0; // handle unphysical pdf cases in H->ZZ->4l
  bool doUncap            = 1; // uncap p0
  bool doInj              = 0; // setup the poi for injection study (zero is faster if you're not)
  bool doObs              = 1; // compute median significance
  bool doMedian           = 1; // compute observed significance

  TStopwatch timer;
  timer.Start();

  TFile f(inFileName);
  RooWorkspace* ws = (RooWorkspace*)f.Get(wsName);
  if (!ws)
  {
    cout << "ERROR::Workspace: " << wsName << " doesn't exist!" << endl;
    return;
  }
  ModelConfig* mc = (ModelConfig*)ws->obj(modelConfigName);
  if (!mc)
  {
    cout << "ERROR::ModelConfig: " << modelConfigName << " doesn't exist!" << endl;
    return;
  }
  RooDataSet* data = (RooDataSet*)ws->data(dataName);
  if (!data)
  {
    cout << "ERROR::Dataset: " << dataName << " doesn't exist!" << endl;
    return;
  }

  mc->GetNuisanceParameters()->Print("v");

  ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
  ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
  ROOT::Math::MinimizerOptions::SetDefaultPrintLevel(1);
  cout << "Setting max function calls" << endl;

  ws->loadSnapshot("conditionalNuis_0");
  RooArgSet nuis(*mc->GetNuisanceParameters());

  RooRealVar* mu = (RooRealVar*)mc->GetParametersOfInterest()->first();

  RooAbsPdf* pdf = mc->GetPdf();

  string condSnapshot(conditional1Snapshot);
  RooArgSet nuis_tmp2 = *mc->GetNuisanceParameters();
  RooNLLVar* obs_nll = doObs ? (RooNLLVar*)pdf->createNLL(*data, Constrain(nuis_tmp2)) : NULL;

  RooDataSet* asimovData1 = (RooDataSet*)ws->data(asimov1DataName);
  RooRealVar* emb = (RooRealVar*)mc->GetNuisanceParameters()->find("ATLAS_EMB");
  if (!asimovData1 || (string(inFileName).find("ic10") != string::npos && emb))
  {
    if (emb) emb->setVal(0.7);
    cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
    string mu_str, mu_prof_str;
    asimovData1 = makeAsimovData(mc, doConditional, ws, obs_nll, 1, &mu_str, &mu_prof_str, mu_profile_value, true);
    condSnapshot="conditionalGlobs"+mu_prof_str;
  }
  
  if (!doUncap) mu->setRange(0, 40);
  else mu->setRange(-40, 40);

  RooAbsPdf* pdf = mc->GetPdf();

  RooArgSet nuis_tmp1 = *mc->GetNuisanceParameters();
  RooNLLVar* asimov_nll = (RooNLLVar*)pdf->createNLL(*asimovData1, Constrain(nuis_tmp1));

  //do asimov
  mu->setVal(1);
  mu->setConstant(0);
  if (!doInj) mu->setConstant(1);

  int status,sign;
  double med_sig=0,obs_sig=0,asimov_q0=0,obs_q0=0;

  if (doMedian)
  {
    ws->loadSnapshot(condSnapshot.c_str());
    if (doInj) ws->loadSnapshot("conditionalNuis_inj");
    else ws->loadSnapshot("conditionalNuis_1");
    mc->GetGlobalObservables()->Print("v");
    mu->setVal(0);
    mu->setConstant(1);
    status = minimize(asimov_nll, ws);
    if (status < 0) 
    {
      cout << "Retrying with conditional snapshot at mu=1" << endl;
      ws->loadSnapshot("conditionalNuis_0");
      status = minimize(asimov_nll, ws);
      if (status >= 0) cout << "Success!" << endl;
    }
    double asimov_nll_cond = asimov_nll->getVal();

    mu->setVal(1);
    if (doInj) ws->loadSnapshot("conditionalNuis_inj");
    else ws->loadSnapshot("conditionalNuis_1");
    if (doInj) mu->setConstant(0);
    status = minimize(asimov_nll, ws);
    if (status < 0) 
    {
      cout << "Retrying with conditional snapshot at mu=1" << endl;
      ws->loadSnapshot("conditionalNuis_0");
      status = minimize(asimov_nll, ws);
      if (status >= 0) cout << "Success!" << endl;
    }

    double asimov_nll_min = asimov_nll->getVal();
    asimov_q0 = 2*(asimov_nll_cond - asimov_nll_min);
    if (doUncap && mu->getVal() < 0) asimov_q0 = -asimov_q0;

    sign = int(asimov_q0 != 0 ? asimov_q0/fabs(asimov_q0) : 0);
    med_sig = sign*sqrt(fabs(asimov_q0));

    ws->loadSnapshot(nominalSnapshot);
  }

  if (doObs)
  {

    ws->loadSnapshot("conditionalNuis_0");
    mu->setVal(0);
    mu->setConstant(1);
    status = minimize(obs_nll, ws);
    if (status < 0) 
    {
      cout << "Retrying with conditional snapshot at mu=1" << endl;
      ws->loadSnapshot("conditionalNuis_0");
      status = minimize(obs_nll, ws);
      if (status >= 0) cout << "Success!" << endl;
    }
    double obs_nll_cond = obs_nll->getVal();

    mu->setConstant(0);
    status = minimize(obs_nll, ws);
    if (status < 0) 
    {
      cout << "Retrying with conditional snapshot at mu=1" << endl;
      ws->loadSnapshot("conditionalNuis_0");
      status = minimize(obs_nll, ws);
      if (status >= 0) cout << "Success!" << endl;
    }

    double obs_nll_min = obs_nll->getVal();



    obs_q0 = 2*(obs_nll_cond - obs_nll_min);
    if (doUncap && mu->getVal() < 0) obs_q0 = -obs_q0;

    sign = int(obs_q0 == 0 ? 0 : obs_q0 / fabs(obs_q0));
    if (!doUncap && (obs_q0 < 0 && obs_q0 > -0.1 || mu->getVal() < 0.001)) obs_sig = 0; 
    else obs_sig = sign*sqrt(fabs(obs_q0));
  }

