C++ ToyMCSampler::SetGlobalObservables方法代码示例

//.........这里部分代码省略.........
   /* ((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

void statTest(double mu_pe, double mu_hyp, ModelConfig *mc , RooDataSet *data ){

    int nToyMC = 5;
    // set roofit seed
    RooRandom::randomGenerator()->SetSeed();

    cout << endl;
    cout << endl;
    cout << "Will generate " << nToyMC << " pseudo-experiments for : " << endl;
    cout << " - mu[pseudo-data] = " << mu_pe  << endl;
    cout << " - mu[stat-test]   = " << mu_hyp << endl;
    cout << endl;

    // Check number of POI (for Wald approx)
    RooArgSet *ParamOfInterest = (RooArgSet*) mc->GetParametersOfInterest();
    int nPOI = ParamOfInterest->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");
    }
    RooRealVar* firstPOI    = (RooRealVar*) ParamOfInterest->first(); 
    RooAbsPdf *simPdf = (mc->GetPdf());
    //PrintAllParametersAndValues( *mc->GetGlobalObservables() );
    //PrintAllParametersAndValues( *mc->GetObservables() );
    firstPOI->setVal(0.0); // FIXME

    //simPdf->fitTo( *data, Hesse(kTRUE), Minos(kTRUE), PrintLevel(1) );
    simPdf->fitTo( *data );

    // set up the sampler
    ToyMCSampler sampler;
    sampler.SetPdf(*mc->GetPdf());
    sampler.SetObservables(*mc->GetObservables());
    sampler.SetNToys(nToyMC);
    sampler.SetGlobalObservables(*mc->GetGlobalObservables());
    sampler.SetParametersForTestStat(*mc->GetParametersOfInterest());
    RooArgSet* poiset = dynamic_cast<RooArgSet*>(ParamOfInterest->Clone());


    // only unconditional fit
    MinNLLTestStat *minNll = new MinNLLTestStat(*mc->GetPdf());
    minNll->EnableDetailedOutput(true);
    sampler.AddTestStatistic(minNll);

    // enable PROOF if desired
    //ProofConfig pc(*w, 8, "workers=8", kFALSE);
    //sampler.SetProofConfig(&pc);

    // evaluate the test statistics - this is where most of our time will be spent
    cout << "Generating " << nToyMC << " toys...this will take a few minutes" << endl;
    TStopwatch *mn_t = new TStopwatch; 
    mn_t->Start();
    RooDataSet* sd = sampler.GetSamplingDistributions(*poiset);
    cout << "Toy generation complete :" << endl;
    // stop timing
    mn_t->Stop();
    cout << " total CPU time: " << mn_t->CpuTime() << endl;
    cout << " total real time: " << mn_t->RealTime() << endl; 

    // now sd contains all information about our test statistics, including detailed output
    // we might eg. want to explore the results either directly, or first converting to a TTree
    // do the conversion
    TFile f("mytoys.root", "RECREATE");
    TTree *toyTree = RooStats::GetAsTTree("toyTree", "TTree created from test statistics", *sd);
    // save result to file, but in general do whatever you like
    f.cd();
    toyTree->Write();
    f.Close();
/*
    TFile* tmpFile = new TFile("mytoys.root","READ");
    TTree* myTree = (TTree*)tmpFile->Get("toyTree");

    // get boundaries for histograms
    TIter nextLeaf( (myTree->GetListOfLeaves())->MakeIterator() );
    TObject* leafObj(0);
    map<TString, float> xMaxs;
    map<TString, float> xMins;
    for(int i(0); i<myTree->GetEntries(); i++) {
      myTree->GetEntry(i);
      nextLeaf = ( (myTree->GetListOfLeaves())->MakeIterator() );
      while( (leafObj = nextLeaf.Next()) ) {
        TString name(leafObj->GetName());
        float value(myTree->GetLeaf( leafObj->GetName() )->GetValue());
        if(value > xMaxs[name]) { xMaxs[name] = value; }
        if(value < xMins[name]) { xMins[name] = value; }
      } // loop over leaves
    } // loop over tree entries

    // plot everything in the tree
    myTree->GetEntry(0);
    nextLeaf = ( (myTree->GetListOfLeaves())->MakeIterator() );
    leafObj = 0;
    // make a histogram per leaf
    map<TString, TH1F*> hists;
    myTree->GetEntry(0);
    while( (leafObj = nextLeaf.Next()) ) {
      if(!leafObj) { continue; }
      //cout << leafObj->GetName() << endl;
      TString name(leafObj->GetName());
      // special ones : fit related things
//.........这里部分代码省略.........

