void MultiNetwork::init(const ModelConfig& config,
ParamInitCallback callback,
const std::vector<ParameterType>& parameterTypes,
bool useGpu) {
CHECK_GT(config.sub_models_size(), 1) << "sub_models_size should GT 1";
// check submodel[0] is root
CHECK_EQ("root", config.sub_models(0).name())
<< "sub_models(0) should be root";
// ignore root
subNetworks_.resize(config.sub_models_size() - 1);
// base class
NeuralNetwork::init(config, callback, parameterTypes, useGpu);
// sub networks
for (int i = 1; i < config.sub_models_size(); ++i) {
std::string subModelName = config.sub_models(i).name();
if (FLAGS_parallel_nn) {
subNetworks_[i - 1] = std::unique_ptr<ParallelNeuralNetwork>(
new ParallelNeuralNetwork(subModelName, this));
} else {
subNetworks_[i - 1] = std::unique_ptr<NeuralNetwork>(
NeuralNetwork::newNeuralNetwork(subModelName, this));
}
subNetworks_[i - 1]->init(config);
}
}
void upper_limit_Bayesian_MCMC(Model* model,double confidence,int Niters){
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
cout<<"Calculating upper limit with the MCMC method"<<endl;
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
RooWorkspace* wspace = new RooWorkspace("wspace");
ModelConfig* modelConfig = new ModelConfig("bayes");
modelConfig->SetWorkspace(*wspace);
modelConfig->SetPdf(*model->get_complete_likelihood());
modelConfig->SetPriorPdf(*model->get_POI_prior());
modelConfig->SetParametersOfInterest(*model->get_POI_set());
// modelConfig->SetNuisanceParameters();
modelConfig->SetNuisanceParameters(*model->get_nuisance_set());
//configure the calculator
//model->Print();
cout<<" POI size "<<model->get_POI_set()->getSize()<<endl;
RooRealVar* firstPOI = (RooRealVar*) modelConfig->GetParametersOfInterest()->first();
MCMCCalculator mcmccalc(*model->get_data(), *modelConfig );
mcmccalc.SetTestSize(1-confidence);
mcmccalc.SetLeftSideTailFraction(0);
mcmccalc.SetNumIters(Niters);
MCMCInterval* interval = mcmccalc.GetInterval();
double ul = interval->UpperLimit(*firstPOI);
cout<<"UpperLimit: "<<ul<<endl;
}
//____________________________________
void DoHypothesisTest(RooWorkspace* wks){
// Use a RooStats ProfileLikleihoodCalculator to do the hypothesis test.
ModelConfig model;
model.SetWorkspace(*wks);
model.SetPdf("model");
//plc.SetData("data");
ProfileLikelihoodCalculator plc;
plc.SetData( *(wks->data("data") ));
// here we explicitly set the value of the parameters for the null.
// We want no signal contribution, eg. mu = 0
RooRealVar* mu = wks->var("mu");
// RooArgSet* nullParams = new RooArgSet("nullParams");
// nullParams->addClone(*mu);
RooArgSet poi(*mu);
RooArgSet * nullParams = (RooArgSet*) poi.snapshot();
nullParams->setRealValue("mu",0);
//plc.SetNullParameters(*nullParams);
plc.SetModel(model);
// NOTE: using snapshot will import nullparams
// in the WS and merge with existing "mu"
// model.SetSnapshot(*nullParams);
//use instead setNuisanceParameters
plc.SetNullParameters( *nullParams);
// We get a HypoTestResult out of the calculator, and we can query it.
HypoTestResult* htr = plc.GetHypoTest();
cout << "-------------------------------------------------" << endl;
cout << "The p-value for the null is " << htr->NullPValue() << endl;
cout << "Corresponding to a signifcance of " << htr->Significance() << endl;
cout << "-------------------------------------------------\n\n" << endl;
}
void MCStudy()
{
string fileName = "h4l_Template_2012_lowmass_unconstrained_new_v00.root";
const char * wsName = "combined"; //"w";
const char * modelSBName = "ModelConfig"; //"modelConfig";
const char * dataName = dataname.c_str();
TFile* file = TFile::Open(fileName);
// get the workspace out of file
RooWorkspace* w = (RooWorkspace*) file->Get(wsName);
if (!wsName) {
cout << "workspace not found" << endl;
return -1.0;
}
// get the modelConfig out of the file
ModelConfig* sbModel = (ModelConfig*) w->obj(modelSBName);
// get the data out of file
//RooAbsData* data = w->data(dataName);
// get toy MC data
TFile *fhist = new TFile("../ToyMC/toyMC_ggF125.root");
TH1F *hsum = (TH1F*) fhist->Get("sumtoy1");
RooRealVar m4l("m4l","m4l",120,130);
RooDataHist* data = new RooDataHist("data","data",x,hsum);
// get pdf
RooAbsPdf* model = sbModel->GetPdf();
RooPlot* xframe = m4l.frame();
data->plotOn(xframe);
model->fitTo(*data);
model->plotOn(xframe,LineColor(kRed));
TCanvas *c = new TCanvas("c","c");
xframe->Draw();
}
void upper_limit_Bayesian(Model* model,double confidence){
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
cout<<"Calculating upper limit with the Bayesian method"<<endl;
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
RooWorkspace* wspace = new RooWorkspace("wspace");
ModelConfig* modelConfig = new ModelConfig("bayes");
modelConfig->SetWorkspace(*wspace);
modelConfig->SetPdf(*model->get_complete_likelihood());
modelConfig->SetPriorPdf(*model->get_POI_prior());
modelConfig->SetParametersOfInterest(*model->get_POI_set());
//modelConfig->SetNuisanceParameters(*model->get_nuisance_set());
//configure the calculator
//model->Print();
cout<<" POI size "<<model->get_POI_set()->getSize()<<endl;
BayesianCalculator bcalc(*model->get_data(), *modelConfig);
//BayesianCalculator bcalc(*model->get_data(),*model->get_complete_likelihood(),*model->get_POI_set(),*model->get_POI_prior(),model->get_nuisance_set());
//BayesianCalculator bcalc(*model->get_data(),*model->get_complete_likelihood(),*model->get_POI_set(),*model->get_POI_prior(),0);
bcalc.SetLeftSideTailFraction(0); //for upper limit
//get the interval
bcalc.SetConfidenceLevel(confidence);
cout<<"Calculating"<<endl;
SimpleInterval* interval = bcalc.GetInterval();
double ul=interval->UpperLimit();
std::cout <<confidence <<"% CL upper limit: "<< ul<<endl;
TCanvas *c1=new TCanvas;
bcalc.SetScanOfPosterior(100);
RooPlot * plot = bcalc.GetPosteriorPlot();
plot->Draw();
c1->SaveAs("bayesian_PosteriorPlot.png");
}
double upper_limit_FC(Model* model,double confidence){
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
cout<<"Calculating upper limit with the FC method"<<endl;
cout<<"///////////////////////////////////////////////////////////////////////////////////////////"<<endl;
RooWorkspace* wspace = new RooWorkspace("wspace");
ModelConfig* modelConfig = new ModelConfig("FC");
modelConfig->SetWorkspace(*wspace);
modelConfig->SetPdf(*model->get_complete_likelihood());
modelConfig->SetPriorPdf(*model->get_POI_prior());
modelConfig->SetParametersOfInterest(*model->get_POI_set());
//modelConfig->SetParametersOfInterest(*wspace->set("poi"));
//modelConfig->SetNuisanceParameters(*wspace->set("nuis"));
// modelConfig->SetNuisanceParameters();
modelConfig->SetNuisanceParameters(*model->get_nuisance_set());
RooDataSet* data = model->get_data();
RooArgSet* poi= model->get_POI_set();
//configure the calculator
//model->Print();
cout<<" POI size "<<model->get_POI_set()->getSize()<<endl;
// use FeldmaCousins (takes ~20 min)
FeldmanCousins fc(*data, *modelConfig);
fc.SetConfidenceLevel(0.95); //0.9 central limit=0.95 upper limit
//fc.SetTestSize(.1); // set size of test
//number counting: dataset always has 1 entry with N events observed
fc.FluctuateNumDataEntries(false);
fc.UseAdaptiveSampling(true);
fc.SetNBins(200);
PointSetInterval* fcInt = NULL;
//ConfInterval* interval = 0;
RooRealVar* firstPOI = (RooRealVar*) modelConfig->GetParametersOfInterest()->first();
// if(doFeldmanCousins){ // takes 7 minutes
fcInt = (PointSetInterval*) fc.GetInterval(); // fix cast
//xs}
//interval = (PointSetInterval*) fc.GetInterval();
cout<<" ["<<fcInt->LowerLimit( *firstPOI ) << ", " <<
fcInt->UpperLimit( *firstPOI ) << "]" << endl;
cout<<" ["<<fcInt->LowerLimit( *firstPOI ) << ", " <<
fcInt->UpperLimit( *firstPOI ) << "]" << endl;
double ul=fcInt->UpperLimit( *firstPOI );
//double ul=interval->UpperLimit( *firstPOI );
return ul;
}
double TwoBody::printMcmcUpperLimit( double peak, ModelConfig &_mc, std::string filename ){
//
// print out the upper limit on the first Parameter of Interest
//
std::string _legend = "[TwoBody::printMcmcUpperLimit]: ";
char buf[1024];
double _limit = numeric_limits<double>::max();
if (mcInt){
//mc.SetWorkspace(*ws);
RooRealVar * firstPOI = (RooRealVar*) _mc.GetParametersOfInterest()->first();
_limit = mcInt->UpperLimit(*firstPOI);
std::cout << "\n95% upper limit on " << firstPOI->GetName() << " is : " <<
_limit << endl;
if (bMcmcConverged){
sprintf(buf, "%7.1f %7.6f", peak, _limit);
}
else{
sprintf(buf, "# %7.1f %7.6f # MCMC did not converge", peak, _limit);
}
}
else{
sprintf(buf, "# MCMC did not converge");
}
if (filename.size()!=0){
std::ofstream aFile;
// append to file if exists
aFile.open(filename.c_str(), std::ios_base::app);
aFile << buf << std::endl;
// close outfile here so it is safe even if subsequent iterations crash
aFile.close();
}
return _limit;
}
Double_t TwoBody::GetPoiUpper(std::string channel, Double_t peak, ModelConfig &_mc){
//
// Estimate a good value for the upper boundary of the range of POI
//
std::string legend = "[TwoBody::GetPoiUpper]: ";
double _range = -1.0;
std::cout << legend << "doing a rough estimate of the POI range" << std::endl;
// adding auto-channel option (multi) while
// preserving backwards compatibility
// if single channel
_range = GetPoiUpperSimple(channel, peak);
std::cout << legend << "crude estimate for poi range (x3): "
<< 3.0*_range << std::endl;
std::cout << legend
<< "this will be used if the profile likelihood ratio estimate fails"
<< std::endl;
std::cout << legend
<< "will try to estimate POI range better with profile likelihood ratio limit now"
<< std::endl;
Double_t result = 0.1;
// estimate limit with profile likelihood ratio and
// set the range to 3 times the limit
// query intervals
RooFit::MsgLevel msglevel = RooMsgService::instance().globalKillBelow();
RooMsgService::instance().setGlobalKillBelow(RooFit::FATAL);
RooRealVar * _poi = (RooRealVar *)_mc.GetParametersOfInterest()->first();
double upper_limit = GetPlrInterval(0.95, _mc)->UpperLimit( *_poi );
RooMsgService::instance().setGlobalKillBelow(msglevel);
// safety in case upper limit == 0
if (upper_limit<std::numeric_limits<double>::min()){
upper_limit = _range;
}
result = 3.0*upper_limit;
return result;
}
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 exercise_3() {
//Open the rootfile and get the workspace from the exercise_0
TFile fIn("exercise_0.root");
fIn.cd();
RooWorkspace *w = (RooWorkspace*)fIn.Get("w");
//You can set constant parameters that are known
//If you leave them floating, the fit procedure will determine their uncertainty
w->var("mean")->setConstant(kFALSE); //don't fix the mean, it's what we want to know the interval for!
w->var("sigma")->setConstant(kTRUE);
w->var("tau")->setConstant(kTRUE);
w->var("Nsig")->setConstant(kTRUE);
w->var("Nbkg")->setConstant(kTRUE);
//Set the RooModelConfig and let it know what the content of the workspace is about
ModelConfig model;
model.SetWorkspace(*w);
model.SetPdf("PDFtot");
//Let the model know what is the parameter of interest
RooRealVar* mean = w->var("mean");
mean->setRange(120., 130.); //this is mostly for plotting reasons
RooArgSet poi(*mean);
// set confidence level
double confidenceLevel = 0.68;
//Build the profile likelihood calculator
ProfileLikelihoodCalculator plc;
plc.SetData(*(w->data("PDFtotData")));
plc.SetModel(model);
plc.SetParameters(poi);
plc.SetConfidenceLevel(confidenceLevel);
//Get the interval
LikelihoodInterval* plInt = plc.GetInterval();
//Now let's do the same for the Bayesian Calculator
//Now we also need to specify a prior in the ModelConfig
//To be quicker, we'll use the PDF factory facility of RooWorkspace
//NB!! For simplicity, we are using a flat prior, but this doesn't mean it's the best choice!