  // Report results
  cout << "obs: " << obs_sig << endl;

  cout << "Observed significance: " << obs_sig << endl;
  cout << "Corresponding to a p-value of " << (1-ROOT::Math::gaussian_cdf( obs_sig )) << endl;
  if (med_sig)
  {
    cout << "Median test stat val: " << asimov_q0 << endl;
    cout << "Median significance:   " << med_sig << endl;
  }


  f.Close();

  stringstream fileName;
  fileName << "root-files/" << folder << "/" << mass << ".root";
  system(("mkdir -vp root-files/" + folder).c_str());
  TFile f2(fileName.str().c_str(),"recreate");

  TH1D* h_hypo = new TH1D("hypo","hypo",2,0,2);
  h_hypo->SetBinContent(1, obs_sig);
  h_hypo->SetBinContent(2, med_sig);

  f2.Write();
  f2.Close();

  timer.Stop();
  timer.Print();
  
}
void OneSidedFrequentistUpperLimitWithBands(const char* infile = "",
                                            const char* workspaceName = "combined",
                                            const char* modelConfigName = "ModelConfig",
                                            const char* dataName = "obsData") {



   double confidenceLevel=0.95;
   int nPointsToScan = 20;
   int nToyMC = 200;

   // -------------------------------------------------------
   // First part is just to access a user-defined file
   // or create the standard example file if it doesn't exist
   const char* filename = "";
   if (!strcmp(infile,"")) {
      filename = "results/example_combined_GaussExample_model.root";
      bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
      // if file does not exists generate with histfactory
      if (!fileExist) {
#ifdef _WIN32
         cout << "HistFactory file cannot be generated on Windows - exit" << endl;
         return;
#endif
         // Normally this would be run on the command line
         cout <<"will run standard hist2workspace example"<<endl;
         gROOT->ProcessLine(".! prepareHistFactory .");
         gROOT->ProcessLine(".! hist2workspace config/example.xml");
         cout <<"\n\n---------------------"<<endl;
         cout <<"Done creating example input"<<endl;
         cout <<"---------------------\n\n"<<endl;
      }

   }
   else
      filename = infile;

   // Try to open the file
   TFile *file = TFile::Open(filename);

   // if input file was specified byt not found, quit
   if(!file ){
      cout <<"StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
      return;
   }


   // -------------------------------------------------------
   // Now get the data and workspace

   // get the workspace out of the file
   RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
   if(!w){
      cout <<"workspace not found" << endl;
      return;
   }

   // get the modelConfig out of the file
   ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);

   // get the modelConfig out of the file
   RooAbsData* data = w->data(dataName);

   // make sure ingredients are found
   if(!data || !mc){
      w->Print();
      cout << "data or ModelConfig was not found" <<endl;
      return;
   }

   // -------------------------------------------------------
   // Now get the POI for convenience
   // you may want to adjust the range of your POI

   RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
   /*  firstPOI->setMin(0);*/
   /*  firstPOI->setMax(10);*/

   // --------------------------------------------
   // Create and use the FeldmanCousins tool
   // to find and plot the 95% confidence interval
   // on the parameter of interest as specified
   // in the model config
   // REMEMBER, we will change the test statistic
   // so this is NOT a Feldman-Cousins interval
   FeldmanCousins fc(*data,*mc);
   fc.SetConfidenceLevel(confidenceLevel);
   /*  fc.AdditionalNToysFactor(0.25); // degrade/improve sampling that defines confidence belt*/
   /*  fc.UseAdaptiveSampling(true); // speed it up a bit, don't use for expected limits*/
   fc.SetNBins(nPointsToScan); // set how many points per parameter of interest to scan
   fc.CreateConfBelt(true); // save the information in the belt for plotting

   // -------------------------------------------------------
   // Feldman-Cousins is a unified limit by definition
   // but the tool takes care of a few things for us like which values
   // of the nuisance parameters should be used to generate toys.
   // so let's just change the test statistic and realize this is
   // no longer "Feldman-Cousins" but is a fully frequentist Neyman-Construction.
   /*  ProfileLikelihoodTestStatModified onesided(*mc->GetPdf());*/
   /*  fc.GetTestStatSampler()->SetTestStatistic(&onesided);*/
   /* ((ToyMCSampler*) fc.GetTestStatSampler())->SetGenerateBinned(true); */
   ToyMCSampler*  toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler();
   ProfileLikelihoodTestStat* testStat = dynamic_cast<ProfileLikelihoodTestStat*>(toymcsampler->GetTestStatistic());
   testStat->SetOneSided(true);

   // Since this tool needs to throw toy MC the PDF needs to be
   // extended or the tool needs to know how many entries in a dataset
   // per pseudo experiment.
   // In the 'number counting form' where the entries in the dataset
   // are counts, and not values of discriminating variables, the
   // datasets typically only have one entry and the PDF is not
   // extended.
   if(!mc->GetPdf()->canBeExtended()){
      if(data->numEntries()==1)
         fc.FluctuateNumDataEntries(false);
      else
         cout <<"Not sure what to do about this model" <<endl;
   }

   // We can use PROOF to speed things along in parallel
   // However, the test statistic has to be installed on the workers
   // so either turn off PROOF or include the modified test statistic
   // in your `$ROOTSYS/roofit/roostats/inc` directory,
   // add the additional line to the LinkDef.h file,
   // and recompile root.
   if (useProof) {
      ProofConfig pc(*w, nworkers, "", false);
      toymcsampler->SetProofConfig(&pc); // enable proof
   }

   if(mc->GetGlobalObservables()){
      cout << "will use global observables for unconditional ensemble"<<endl;
      mc->GetGlobalObservables()->Print();
      toymcsampler->SetGlobalObservables(*mc->GetGlobalObservables());
   }


