示例#1
0
double getChisq(RooAbsData &dat, RooAbsPdf &pdf, RooRealVar &var, bool prt=false) {

    // Find total number of events
    double nEvt;
    double nTot=0.0;

    for(int j=0; j<dat.numEntries(); j++) {
        dat.get(j);
        nEvt=dat.weight();
        nTot+=nEvt;
    }

    // Find chi-squared equivalent 2NLL
    //RooRealVar *var=(RooRealVar*)(pdf.getParameters(*dat)->find("CMS_hgg_mass"));
    double totNLL=0.0;
    double prbSum=0.0;

    for(int j=0; j<dat.numEntries(); j++) {
        double m=dat.get(j)->getRealValue(var.GetName());
        if ( m < var.getMin() || m > var.getMax())  continue;
        // Find probability density and hence probability
        var.setVal(m);
        double prb = var.getBinWidth(0)*pdf.getVal(var);
        prbSum+=prb;

        dat.get(j);
        nEvt=dat.weight();

        double mubin=nTot*prb;
        double contrib(0.);
        if (nEvt < 1) contrib = mubin;
        else contrib=mubin-nEvt+nEvt*log(nEvt/mubin);
        totNLL+=contrib;

        if(prt) cout << "Bin " << j << " prob = " << prb << " nEvt = " << nEvt << ", mu = " << mubin << " contribution " << contrib << endl;
    }

    totNLL*=2.0;
    if(prt) cout << pdf.GetName() << " nTot = " << nTot << " 2NLL constant = " << totNLL << endl;

    return totNLL;
}
示例#2
0
void setup(ModelConfig* mcInWs) {
  RooAbsPdf* combPdf = mcInWs->GetPdf();

  RooArgSet mc_obs = *mcInWs->GetObservables();
  RooArgSet mc_globs = *mcInWs->GetGlobalObservables();
  RooArgSet mc_nuis = *mcInWs->GetNuisanceParameters();

  // pair the nuisance parameter to the global observable
  RooArgSet mc_nuis_tmp = mc_nuis;
  RooArgList nui_list;
  RooArgList glob_list;
  RooArgSet constraint_set_tmp(*combPdf->getAllConstraints(mc_obs, mc_nuis_tmp, false));
  RooArgSet constraint_set;
  int counter_tmp = 0;
  unfoldConstraints(constraint_set_tmp, constraint_set, mc_obs, mc_nuis_tmp, counter_tmp);

  TIterator* cIter = constraint_set.createIterator();
  RooAbsArg* arg;
  while ((arg = (RooAbsArg*)cIter->Next())) {
    RooAbsPdf* pdf = (RooAbsPdf*)arg;
    if (!pdf) continue;

    // pdf->Print();

    TIterator* nIter = mc_nuis.createIterator();
    RooRealVar* thisNui = NULL;
    RooAbsArg* nui_arg;
    while ((nui_arg = (RooAbsArg*)nIter->Next())) {
      if (pdf->dependsOn(*nui_arg)) {
        thisNui = (RooRealVar*)nui_arg;
        break;
      }
    }
    delete nIter;

    // need this incase the observable isn't fundamental. 
    // in this case, see which variable is dependent on the nuisance parameter and use that.
    RooArgSet* components = pdf->getComponents();
    // components->Print();
    components->remove(*pdf);
    if (components->getSize()) {
      TIterator* itr1 = components->createIterator();
      RooAbsArg* arg1;
      while ((arg1 = (RooAbsArg*)itr1->Next())) {
        TIterator* itr2 = components->createIterator();
        RooAbsArg* arg2;
        while ((arg2 = (RooAbsArg*)itr2->Next())) {
          if (arg1 == arg2) continue;
          if (arg2->dependsOn(*arg1)) {
            components->remove(*arg1);
          }
        }
        delete itr2;
      }
      delete itr1;
    }

    if (components->getSize() > 1) {
      cout << "ERROR::Couldn't isolate proper nuisance parameter" << endl;
      return;
    }
    else if (components->getSize() == 1) {
      thisNui = (RooRealVar*)components->first();
    }