w->factory("Uniform::prior(mean)");
model.SetPriorPdf(*w->pdf("prior"));
//Construct the bayesian calculator
BayesianCalculator bc(*(w->data("PDFtotData")), model);
bc.SetConfidenceLevel(confidenceLevel);
bc.SetParameters(poi);
SimpleInterval* bcInt = bc.GetInterval();
// Let's make a plot
TCanvas dataCanvas("dataCanvas");
dataCanvas.Divide(2,1);
dataCanvas.cd(1);
LikelihoodIntervalPlot plotInt((LikelihoodInterval*)plInt);
plotInt.SetTitle("Profile Likelihood Ratio and Posterior for mH");
plotInt.SetMaximum(3.);
plotInt.Draw();
dataCanvas.cd(2);
RooPlot *bcPlot = bc.GetPosteriorPlot();
bcPlot->Draw();
dataCanvas.SaveAs("exercise_3.gif");
//Now print the interval for mH for the two methods
cout << "PLC interval is [" << plInt->LowerLimit(*mean) << ", " <<
plInt->UpperLimit(*mean) << "]" << endl;
cout << "Bayesian interval is [" << bcInt->LowerLimit() << ", " <<
bcInt->UpperLimit() << "]" << endl;
}
// implementation
void TwoBinInstructional( void ){
// let's time this example
TStopwatch t;
t.Start();
// set RooFit random seed for reproducible results
RooRandom::randomGenerator()->SetSeed(4357);
// make model
RooWorkspace * pWs = new RooWorkspace("ws");
// derived from data
pWs->factory("xsec[0.2,0,2]"); // POI
pWs->factory("bg_b[10,0,50]"); // data driven nuisance
// predefined nuisances
pWs->factory("lumi[100,0,1000]");
pWs->factory("eff_a[0.2,0,1]");
pWs->factory("eff_b[0.05,0,1]");
pWs->factory("tau[0,1]");
pWs->factory("xsec_bg_a[0.05]"); // constant
pWs->var("xsec_bg_a")->setConstant(1);
// channel a (signal): lumi*xsec*eff_a + lumi*bg_a + tau*bg_b
pWs->factory("prod::sig_a(lumi,xsec,eff_a)");
pWs->factory("prod::bg_a(lumi,xsec_bg_a)");
pWs->factory("prod::tau_bg_b(tau, bg_b)");
pWs->factory("Poisson::pdf_a(na[14,0,100],sum::mu_a(sig_a,bg_a,tau_bg_b))");
// channel b (control): lumi*xsec*eff_b + bg_b
pWs->factory("prod::sig_b(lumi,xsec,eff_b)");
pWs->factory("Poisson::pdf_b(nb[11,0,100],sum::mu_b(sig_b,bg_b))");
// nuisance constraint terms (systematics)
pWs->factory("Lognormal::l_lumi(lumi,nom_lumi[100,0,1000],sum::kappa_lumi(1,d_lumi[0.1]))");
pWs->factory("Lognormal::l_eff_a(eff_a,nom_eff_a[0.20,0,1],sum::kappa_eff_a(1,d_eff_a[0.05]))");
pWs->factory("Lognormal::l_eff_b(eff_b,nom_eff_b[0.05,0,1],sum::kappa_eff_b(1,d_eff_b[0.05]))");
pWs->factory("Lognormal::l_tau(tau,nom_tau[0.50,0,1],sum::kappa_tau(1,d_tau[0.05]))");
//pWs->factory("Lognormal::l_bg_a(bg_a,nom_bg_a[0.05,0,1],sum::kappa_bg_a(1,d_bg_a[0.10]))");
// complete model PDF
pWs->factory("PROD::model(pdf_a,pdf_b,l_lumi,l_eff_a,l_eff_b,l_tau)");
// Now create sets of variables. Note that we could use the factory to
// create sets but in that case many of the sets would be duplicated
// when the ModelConfig objects are imported into the workspace. So,
// we create the sets outside the workspace, and only the needed ones
// will be automatically imported by ModelConfigs
// observables
RooArgSet obs(*pWs->var("na"), *pWs->var("nb"), "obs");
// global observables
RooArgSet globalObs(*pWs->var("nom_lumi"), *pWs->var("nom_eff_a"), *pWs->var("nom_eff_b"),
*pWs->var("nom_tau"),
"global_obs");
// parameters of interest
RooArgSet poi(*pWs->var("xsec"), "poi");
// nuisance parameters
RooArgSet nuis(*pWs->var("lumi"), *pWs->var("eff_a"), *pWs->var("eff_b"), *pWs->var("tau"), "nuis");
// priors (for Bayesian calculation)
pWs->factory("Uniform::prior_xsec(xsec)"); // for parameter of interest
pWs->factory("Uniform::prior_bg_b(bg_b)"); // for data driven nuisance parameter
pWs->factory("PROD::prior(prior_xsec,prior_bg_b)"); // total prior
// create data
pWs->var("na")->setVal(14);
pWs->var("nb")->setVal(11);
RooDataSet * pData = new RooDataSet("data","",obs);
pData->add(obs);
pWs->import(*pData);
//pData->Print();
// signal+background model
ModelConfig * pSbModel = new ModelConfig("SbModel");
pSbModel->SetWorkspace(*pWs);
pSbModel->SetPdf(*pWs->pdf("model"));
pSbModel->SetPriorPdf(*pWs->pdf("prior"));
pSbModel->SetParametersOfInterest(poi);
pSbModel->SetNuisanceParameters(nuis);
pSbModel->SetObservables(obs);
pSbModel->SetGlobalObservables(globalObs);
// set all but obs, poi and nuisance to const
SetConstants(pWs, pSbModel);
pWs->import(*pSbModel);
// background-only model
// use the same PDF as s+b, with xsec=0
// POI value under the background hypothesis
Double_t poiValueForBModel = 0.0;
ModelConfig* pBModel = new ModelConfig(*(RooStats::ModelConfig *)pWs->obj("SbModel"));
pBModel->SetName("BModel");
pBModel->SetWorkspace(*pWs);
pWs->import(*pBModel);
// find global maximum with the signal+background model
// with conditional MLEs for nuisance parameters
// and save the parameter point snapshot in the Workspace
// - safer to keep a default name because some RooStats calculators
// will anticipate it
RooAbsReal * pNll = pSbModel->GetPdf()->createNLL(*pData);
RooAbsReal * pProfile = pNll->createProfile(RooArgSet());
pProfile->getVal(); // this will do fit and set POI and nuisance parameters to fitted values
RooArgSet * pPoiAndNuisance = new RooArgSet();
if(pSbModel->GetNuisanceParameters())
pPoiAndNuisance->add(*pSbModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pSbModel->GetParametersOfInterest());
cout << "\nWill save these parameter points that correspond to the fit to data" << endl;
pPoiAndNuisance->Print("v");
pSbModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
// Find a parameter point for generating pseudo-data
// with the background-only data.
// Save the parameter point snapshot in the Workspace
pNll = pBModel->GetPdf()->createNLL(*pData);
pProfile = pNll->createProfile(poi);
((RooRealVar *)poi.first())->setVal(poiValueForBModel);
pProfile->getVal(); // this will do fit and set nuisance parameters to profiled values
pPoiAndNuisance = new RooArgSet();
if(pBModel->GetNuisanceParameters())
pPoiAndNuisance->add(*pBModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pBModel->GetParametersOfInterest());
cout << "\nShould use these parameter points to generate pseudo data for bkg only" << endl;
pPoiAndNuisance->Print("v");
pBModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
// inspect workspace
pWs->Print();
// save workspace to file
pWs->writeToFile("ws_twobin.root");
// clean up
delete pWs;
delete pData;
delete pSbModel;
delete pBModel;
} // ----- end of tutorial ----------------------------------------
void StandardFeldmanCousinsDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData"){
// -------------------------------------------------------
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
const char* filename = "";
if (!strcmp(infile,"")) {
filename = "results/example_combined_GaussExample_model.root";
bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
// if file does not exists generate with histfactory
if (!fileExist) {
#ifdef _WIN32
cout << "HistFactory file cannot be generated on Windows - exit" << endl;
return;
#endif
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
}
else
filename = infile;
// Try to open the file
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file ){
cout <<"StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
return;
}
// -------------------------------------------------------
// Tutorial starts here
// -------------------------------------------------------
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !mc){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
// -------------------------------------------------------
// 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
FeldmanCousins fc(*data,*mc);
fc.SetConfidenceLevel(0.95); // 95% interval
//fc.AdditionalNToysFactor(0.1); // to speed up the result
fc.UseAdaptiveSampling(true); // speed it up a bit
fc.SetNBins(10); // set how many points per parameter of interest to scan
fc.CreateConfBelt(true); // save the information in the belt for plotting
// 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, 1, "workers=4", kFALSE);
// ToyMCSampler* toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler();
// 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
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
interval->LowerLimit(*firstPOI) << ", "<<
interval->UpperLimit(*firstPOI) <<"] "<<endl;
// ---------------------------------------------
// No nice plots yet, so plot the belt by hand
// 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());
// 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 arMin = belt->GetAcceptanceRegionMax(*tmpPoint);
double poiVal = tmpPoint->getRealValue(firstPOI->GetName()) ;
histOfThresholds->Fill(poiVal,arMax);
}
histOfThresholds->SetMinimum(0);
histOfThresholds->Draw();
}
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 IntervalExamples()
{
// Time this macro
TStopwatch t;
t.Start();
// set RooFit random seed for reproducible results
RooRandom::randomGenerator()->SetSeed(3001);
// make a simple model via the workspace factory
RooWorkspace* wspace = new RooWorkspace();
wspace->factory("Gaussian::normal(x[-10,10],mu[-1,1],sigma[1])");
wspace->defineSet("poi","mu");
wspace->defineSet("obs","x");
// specify components of model for statistical tools
ModelConfig* modelConfig = new ModelConfig("Example G(x|mu,1)");
modelConfig->SetWorkspace(*wspace);
modelConfig->SetPdf( *wspace->pdf("normal") );
modelConfig->SetParametersOfInterest( *wspace->set("poi") );
modelConfig->SetObservables( *wspace->set("obs") );
// create a toy dataset
RooDataSet* data = wspace->pdf("normal")->generate(*wspace->set("obs"),100);
data->Print();
// for convenience later on
RooRealVar* x = wspace->var("x");
RooRealVar* mu = wspace->var("mu");
// set confidence level
double confidenceLevel = 0.95;
// example use profile likelihood calculator
ProfileLikelihoodCalculator plc(*data, *modelConfig);
plc.SetConfidenceLevel( confidenceLevel);
LikelihoodInterval* plInt = plc.GetInterval();
// example use of Feldman-Cousins
FeldmanCousins fc(*data, *modelConfig);
fc.SetConfidenceLevel( confidenceLevel);
fc.SetNBins(100); // number of points to test per parameter
fc.UseAdaptiveSampling(true); // make it go faster
// Here, we consider only ensembles with 100 events
// The PDF could be extended and this could be removed
fc.FluctuateNumDataEntries(false);
// Proof
// ProofConfig pc(*wspace, 4, "workers=4", kFALSE); // proof-lite
//ProofConfig pc(w, 8, "localhost"); // proof cluster at "localhost"
// ToyMCSampler* toymcsampler = (ToyMCSampler*) fc.GetTestStatSampler();
// toymcsampler->SetProofConfig(&pc); // enable proof
PointSetInterval* interval = (PointSetInterval*) fc.GetInterval();
// example use of BayesianCalculator
// now we also need to specify a prior in the ModelConfig
wspace->factory("Uniform::prior(mu)");
modelConfig->SetPriorPdf(*wspace->pdf("prior"));
// example usage of BayesianCalculator
BayesianCalculator bc(*data, *modelConfig);
bc.SetConfidenceLevel( confidenceLevel);
SimpleInterval* bcInt = bc.GetInterval();
// example use of MCMCInterval
MCMCCalculator mc(*data, *modelConfig);
mc.SetConfidenceLevel( confidenceLevel);
// special options
mc.SetNumBins(200); // bins used internally for representing posterior
mc.SetNumBurnInSteps(500); // first N steps to be ignored as burn-in
mc.SetNumIters(100000); // how long to run chain
mc.SetLeftSideTailFraction(0.5); // for central interval
MCMCInterval* mcInt = mc.GetInterval();