   // Now get the interval
   PointSetInterval* interval = fc.GetInterval();
   ConfidenceBelt* belt = fc.GetConfidenceBelt();

   // print out the interval on the first Parameter of Interest
   cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
      interval->LowerLimit(*firstPOI) << ", "<<
      interval->UpperLimit(*firstPOI) <<"] "<<endl;

   // get observed UL and value of test statistic evaluated there
   RooArgSet tmpPOI(*firstPOI);
   double observedUL = interval->UpperLimit(*firstPOI);
   firstPOI->setVal(observedUL);
   double obsTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*data,tmpPOI);


   // Ask the calculator which points were scanned
   RooDataSet* parameterScan = (RooDataSet*) fc.GetPointsToScan();
   RooArgSet* tmpPoint;

   // make a histogram of parameter vs. threshold
   TH1F* histOfThresholds = new TH1F("histOfThresholds","",
                                       parameterScan->numEntries(),
                                       firstPOI->getMin(),
                                       firstPOI->getMax());
   histOfThresholds->GetXaxis()->SetTitle(firstPOI->GetName());
   histOfThresholds->GetYaxis()->SetTitle("Threshold");

   // loop through the points that were tested and ask confidence belt
   // what the upper/lower thresholds were.
   // For FeldmanCousins, the lower cut off is always 0
   for(Int_t i=0; i<parameterScan->numEntries(); ++i){
      tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
      //cout <<"get threshold"<<endl;
      double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
      double poiVal = tmpPoint->getRealValue(firstPOI->GetName()) ;
      histOfThresholds->Fill(poiVal,arMax);
   }
   TCanvas* c1 = new TCanvas();
   c1->Divide(2);
   c1->cd(1);
   histOfThresholds->SetMinimum(0);
   histOfThresholds->Draw();
   c1->cd(2);

   // -------------------------------------------------------
   // Now we generate the expected bands and power-constraint

   // First: find parameter point for mu=0, with conditional MLEs for nuisance parameters
   RooAbsReal* nll = mc->GetPdf()->createNLL(*data);
   RooAbsReal* profile = nll->createProfile(*mc->GetParametersOfInterest());
   firstPOI->setVal(0.);
   profile->getVal(); // this will do fit and set nuisance parameters to profiled values
   RooArgSet* poiAndNuisance = new RooArgSet();
   if(mc->GetNuisanceParameters())
      poiAndNuisance->add(*mc->GetNuisanceParameters());
   poiAndNuisance->add(*mc->GetParametersOfInterest());
   w->saveSnapshot("paramsToGenerateData",*poiAndNuisance);
   RooArgSet* paramsToGenerateData = (RooArgSet*) poiAndNuisance->snapshot();
   cout << "\nWill use these parameter points to generate pseudo data for bkg only" << endl;
   paramsToGenerateData->Print("v");


   RooArgSet unconditionalObs;
   unconditionalObs.add(*mc->GetObservables());
   unconditionalObs.add(*mc->GetGlobalObservables()); // comment this out for the original conditional ensemble

   double CLb=0;
   double CLbinclusive=0;

   // Now we generate background only and find distribution of upper limits
   TH1F* histOfUL = new TH1F("histOfUL","",100,0,firstPOI->getMax());
   histOfUL->GetXaxis()->SetTitle("Upper Limit (background only)");
   histOfUL->GetYaxis()->SetTitle("Entries");
   for(int imc=0; imc<nToyMC; ++imc){

      // set parameters back to values for generating pseudo data
      //    cout << "\n get current nuis, set vals, print again" << endl;
      w->loadSnapshot("paramsToGenerateData");
      //    poiAndNuisance->Print("v");

      RooDataSet* toyData = 0;
      // now generate a toy dataset
      if(!mc->GetPdf()->canBeExtended()){
         if(data->numEntries()==1)
            toyData = mc->GetPdf()->generate(*mc->GetObservables(),1);
         else
            cout <<"Not sure what to do about this model" <<endl;
      } else{
         //      cout << "generating extended dataset"<<endl;
         toyData = mc->GetPdf()->generate(*mc->GetObservables(),Extended());
      }

      // generate global observables
      // need to be careful for simpdf
      //    RooDataSet* globalData = mc->GetPdf()->generate(*mc->GetGlobalObservables(),1);

      RooSimultaneous* simPdf = dynamic_cast<RooSimultaneous*>(mc->GetPdf());
      if(!simPdf){
         RooDataSet *one = mc->GetPdf()->generate(*mc->GetGlobalObservables(), 1);
         const RooArgSet *values = one->get();
         RooArgSet *allVars = mc->GetPdf()->getVariables();
         *allVars = *values;
         delete allVars;
         delete values;
         delete one;
      } else {

         //try fix for sim pdf
         TIterator* iter = simPdf->indexCat().typeIterator() ;
         RooCatType* tt = NULL;
         while((tt=(RooCatType*) iter->Next())) {

            // Get pdf associated with state from simpdf
            RooAbsPdf* pdftmp = simPdf->getPdf(tt->GetName()) ;

            // Generate only global variables defined by the pdf associated with this state
            RooArgSet* globtmp = pdftmp->getObservables(*mc->GetGlobalObservables()) ;
            RooDataSet* tmp = pdftmp->generate(*globtmp,1) ;

            // Transfer values to output placeholder
            *globtmp = *tmp->get(0) ;

            // Cleanup
            delete globtmp ;
            delete tmp ;
         }
      }