    TIterator* gIter = mc_globs.createIterator();
    RooRealVar* thisGlob = NULL;
    RooAbsArg* glob_arg;
    while ((glob_arg = (RooAbsArg*)gIter->Next())) {
      if (pdf->dependsOn(*glob_arg)) {
        thisGlob = (RooRealVar*)glob_arg;
        break;
      }
    }
    delete gIter;

    if (!thisNui || !thisGlob) {
      cout << "WARNING::Couldn't find nui or glob for constraint: " << pdf->GetName() << endl;
      //return;
      continue;
    }

    // cout << "Pairing nui: " << thisNui->GetName() << ", with glob: " << thisGlob->GetName() << ", from constraint: " << pdf->GetName() << endl;

    nui_list.add(*thisNui);
    glob_list.add(*thisGlob);

    if (string(pdf->ClassName()) == "RooPoisson")  {
      double minVal = max(0.0, thisGlob->getVal() - 8*sqrt(thisGlob->getVal()));
      double maxVal = max(10.0, thisGlob->getVal() + 8*sqrt(thisGlob->getVal()));
      thisNui->setRange(minVal, maxVal);
      thisGlob->setRange(minVal, maxVal);
    }
    else if (string(pdf->ClassName()) == "RooGaussian") {
      thisNui->setRange(-7, 7);
      thisGlob->setRange(-10, 10);
    }

    // thisNui->Print();
    // thisGlob->Print();
  }
  delete cIter;

}
示例#3
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));
}
// 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#5
0
//put very small data entries in a binned dataset to avoid unphysical pdfs, specifically for H->ZZ->4l
RooDataSet* makeData(RooDataSet* orig, RooSimultaneous* simPdf, const RooArgSet* observables, RooRealVar* firstPOI, double mass, double& mu_min)
{

  double max_soverb = 0;

  mu_min = -10e9;

  map<string, RooDataSet*> data_map;
  firstPOI->setVal(0);
  RooCategory* cat = (RooCategory*)&simPdf->indexCat();
  TList* datalist = orig->split(*(RooAbsCategory*)cat, true);
  TIterator* dataItr = datalist->MakeIterator();
  RooAbsData* ds;
  RooRealVar* weightVar = new RooRealVar("weightVar","weightVar",1);
  while ((ds = (RooAbsData*)dataItr->Next()))
  {
    string typeName(ds->GetName());
    cat->setLabel(typeName.c_str());
    RooAbsPdf* pdf = simPdf->getPdf(typeName.c_str());
    cout << "pdf: " << pdf << endl;
    RooArgSet* obs = pdf->getObservables(observables);
    cout << "obs: " << obs << endl;

    RooArgSet obsAndWeight(*obs, *weightVar);
    obsAndWeight.add(*cat);
    stringstream datasetName;
    datasetName << "newData_" << typeName;
    RooDataSet* thisData = new RooDataSet(datasetName.str().c_str(),datasetName.str().c_str(), obsAndWeight, WeightVar(*weightVar));

    RooRealVar* firstObs = (RooRealVar*)obs->first();
    //int ibin = 0;
    int nrEntries = ds->numEntries();
    for (int ib=0;ib<nrEntries;ib++)
    {
      const RooArgSet* event = ds->get(ib);
      const RooRealVar* thisObs = (RooRealVar*)event->find(firstObs->GetName());
      firstObs->setVal(thisObs->getVal());

      firstPOI->setVal(0);
      double b = pdf->expectedEvents(*firstObs)*pdf->getVal(obs);
      firstPOI->setVal(1);
      double s = pdf->expectedEvents(*firstObs)*pdf->getVal(obs) - b;

      if (s > 0)
      {
	mu_min = max(mu_min, -b/s);
	double soverb = s/b;
	if (soverb > max_soverb)
	{
	  max_soverb = soverb;
	  cout << "Found new max s/b: " << soverb << " in pdf " << pdf->GetName() << " at m = " << thisObs->getVal() << endl;
	}
      }

      if (b == 0 && s != 0)
      {
	cout << "Expecting non-zero signal and zero bg at m=" << firstObs->getVal() << " in pdf " << pdf->GetName() << endl;
      }
      if (s+b <= 0) 
      {
	cout << "expecting zero" << endl;
	continue;
      }