// for this example we know the expected intervals
double expectedLL = data->mean(*x)
+ ROOT::Math::normal_quantile( (1-confidenceLevel)/2,1)
/ sqrt(data->numEntries());
double expectedUL = data->mean(*x)
+ ROOT::Math::normal_quantile_c((1-confidenceLevel)/2,1)
/ sqrt(data->numEntries()) ;
// Use the intervals
std::cout << "expected interval is [" <<
expectedLL << ", " <<
expectedUL << "]" << endl;
cout << "plc interval is [" <<
plInt->LowerLimit(*mu) << ", " <<
plInt->UpperLimit(*mu) << "]" << endl;
std::cout << "fc interval is ["<<
interval->LowerLimit(*mu) << " , " <<
interval->UpperLimit(*mu) << "]" << endl;
cout << "bc interval is [" <<
bcInt->LowerLimit() << ", " <<
bcInt->UpperLimit() << "]" << endl;
cout << "mc interval is [" <<
mcInt->LowerLimit(*mu) << ", " <<
mcInt->UpperLimit(*mu) << "]" << endl;
mu->setVal(0);
cout << "is mu=0 in the interval? " <<
plInt->IsInInterval(RooArgSet(*mu)) << endl;
// make a reasonable style
gStyle->SetCanvasColor(0);
gStyle->SetCanvasBorderMode(0);
gStyle->SetPadBorderMode(0);
gStyle->SetPadColor(0);
gStyle->SetCanvasColor(0);
gStyle->SetTitleFillColor(0);
gStyle->SetFillColor(0);
gStyle->SetFrameFillColor(0);
gStyle->SetStatColor(0);
// some plots
TCanvas* canvas = new TCanvas("canvas");
canvas->Divide(2,2);
// plot the data
canvas->cd(1);
RooPlot* frame = x->frame();
data->plotOn(frame);
data->statOn(frame);
frame->Draw();
// plot the profile likelihood
canvas->cd(2);
LikelihoodIntervalPlot plot(plInt);
plot.Draw();
// plot the MCMC interval
canvas->cd(3);
MCMCIntervalPlot* mcPlot = new MCMCIntervalPlot(*mcInt);
mcPlot->SetLineColor(kGreen);
mcPlot->SetLineWidth(2);
mcPlot->Draw();
canvas->cd(4);
RooPlot * bcPlot = bc.GetPosteriorPlot();
bcPlot->Draw();
canvas->Update();
t.Stop();
t.Print();
}
void PlotAll(TString wsname)
{
char* binLabels[19] = {"60","70","80","90","100","110","120","130","140","150","160","170","180","190","200","250","300","400","1000"};
//get the stuff from the workspace:
TFile* file=TFile::Open(wsname);
RooWorkspace* ws = (RooWorkspace*)file->Get("combined");
ModelConfig *mc = (ModelConfig*)ws->obj("ModelConfig");
RooAbsData *data = ws->data("obsData");
RooSimultaneous* simPdf=(RooSimultaneous*)(mc->GetPdf());
RooAbsReal* nll=simPdf->createNLL(*data);
// FPT 0 **************************************
// EM channel
RooCategory* chanCat = (RooCategory*) (&simPdf->indexCat());
TIterator* iterat = chanCat->typeIterator() ;
RooCatType* ttype = (RooCatType*)iterat->Next();
RooAbsPdf *pdf_stateEM = simPdf->getPdf(ttype->GetName()) ;
RooArgSet *obstmpEM = pdf_stateEM->getObservables( *mc->GetObservables() ) ;
// get EM data
RooAbsData *dataEM = data->reduce(Form("%s==%s::%s",chanCat->GetName(),chanCat->GetName(),ttype->GetName()));
RooRealVar *obsEM = ((RooRealVar*) obstmpEM->first());
TString chanName1(ttype->GetName());
// create data histogram
TH1* hdataEM = dataEM->createHistogram("Data "+chanName1,*obsEM);
// set errors to gaussian
for (int ib=0 ; ib<hdataEM->GetNbinsX()+1 ; ib++) hdataEM->SetBinError(ib, sqrt(hdataEM->GetBinContent(ib)));
double EMnorm = pdf_stateEM->expectedEvents(*obsEM);
//****************************
// ME channel
ttype = (RooCatType*)iterat->Next();
RooAbsPdf* pdf_stateME = simPdf->getPdf(ttype->GetName()) ;
RooArgSet* obstmpME = pdf_stateME->getObservables( *mc->GetObservables() ) ;
// get ME data
RooAbsData *dataME = data->reduce(Form("%s==%s::%s",chanCat->GetName(),chanCat->GetName(),ttype->GetName()));
RooRealVar* obsME = ((RooRealVar*) obstmpME->first());
TString chanName2(ttype->GetName());
// create data histogram
TH1* hdataME = dataME->createHistogram("Data "+chanName2,*obsME);
// set errors to gaussian
for (int ib=0 ; ib<hdataME->GetNbinsX()+1 ; ib++) hdataME->SetBinError(ib, sqrt(hdataME->GetBinContent(ib)));
// get initial BG histogram
//TH1* h_initial_BG_EM = pdf_stateEM->createHistogram("initial_BG_EM",*obsEM);
//TH1* h_initial_BG_ME = pdf_stateME->createHistogram("initial_BG_ME",*obsME);
double MEnorm = pdf_stateME->expectedEvents(*obsME);
cout << "EM expected events = " << EMnorm << ", ME expected events = " << MEnorm << "." << endl;
//h_initial_BG_EM->Scale(EMnorm);
//h_initial_BG_ME->Scale(MEnorm);
// get initial gammas
int nbins = hdataEM->GetNbinsX();
double InitGamma[nbins];
for (int i=0; i<nbins; i++)
{
TString varname = "gamma_B0_l1pt0_bin_"+NumberToString(i);
InitGamma[i] = ws->var(varname)->getVal();
cout << "initial gamma"+NumberToString(i)+" = " << InitGamma[i] << endl;
}
double InitFpt = ws->var("fl1pt_l1pt0")->getVal();
cout << "initial fpt_l1pt0 = " << InitFpt << endl;
// DO THE GLOBAL FIT
minimize(nll);
// get final BG histograms
TH1* h_final_BG_EM = pdf_stateEM->createHistogram("final_BG_EM",*obsEM);
TH1* h_final_BG_ME = pdf_stateME->createHistogram("final_BG_ME",*obsME);
h_final_BG_EM->Scale(EMnorm);
h_final_BG_ME->Scale(MEnorm);
// uncertainty bands
TH1D* BuncertaintyEM = new TH1D("BuncertaintyEM","BuncertaintyEM",nbins,0,nbins);
TH1D* BuncertaintyME = new TH1D("BuncertaintyME","BuncertaintyME",nbins,0,nbins);
for (int i=1; i<=nbins; i++){
double sigbEM = h_final_BG_EM->GetBinError(i);
double bEM = h_final_BG_EM->GetBinContent(i);
BuncertaintyEM->SetBinError(i,sigbEM); BuncertaintyEM->SetBinContent(i,bEM);
double sigbME = h_final_BG_ME->GetBinError(i);
double bME = h_final_BG_ME->GetBinContent(i);
BuncertaintyME->SetBinError(i,sigbME); BuncertaintyME->SetBinContent(i,bME);
}
//BuncertaintyEM->SetFillStyle(3004);
BuncertaintyEM->SetFillColor(kGreen-9);
BuncertaintyEM->SetLineColor(kBlack); BuncertaintyEM->SetLineStyle(2);
//BuncertaintyME->SetFillStyle(3004);
BuncertaintyME->SetFillColor(kBlue-9);
BuncertaintyME->SetLineColor(kBlack); BuncertaintyME->SetLineStyle(2);
// get gammas after fit
double FinalGamma[nbins];
//TH1* h_initBG_times_gamma = (TH1*)h_initial_BG_EM->Clone("initBGEM_times_gamma");
for (int i=0; i<nbins; i++)
{
TString varname = "gamma_B0_l1pt0_bin_"+NumberToString(i);
FinalGamma[i] = ws->var(varname)->getVal();
cout << "Final gamma in bin "+NumberToString(i)+" = " << FinalGamma[i] << endl;
// h_initBG_times_gamma->SetBinContent(i+1,h_initial_BG_EM->GetBinContent(i+1)*FinalGamma[i]);
}
//double FinalFpt = ws->var("fl1pt_l1pt0")->getVal();
// get final alpha (pull)
RooRealVar* alphaVar = ws->var("alpha_l1ptsys_l1pt0");
double alpha, alphaErr;
if (alphaVar != NULL) {
alpha = ws->var("alpha_l1ptsys_l1pt0")->getVal();
alphaErr = ws->var("alpha_l1ptsys_l1pt0")->getError();
}
//FOR UNCONSTRAINED FPT - get final fpts
double FinalFpt[5];
double FinalFptErr[5];
for (int k=0; k<5; k++){
TString varname = "fl1pt_l1pt"+NumberToString(k);
FinalFpt[k] = ws->var(varname)->getVal();
FinalFptErr[k] = ws->var(varname)->getError();
cout << varname << " = " << FinalFpt[k] << " +- " << FinalFptErr[k] << endl;
}
// get POI value
double mu = ws->var("mu_BR_htm")->getVal();
double muErr = ws->var("mu_BR_htm")->getError();
// Draw
TCanvas* c1 = new TCanvas("BG and Data "+chanName1+" "+chanName2,"BG and Data "+chanName1+" "+chanName2,600,600);
BuncertaintyEM->Draw("E3 sames"); BuncertaintyME->Draw("E3 sames");
//h_initial_BG_EM->SetLineColor(kGreen+2); h_initial_BG_EM->SetLineStyle(2); h_initial_BG_EM->Draw("sames");
hdataEM->SetLineColor(kGreen+2); hdataEM->SetMarkerStyle(20); hdataEM->SetMarkerColor(kGreen+2);
hdataEM->Draw("e1 sames");
//h_initial_BG_ME->SetLineColor(kBlue); h_initial_BG_ME->SetLineStyle(2); h_initial_BG_ME->Draw("sames");
hdataME->SetLineColor(kBlue); hdataME->SetMarkerStyle(20); hdataME->SetMarkerColor(kBlue);
hdataME->Draw("e1 sames");
h_final_BG_EM->SetLineColor(kGreen+2); h_final_BG_EM->SetLineWidth(2); h_final_BG_EM->Draw("sames");
h_final_BG_ME->SetLineColor(kBlue); h_final_BG_ME->SetLineWidth(2); h_final_BG_ME->Draw("sames");
TLegend* leg = new TLegend(0.5,0.45,0.85,0.65);
leg->SetFillColor(kWhite); leg->SetBorderSize(1); leg->SetLineColor(0); //leg->SetTextFont(14);
leg->SetTextSize(.03);
leg->AddEntry(hdataME,"DATA #mue","lep");
leg->AddEntry(hdataEM,"DATA e#mu","lep");
//leg->AddEntry(h_initial_BG_ME,"Initial #mue PDF","l");
//leg->AddEntry(h_initial_BG_EM,"Initial e#mu PDF","l");
leg->AddEntry(h_final_BG_ME,"#mue PDF = #gamma_{i}B_{i} + #muS_{i}","l");
leg->AddEntry(h_final_BG_EM,"e#mu PDF = f(1+#alpha#sigma)(#gamma_{i}B_{i}+#muW_{i})","l");
leg->Draw();
cout << " ********************* Fit Values **************************** " << endl;
if (alphaVar != NULL){cout << "alpha = " << alpha << " +- " << alphaErr << endl;}
cout << "mu = " << mu << " +- " << muErr << endl;
TString WriteDownAlphaValue;
TString WriteDownMuValue;
WriteDownAlphaValue = "Fpt0 = ";
WriteDownMuValue = "#mu = ";
WriteDownAlphaValue += Form("%4.4f",FinalFpt[0]);
WriteDownAlphaValue += "#pm";
WriteDownAlphaValue += Form("%4.4f",FinalFptErr[0]);
WriteDownMuValue += Form("%4.4f",mu);
WriteDownMuValue += "#pm";
WriteDownMuValue += Form("%4.4f",muErr);
TLatex *texl = new TLatex(12,25,WriteDownAlphaValue);
texl->SetTextAlign(22); texl->SetTextSize(0.03);
TLatex *texl2 = new TLatex(12,23,WriteDownMuValue);
texl2->SetTextAlign(22); texl2->SetTextSize(0.03);
texl->Draw();
texl2->Draw();
//FPT 1 ***********************************
ttype = (RooCatType*)iterat->Next();
RooAbsPdf *pdf_stateEM1 = simPdf->getPdf(ttype->GetName()) ;
RooArgSet *obstmpEM1 = pdf_stateEM1->getObservables( *mc->GetObservables() ) ;
RooAbsData *dataEM1 = data->reduce(Form("%s==%s::%s",chanCat->GetName(),chanCat->GetName(),ttype->GetName()));
RooRealVar *obsEM1 = ((RooRealVar*) obstmpEM1->first());
TString chanName11(ttype->GetName());
TH1* hdataEM1 = dataEM1->createHistogram("Data "+chanName11,*obsEM1);
for (int ib=0 ; ib<hdataEM1->GetNbinsX()+1 ; ib++) hdataEM1->SetBinError(ib, sqrt(hdataEM1->GetBinContent(ib)));
double EMnorm1 = pdf_stateEM1->expectedEvents(*obsEM1);
ttype = (RooCatType*)iterat->Next();
RooAbsPdf* pdf_stateME1 = simPdf->getPdf(ttype->GetName()) ;
RooArgSet* obstmpME1 = pdf_stateME1->getObservables( *mc->GetObservables() ) ;
RooAbsData *dataME1 = data->reduce(Form("%s==%s::%s",chanCat->GetName(),chanCat->GetName(),ttype->GetName()));
RooRealVar* obsME1 = ((RooRealVar*) obstmpME1->first());
TString chanName21(ttype->GetName());
TH1* hdataME1 = dataME1->createHistogram("Data "+chanName21,*obsME1);
for (int ib=0 ; ib<hdataME1->GetNbinsX()+1 ; ib++) hdataME1->SetBinError(ib, sqrt(hdataME1->GetBinContent(ib)));
double MEnorm1 = pdf_stateME1->expectedEvents(*obsME1);
TH1* h_final_BG_EM1 = pdf_stateEM1->createHistogram("final_BG_EM1",*obsEM1);
TH1* h_final_BG_ME1 = pdf_stateME1->createHistogram("final_BG_ME1",*obsME1);
h_final_BG_EM1->Scale(EMnorm1);
h_final_BG_ME1->Scale(MEnorm1);
TH1D* BuncertaintyEM1 = new TH1D("BuncertaintyEM1","BuncertaintyEM1",nbins,0,nbins);
TH1D* BuncertaintyME1 = new TH1D("BuncertaintyME1","BuncertaintyME1",nbins,0,nbins);
for (int i=1; i<=nbins; i++){
double sigbEM = h_final_BG_EM1->GetBinError(i);
double bEM = h_final_BG_EM1->GetBinContent(i);
BuncertaintyEM1->SetBinError(i,sigbEM); BuncertaintyEM1->SetBinContent(i,bEM);
double sigbME = h_final_BG_ME1->GetBinError(i);
double bME = h_final_BG_ME1->GetBinContent(i);
BuncertaintyME1->SetBinError(i,sigbME); BuncertaintyME1->SetBinContent(i,bME);
}
BuncertaintyEM1->SetFillColor(kGreen-9);
BuncertaintyEM1->SetLineColor(kBlack); BuncertaintyEM1->SetLineStyle(2);