      //    globalData->Print("v");
      //    unconditionalObs = *globalData->get();
      //    mc->GetGlobalObservables()->Print("v");
      //    delete globalData;
      //    cout << "toy data = " << endl;
      //    toyData->get()->Print("v");

      // get test stat at observed UL in observed data
      firstPOI->setVal(observedUL);
      double toyTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
      //    toyData->get()->Print("v");
      //    cout <<"obsTSatObsUL " <<obsTSatObsUL << "toyTS " << toyTSatObsUL << endl;
      if(obsTSatObsUL < toyTSatObsUL) // not sure about <= part yet
         CLb+= (1.)/nToyMC;
      if(obsTSatObsUL <= toyTSatObsUL) // not sure about <= part yet
         CLbinclusive+= (1.)/nToyMC;


      // loop over points in belt to find upper limit for this toy data
      double thisUL = 0;
      for(Int_t i=0; i<parameterScan->numEntries(); ++i){
         tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
         double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
         firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
         //   double thisTS = profile->getVal();
         double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);

         //   cout << "poi = " << firstPOI->getVal()
         // << " max is " << arMax << " this profile = " << thisTS << endl;
         //      cout << "thisTS = " << thisTS<<endl;
         if(thisTS<=arMax){
            thisUL = firstPOI->getVal();
         } else{
            break;
         }
      }



      /*
      // loop over points in belt to find upper limit for this toy data
      double thisUL = 0;
      for(Int_t i=0; i<histOfThresholds->GetNbinsX(); ++i){
         tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
         cout <<"----------------  "<<i<<endl;
         tmpPoint->Print("v");
         cout << "from hist " << histOfThresholds->GetBinCenter(i+1) <<endl;
         double arMax = histOfThresholds->GetBinContent(i+1);
         // cout << " threhold from Hist = aMax " << arMax<<endl;
         // double arMax2 = belt->GetAcceptanceRegionMax(*tmpPoint);
         // cout << "from scan arMax2 = "<< arMax2 << endl; // not the same due to TH1F not TH1D
         // cout << "scan - hist" << arMax2-arMax << endl;
         firstPOI->setVal( histOfThresholds->GetBinCenter(i+1));
         //   double thisTS = profile->getVal();
         double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);

         //   cout << "poi = " << firstPOI->getVal()
         // << " max is " << arMax << " this profile = " << thisTS << endl;
         //      cout << "thisTS = " << thisTS<<endl;

         // NOTE: need to add a small epsilon term for single precision vs. double precision
         if(thisTS<=arMax + 1e-7){
            thisUL = firstPOI->getVal();
         } else{
            break;
         }
      }
      */

      histOfUL->Fill(thisUL);

      // for few events, data is often the same, and UL is often the same
      //    cout << "thisUL = " << thisUL<<endl;

      delete toyData;
   }
   histOfUL->Draw();
   c1->SaveAs("one-sided_upper_limit_output.pdf");

   // if you want to see a plot of the sampling distribution for a particular scan point:
   /*
   SamplingDistPlot sampPlot;
   int indexInScan = 0;
   tmpPoint = (RooArgSet*) parameterScan->get(indexInScan)->clone("temp");
   firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
   toymcsampler->SetParametersForTestStat(tmpPOI);
   SamplingDistribution* samp = toymcsampler->GetSamplingDistribution(*tmpPoint);
   sampPlot.AddSamplingDistribution(samp);
   sampPlot.Draw();
      */

   // Now find bands and power constraint
   Double_t* bins = histOfUL->GetIntegral();
   TH1F* cumulative = (TH1F*) histOfUL->Clone("cumulative");
   cumulative->SetContent(bins);
   double band2sigDown, band1sigDown, bandMedian, band1sigUp,band2sigUp;
   for(int i=1; i<=cumulative->GetNbinsX(); ++i){
      if(bins[i]<RooStats::SignificanceToPValue(2))
         band2sigDown=cumulative->GetBinCenter(i);
      if(bins[i]<RooStats::SignificanceToPValue(1))
         band1sigDown=cumulative->GetBinCenter(i);
      if(bins[i]<0.5)
         bandMedian=cumulative->GetBinCenter(i);
      if(bins[i]<RooStats::SignificanceToPValue(-1))
         band1sigUp=cumulative->GetBinCenter(i);
      if(bins[i]<RooStats::SignificanceToPValue(-2))
         band2sigUp=cumulative->GetBinCenter(i);
   }
   cout << "-2 sigma  band " << band2sigDown << endl;
   cout << "-1 sigma  band " << band1sigDown << " [Power Constraint)]" << endl;
   cout << "median of band " << bandMedian << endl;
   cout << "+1 sigma  band " << band1sigUp << endl;
   cout << "+2 sigma  band " << band2sigUp << endl;

   // print out the interval on the first Parameter of Interest
   cout << "\nobserved 95% upper-limit "<< interval->UpperLimit(*firstPOI) <<endl;
   cout << "CLb strict [P(toy>obs|0)] for observed 95% upper-limit "<< CLb <<endl;
   cout << "CLb inclusive [P(toy>=obs|0)] for observed 95% upper-limit "<< CLbinclusive <<endl;

   delete profile;
   delete nll;

}
void OneSidedFrequentistUpperLimitWithBands_intermediate(const char* infile = "",
					    const char* workspaceName = "combined",
					    const char* modelConfigName = "ModelConfig",
					    const char* dataName = "obsData"){


  double confidenceLevel=0.95;
  // degrade/improve number of pseudo-experiments used to define the confidence belt.  
  // value of 1 corresponds to default number of toys in the tail, which is 50/(1-confidenceLevel)
  double additionalToysFac = 1.;  
  int nPointsToScan = 30; // number of steps in the parameter of interest 
  int nToyMC = 100; // number of toys used to define the expected limit and band