//.........这里部分代码省略.........
  // 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");

result fit_toy(RooWorkspace* wspace, int n, const RooArgSet* globals) {
    RooRandom::randomGenerator()->SetSeed(0);
    // TFile f(filename);
    // RooWorkspace *wspace = (RooWorkspace*)f.Get("combined");
    ModelConfig* model = (ModelConfig*)wspace->obj("ModelConfig");

    RooAbsPdf* pdf;
    pdf = model->GetPdf();

    RooAbsPdf* top_constraint = (RooAbsPdf*)wspace->obj("top_ratio_constraint");
    RooAbsPdf* vv_constraint = (RooAbsPdf*)wspace->obj("vv_ratio_constraint");
    RooAbsPdf* top_vv_constraint_sf = (RooAbsPdf*)wspace->obj("top_vv_ratio_sf_constraint");
    RooAbsPdf* top_vv_constraint_of = (RooAbsPdf*)wspace->obj("top_vv_ratio_of_constraint");


    // generate constraint global observables
    RooRealVar *nom_top_ratio = (RooRealVar*)wspace->obj("nom_top_ratio");
    nom_top_ratio->setRange(0, 100);
    RooRealVar *nom_vv_ratio = (RooRealVar*)wspace->obj("nom_vv_ratio");
    nom_vv_ratio->setRange(0,100);
    RooRealVar *nom_top_vv_ratio_sf = (RooRealVar*)wspace->obj("nom_top_vv_ratio_sf");
    nom_top_vv_ratio_sf->setRange(0,100);
    RooRealVar *nom_top_vv_ratio_of = (RooRealVar*)wspace->obj("nom_top_vv_ratio_of");
    nom_top_vv_ratio_of->setRange(0,100);

    RooDataSet *nom_top_generated = top_constraint->generateSimGlobal(RooArgSet(*nom_top_ratio), 1);
    nom_top_ratio->setVal(((RooRealVar*)nom_top_generated->get(0)->find("nom_top_ratio"))->getVal());

    RooDataSet *nom_vv_generated = vv_constraint->generateSimGlobal(RooArgSet(*nom_vv_ratio), 1);
    nom_vv_ratio->setVal(((RooRealVar*)nom_vv_generated->get(0)->find("nom_vv_ratio"))->getVal());

    RooDataSet *nom_top_vv_sf_generated = top_vv_constraint_sf->generateSimGlobal(RooArgSet(*nom_top_vv_ratio_sf), 1);
    nom_top_vv_ratio_sf->setVal(((RooRealVar*)nom_top_vv_sf_generated->get(0)->find("nom_top_vv_ratio_sf"))->getVal());

    RooDataSet *nom_top_vv_of_generated = top_vv_constraint_of->generateSimGlobal(RooArgSet(*nom_top_vv_ratio_of), 1);
    nom_top_vv_ratio_of->setVal(((RooRealVar*)nom_top_vv_of_generated->get(0)->find("nom_top_vv_ratio_of"))->getVal());

    NumEventsTestStat* dummy = new NumEventsTestStat(*pdf);

    ToyMCSampler* mc = new ToyMCSampler(*dummy, 1);
    mc->SetPdf(*pdf);
    mc->SetObservables(*model->GetObservables());
    mc->SetGlobalObservables(*globals);
    mc->SetNuisanceParameters(*model->GetNuisanceParameters());
    mc->SetParametersForTestStat(*model->GetParametersOfInterest());
    mc->SetNEventsPerToy(n);

    RooArgSet constr;
    constr.add(*(model->GetNuisanceParameters()));
    RemoveConstantParameters(&constr);

    RooDataSet* toy_data = (RooDataSet*)mc->GenerateToyData(*const_cast<RooArgSet*>(model->GetSnapshot()));

    RooFitResult *res = pdf->fitTo(*toy_data, Constrain(constr), PrintLevel(0), Save(),
                                               Range("fitRange"), InitialHesse(),
                                               ExternalConstraints(RooArgSet(*top_constraint, *vv_constraint, *top_vv_constraint_sf, *top_vv_constraint_of)));
    result yield = get_results(wspace, res);
    yield.of.generated_sum.val = toy_data->sumEntries("(channelCat==channelCat::of) & (obs_x_of>120)");
    yield.sf.generated_sum.val = toy_data->sumEntries("(channelCat==channelCat::sf) & (obs_x_sf>120)");

    delete mc;
    delete dummy;
    // f.Close();

    return yield;
}