BuncertaintyME1->SetFillColor(kBlue-9);
BuncertaintyME1->SetLineColor(kBlack); BuncertaintyME1->SetLineStyle(2);
double FinalGamma1[nbins];
for (int i=0; i<nbins; i++)
{
TString varname = "gamma_B0_l1pt1_bin_"+NumberToString(i);
FinalGamma1[i] = ws->var(varname)->getVal();
cout << "Final gamma in bin "+NumberToString(i)+" = " << FinalGamma1[i] << endl;
}
TCanvas* c2 = new TCanvas("BG and Data "+chanName11+" "+chanName21,"BG and Data "+chanName11+" "+chanName21,600,600);
BuncertaintyEM1->Draw("E3 sames"); BuncertaintyME1->Draw("E3 sames");
hdataEM1->SetLineColor(kGreen+2); hdataEM1->SetMarkerStyle(20); hdataEM1->SetMarkerColor(kGreen+2);
hdataEM1->Draw("e1 sames");
hdataME1->SetLineColor(kBlue); hdataME1->SetMarkerStyle(20); hdataME1->SetMarkerColor(kBlue);
hdataME1->Draw("e1 sames");
h_final_BG_EM1->SetLineColor(kGreen+2); h_final_BG_EM1->SetLineWidth(2); h_final_BG_EM1->Draw("sames");
h_final_BG_ME1->SetLineColor(kBlue); h_final_BG_ME1->SetLineWidth(2); h_final_BG_ME1->Draw("sames");
leg->Draw();
cout << " ********************* Fit Values **************************** " << endl;
cout << "mu = " << mu << " +- " << muErr << endl;
TString WriteDownAlphaValue1;
WriteDownAlphaValue1 = "Fpt1 = ";
WriteDownAlphaValue1 += Form("%4.4f",FinalFpt[1]);
WriteDownAlphaValue1 += "#pm";
WriteDownAlphaValue1 += Form("%4.4f",FinalFptErr[1]);
TLatex *texl11 = new TLatex(12,25,WriteDownAlphaValue1);
texl11->SetTextAlign(22); texl11->SetTextSize(0.03);
texl11->Draw();
texl2->Draw();
}
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;
}
//void RunToyScan5(TString fileName, double startVal, double stopVal, TString outFile) {
void frequentist(TString fileName) {
cout << "Starting frequentist " << time(NULL) << endl;
double startVal = 0;
double stopVal = 200;
TString outFile = "";
int nToys = 1 ;
int nscanpoints = 2 ;
/*
gROOT->LoadMacro("RooBetaPdf.cxx+") ;
gROOT->LoadMacro("RooRatio.cxx+") ;
gROOT->LoadMacro("RooPosDefCorrGauss.cxx+") ;
*/
// get relevant objects out of the "ws" file
TFile *file = TFile::Open(fileName);
if(!file){
cout <<"file not found" << endl;
return;
}
RooWorkspace* w = (RooWorkspace*) file->Get("workspace");
if(!w){
cout <<"workspace not found" << endl;
return;
}
ModelConfig* mc = (ModelConfig*) w->obj("S+B_model");
RooAbsData* data = w->data("data");
if( !data || !mc ){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
RooRealVar* myPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
myPOI->setRange(0, 1000.);
ModelConfig* bModel = (ModelConfig*) w->obj("B_model");
ModelConfig* sbModel = (ModelConfig*) w->obj("S+B_model");
ProfileLikelihoodTestStat profll(*sbModel->GetPdf());
profll.SetPrintLevel(2);
profll.SetOneSided(1);
TestStatistic * testStat = &profll;
HypoTestCalculatorGeneric * hc = 0;
hc = new FrequentistCalculator(*data, *bModel, *sbModel);
ToyMCSampler *toymcs = (ToyMCSampler*)hc->GetTestStatSampler();
toymcs->SetMaxToys(10000);
toymcs->SetNEventsPerToy(1);
toymcs->SetTestStatistic(testStat);
((FrequentistCalculator *)hc)->SetToys(nToys,nToys);
HypoTestInverter calc(*hc);
calc.SetConfidenceLevel(0.95);
calc.UseCLs(true);
//calc.SetVerbose(true);
calc.SetVerbose(2);
cout << "About to set fixed scan " << time(NULL) << endl;
calc.SetFixedScan(nscanpoints,startVal,stopVal);
cout << "About to do inverter " << time(NULL) << endl;
HypoTestInverterResult * res_toysCLs_calculator = calc.GetInterval();
cout << "CLs = " << res_toysCLs_calculator->UpperLimit()
<< " CLs_exp = " << res_toysCLs_calculator->GetExpectedUpperLimit(0)
<< " CLs_exp(-1s) = " << res_toysCLs_calculator->GetExpectedUpperLimit(-1)
<< " CLs_exp(+1s) = " << res_toysCLs_calculator->GetExpectedUpperLimit(1) << endl ;
/*
// dump results string to output file
ofstream outStream ;
outStream.open(outFile,ios::app) ;
outStream << "CLs = " << res_toysCLs_calculator->UpperLimit()
<< " CLs_exp = " << res_toysCLs_calculator->GetExpectedUpperLimit(0)
<< " CLs_exp(-1s) = " << res_toysCLs_calculator->GetExpectedUpperLimit(-1)
<< " CLs_exp(+1s) = " << res_toysCLs_calculator->GetExpectedUpperLimit(1) << endl ;
outStream.close() ;
*/
cout << "End of frequentist " << time(NULL) << endl;
return ;
}
void runQ(const char* inFileName,
const char* wsName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData",
const char* asimov0DataName = "asimovData_0",
const char* conditional0Snapshot = "conditionalGlobs_0",
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;
bool errFast = 0;
bool goFast = 1;
bool remakeData = 1;
bool doRightSided = 1;
bool doInj = 0;
bool doObs = 1;
bool doMedian = 1;
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");
RooNLLVar::SetIgnoreZeroEntries(1);
ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
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();
if (string(mc->GetPdf()->ClassName()) == "RooSimultaneous" && remakeData)
{
RooSimultaneous* simPdf = (RooSimultaneous*)mc->GetPdf();
double min_mu;
data = makeData(data, simPdf, mc->GetObservables(), mu, mass, min_mu);
}
RooDataSet* asimovData0 = (RooDataSet*)ws->data(asimov0DataName);
if (!asimovData0)
{
cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
makeAsimovData(mc, true, ws, mc->GetPdf(), data, 1);
ws->Print();
asimovData0 = (RooDataSet*)ws->data("asimovData_0");
}
RooDataSet* asimovData1 = (RooDataSet*)ws->data(asimov1DataName);
if (!asimovData1)
{
cout << "Asimov data doesn't exist! Please, allow me to build one for you..." << endl;
makeAsimovData(mc, true, ws, mc->GetPdf(), data, 0);
ws->Print();
asimovData1 = (RooDataSet*)ws->data("asimovData_1");
}
if (!doRightSided) mu->setRange(0, 40);
else mu->setRange(-40, 40);
bool old = false;
if (old)
{
mu->setVal(0);
RooArgSet poi(*mu);
ProfileLikelihoodTestStat_modified asimov_testStat_sig(*mc->GetPdf());
asimov_testStat_sig.SetRightSided(doRightSided);
asimov_testStat_sig.SetNuis(&nuis);
if (!doInj) asimov_testStat_sig.SetDoAsimov(true, 1);
asimov_testStat_sig.SetWorkspace(ws);
ProfileLikelihoodTestStat_modified testStat(*mc->GetPdf());
testStat.SetRightSided(doRightSided);
testStat.SetNuis(&nuis);
testStat.SetWorkspace(ws);
//RooMinimizerFcn::SetOverrideEverything(true);
double med_sig = 0;
double med_testStat_val = 0;
//gRandom->SetSeed(1);
//RooRandom::randomGenerator()->SetSeed(1);
RooNLLVar::SetIgnoreZeroEntries(1);
if (asimov1DataName != "" && doMedian)
{
mu->setVal(0);
if (!doInj) mu->setRange(0, 2);
ws->loadSnapshot("conditionalNuis_0");
asimov_testStat_sig.SetLoadUncondSnapshot("conditionalNuis_1");
if (string(conditional1Snapshot) != "") ws->loadSnapshot(conditional1Snapshot);
med_testStat_val = 2*asimov_testStat_sig.Evaluate(*asimovData1, poi);
if (med_testStat_val < 0 && !doInj)
{
mu->setVal(0);
med_testStat_val = 2*asimov_testStat_sig.Evaluate(*asimovData1, poi); // just try again
}
int sign = med_testStat_val != 0 ? med_testStat_val/fabs(med_testStat_val) : 0;
med_sig = sign*sqrt(fabs(med_testStat_val));
if (string(nominalSnapshot) != "") ws->loadSnapshot(nominalSnapshot);
if (!doRightSided) mu->setRange(0, 40);
else mu->setRange(-40, 40);
}
RooNLLVar::SetIgnoreZeroEntries(0);
//gRandom->SetSeed(1);
//RooRandom::randomGenerator()->SetSeed(1);
//RooMinimizerFcn::SetOverrideEverything(false);
cout << "med test stat: " << med_testStat_val << endl;
ws->loadSnapshot("nominalGlobs");
ws->loadSnapshot("conditionalNuis_0");
mu->setVal(0);
testStat.SetWorkspace(ws);
testStat.SetLoadUncondSnapshot("ucmles");
double obsTestStat_val = doObs ? 2*testStat.Evaluate(*data, poi) : 0;
cout << "obs test stat: " << obsTestStat_val << endl;
// obsTestStat_val = 2*testStat.Evaluate(*data, poi);
// cout << "obs test stat: " << obsTestStat_val << endl;
// obsTestStat_val = 2*testStat.Evaluate(*data, poi);
// cout << "obs test stat: " << obsTestStat_val << endl;
double obs_sig;
int sign = obsTestStat_val == 0 ? 0 : obsTestStat_val / fabs(obsTestStat_val);
if (!doRightSided && (obsTestStat_val < 0 && obsTestStat_val > -0.1 || mu->getVal() < 0.001)) obs_sig = 0;
else obs_sig = sign*sqrt(fabs(obsTestStat_val));
if (obs_sig != obs_sig) //nan, do by hand
{
cout << "Obs test stat gave nan: try by hand" << endl;
mu->setVal(0);
mu->setConstant(1);
mc->GetPdf()->fitTo(*data, Hesse(0), Minos(0), PrintLevel(-1), Constrain(*mc->GetNuisanceParameters()));
mu->setConstant(0);
double L_0 = mc->GetPdf()->getVal();
//mu->setVal(0);
//mu->setConstant(1);
mc->GetPdf()->fitTo(*data, Hesse(0), Minos(0), PrintLevel(-1), Constrain(*mc->GetNuisanceParameters()));
//mu->setConstant(0);
double L_muhat = mc->GetPdf()->getVal();
cout << "L_0: " << L_0 << ", L_muhat: " << L_muhat << endl;
obs_sig = sqrt(-2*TMath::Log(L_0/L_muhat));
//still nan
if (obs_sig != obs_sig && fabs(L_0 - L_muhat) < 0.000001) obs_sig = 0;
}
cout << "obs: " << obs_sig << endl;
cout << "Observed significance: " << obs_sig << endl;
if (med_sig)
{
cout << "Median test stat val: " << med_testStat_val << 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");
// stringstream fileName;
// fileName << "results_sig/" << mass << ".root";
// system("mkdir results_sig");
// TFile f(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();
//mc->GetPdf()->fitTo(*data, PrintLevel(0));
timer.Stop();
timer.Print();
}
else
{
RooAbsPdf* pdf = mc->GetPdf();
RooArgSet nuis_tmp1 = *mc->GetNuisanceParameters();
RooNLLVar* asimov_nll0 = (RooNLLVar*)pdf->createNLL(*asimovData0, Constrain(nuis_tmp1));
RooArgSet nuis_tmp2 = *mc->GetNuisanceParameters();
RooNLLVar* asimov_nll1 = (RooNLLVar*)pdf->createNLL(*asimovData1, Constrain(nuis_tmp2));
RooArgSet nuis_tmp3 = *mc->GetNuisanceParameters();
RooNLLVar* obs_nll = (RooNLLVar*)pdf->createNLL(*data, Constrain(nuis_tmp3));
//do asimov
int status;
//get sigma_b
ws->loadSnapshot(conditional0Snapshot);
status = ws->loadSnapshot("conditionalNuis_0");
if (status != 0 && goFast) errFast = 1;
mu->setVal(0);
mu->setConstant(1);
status = goFast ? 0 : minimize(asimov_nll0, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll0, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov0_nll0 = asimov_nll0->getVal();
mu->setVal(1);
ws->loadSnapshot("conditionalNuis_1");
status = minimize(asimov_nll0, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll0, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov0_nll1 = asimov_nll0->getVal();
double asimov0_q = 2*(asimov0_nll1 - asimov0_nll0);
double sigma_b = sqrt(1./asimov0_q);
ws->loadSnapshot(nominalSnapshot);
//get sigma_sb
ws->loadSnapshot(conditional1Snapshot);
ws->loadSnapshot("conditionalNuis_0");
mu->setVal(0);
mu->setConstant(1);
status = minimize(asimov_nll1, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll1, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov1_nll0 = asimov_nll1->getVal();
mu->setVal(1);
status = ws->loadSnapshot("conditionalNuis_1");
if (status != 0 && goFast) errFast = 1;
status = goFast ? 0 : minimize(asimov_nll1, ws);
if (status < 0)
{
cout << "Retrying" << endl;
//ws->loadSnapshot("conditionalNuis_0");
status = minimize(asimov_nll1, ws);
if (status >= 0) cout << "Success!" << endl;
}
double asimov1_nll1 = asimov_nll1->getVal();
double asimov1_q = 2*(asimov1_nll1 - asimov1_nll0);
double sigma_sb = sqrt(-1./asimov1_q);
ws->loadSnapshot(nominalSnapshot);
//do obs
mu->setVal(0);
status = ws->loadSnapshot("conditionalNuis_0");
if (status != 0 && goFast) errFast = 1;
mu->setConstant(1);