  TStopwatch t;
  t.Start();
  /////////////////////////////////////////////////////////////
  // First part is just to access a user-defined file 
  // or create the standard example file if it doesn't exist
  ////////////////////////////////////////////////////////////
  const char* filename = "";
  if (!strcmp(infile,""))
    filename = "results/example_combined_GaussExample_model.root";
  else
    filename = infile;
  // Check if example input file exists
  TFile *file = TFile::Open(filename);

  // if input file was specified byt not found, quit
  if(!file && strcmp(infile,"")){
    cout <<"file not found" << endl;
    return;
  } 

  // if default file not found, try to create it
  if(!file ){
    // Normally this would be run on the command line
    cout <<"will run standard hist2workspace example"<<endl;
    gROOT->ProcessLine(".! prepareHistFactory .");
    gROOT->ProcessLine(".! hist2workspace config/example.xml");
    cout <<"\n\n---------------------"<<endl;
    cout <<"Done creating example input"<<endl;
    cout <<"---------------------\n\n"<<endl;
  }

  // now try to access the file again
  file = TFile::Open(filename);
  if(!file){
    // if it is still not there, then we can't continue
    cout << "Not able to run hist2workspace to create example input" <<endl;
    return;
  }

  
  /////////////////////////////////////////////////////////////
  // Now get the data and workspace
  ////////////////////////////////////////////////////////////

  // get the workspace out of the file
  RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
  if(!w){
    cout <<"workspace not found" << endl;
    return;
  }

  // get the modelConfig out of the file
  ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);

  // get the modelConfig out of the file
  RooAbsData* data = w->data(dataName);

  // make sure ingredients are found
  if(!data || !mc){
    w->Print();
    cout << "data or ModelConfig was not found" <<endl;
    return;
  }

  cout << "Found data and ModelConfig:" <<endl;
  mc->Print();

  /////////////////////////////////////////////////////////////
  // Now get the POI for convenience
  // you may want to adjust the range of your POI
  ////////////////////////////////////////////////////////////
  RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
  //  firstPOI->setMin(0);
  //  firstPOI->setMax(10);

  /////////////////////////////////////////////
  // create and use the FeldmanCousins tool
  // to find and plot the 95% confidence interval
  // on the parameter of interest as specified
  // in the model config
  // REMEMBER, we will change the test statistic
  // so this is NOT a Feldman-Cousins interval
  FeldmanCousins fc(*data,*mc);
  fc.SetConfidenceLevel(confidenceLevel); 
  fc.AdditionalNToysFactor(additionalToysFac); // improve sampling that defines confidence belt
  //  fc.UseAdaptiveSampling(true); // speed it up a bit, but don't use for expectd limits
  fc.SetNBins(nPointsToScan); // set how many points per parameter of interest to scan
  fc.CreateConfBelt(true); // save the information in the belt for plotting

  /////////////////////////////////////////////
  // Feldman-Cousins is a unified limit by definition
  // but the tool takes care of a few things for us like which values
  // of the nuisance parameters should be used to generate toys.
  // so let's just change the test statistic and realize this is 
  // no longer "Feldman-Cousins" but is a fully frequentist Neyman-Construction.
  //  ProfileLikelihoodTestStatModified onesided(*mc->GetPdf());
  //  fc.GetTestStatSampler()->SetTestStatistic(&onesided);
  // ((ToyMCSampler*) fc.GetTestStatSampler())->SetGenerateBinned(true);
  ToyMCSampler*  toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler(); 
  ProfileLikelihoodTestStat* testStat = dynamic_cast<ProfileLikelihoodTestStat*>(toymcsampler->GetTestStatistic());
  testStat->SetOneSided(true);


  // test speedups:
  testStat->SetReuseNLL(true);
  //  toymcsampler->setUseMultiGen(true); // not fully validated

  // Since this tool needs to throw toy MC the PDF needs to be
  // extended or the tool needs to know how many entries in a dataset
  // per pseudo experiment.  
  // In the 'number counting form' where the entries in the dataset
  // are counts, and not values of discriminating variables, the
  // datasets typically only have one entry and the PDF is not
  // extended.  
  if(!mc->GetPdf()->canBeExtended()){
    if(data->numEntries()==1)     
      fc.FluctuateNumDataEntries(false);
    else
      cout <<"Not sure what to do about this model" <<endl;
  }

  // We can use PROOF to speed things along in parallel
  ProofConfig pc(*w, 4, "",false); 
  if(mc->GetGlobalObservables()){
    cout << "will use global observables for unconditional ensemble"<<endl;
    mc->GetGlobalObservables()->Print();
    toymcsampler->SetGlobalObservables(*mc->GetGlobalObservables());
  }
  toymcsampler->SetProofConfig(&pc);	// enable proof


  // Now get the interval
  PointSetInterval* interval = fc.GetInterval();
  ConfidenceBelt* belt = fc.GetConfidenceBelt();
 
  // print out the iterval on the first Parameter of Interest
  cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
    interval->LowerLimit(*firstPOI) << ", "<<
    interval->UpperLimit(*firstPOI) <<"] "<<endl;

  // get observed UL and value of test statistic evaluated there
  RooArgSet tmpPOI(*firstPOI);
  double observedUL = interval->UpperLimit(*firstPOI);
  firstPOI->setVal(observedUL);
  double obsTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*data,tmpPOI);


  // Ask the calculator which points were scanned
  RooDataSet* parameterScan = (RooDataSet*) fc.GetPointsToScan();
  RooArgSet* tmpPoint;

  // make a histogram of parameter vs. threshold
  TH1F* histOfThresholds = new TH1F("histOfThresholds","",
				    parameterScan->numEntries(),
				    firstPOI->getMin(),
				    firstPOI->getMax());
  histOfThresholds->GetXaxis()->SetTitle(firstPOI->GetName());
  histOfThresholds->GetYaxis()->SetTitle("Threshold");