      double weight = ds->weight();
      if ((typeName.find("ATLAS_H_4mu") != string::npos || 
	   typeName.find("ATLAS_H_4e") != string::npos ||
	   typeName.find("ATLAS_H_2mu2e") != string::npos ||
	   typeName.find("ATLAS_H_2e2mu") != string::npos) && fabs(firstObs->getVal() - mass) < 10 && weight == 0)
      {
	cout << "adding event: " << firstObs->getVal() << endl;
	thisData->add(*event, pow(10., -9.));
      }
      else
      {
	//weight = max(pow(10.0, -9), weight);
	thisData->add(*event, weight);
      }
    }



    data_map[string(ds->GetName())] = (RooDataSet*)thisData;
  }

  
  RooDataSet* newData = new RooDataSet("newData","newData",RooArgSet(*observables, *weightVar), 
				       Index(*cat), Import(data_map), WeightVar(*weightVar));

  orig->Print();
  newData->Print();
  //newData->tree()->Scan("*");
  return newData;

}
示例#6
0
///
/// Fit to the minimum using an improve method.
/// The idea is to kill known minima. For this, we add a multivariate
/// Gaussian to the chi2 at the position of the minimum. Ideally it should
/// be a parabola shaped function, but the Gaussian is readily available.
/// A true parabola like in the original IMPROVE algorithm doesn't work
/// because apparently it affects the other regions of
/// the chi2 too much. There are two parameters to tune: the width of the
/// Gaussian, which is controlled by the error definition of the first fit,
/// and the height of the Gaussian, which is set to 16 (=4 sigma).
/// Three fits are performed: 1) initial fit, 2) fit with improved FCN,
/// 3) fit of the non-improved FCN using the result from step 2 as the start
/// parameters.
/// So far it is only available for the Prob method, via the probimprove
/// command line flag.
///
RooFitResult* Utils::fitToMinImprove(RooWorkspace *w, TString name)
{
	TString parsName = "par_"+name;
	TString obsName  = "obs_"+name;
	TString pdfName  = "pdf_"+name;
	int printlevel = -1;
	RooMsgService::instance().setGlobalKillBelow(ERROR);

	// step 1: find a minimum to start with
	RooFitResult *r1 = 0;
	{
		RooFormulaVar ll("ll", "ll", "-2*log(@0)", RooArgSet(*w->pdf(pdfName)));
		// RooFitResult* r1 = fitToMin(&ll, printlevel);
		RooMinuit m(ll);
		m.setPrintLevel(-2);
		m.setNoWarn();
		m.setErrorLevel(4.0); ///< define 2 sigma errors. This will make the hesse PDF 2 sigma wide!
		int status = m.migrad();
		r1 = m.save();
		// if ( 102<RadToDeg(w->var("g")->getVal())&&RadToDeg(w->var("g")->getVal())<103 )
		// {
		//   cout << "step 1" << endl;
		//   r1->Print("v");
		//   gStyle->SetPalette(1);
		//   float xmin = 0.;
		//   float xmax = 3.14;
		//   float ymin = 0.;
		//   float ymax = 0.2;
		//   TH2F* histo = new TH2F("histo", "histo", 100, xmin, xmax, 100, ymin, ymax);
		//   for ( int ix=0; ix<100; ix++ )
		//   for ( int iy=0; iy<100; iy++ )
		//   {
		//     float x = xmin + (xmax-xmin)*(double)ix/(double)100;
		//     float y = ymin + (ymax-ymin)*(double)iy/(double)100;
		//     w->var("d_dk")->setVal(x);
		//     w->var("r_dk")->setVal(y);
		//     histo->SetBinContent(ix+1,iy+1,ll.getVal());
		//   }
		//   newNoWarnTCanvas("c2");
		//   histo->GetZaxis()->SetRangeUser(0,20);
		//   histo->Draw("colz");
		//   setParameters(w, parsName, r1);
		// }
	}