status = goFast ? 0 : 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_nll0 = obs_nll->getVal();
status = ws->loadSnapshot("conditionalNuis_1");
if (status != 0 && goFast) errFast = 1;
mu->setVal(1);
status = goFast ? 0 : 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_nll1 = obs_nll->getVal();
double obs_q = 2*(obs_nll1 - obs_nll0);
double Zobs = (1./sigma_b/sigma_b - obs_q) / (2./sigma_b);
double Zexp = (1./sigma_b/sigma_b - asimov1_q) / (2./sigma_b);
double pb_obs = 1-ROOT::Math::gaussian_cdf(Zobs);
double pb_exp = 1-ROOT::Math::gaussian_cdf(Zexp);
cout << "asimov0_q = " << asimov0_q << endl;
cout << "asimov1_q = " << asimov1_q << endl;
cout << "obs_q = " << obs_q << endl;
cout << "sigma_b = " << sigma_b << endl;
cout << "sigma_sb = " << sigma_sb << endl;
cout << "Z obs = " << Zobs << endl;
cout << "Z exp = " << Zexp << 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_tev","hypo_tev",2,0,2);
h_hypo->SetBinContent(1, pb_obs);
h_hypo->SetBinContent(2, pb_exp);
f2.Write();
f2.Close();
stringstream fileName3;
fileName3 << "root_files/" << folder << "_llr/" << mass << ".root";
system(("mkdir -vp root_files/" + folder + "_llr").c_str());
TFile f3(fileName3.str().c_str(),"recreate");
TH1D* h_hypo3 = new TH1D("hypo_llr","hypo_llr",7,0,7);
h_hypo3->SetBinContent(1, -obs_q);
h_hypo3->SetBinContent(2, -asimov1_q);
h_hypo3->SetBinContent(3, -asimov0_q);
h_hypo3->SetBinContent(4, -asimov0_q-2*2/sigma_b);
h_hypo3->SetBinContent(5, -asimov0_q-1*2/sigma_b);
h_hypo3->SetBinContent(6, -asimov0_q+1*2/sigma_b);
h_hypo3->SetBinContent(7, -asimov0_q+2*2/sigma_b);
f3.Write();
f3.Close();
timer.Stop();
timer.Print();
}
}
void StandardHypoTestDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelSBName = "ModelConfig",
const char* modelBName = "",
const char* dataName = "obsData",
int calcType = 0, // 0 freq 1 hybrid, 2 asymptotic
int testStatType = 3, // 0 LEP, 1 TeV, 2 LHC, 3 LHC - one sided
int ntoys = 5000,
bool useNC = false,
const char * nuisPriorName = 0)
{
/*
Other Parameter to pass in tutorial
apart from standard for filename, ws, modelconfig and data
type = 0 Freq calculator
type = 1 Hybrid calculator
type = 2 Asymptotic calculator
testStatType = 0 LEP
= 1 Tevatron
= 2 Profile Likelihood
= 3 Profile Likelihood one sided (i.e. = 0 if mu < mu_hat)
ntoys: number of toys to use
useNumberCounting: set to true when using number counting events
nuisPriorName: name of prior for the nnuisance. This is often expressed as constraint term in the global model
It is needed only when using the HybridCalculator (type=1)
If not given by default the prior pdf from ModelConfig is used.
extra options are available as global paramwters of the macro. They major ones are:
generateBinned generate binned data sets for toys (default is false) - be careful not to activate with
a too large (>=3) number of observables
nToyRatio ratio of S+B/B toys (default is 2)
printLevel
*/
// disable - can cause some problems
//ToyMCSampler::SetAlwaysUseMultiGen(true);
SimpleLikelihoodRatioTestStat::SetAlwaysReuseNLL(true);
ProfileLikelihoodTestStat::SetAlwaysReuseNLL(true);
RatioOfProfiledLikelihoodsTestStat::SetAlwaysReuseNLL(true);
//RooRandom::randomGenerator()->SetSeed(0);
// to change minimizers
// ROOT::Math::MinimizerOptions::SetDefaultStrategy(0);
// ROOT::Math::MinimizerOptions::SetDefaultMinimizer("Minuit2");
// ROOT::Math::MinimizerOptions::SetDefaultTolerance(1);
/////////////////////////////////////////////////////////////
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
////////////////////////////////////////////////////////////
const char* filename = "";
if (!strcmp(infile,""))
filename = "results/example_combined_GaussExample_model.root";
else
filename = infile;
// Check if example input file exists
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file && strcmp(infile,"")){
cout <<"file not found" << endl;
return;
}
// if default file not found, try to create it
if(!file ){
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
// now try to access the file again
file = TFile::Open(filename);
if(!file){
// if it is still not there, then we can't continue
cout << "Not able to run hist2workspace to create example input" <<endl;
return;
}
/////////////////////////////////////////////////////////////
// Tutorial starts here
////////////////////////////////////////////////////////////
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
w->Print();
// get the modelConfig out of the file
ModelConfig* sbModel = (ModelConfig*) w->obj(modelSBName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !sbModel){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
// make b model
ModelConfig* bModel = (ModelConfig*) w->obj(modelBName);
// case of no systematics
// remove nuisance parameters from model
if (noSystematics) {
const RooArgSet * nuisPar = sbModel->GetNuisanceParameters();
if (nuisPar && nuisPar->getSize() > 0) {
std::cout << "StandardHypoTestInvDemo" << " - Switch off all systematics by setting them constant to their initial values" << std::endl;
RooStats::SetAllConstant(*nuisPar);
}
if (bModel) {
const RooArgSet * bnuisPar = bModel->GetNuisanceParameters();
if (bnuisPar)
RooStats::SetAllConstant(*bnuisPar);
}
}
if (!bModel ) {
Info("StandardHypoTestInvDemo","The background model %s does not exist",modelBName);
Info("StandardHypoTestInvDemo","Copy it from ModelConfig %s and set POI to zero",modelSBName);
bModel = (ModelConfig*) sbModel->Clone();
bModel->SetName(TString(modelSBName)+TString("B_only"));
RooRealVar * var = dynamic_cast<RooRealVar*>(bModel->GetParametersOfInterest()->first());
if (!var) return;
double oldval = var->getVal();
var->setVal(0);
//bModel->SetSnapshot( RooArgSet(*var, *w->var("lumi")) );
bModel->SetSnapshot( RooArgSet(*var) );
var->setVal(oldval);
}
if (!sbModel->GetSnapshot() || poiValue > 0) {
Info("StandardHypoTestDemo","Model %s has no snapshot - make one using model poi",modelSBName);
RooRealVar * var = dynamic_cast<RooRealVar*>(sbModel->GetParametersOfInterest()->first());
if (!var) return;
double oldval = var->getVal();
if (poiValue > 0) var->setVal(poiValue);
//sbModel->SetSnapshot( RooArgSet(*var, *w->var("lumi") ) );
sbModel->SetSnapshot( RooArgSet(*var) );
if (poiValue > 0) var->setVal(oldval);
//sbModel->SetSnapshot( *sbModel->GetParametersOfInterest() );
}
// part 1, hypothesis testing
SimpleLikelihoodRatioTestStat * slrts = new SimpleLikelihoodRatioTestStat(*bModel->GetPdf(), *sbModel->GetPdf());
// null parameters must includes snapshot of poi plus the nuisance values
RooArgSet nullParams(*bModel->GetSnapshot());
if (bModel->GetNuisanceParameters()) nullParams.add(*bModel->GetNuisanceParameters());
slrts->SetNullParameters(nullParams);
RooArgSet altParams(*sbModel->GetSnapshot());
if (sbModel->GetNuisanceParameters()) altParams.add(*sbModel->GetNuisanceParameters());
slrts->SetAltParameters(altParams);
ProfileLikelihoodTestStat * profll = new ProfileLikelihoodTestStat(*bModel->GetPdf());
RatioOfProfiledLikelihoodsTestStat *
ropl = new RatioOfProfiledLikelihoodsTestStat(*bModel->GetPdf(), *sbModel->GetPdf(), sbModel->GetSnapshot());
ropl->SetSubtractMLE(false);
if (testStatType == 3) profll->SetOneSidedDiscovery(1);
profll->SetPrintLevel(printLevel);
// profll.SetReuseNLL(mOptimize);
// slrts.SetReuseNLL(mOptimize);
// ropl.SetReuseNLL(mOptimize);
AsymptoticCalculator::SetPrintLevel(printLevel);
HypoTestCalculatorGeneric * hypoCalc = 0;
// note here Null is B and Alt is S+B
if (calcType == 0) hypoCalc = new FrequentistCalculator(*data, *sbModel, *bModel);
else if (calcType == 1) hypoCalc= new HybridCalculator(*data, *sbModel, *bModel);
else if (calcType == 2) hypoCalc= new AsymptoticCalculator(*data, *sbModel, *bModel);
if (calcType == 0)
((FrequentistCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
if (calcType == 1)
((HybridCalculator*)hypoCalc)->SetToys(ntoys, ntoys/nToysRatio);
if (calcType == 2 ) {
if (testStatType == 3) ((AsymptoticCalculator*) hypoCalc)->SetOneSidedDiscovery(true);
if (testStatType != 2 && testStatType != 3)
Warning("StandardHypoTestDemo","Only the PL test statistic can be used with AsymptoticCalculator - use by default a two-sided PL");
}
// check for nuisance prior pdf in case of nuisance parameters
if (calcType == 1 && (bModel->GetNuisanceParameters() || sbModel->GetNuisanceParameters() )) {
RooAbsPdf * nuisPdf = 0;
if (nuisPriorName) nuisPdf = w->pdf(nuisPriorName);
// use prior defined first in bModel (then in SbModel)
if (!nuisPdf) {
Info("StandardHypoTestDemo","No nuisance pdf given for the HybridCalculator - try to deduce pdf from the model");
if (bModel->GetPdf() && bModel->GetObservables() )
nuisPdf = RooStats::MakeNuisancePdf(*bModel,"nuisancePdf_bmodel");
else
nuisPdf = RooStats::MakeNuisancePdf(*sbModel,"nuisancePdf_sbmodel");
}
if (!nuisPdf ) {
if (bModel->GetPriorPdf()) {
nuisPdf = bModel->GetPriorPdf();
Info("StandardHypoTestDemo","No nuisance pdf given - try to use %s that is defined as a prior pdf in the B model",nuisPdf->GetName());
}
else {
Error("StandardHypoTestDemo","Cannnot run Hybrid calculator because no prior on the nuisance parameter is specified or can be derived");
return;
}
}
assert(nuisPdf);
Info("StandardHypoTestDemo","Using as nuisance Pdf ... " );
nuisPdf->Print();
const RooArgSet * nuisParams = (bModel->GetNuisanceParameters() ) ? bModel->GetNuisanceParameters() : sbModel->GetNuisanceParameters();
RooArgSet * np = nuisPdf->getObservables(*nuisParams);
if (np->getSize() == 0) {
Warning("StandardHypoTestDemo","Prior nuisance does not depend on nuisance parameters. They will be smeared in their full range");
}
delete np;
((HybridCalculator*)hypoCalc)->ForcePriorNuisanceAlt(*nuisPdf);
((HybridCalculator*)hypoCalc)->ForcePriorNuisanceNull(*nuisPdf);
}
// hypoCalc->ForcePriorNuisanceAlt(*sbModel->GetPriorPdf());
// hypoCalc->ForcePriorNuisanceNull(*bModel->GetPriorPdf());
ToyMCSampler * sampler = (ToyMCSampler *)hypoCalc->GetTestStatSampler();
if (sampler && (calcType == 0 || calcType == 1) ) {
// look if pdf is number counting or extended
if (sbModel->GetPdf()->canBeExtended() ) {
if (useNC) Warning("StandardHypoTestDemo","Pdf is extended: but number counting flag is set: ignore it ");
}
else {
// for not extended pdf
if (!useNC) {
int nEvents = data->numEntries();
Info("StandardHypoTestDemo","Pdf is not extended: number of events to generate taken from observed data set is %d",nEvents);
sampler->SetNEventsPerToy(nEvents);
}
else {
Info("StandardHypoTestDemo","using a number counting pdf");
sampler->SetNEventsPerToy(1);
}
}
if (data->isWeighted() && !generateBinned) {
Info("StandardHypoTestDemo","Data set is weighted, nentries = %d and sum of weights = %8.1f but toy generation is unbinned - it would be faster to set generateBinned to true\n",data->numEntries(), data->sumEntries());
}
if (generateBinned) sampler->SetGenerateBinned(generateBinned);
// set the test statistic
if (testStatType == 0) sampler->SetTestStatistic(slrts);
if (testStatType == 1) sampler->SetTestStatistic(ropl);
if (testStatType == 2 || testStatType == 3) sampler->SetTestStatistic(profll);
}
HypoTestResult * htr = hypoCalc->GetHypoTest();
htr->SetPValueIsRightTail(true);
htr->SetBackgroundAsAlt(false);
htr->Print(); // how to get meaningfull CLs at this point?