  // loop through the points that were tested and ask confidence belt
  // what the upper/lower thresholds were.
  // For FeldmanCousins, the lower cut off is always 0
  for(Int_t i=0; i<parameterScan->numEntries(); ++i){
    tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
    double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
    double poiVal = tmpPoint->getRealValue(firstPOI->GetName()) ;
    histOfThresholds->Fill(poiVal,arMax);
  }
  TCanvas* c1 = new TCanvas();
  c1->Divide(2);
  c1->cd(1);
  histOfThresholds->SetMinimum(0);
  histOfThresholds->Draw();
  c1->cd(2);

  /////////////////////////////////////////////////////////////
  // Now we generate the expected bands and power-constriant
  ////////////////////////////////////////////////////////////

  // First: find parameter point for mu=0, with conditional MLEs for nuisance parameters
  RooAbsReal* nll = mc->GetPdf()->createNLL(*data);
  RooAbsReal* profile = nll->createProfile(*mc->GetParametersOfInterest());
  firstPOI->setVal(0.);
  profile->getVal(); // this will do fit and set nuisance parameters to profiled values
  RooArgSet* poiAndNuisance = new RooArgSet();
  if(mc->GetNuisanceParameters())
    poiAndNuisance->add(*mc->GetNuisanceParameters());
  poiAndNuisance->add(*mc->GetParametersOfInterest());
  w->saveSnapshot("paramsToGenerateData",*poiAndNuisance);
  RooArgSet* paramsToGenerateData = (RooArgSet*) poiAndNuisance->snapshot();
  cout << "\nWill use these parameter points to generate pseudo data for bkg only" << endl;
  paramsToGenerateData->Print("v");


  double CLb=0;
  double CLbinclusive=0;

  // Now we generate background only and find distribution of upper limits
  TH1F* histOfUL = new TH1F("histOfUL","",100,0,firstPOI->getMax());
  histOfUL->GetXaxis()->SetTitle("Upper Limit (background only)");
  histOfUL->GetYaxis()->SetTitle("Entries");
  for(int imc=0; imc<nToyMC; ++imc){

    // set parameters back to values for generating pseudo data
    w->loadSnapshot("paramsToGenerateData");

    // in 5.30 there is a nicer way to generate toy data  & randomize global obs
    RooAbsData* toyData = toymcsampler->GenerateToyData(*paramsToGenerateData);

    // get test stat at observed UL in observed data
    firstPOI->setVal(observedUL);
    double toyTSatObsUL = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);
    //    toyData->get()->Print("v");
    //    cout <<"obsTSatObsUL " <<obsTSatObsUL << "toyTS " << toyTSatObsUL << endl;
    if(obsTSatObsUL < toyTSatObsUL) // (should be checked)
      CLb+= (1.)/nToyMC;
    if(obsTSatObsUL <= toyTSatObsUL) // (should be checked)
      CLbinclusive+= (1.)/nToyMC;


    // loop over points in belt to find upper limit for this toy data
    double thisUL = 0;
    for(Int_t i=0; i<parameterScan->numEntries(); ++i){
      tmpPoint = (RooArgSet*) parameterScan->get(i)->clone("temp");
      double arMax = belt->GetAcceptanceRegionMax(*tmpPoint);
      firstPOI->setVal( tmpPoint->getRealValue(firstPOI->GetName()) );
      double thisTS = fc.GetTestStatSampler()->EvaluateTestStatistic(*toyData,tmpPOI);

      if(thisTS<=arMax){
	thisUL = firstPOI->getVal();
      } else{
	break;
      }
    }
    

    histOfUL->Fill(thisUL);

    
    delete toyData;
  }
  histOfUL->Draw();
  c1->SaveAs("one-sided_upper_limit_output.pdf");

  // if you want to see a plot of the sampling distribution for a particular scan point:

  // Now find bands and power constraint
  Double_t* bins = histOfUL->GetIntegral();
  TH1F* cumulative = (TH1F*) histOfUL->Clone("cumulative");
  cumulative->SetContent(bins);
  double band2sigDown=0, band1sigDown=0, bandMedian=0, band1sigUp=0,band2sigUp=0;
  for(int i=1; i<=cumulative->GetNbinsX(); ++i){
    if(bins[i]<RooStats::SignificanceToPValue(2))
      band2sigDown=cumulative->GetBinCenter(i);
    if(bins[i]<RooStats::SignificanceToPValue(1))
      band1sigDown=cumulative->GetBinCenter(i);
    if(bins[i]<0.5)
      bandMedian=cumulative->GetBinCenter(i);
    if(bins[i]<RooStats::SignificanceToPValue(-1))
      band1sigUp=cumulative->GetBinCenter(i);
    if(bins[i]<RooStats::SignificanceToPValue(-2))
      band2sigUp=cumulative->GetBinCenter(i);
  }

  t.Stop();
  t.Print();

  cout << "-2 sigma  band " << band2sigDown << endl;
  cout << "-1 sigma  band " << band1sigDown  << endl;
  cout << "median of band " << bandMedian << " [Power Constriant)]" << endl;
  cout << "+1 sigma  band " << band1sigUp << endl;
  cout << "+2 sigma  band " << band2sigUp << endl;

  // print out the iterval on the first Parameter of Interest
  cout << "\nobserved 95% upper-limit "<< interval->UpperLimit(*firstPOI) <<endl;
  cout << "CLb strict [P(toy>obs|0)] for observed 95% upper-limit "<< CLb <<endl;
  cout << "CLb inclusive [P(toy>=obs|0)] for observed 95% upper-limit "<< CLbinclusive <<endl;

  delete profile;
  delete nll;