	// step 2: build and fit the improved fcn
	RooFitResult *r2 = 0;
	{
		// create a Hesse PDF, import both PDFs into a new workspace,
		// so that their parameters are linked
		RooAbsPdf* hessePdf = r1->createHessePdf(*w->set(parsName));
		if ( !hessePdf ) return r1;
		// RooWorkspace* wImprove = (RooWorkspace*)w->Clone();
		RooWorkspace* wImprove = new RooWorkspace();
		wImprove->import(*w->pdf(pdfName));
		wImprove->import(*hessePdf);
		hessePdf = wImprove->pdf(hessePdf->GetName());
		RooAbsPdf* fullPdf = wImprove->pdf(pdfName);

		RooFormulaVar ll("ll", "ll", "-2*log(@0) +16*@1", RooArgSet(*fullPdf, *hessePdf));
		// RooFitResult *r2 = fitToMin(&ll, printlevel);
		RooMinuit m(ll);
		m.setPrintLevel(-2);
		m.setNoWarn();
		m.setErrorLevel(1.0);
		int status = m.migrad();
		r2 = m.save();

		// if ( 102<RadToDeg(w->var("g")->getVal())&&RadToDeg(w->var("g")->getVal())<103 )
		// {
		//   cout << "step 3" << endl;
		//   r2->Print("v");
		//
		//   gStyle->SetPalette(1);
		//   float xmin = 0.;
		//   float xmax = 3.14;
		//   float ymin = 0.;
		//   float ymax = 0.2;
		//   TH2F* histo = new TH2F("histo", "histo", 100, xmin, xmax, 100, ymin, ymax);
		//   for ( int ix=0; ix<100; ix++ )
		//   for ( int iy=0; iy<100; iy++ )
		//   {
		//     float x = xmin + (xmax-xmin)*(double)ix/(double)100;
		//     float y = ymin + (ymax-ymin)*(double)iy/(double)100;
		//     wImprove->var("d_dk")->setVal(x);
		//     wImprove->var("r_dk")->setVal(y);
		//     histo->SetBinContent(ix+1,iy+1,ll.getVal());
		//   }
		//   newNoWarnTCanvas("c7");
		//   histo->GetZaxis()->SetRangeUser(0,20);
		//   histo->Draw("colz");
		//   // setParameters(wImprove, parsName, r1);
		// }
		delete wImprove;
	}

	// step 3: use the fit result of the improved fit as
	// start parameters for the nominal fcn
	RooFitResult* r3;
	{
		setParameters(w, parsName, r2);
		RooFormulaVar ll("ll", "ll", "-2*log(@0)", RooArgSet(*w->pdf(pdfName)));
		RooMinuit m(ll);
		m.setPrintLevel(-2);
		m.setNoWarn();
		m.setErrorLevel(1.0);
		int status = m.migrad();
		r3 = m.save();
		// if ( 102<RadToDeg(w->var("g")->getVal())&&RadToDeg(w->var("g")->getVal())<103 )
		// {
		//   cout << "step 3" << endl;
		//   r3->Print("v");
		// }
	}

	// step 5: chose better minimum
	// cout << r1->minNll() << " " << r3->minNll() << endl;
	RooFitResult* r = 0;
	if ( r1->minNll()<r3->minNll() )
	{
		delete r3;
		r = r1;
	}
	else
	{
		delete r1;
		r = r3;
		// cout << "Utils::fitToMinImprove() : improved fit is better!" << endl;
	}

	RooMsgService::instance().setGlobalKillBelow(INFO);

	// set to best parameters
	setParameters(w, parsName, r);
	return r;
}
void StandardHypoTestDemo(const char* infile = "",
                          const char* workspaceName = "combined",
                          const char* modelSBName = "ModelConfig",
                          const char* modelBName = "",
                          const char* dataName = "obsData", 
                          int calcType = 0, // 0 freq 1 hybrid, 2 asymptotic
                          int testStatType = 3,   // 0 LEP, 1 TeV, 2 LHC, 3 LHC - one sided
                          int ntoys = 5000, 
                          bool useNC = false, 
                          const char * nuisPriorName = 0)
{