delete sampler;
delete slrts;
delete ropl;
delete profll;
if (calcType != 2) {
HypoTestPlot * plot = new HypoTestPlot(*htr,100);
plot->SetLogYaxis(true);
plot->Draw();
}
else {
std::cout << "Asymptotic results " << std::endl;
}
// look at expected significances
// found median of S+B distribution
if (calcType != 2) {
SamplingDistribution * altDist = htr->GetAltDistribution();
HypoTestResult htExp("Expected Result");
htExp.Append(htr);
// find quantiles in alt (S+B) distribution
double p[5];
double q[5];
for (int i = 0; i < 5; ++i) {
double sig = -2 + i;
p[i] = ROOT::Math::normal_cdf(sig,1);
}
std::vector<double> values = altDist->GetSamplingDistribution();
TMath::Quantiles( values.size(), 5, &values[0], q, p, false);
for (int i = 0; i < 5; ++i) {
htExp.SetTestStatisticData( q[i] );
double sig = -2 + i;
std::cout << " Expected p -value and significance at " << sig << " sigma = "
<< htExp.NullPValue() << " significance " << htExp.Significance() << " sigma " << std::endl;
}
}
else {
// case of asymptotic calculator
for (int i = 0; i < 5; ++i) {
double sig = -2 + i;
// sigma is inverted here
double pval = AsymptoticCalculator::GetExpectedPValues( htr->NullPValue(), htr->AlternatePValue(), -sig, false);
std::cout << " Expected p -value and significance at " << sig << " sigma = "
<< pval << " significance " << ROOT::Math::normal_quantile_c(pval,1) << " sigma " << std::endl;
}
}
}
void build_hbb_workspace1( const char* infile = "outputfiles/input-file.txt", const char* outfile = "outputfiles/ws.root" ) {
//-------------------------------------------------------------------------
//-- Create workspace and other RooStats things.
printf("\n\n Creating workspace.\n\n") ;
RooWorkspace workspace("ws") ;
workspace.autoImportClassCode(true) ;
globalObservables = new RooArgSet("globalObservables");
allNuisances = new RooArgSet("allNuisances");
allNuisancePdfs = new RooArgSet("allNuisancePdfs");
RooArgSet* observedParametersList = new RooArgSet("observables") ;
//-------------------------------------------------------------------------
printf("\n\n Reading input file: %s\n\n", infile ) ;
float fileVal ;
char pname[1000] ;
char formula[1000] ;
sprintf( pname, "bins_of_met" ) ;
if ( !getFileValue( infile, pname, fileVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
int bins_of_met = TMath::Nint( fileVal ) ;
//-- save bins_of_met in the workspace for convenience.
RooRealVar bom( "bins_of_met", "bins_of_met", bins_of_met, 0., 1000. ) ;
bom.setConstant(kTRUE) ;
workspace.import(bom) ;
//-- save bins_of_nb in the workspace for convenience.
RooRealVar bonb( "bins_of_nb", "bins_of_nb", bins_of_nb, 0., 1000. ) ;
bonb.setConstant(kTRUE) ;
workspace.import(bonb) ;
RooRealVar* rv_N_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooRealVar* rv_N_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooRealVar* rv_smc_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooRealVar* rv_smc_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_Rsigsb_corr[bins_of_nb][max_bins_of_met] ;
for ( int nbi=0; nbi<bins_of_nb; nbi++ ) {
for ( int mbi=0; mbi<bins_of_met; mbi++ ) {
sprintf( pname, "N_%db_msig_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, fileVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
rv_N_msig[nbi][mbi] = new RooRealVar( pname, pname, 0., 1.e6 ) ;
rv_N_msig[nbi][mbi] -> setVal( TMath::Nint(fileVal) ) ;
rv_N_msig[nbi][mbi] -> setConstant( kTRUE ) ;
observedParametersList -> add( *rv_N_msig[nbi][mbi] ) ;
sprintf( pname, "N_%db_msb_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, fileVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
rv_N_msb[nbi][mbi] = new RooRealVar( pname, pname, 0., 1.e6 ) ;
rv_N_msb[nbi][mbi] -> setVal( TMath::Nint(fileVal) ) ;
rv_N_msb[nbi][mbi] -> setConstant( kTRUE ) ;
observedParametersList -> add( *rv_N_msb[nbi][mbi] ) ;
sprintf( pname, "smc_%db_msig_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, fileVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
rv_smc_msig[nbi][mbi] = new RooRealVar( pname, pname, 0., 1.e6 ) ;
rv_smc_msig[nbi][mbi] -> setVal( TMath::Nint(fileVal) ) ;
rv_smc_msig[nbi][mbi] -> setConstant( kTRUE ) ;
sprintf( pname, "smc_%db_msb_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, fileVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
rv_smc_msb[nbi][mbi] = new RooRealVar( pname, pname, 0., 1.e6 ) ;
rv_smc_msb[nbi][mbi] -> setVal( TMath::Nint(fileVal) ) ;
rv_smc_msb[nbi][mbi] -> setConstant( kTRUE ) ;
float corrVal, corrSyst ;
sprintf( pname, "Rsigsb_syst_%db_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, corrSyst ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
sprintf( pname, "Rsigsb_corr_%db_met%d", nbi+2, mbi+1 ) ;
if ( !getFileValue( infile, pname, corrVal ) ) { printf("\n\n *** Error. Can't find %s\n\n", pname ) ; return ; }
rv_Rsigsb_corr[nbi][mbi] = makeLognormalConstraint( pname, corrVal, corrSyst ) ;
} // mbi.
} // nbi.
//-- Finished reading input from file.
//-------------------------------------------------------------------------
printf("\n\n Creating and importing dataset into workspace.\n\n") ;
RooDataSet* dsObserved = new RooDataSet("hbb_observed_rds", "hbb observed data values", *observedParametersList ) ;
dsObserved -> add( *observedParametersList ) ;
workspace.import( *dsObserved ) ;
//-------------------------------------------------------------------------
//-- Define all floats.
printf("\n\n Defining all unconstrained floats (Ratios, signal strength).\n\n") ;
double R_msigmsb_initialval(0.15) ;
RooRealVar* rv_R_msigmsb[50] ;
for ( int mbi=0; mbi<bins_of_met; mbi++ ) {
sprintf( pname, "R_msigmsb_met%d", mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_R_msigmsb[mbi] = new RooRealVar( pname, pname, R_msigmsb_initialval, 0., 3. ) ;
rv_R_msigmsb[mbi] -> setConstant( kFALSE ) ;
rv_R_msigmsb[mbi] -> Print() ;
} // mbi.
printf("\n") ;
sprintf( pname, "sig_strength" ) ;
RooRealVar* rv_sig_strength = new RooRealVar( pname, pname, 1.0, 0., 10. ) ;
rv_sig_strength -> setConstant(kFALSE) ;
rv_sig_strength -> Print() ;
printf(" %s\n\n", pname ) ;
//-------------------------------------------------------------------------
//-- Define all mu parameters.
printf("\n\n Defining mu parameters.\n\n") ;
RooAbsReal* rv_mu_bg_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_mu_bg_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_mu_sig_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_mu_sig_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
for ( int nbi=0; nbi<bins_of_nb; nbi++ ) {
for ( int mbi=0; mbi<bins_of_met; mbi++ ) {
sprintf( pname, "mu_bg_%db_msb_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_mu_bg_msb[nbi][mbi] = new RooRealVar( pname, pname, rv_N_msb[nbi][mbi] -> getVal(), 0., 1.e6 ) ;
rv_mu_bg_msb[nbi][mbi] -> Print() ;
sprintf( formula, "@0 * @1 * @2" ) ;
sprintf( pname, "mu_bg_%db_msig_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_mu_bg_msig[nbi][mbi] = new RooFormulaVar( pname, formula, RooArgSet( *rv_Rsigsb_corr[nbi][mbi], *rv_R_msigmsb[mbi], *rv_mu_bg_msb[nbi][mbi] ) ) ;
rv_mu_bg_msig[nbi][mbi] -> Print() ;
sprintf( formula, "@0 * @1" ) ;
sprintf( pname, "mu_sig_%db_msig_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_mu_sig_msig[nbi][mbi] = new RooFormulaVar( pname, formula, RooArgSet( *rv_sig_strength, *rv_smc_msig[nbi][mbi] ) ) ;
rv_mu_sig_msig[nbi][mbi] -> Print() ;
sprintf( formula, "@0 * @1" ) ;
sprintf( pname, "mu_sig_%db_msb_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_mu_sig_msb[nbi][mbi] = new RooFormulaVar( pname, formula, RooArgSet( *rv_sig_strength, *rv_smc_msb[nbi][mbi] ) ) ;
rv_mu_sig_msb[nbi][mbi] -> Print() ;
} // mbi.
} // nbi.
//-- Finished defining mu parameters.