}
void StandardTestStatDistributionDemo(const char* infile = "",
                                      const char* workspaceName = "combined",
                                      const char* modelConfigName = "ModelConfig",
                                      const char* dataName = "obsData"){


  // the number of toy MC used to generate the distribution
  int nToyMC = 1000;
  // The parameter below is needed for asymptotic distribution to be chi-square,
  // but set to false if your model is not numerically stable if mu<0
  bool allowNegativeMu=true;


  /////////////////////////////////////////////////////////////
  // 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;
  }

  mc->Print();
  /////////////////////////////////////////////////////////////
  // Now find the upper limit based on the asymptotic results
  ////////////////////////////////////////////////////////////
  RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
  ProfileLikelihoodCalculator plc(*data,*mc);
  LikelihoodInterval* interval = plc.GetInterval();
  double plcUpperLimit = interval->UpperLimit(*firstPOI);
  delete interval;
  cout << "\n\n--------------------------------------"<<endl;
  cout <<"Will generate sampling distribution at " << firstPOI->GetName() << " = " << plcUpperLimit <<endl;
  int nPOI = mc->GetParametersOfInterest()->getSize();
  if(nPOI>1){
    cout <<"not sure what to do with other parameters of interest, but here are their values"<<endl;
    mc->GetParametersOfInterest()->Print("v");
  }

  /////////////////////////////////////////////
  // create thte test stat sampler
  ProfileLikelihoodTestStat ts(*mc->GetPdf());

  // to avoid effects from boundary and simplify asymptotic comparison, set min=-max
  if(allowNegativeMu)
    firstPOI->setMin(-1*firstPOI->getMax());

  // temporary RooArgSet
  RooArgSet poi;
  poi.add(*mc->GetParametersOfInterest());

  // create and configure the ToyMCSampler
  ToyMCSampler sampler(ts,nToyMC);
  sampler.SetPdf(*mc->GetPdf());
  sampler.SetObservables(*mc->GetObservables());
  sampler.SetGlobalObservables(*mc->GetGlobalObservables());
  if(!mc->GetPdf()->canBeExtended() && (data->numEntries()==1)){
    cout << "tell it to use 1 event"<<endl;
    sampler.SetNEventsPerToy(1);
  }
  firstPOI->setVal(plcUpperLimit); // set POI value for generation
  sampler.SetParametersForTestStat(*mc->GetParametersOfInterest()); // set POI value for evaluation

  if (useProof) {
     ProofConfig pc(*w, nworkers, "",false);
     sampler.SetProofConfig(&pc); // enable proof
  }

  firstPOI->setVal(plcUpperLimit);
  RooArgSet allParameters;
  allParameters.add(*mc->GetParametersOfInterest());
  allParameters.add(*mc->GetNuisanceParameters());
  allParameters.Print("v");

  SamplingDistribution* sampDist = sampler.GetSamplingDistribution(allParameters);
  SamplingDistPlot plot;
  plot.AddSamplingDistribution(sampDist);
  plot.GetTH1F(sampDist)->GetYaxis()->SetTitle(Form("f(-log #lambda(#mu=%.2f) | #mu=%.2f)",plcUpperLimit,plcUpperLimit));
  plot.SetAxisTitle(Form("-log #lambda(#mu=%.2f)",plcUpperLimit));

  TCanvas* c1 = new TCanvas("c1");
  c1->SetLogy();
  plot.Draw();
  double min = plot.GetTH1F(sampDist)->GetXaxis()->GetXmin();
  double max = plot.GetTH1F(sampDist)->GetXaxis()->GetXmax();

  TF1* f = new TF1("f",Form("2*ROOT::Math::chisquared_pdf(2*x,%d,0)",nPOI),min,max);
  f->Draw("same");
  c1->SaveAs("standard_test_stat_distribution.pdf");

}
示例#7
0
文件: runSig.C 项目: sagittaeri/htt
TH1D* runSig(RooWorkspace* ws,
             const char* modelConfigName = "ModelConfig",
             const char* dataName = "obsData",
             const char* asimov1DataName = "asimovData_1",
             const char* conditional1Snapshot = "conditionalGlobs_1",
             const char* nominalSnapshot = "nominalGlobs")
{
    string defaultMinimizer    = "Minuit";     // or "Minuit"
    int defaultStrategy        = 2;             // Minimization strategy. 0-2. 0 = fastest, least robust. 2 = slowest, most robust

    double mu_profile_value = 1; // mu value to profile the obs data at wbefore generating the expected
    bool doUncap            = 1; // uncap p0
    bool doInj              = 0; // setup the poi for injection study (zero is faster if you're not)
    bool doMedian           = 1; // compute median significance
    bool isBlind            = 0; // Dont look at observed data
    bool doConditional      = !isBlind; // do conditional expected data
    bool doObs              = !isBlind; // compute observed significance

    TStopwatch timer;
    timer.Start();

    if (!ws)
    {
        cout << "ERROR::Workspace is NULL!" << endl;
        return NULL;
    }
    ModelConfig* mc = (ModelConfig*)ws->obj(modelConfigName);
    if (!mc)
    {
        cout << "ERROR::ModelConfig: " << modelConfigName << " doesn't exist!" << endl;
        return NULL;
    }
    RooDataSet* data = (RooDataSet*)ws->data(dataName);
    if (!data)
    {
        cout << "ERROR::Dataset: " << dataName << " doesn't exist!" << endl;
        return NULL;
    }

    mc->GetNuisanceParameters()->Print("v");