/*

  Other Parameter to pass in tutorial
  apart from standard for filename, ws, modelconfig and data

  type = 0 Freq calculator 
  type = 1 Hybrid calculator
  type = 2 Asymptotic calculator  

  testStatType = 0 LEP
  = 1 Tevatron 
  = 2 Profile Likelihood
  = 3 Profile Likelihood one sided (i.e. = 0 if mu < mu_hat)

  ntoys:         number of toys to use 

  useNumberCounting:  set to true when using number counting events 

  nuisPriorName:   name of prior for the nnuisance. This is often expressed as constraint term in the global model
  It is needed only when using the HybridCalculator (type=1)
  If not given by default the prior pdf from ModelConfig is used. 

  extra options are available as global paramwters of the macro. They major ones are: 
 
  generateBinned       generate binned data sets for toys (default is false) - be careful not to activate with 
  a too large (>=3) number of observables 
  nToyRatio            ratio of S+B/B toys (default is 2)
  printLevel
  
*/

   // disable - can cause some problems
   //ToyMCSampler::SetAlwaysUseMultiGen(true);

   SimpleLikelihoodRatioTestStat::SetAlwaysReuseNLL(true);
   ProfileLikelihoodTestStat::SetAlwaysReuseNLL(true);
   RatioOfProfiledLikelihoodsTestStat::SetAlwaysReuseNLL(true);

   //RooRandom::randomGenerator()->SetSeed(0);

   // to change minimizers 
   // ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
   // ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
   // ROOT::Math::MinimizerOptions::SetDefaultTolerance(1);

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

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

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

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

  
  /////////////////////////////////////////////////////////////
  // Tutorial starts here
  ////////////////////////////////////////////////////////////

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

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


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

  // make sure ingredients are found
  if(!data || !sbModel){
    w->Print();
    cout << "data or ModelConfig was not found" <<endl;
    return;
  }
  // make b model
  ModelConfig* bModel = (ModelConfig*) w->obj(modelBName);


   // case of no systematics
   // remove nuisance parameters from model
   if (noSystematics) { 
      const RooArgSet * nuisPar = sbModel->GetNuisanceParameters();
      if (nuisPar && nuisPar->getSize() > 0) { 
         std::cout << "StandardHypoTestInvDemo" << "  -  Switch off all systematics by setting them constant to their initial values" << std::endl;
         RooStats::SetAllConstant(*nuisPar);
      }
      if (bModel) { 
         const RooArgSet * bnuisPar = bModel->GetNuisanceParameters();
         if (bnuisPar) 
            RooStats::SetAllConstant(*bnuisPar);
      }
   }


  if (!bModel ) {
      Info("StandardHypoTestInvDemo","The background model %s does not exist",modelBName);
      Info("StandardHypoTestInvDemo","Copy it from ModelConfig %s and set POI to zero",modelSBName);
      bModel = (ModelConfig*) sbModel->Clone();
      bModel->SetName(TString(modelSBName)+TString("B_only"));      
      RooRealVar * var = dynamic_cast<RooRealVar*>(bModel->GetParametersOfInterest()->first());
      if (!var) return;
      double oldval = var->getVal();
      var->setVal(0);
      //bModel->SetSnapshot( RooArgSet(*var, *w->var("lumi"))  );
      bModel->SetSnapshot( RooArgSet(*var)  );
      var->setVal(oldval);
  }
  
   if (!sbModel->GetSnapshot() || poiValue > 0) { 
      Info("StandardHypoTestDemo","Model %s has no snapshot  - make one using model poi",modelSBName);
      RooRealVar * var = dynamic_cast<RooRealVar*>(sbModel->GetParametersOfInterest()->first());
      if (!var) return;
      double oldval = var->getVal();
      if (poiValue > 0)  var->setVal(poiValue);
      //sbModel->SetSnapshot( RooArgSet(*var, *w->var("lumi") ) );
      sbModel->SetSnapshot( RooArgSet(*var) );
      if (poiValue > 0) var->setVal(oldval);
      //sbModel->SetSnapshot( *sbModel->GetParametersOfInterest() );
   }

   