//-------------------------------------------------------------------------
//-- Defining small n's
printf("\n\n Defining small n's.\n\n") ;
RooAbsReal* rv_n_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_n_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
for ( int nbi=0; nbi<bins_of_nb; nbi++ ) {
for ( int mbi=0; mbi<bins_of_met; mbi++ ) {
sprintf( formula, "@0 + @1" ) ;
sprintf( pname, "n_%db_msig_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_n_msig[nbi][mbi] = new RooFormulaVar( pname, formula, RooArgSet( *rv_mu_sig_msig[nbi][mbi], *rv_mu_bg_msig[nbi][mbi] ) ) ;
rv_n_msig[nbi][mbi] -> Print() ;
workspace.import( *rv_n_msig[nbi][mbi] ) ;
sprintf( pname, "n_%db_msb_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_n_msb[nbi][mbi] = new RooFormulaVar( pname, formula, RooArgSet( *rv_mu_sig_msb[nbi][mbi], *rv_mu_bg_msb[nbi][mbi] ) ) ;
rv_n_msb[nbi][mbi] -> Print() ;
workspace.import( *rv_n_msb[nbi][mbi] ) ;
} // mbi.
} // nbi.
//-------------------------------------------------------------------------
//-- Define the Poisson pdfs for the observables.
printf("\n\n Defining Poisson pdfs for the observables.\n\n") ;
RooAbsReal* rv_pdf_msig[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooAbsReal* rv_pdf_msb[bins_of_nb][max_bins_of_met] ; // first index is number of btags, second is met bin.
RooArgSet pdflist ;
for ( int nbi=0; nbi<bins_of_nb; nbi++ ) {
for ( int mbi=0; mbi<bins_of_met; mbi++ ) {
sprintf( pname, "pdf_%db_msig_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_pdf_msig[nbi][mbi] = new RooPoisson( pname, pname, *rv_N_msig[nbi][mbi], *rv_n_msig[nbi][mbi] ) ;
rv_pdf_msig[nbi][mbi] -> Print() ;
pdflist.add( *rv_pdf_msig[nbi][mbi] ) ;
sprintf( pname, "pdf_%db_msb_met%d", nbi+2, mbi+1 ) ;
printf( " %s\n", pname ) ;
rv_pdf_msb[nbi][mbi] = new RooPoisson( pname, pname, *rv_N_msb[nbi][mbi], *rv_n_msb[nbi][mbi] ) ;
rv_pdf_msb[nbi][mbi] -> Print() ;
pdflist.add( *rv_pdf_msb[nbi][mbi] ) ;
} // mbi.
} // nbi.
//-------------------------------------------------------------------------
//-- Build the likelihood.
printf("\n\n Building the likelihood.\n\n") ;
pdflist.add( *allNuisancePdfs ) ;
pdflist.Print() ;
printf("\n") ;
RooProdPdf* likelihood = new RooProdPdf( "likelihood", "hbb likelihood", pdflist ) ;
likelihood->Print() ;
//-------------------------------------------------------------------------
// printf("\n\n Running a test fit.\n\n") ;
// dsObserved -> Print() ;
// dsObserved -> printMultiline(cout, 1, kTRUE, "") ;
// printf("\n\n =============================================\n\n") ;
// likelihood -> fitTo( *dsObserved, PrintLevel(3), Hesse(0), Minos(0) ) ;
// printf("\n\n =============================================\n\n") ;
//-- Set up RooStats models.
printf("\n\n Setting up S+B model.\n\n") ;
RooArgSet poi( *rv_sig_strength, "poi" ) ;
RooUniform signal_prior( "signal_prior", "signal_prior", *rv_sig_strength ) ;
ModelConfig sbModel ("SbModel");
sbModel.SetWorkspace( workspace ) ;
sbModel.SetPdf( *likelihood ) ;
sbModel.SetParametersOfInterest( poi );
sbModel.SetPriorPdf(signal_prior);
sbModel.SetObservables( *observedParametersList );
sbModel.SetNuisanceParameters( *allNuisances );
sbModel.SetGlobalObservables( *globalObservables );
workspace.Print() ;
printf("\n\n Doing fit for S+B model.\n" ) ; fflush(stdout) ;
RooAbsReal* pNll = sbModel.GetPdf()->createNLL(*dsObserved);
RooAbsReal* pProfile = pNll->createProfile(RooArgSet());
pProfile->getVal();
RooArgSet* pPoiAndNuisance = new RooArgSet();
pPoiAndNuisance->add(*sbModel.GetParametersOfInterest());
if(sbModel.GetNuisanceParameters()) pPoiAndNuisance->add(*sbModel.GetNuisanceParameters());
printf("\n\n Will save these parameter points that correspond to the fit to data.\n\n") ; fflush(stdout) ;
pPoiAndNuisance->Print("v");
sbModel.SetSnapshot(*pPoiAndNuisance);
workspace.import (sbModel);
delete pProfile ;
delete pNll ;
delete pPoiAndNuisance ;
printf("\n\n Setting up BG-only model.\n\n") ;
ModelConfig bModel (*(RooStats::ModelConfig *)workspace.obj("SbModel"));
bModel.SetName("BModel");
bModel.SetWorkspace(workspace);
printf("\n\n Doing fit for BG-only model.\n" ) ; fflush(stdout) ;
pNll = bModel.GetPdf()->createNLL(*dsObserved);
pProfile = pNll->createProfile(*bModel.GetParametersOfInterest());
((RooRealVar *)(bModel.GetParametersOfInterest()->first()))->setVal(0.);
pProfile->getVal();
pPoiAndNuisance = new RooArgSet();
pPoiAndNuisance->add(*bModel.GetParametersOfInterest());
if(bModel.GetNuisanceParameters()) pPoiAndNuisance->add(*bModel.GetNuisanceParameters());
printf("\n\n Should use these parameter points to generate pseudo data for bkg only.\n\n") ; fflush(stdout) ;
pPoiAndNuisance->Print("v");
bModel.SetSnapshot(*pPoiAndNuisance);
workspace.import (bModel);
delete pProfile ;
delete pNll ;
delete pPoiAndNuisance ;
workspace.Print() ;
printf("\n\n Saving workspace in : %s\n\n", outfile ) ;
gSystem->Exec(" mkdir -p outputfiles " ) ;
workspace.writeToFile( outfile ) ;
} // build_hbb_workspace1.
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;
}
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 new_RA4(){
// let's time this challenging example
TStopwatch t;
t.Start();
// set RooFit random seed for reproducible results
RooRandom::randomGenerator()->SetSeed(4357);
// make model
RooWorkspace* wspace = new RooWorkspace("wspace");
wspace->factory("Gaussian::sigCons(prime_SigEff[0,-5,5], nom_SigEff[0,-5,5], 1)");
wspace->factory("expr::SigEff('1.0*pow(1.20,@0)',prime_SigEff)"); // // 1+-20%, 1.20=exp(20%)
wspace->factory("Poisson::on(non[0,50], sum::splusb(prod::SigUnc(s[0,0,50],SigEff),mainb[8.8,0,50],dilep[0.9,0,20],tau[2.3,0,20],QCD[0.,0,10],MC[0.1,0,4]))");
wspace->factory("Gaussian::mcCons(prime_rho[0,-5,5], nom_rho[0,-5,5], 1)");
wspace->factory("expr::rho('1.0*pow(1.39,@0)',prime_rho)"); // // 1+-39%
wspace->factory("Poisson::off(noff[0,200], prod::rhob(mainb,rho,mu_plus_e[0.74,0.01,10],1.08))");
wspace->factory("Gaussian::mcCons2(mu_plus_enom[0.74,0.01,4], mu_plus_e, sigmatwo[.05])");
wspace->factory("Gaussian::dilep_pred(dilep_nom[0.9,0,20], dilep, sigma3[2.2])");
wspace->factory("Gaussian::tau_pred(tau_nom[2.3,0,20], tau, sigma4[0.5])");
wspace->factory("Gaussian::QCD_pred(QCD_nom[0.0,0,10], QCD, sigma5[1.0])");
wspace->factory("Gaussian::MC_pred(MC_nom[0.1,0.01,4], MC, sigma7[0.14])");
wspace->factory("PROD::model(on,off,mcCons,mcCons2,sigCons,dilep_pred,tau_pred,QCD_pred,MC_pred)");
RooArgSet obs(*wspace->var("non"), *wspace->var("noff"), *wspace->var("mu_plus_enom"), *wspace->var("dilep_nom"), *wspace->var("tau_nom"), "obs");
obs.add(*wspace->var("QCD_nom")); obs.add(*wspace->var("MC_nom"));
RooArgSet globalObs(*wspace->var("nom_SigEff"), *wspace->var("nom_rho"), "global_obs");
// fix global observables to their nominal values
wspace->var("nom_SigEff")->setConstant();
wspace->var("nom_rho")->setConstant();
RooArgSet poi(*wspace->var("s"), "poi");
RooArgSet nuis(*wspace->var("mainb"), *wspace->var("prime_rho"), *wspace->var("prime_SigEff"), *wspace->var("mu_plus_e"), *wspace->var("dilep"), *wspace->var("tau"), "nuis");
nuis.add(*wspace->var("QCD")); nuis.add(*wspace->var("MC"));
wspace->factory("Uniform::prior_poi({s})");
wspace->factory("Uniform::prior_nuis({mainb,mu_plus_e,dilep,tau,QCD,MC})");
wspace->factory("PROD::prior(prior_poi,prior_nuis)");
wspace->var("non")->setVal(8); //observed
//wspace->var("non")->setVal(12); //expected observation
wspace->var("noff")->setVal(7); //observed events in control region
wspace->var("mu_plus_enom")->setVal(0.74);
wspace->var("dilep_nom")->setVal(0.9);
wspace->var("tau_nom")->setVal(2.3);
wspace->var("QCD")->setVal(0.0);
wspace->var("MC")->setVal(0.1);
RooDataSet * data = new RooDataSet("data","",obs);
data->add(obs);
wspace->import(*data);
/////////////////////////////////////////////////////
// Now the statistical tests
// model config
ModelConfig* pSbModel = new ModelConfig("SbModel");
pSbModel->SetWorkspace(*wspace);
pSbModel->SetPdf(*wspace->pdf("model"));
pSbModel->SetPriorPdf(*wspace->pdf("prior"));
pSbModel->SetParametersOfInterest(poi);
pSbModel->SetNuisanceParameters(nuis);
pSbModel->SetObservables(obs);
pSbModel->SetGlobalObservables(globalObs);
wspace->import(*pSbModel);
// set all but obs, poi and nuisance to const
SetConstants(wspace, pSbModel);
wspace->import(*pSbModel);
Double_t poiValueForBModel = 0.0;
ModelConfig* pBModel = new ModelConfig(*(RooStats::ModelConfig *)wspace->obj("SbModel"));
pBModel->SetName("BModel");
pBModel->SetWorkspace(*wspace);
wspace->import(*pBModel);
RooAbsReal * pNll = pSbModel->GetPdf()->createNLL(*data);
RooAbsReal * pProfile = pNll->createProfile(RooArgSet());
pProfile->getVal(); // this will do fit and set POI and nuisance parameters to fitted values
RooArgSet * pPoiAndNuisance = new RooArgSet();
//if(pSbModel->GetNuisanceParameters())
// pPoiAndNuisance->add(*pSbModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pSbModel->GetParametersOfInterest());
cout << "\nWill save these parameter points that correspond to the fit to data" << endl;
pPoiAndNuisance->Print("v");
pSbModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
pNll = pBModel->GetPdf()->createNLL(*data);
pProfile = pNll->createProfile(poi);
((RooRealVar *)poi.first())->setVal(poiValueForBModel);
pProfile->getVal(); // this will do fit and set nuisance parameters to profiled values
pPoiAndNuisance = new RooArgSet();
//if(pBModel->GetNuisanceParameters())
// pPoiAndNuisance->add(*pBModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pBModel->GetParametersOfInterest());
cout << "\nShould use these parameter points to generate pseudo data for bkg only" << endl;
pPoiAndNuisance->Print("v");
pBModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
// inspect workspace
wspace->Print();
// save workspace to file
wspace->writeToFile("tight.root");
//wspace->writeToFile("tight_median.root");
// clean up
delete wspace;
delete data;
delete pSbModel;
delete pBModel;
}
void StandardProfileLikelihoodDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData"){
double confLevel = optPL.confLevel;
double nScanPoints = optPL.nScanPoints;
bool plotAsTF1 = optPL.plotAsTF1;
double poiXMin = optPL.poiMinPlot;
double poiXMax = optPL.poiMaxPlot;
bool doHypoTest = optPL.doHypoTest;
double nullParamValue = optPL.nullValue;
// -------------------------------------------------------
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
const char* filename = "";
if (!strcmp(infile,"")) {
filename = "results/example_combined_GaussExample_model.root";
bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
// if file does not exists generate with histfactory
if (!fileExist) {
#ifdef _WIN32
cout << "HistFactory file cannot be generated on Windows - exit" << endl;
return;
#endif
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
}
else
filename = infile;
// Try to open the file
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file ){
cout <<"StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
return;
}
// -------------------------------------------------------
// Tutorial starts here
// -------------------------------------------------------
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !mc){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
// ---------------------------------------------
// create and use the ProfileLikelihoodCalculator
// to find and plot the 95% confidence interval
// on the parameter of interest as specified
// in the model config
ProfileLikelihoodCalculator pl(*data,*mc);
pl.SetConfidenceLevel(confLevel); // 95% interval
LikelihoodInterval* interval = pl.GetInterval();
// print out the interval on the first Parameter of Interest
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
cout << "\n>>>> RESULT : " << confLevel*100 << "% interval on " <<firstPOI->GetName()<<" is : ["<<
interval->LowerLimit(*firstPOI) << ", "<<
interval->UpperLimit(*firstPOI) <<"]\n "<<endl;
// make a plot
cout << "making a plot of the profile likelihood function ....(if it is taking a lot of time use less points or the TF1 drawing option)\n";
LikelihoodIntervalPlot plot(interval);
plot.SetNPoints(nScanPoints); // do not use too many points, it could become very slow for some models
if (poiXMin < poiXMax) plot.SetRange(poiXMin, poiXMax);
TString opt;
if (plotAsTF1) opt += TString("tf1");
plot.Draw(opt); // use option TF1 if too slow (plot.Draw("tf1")
// if requested perform also an hypothesis test for the significance
if (doHypoTest) {
RooArgSet nullparams("nullparams");
nullparams.addClone(*firstPOI);
nullparams.setRealValue(firstPOI->GetName(), nullParamValue);
pl.SetNullParameters(nullparams);
std::cout << "Perform Test of Hypothesis : null Hypothesis is " << firstPOI->GetName() << nullParamValue << std::endl;
auto result = pl.GetHypoTest();
std::cout << "\n>>>> Hypotheis Test Result \n";
result->Print();
}
}
double StandardFrequentistDiscovery(
const char* infile = "",
const char* workspaceName = "channel1",
const char* modelConfigNameSB = "ModelConfig",
const char* dataName = "obsData",
int toys = 1000,
double poiValueForBackground = 0.0,
double poiValueForSignal = 1.0
) {
// The workspace contains the model for s+b. The b model is "autogenerated"
// by copying s+b and setting the one parameter of interest to zero.