    //RooNLLVar::SetIgnoreZeroEntries(1);
    ROOT::Math::MinimizerOptions::SetDefaultMinimizer(defaultMinimizer.c_str());
    ROOT::Math::MinimizerOptions::SetDefaultStrategy(defaultStrategy);
    ROOT::Math::MinimizerOptions::SetDefaultPrintLevel(-1);
    //  cout << "Setting max function calls" << endl;
    //ROOT::Math::MinimizerOptions::SetDefaultMaxFunctionCalls(20000);
    //RooMinimizer::SetMaxFunctionCalls(10000);

    ws->loadSnapshot("conditionalNuis_0");
    RooArgSet nuis(*mc->GetNuisanceParameters());

    RooRealVar* mu = (RooRealVar*)mc->GetParametersOfInterest()->first();

    RooAbsPdf* pdf_temp = mc->GetPdf();

    string condSnapshot(conditional1Snapshot);
    RooArgSet nuis_tmp2 = *mc->GetNuisanceParameters();
    RooNLLVar* obs_nll = doObs ? (RooNLLVar*)pdf_temp->createNLL(*data, Constrain(nuis_tmp2)) : NULL;

    RooDataSet* asimovData1 = (RooDataSet*)ws->data(asimov1DataName);
    if (!asimovData1)
    {
        cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
        string mu_str, mu_prof_str;

        asimovData1 = makeAsimovData(mc, doConditional, ws, obs_nll, 1, &mu_str, &mu_prof_str, mu_profile_value, true);
        condSnapshot="conditionalGlobs"+mu_prof_str;

        //makeAsimovData(mc, true, ws, mc->GetPdf(), data, 0);
        //ws->Print();
        //asimovData1 = (RooDataSet*)ws->data("asimovData_1");
    }

    if (!doUncap) mu->setRange(0, 40);
    else mu->setRange(-40, 40);

    RooAbsPdf* pdf = mc->GetPdf();
    RooArgSet nuis_tmp1 = *mc->GetNuisanceParameters();
    RooNLLVar* asimov_nll = (RooNLLVar*)pdf->createNLL(*asimovData1, Constrain(nuis_tmp1));

    //do asimov
    mu->setVal(1);
    mu->setConstant(0);
    if (!doInj) mu->setConstant(1);

    int status,sign;
    double med_sig=0,obs_sig=0,asimov_q0=0,obs_q0=0;

    if (doMedian)
    {
        ws->loadSnapshot(condSnapshot.c_str());
        if (doInj) ws->loadSnapshot("conditionalNuis_inj");
        else ws->loadSnapshot("conditionalNuis_1");
        mc->GetGlobalObservables()->Print("v");
        mu->setVal(0);
        mu->setConstant(1);
        status = minimize(asimov_nll, ws);
        if (status >= 0) cout << "Success!" << endl;

        if (status < 0) 
        {
            cout << "Retrying with conditional snapshot at mu=1" << endl;
            ws->loadSnapshot("conditionalNuis_0");
            status = minimize(asimov_nll, ws);
            if (status >= 0) cout << "Success!" << endl;
        }
        double asimov_nll_cond = asimov_nll->getVal();

        mu->setVal(1);
        if (doInj) ws->loadSnapshot("conditionalNuis_inj");
        else ws->loadSnapshot("conditionalNuis_1");
        if (doInj) mu->setConstant(0);
        status = minimize(asimov_nll, ws);
        if (status >= 0) cout << "Success!" << endl;

        if (status < 0) 
        {
            cout << "Retrying with conditional snapshot at mu=1" << endl;
            ws->loadSnapshot("conditionalNuis_0");
            status = minimize(asimov_nll, ws);
            if (status >= 0) cout << "Success!" << endl;
        }

        double asimov_nll_min = asimov_nll->getVal();
        asimov_q0 = 2*(asimov_nll_cond - asimov_nll_min);
        if (doUncap && mu->getVal() < 0) asimov_q0 = -asimov_q0;

        sign = int(asimov_q0 != 0 ? asimov_q0/fabs(asimov_q0) : 0);
        med_sig = sign*sqrt(fabs(asimov_q0));

        ws->loadSnapshot(nominalSnapshot);
    }

    if (doObs)
    {
        ws->loadSnapshot("conditionalNuis_0");
        mu->setVal(0);
        mu->setConstant(1);
        status = minimize(obs_nll, ws);
        if (status < 0) 
        {
            cout << "Retrying with conditional snapshot at mu=1" << endl;
            ws->loadSnapshot("conditionalNuis_0");
            status = minimize(obs_nll, ws);
            if (status >= 0) cout << "Success!" << endl;
        }
        double obs_nll_cond = obs_nll->getVal();

        //ws->loadSnapshot("ucmles");
        mu->setConstant(0);
        status = minimize(obs_nll, ws);
        if (status < 0) 
        {
            cout << "Retrying with conditional snapshot at mu=1" << endl;
            ws->loadSnapshot("conditionalNuis_0");
            status = minimize(obs_nll, ws);
            if (status >= 0) cout << "Success!" << endl;
        }

        double obs_nll_min = obs_nll->getVal();

        obs_q0 = 2*(obs_nll_cond - obs_nll_min);
        if (doUncap && mu->getVal() < 0) obs_q0 = -obs_q0;

        sign = int(obs_q0 == 0 ? 0 : obs_q0 / fabs(obs_q0));
        if (!doUncap && ((obs_q0 < 0 && obs_q0 > -0.1) || mu->getVal() < 0.001)) obs_sig = 0; 
        else obs_sig = sign*sqrt(fabs(obs_q0));
    }

    cout << "obs: " << obs_sig << endl;
    cout << "Observed significance: " << obs_sig << endl;

    if (med_sig)
    {
        cout << "Median test stat val: " << asimov_q0 << endl;
        cout << "Median significance:   " << med_sig << endl;
    }

    TH1D* h_hypo = new TH1D("hypo","hypo",2,0,2);
    h_hypo->SetBinContent(1, obs_sig);
    h_hypo->SetBinContent(2, med_sig);

    timer.Stop();
    timer.Print();
    return h_hypo;
}