   // part 1, hypothesis testing 
   SimpleLikelihoodRatioTestStat * slrts = new SimpleLikelihoodRatioTestStat(*bModel->GetPdf(), *sbModel->GetPdf());
   // null parameters must includes snapshot of poi plus the nuisance values 
   RooArgSet nullParams(*bModel->GetSnapshot());
   if (bModel->GetNuisanceParameters()) nullParams.add(*bModel->GetNuisanceParameters());
   
   slrts->SetNullParameters(nullParams);
   RooArgSet altParams(*sbModel->GetSnapshot());
   if (sbModel->GetNuisanceParameters()) altParams.add(*sbModel->GetNuisanceParameters());
   slrts->SetAltParameters(altParams);


   ProfileLikelihoodTestStat * profll = new ProfileLikelihoodTestStat(*bModel->GetPdf());


   RatioOfProfiledLikelihoodsTestStat * 
      ropl = new RatioOfProfiledLikelihoodsTestStat(*bModel->GetPdf(), *sbModel->GetPdf(), sbModel->GetSnapshot());
   ropl->SetSubtractMLE(false);

   if (testStatType == 3) profll->SetOneSidedDiscovery(1);
   profll->SetPrintLevel(printLevel);

   // profll.SetReuseNLL(mOptimize);
   // slrts.SetReuseNLL(mOptimize);
   // ropl.SetReuseNLL(mOptimize);

   AsymptoticCalculator::SetPrintLevel(printLevel);

   HypoTestCalculatorGeneric *  hypoCalc = 0;
   // note here Null is B and Alt is S+B
   if (calcType == 0) hypoCalc = new  FrequentistCalculator(*data, *sbModel, *bModel);
   else if (calcType == 1) hypoCalc= new  HybridCalculator(*data, *sbModel, *bModel);
   else if (calcType == 2) hypoCalc= new  AsymptoticCalculator(*data, *sbModel, *bModel);

   if (calcType == 0) 
       ((FrequentistCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
   if (calcType == 1) 
       ((HybridCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
   if (calcType == 2 ) { 
      if (testStatType == 3) ((AsymptoticCalculator*) hypoCalc)->SetOneSidedDiscovery(true);  
      if (testStatType != 2 && testStatType != 3)  
         Warning("StandardHypoTestDemo","Only the PL test statistic can be used with AsymptoticCalculator - use by default a two-sided PL");
      

   }


   // check for nuisance prior pdf in case of nuisance parameters 
   if (calcType == 1 && (bModel->GetNuisanceParameters() || sbModel->GetNuisanceParameters() )) {
         RooAbsPdf * nuisPdf = 0; 
         if (nuisPriorName) nuisPdf = w->pdf(nuisPriorName);
         // use prior defined first in bModel (then in SbModel)
         if (!nuisPdf)  { 
            Info("StandardHypoTestDemo","No nuisance pdf given for the HybridCalculator - try to deduce  pdf from the   model");
            if (bModel->GetPdf() && bModel->GetObservables() ) 
               nuisPdf = RooStats::MakeNuisancePdf(*bModel,"nuisancePdf_bmodel");
            else 
               nuisPdf = RooStats::MakeNuisancePdf(*sbModel,"nuisancePdf_sbmodel");
         }   
         if (!nuisPdf ) {
            if (bModel->GetPriorPdf())  { 
               nuisPdf = bModel->GetPriorPdf();
               Info("StandardHypoTestDemo","No nuisance pdf given - try to use %s that is defined as a prior pdf in the B model",nuisPdf->GetName());            
            }
            else { 
               Error("StandardHypoTestDemo","Cannnot run Hybrid calculator because no prior on the nuisance parameter is specified or can be derived");
               return;
            }
         }
         assert(nuisPdf);
         Info("StandardHypoTestDemo","Using as nuisance Pdf ... " );
         nuisPdf->Print();
      
         const RooArgSet * nuisParams = (bModel->GetNuisanceParameters() ) ? bModel->GetNuisanceParameters() : sbModel->GetNuisanceParameters();
         RooArgSet * np = nuisPdf->getObservables(*nuisParams);
         if (np->getSize() == 0) { 
            Warning("StandardHypoTestDemo","Prior nuisance does not depend on nuisance parameters. They will be smeared in their full range");
         }
         delete np;
      
         ((HybridCalculator*)hypoCalc)->ForcePriorNuisanceAlt(*nuisPdf);
         ((HybridCalculator*)hypoCalc)->ForcePriorNuisanceNull(*nuisPdf);
   }

   // hypoCalc->ForcePriorNuisanceAlt(*sbModel->GetPriorPdf());
   // hypoCalc->ForcePriorNuisanceNull(*bModel->GetPriorPdf());

   ToyMCSampler * sampler = (ToyMCSampler *)hypoCalc->GetTestStatSampler();

   if (sampler && (calcType == 0 || calcType == 1) ) { 

      // look if pdf is number counting or extended
      if (sbModel->GetPdf()->canBeExtended() ) { 
         if (useNC)   Warning("StandardHypoTestDemo","Pdf is extended: but number counting flag is set: ignore it ");
      }
      else {
         // for not extended pdf
         if (!useNC)  { 
            int nEvents = data->numEntries();
            Info("StandardHypoTestDemo","Pdf is not extended: number of events to generate taken  from observed data set is %d",nEvents);
            sampler->SetNEventsPerToy(nEvents);
         }
         else {
            Info("StandardHypoTestDemo","using a number counting pdf");
            sampler->SetNEventsPerToy(1);
         }
      }
      
      if (data->isWeighted() && !generateBinned) { 
         Info("StandardHypoTestDemo","Data set is weighted, nentries = %d and sum of weights = %8.1f but toy generation is unbinned - it would be faster to set generateBinned to true\n",data->numEntries(), data->sumEntries());
      }
      if (generateBinned)  sampler->SetGenerateBinned(generateBinned);


      // set the test statistic
      if (testStatType == 0) sampler->SetTestStatistic(slrts); 
      if (testStatType == 1) sampler->SetTestStatistic(ropl); 
      if (testStatType == 2 || testStatType == 3) sampler->SetTestStatistic(profll); 

   }
   
   HypoTestResult *  htr = hypoCalc->GetHypoTest();
   htr->SetPValueIsRightTail(true);
   htr->SetBackgroundAsAlt(false);
   htr->Print(); // how to get meaningfull CLs at this point?

   delete sampler;
   delete slrts; 
   delete ropl; 
   delete profll;

   if (calcType != 2) {
      HypoTestPlot * plot = new HypoTestPlot(*htr,100);
      plot->SetLogYaxis(true);
      plot->Draw();
   }
   else { 
      std::cout << "Asymptotic results " << std::endl;
      
   }

   // look at expected significances 
   // found median of S+B distribution
   if (calcType != 2) { 

      SamplingDistribution * altDist = htr->GetAltDistribution();   
      HypoTestResult htExp("Expected Result");
      htExp.Append(htr);
      // find quantiles in alt (S+B) distribution 
      double p[5];
      double q[5];
      for (int i = 0; i < 5; ++i) { 
         double sig = -2  + i;
         p[i] = ROOT::Math::normal_cdf(sig,1);
      }
      std::vector<double> values = altDist->GetSamplingDistribution();
      TMath::Quantiles( values.size(), 5, &values[0], q, p, false);  

      for (int i = 0; i < 5; ++i) { 
         htExp.SetTestStatisticData( q[i] );
         double sig = -2  + i;      
         std::cout << " Expected p -value and significance at " << sig << " sigma = " 
                   << htExp.NullPValue() << " significance " << htExp.Significance() << " sigma " << std::endl; 
         
      }
   }
   else { 
      // case of asymptotic calculator 
      for (int i = 0; i < 5; ++i) { 
         double sig = -2  + i;      
         // sigma is inverted here 
         double pval = AsymptoticCalculator::GetExpectedPValues( htr->NullPValue(), htr->AlternatePValue(), -sig, false);
         std::cout << " Expected p -value and significance at " << sig << " sigma = " 
                   << pval << " significance " << ROOT::Math::normal_quantile_c(pval,1) << " sigma " << std::endl; 
         
      }
   }

}