// To keep the script simple, multiple parameters of interest or different
// functional forms of the b model are not supported.
// for now, assume there is only one parameter of interest, and these are
// its values:
/////////////////////////////////////////////////////////////
// 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_channel1_GammaExample_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 -1;
#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 -1;
}
/////////////////////////////////////////////////////////////
// Tutorial starts here
////////////////////////////////////////////////////////////
TStopwatch *mn_t = new TStopwatch;
mn_t->Start();
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if (!w) {
cout << "workspace not found" << endl;
return -1.0;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigNameSB);
// get the data 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 -1.0;
}
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
firstPOI->setVal(poiValueForSignal);
mc->SetSnapshot(*mc->GetParametersOfInterest());
// create null model
ModelConfig *mcNull = mc->Clone("ModelConfigNull");
firstPOI->setVal(poiValueForBackground);
mcNull->SetSnapshot(*(RooArgSet*)mcNull->GetParametersOfInterest()->snapshot());
// ----------------------------------------------------
// Configure a ProfileLikelihoodTestStat and a SimpleLikelihoodRatioTestStat
// to use simultaneously with ToyMCSampler
ProfileLikelihoodTestStat* plts = new ProfileLikelihoodTestStat(*mc->GetPdf());
plts->SetOneSidedDiscovery(true);
plts->SetVarName( "q_{0}/2" );
// ----------------------------------------------------
// configure the ToyMCImportanceSampler with two test statistics
ToyMCSampler toymcs(*plts, 50);
// 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) {
toymcs.SetNEventsPerToy(1);
} else cout << "Not sure what to do about this model" << endl;
}
// We can use PROOF to speed things along in parallel
// ProofConfig pc(*w, 2, "user@yourfavoriteproofcluster", false);
ProofConfig pc(*w, 2, "", false);
//toymcs.SetProofConfig(&pc); // enable proof
// instantiate the calculator
FrequentistCalculator freqCalc(*data, *mc, *mcNull, &toymcs);
freqCalc.SetToys( toys,toys ); // null toys, alt toys
// Run the calculator and print result
HypoTestResult* freqCalcResult = freqCalc.GetHypoTest();
freqCalcResult->GetNullDistribution()->SetTitle( "b only" );
freqCalcResult->GetAltDistribution()->SetTitle( "s+b" );
freqCalcResult->Print();
double pvalue = freqCalcResult->NullPValue();
// stop timing
mn_t->Stop();
cout << "total CPU time: " << mn_t->CpuTime() << endl;
cout << "total real time: " << mn_t->RealTime() << endl;
// plot
TCanvas* c1 = new TCanvas();
HypoTestPlot *plot = new HypoTestPlot(*freqCalcResult, 100, -0.49, 9.51 );
plot->SetLogYaxis(true);
// add chi2 to plot
int nPOI = 1;
TF1* f = new TF1("f", TString::Format("1*ROOT::Math::chisquared_pdf(2*x,%d,0)",nPOI), 0,20);
f->SetLineColor( kBlack );
f->SetLineStyle( 7 );
plot->AddTF1( f, TString::Format("#chi^{2}(2x,%d)",nPOI) );
plot->Draw();
c1->SaveAs("standard_discovery_output.pdf");
return pvalue;
}
/*
* Prepares the workspace to be used by the hypothesis test calculator
*/
void workspace_preparer(char *signal_file_name, char *signal_hist_name_in_file, char *background_file_name, char *background_hist_name_in_file, char *data_file_name, char *data_hist_name_in_file, char *config_file) {
// Include the config_reader class.
TString path = gSystem->GetIncludePath();
path.Append(" -I/home/max/cern/cls/mario");
gSystem->SetIncludePath(path);
gROOT->LoadMacro("config_reader.cxx");
// RooWorkspace used to store values.
RooWorkspace * pWs = new RooWorkspace("ws");
// Create a config_reader (see source for details) to read the config
// file.
config_reader reader(config_file, pWs);
// Read MR and RR bounds from the config file.
double MR_lower = reader.find_double("MR_lower");
double MR_upper = reader.find_double("MR_upper");
double RR_lower = reader.find_double("RR_lower");
double RR_upper = reader.find_double("RR_upper");
double MR_initial = (MR_lower + MR_upper)/2;
double RR_initial = (RR_lower + RR_upper)/2;
// Define the Razor Variables
RooRealVar MR = RooRealVar("MR", "MR", MR_initial, MR_lower, MR_upper);
RooRealVar RR = RooRealVar("RSQ", "RSQ", RR_initial, RR_lower, RR_upper);
// Argument lists
RooArgList pdf_arg_list(MR, RR, "input_args_list");
RooArgSet pdf_arg_set(MR, RR, "input_pdf_args_set");
/***********************************************************************/
/* PART 1: IMPORTING SIGNAL AND BACKGROUND HISTOGRAMS */
/***********************************************************************/
/*
* Get the signal's unextended pdf by converting the TH2D in the file
* into a RooHistPdf
*/
TFile *signal_file = new TFile(signal_file_name);
TH2D *signal_hist = (TH2D *)signal_file->Get(signal_hist_name_in_file);
RooDataHist *signal_RooDataHist = new RooDataHist("signal_roodatahist",
"signal_roodatahist",
pdf_arg_list,
signal_hist);
RooHistPdf *unextended_sig_pdf = new RooHistPdf("unextended_sig_pdf",
"unextended_sig_pdf",
pdf_arg_set,
*signal_RooDataHist);
/*
* Repeat this process for the background.
*/
TFile *background_file = new TFile(background_file_name);
TH2D *background_hist =
(TH2D *)background_file->Get(background_hist_name_in_file);
RooDataHist *background_RooDataHist =
new RooDataHist("background_roodatahist", "background_roodatahist",
pdf_arg_list, background_hist);
RooHistPdf *unextended_bkg_pdf = new RooHistPdf("unextended_bkg_pdf",
"unextended_bkg_pdf",
pdf_arg_set,
*background_RooDataHist);
/*
* Now, we want to create the bprime variable, which represents the
* integral over the background-only sample. We will perform the
* integral automatically (that's why this is the only nuisance
* parameter declared in this file - its value can be determined from
* the input histograms).
*/
ostringstream bprime_string;
ostringstream bprime_pdf_string;
bprime_string << "bprime[" << background_hist->Integral() << ", 0, 999999999]";
bprime_pdf_string << "Poisson::bprime_pdf(bprime, " << background_hist->Integral() << ")";
pWs->factory(bprime_string.str().c_str());
pWs->factory(bprime_pdf_string.str().c_str());
/*
* This simple command will create all values from the config file
* with 'make:' at the beginning and a delimiter at the end (see config
* _reader if you don't know what a delimiter is). In other
* words, the luminosity, efficiency, transfer factors, and their pdfs
* are created from this command. The declarations are contained in the
* config file to be changed easily without having to modify this code.
*/
reader.factory_all();
/*
* Now, we want to create the extended pdfs from the unextended pdfs, as
* well as from the S and B values we manufactured in the config file.
* S and B are the values by which the signal and background pdfs,
* respectively, are extended. Recall that they were put in the
* workspace in the reader.facotry_all() command.
*/
RooAbsReal *S = pWs->function("S");
RooAbsReal *B = pWs->function("B");
RooExtendPdf *signalpart = new RooExtendPdf("signalpart", "signalpart",
*unextended_sig_pdf, *S);
RooExtendPdf *backgroundpart =
new RooExtendPdf("backgroundpart", "backgroundpart",
*unextended_bkg_pdf, *B);
RooArgList *pdf_list = new RooArgList(*signalpart, *backgroundpart,
"list");
// Add the signal and background pdfs to make a TotalPdf
RooAddPdf *TotalPdf = new RooAddPdf("TotalPdf", "TotalPdf", *pdf_list);
RooArgList *pdf_prod_list = new RooArgList(*TotalPdf,
*pWs->pdf("lumi_pdf"),
*pWs->pdf("eff_pdf"),
*pWs->pdf("rho_pdf"),
*pWs->pdf("bprime_pdf"));
// This creates the final model pdf.
RooProdPdf *model = new RooProdPdf("model", "model", *pdf_prod_list);
/*
* Up until now, we have been using the workspace pWs to contain all of
* our values. Now, all of our values that we require are in use in the
* RooProdPdf called "model". So, we need to import "model" into a
* RooWorkspace. To avoid recopying values into the rooworkspace, when
* the values may already be present (which can cause problems), we will
* simply create a new RooWorkspace to avoid confusion and problems. The
* new RooWorkspace is created here.
*/
RooWorkspace *newworkspace = new RooWorkspace("newws");
newworkspace->import(*model);
// Immediately delete pWs, so we don't accidentally use it again.
delete pWs;
// Show off the newworkspace
newworkspace->Print();
// observables
RooArgSet obs(*newworkspace->var("MR"), *newworkspace->var("RSQ"), "obs");
// global observables
RooArgSet globalObs(*newworkspace->var("nom_lumi"), *newworkspace->var("nom_eff"), *newworkspace->var("nom_rho"));
//fix global observables to their nominal values
newworkspace->var("nom_lumi")->setConstant();
newworkspace->var("nom_eff")->setConstant();
newworkspace->var("nom_rho")->setConstant();
//Set Parameters of interest
RooArgSet poi(*newworkspace->var("sigma"), "poi");
//Set Nuisnaces
RooArgSet nuis(*newworkspace->var("prime_lumi"), *newworkspace->var("prime_eff"), *newworkspace->var("prime_rho"), *newworkspace->var("bprime"));
// priors (for Bayesian calculation)
newworkspace->factory("Uniform::prior_signal(sigma)"); // for parameter of interest
newworkspace->factory("Uniform::prior_bg_b(bprime)"); // for data driven nuisance parameter
newworkspace->factory("PROD::prior(prior_signal,prior_bg_b)"); // total prior
//Observed data is pulled from histogram.
//TFile *data_file = new TFile(data_file_name);
TFile *data_file = new TFile(data_file_name);
TH2D *data_hist = (TH2D *)data_file->Get(data_hist_name_in_file);
RooDataHist *pData = new RooDataHist("data", "data", obs, data_hist);
newworkspace->import(*pData);
// Now, we will draw our data from a RooDataHist.
/*TFile *data_file = new TFile(data_file_name);
TTree *data_tree = (TTree *) data_file->Get(data_hist_name_in_file);
RooDataSet *pData = new RooDataSet("data", "data", data_tree, obs);
newworkspace->import(*pData);*/
// Craft the signal+background model
ModelConfig * pSbModel = new ModelConfig("SbModel");
pSbModel->SetWorkspace(*newworkspace);
pSbModel->SetPdf(*newworkspace->pdf("model"));
pSbModel->SetPriorPdf(*newworkspace->pdf("prior"));
pSbModel->SetParametersOfInterest(poi);
pSbModel->SetNuisanceParameters(nuis);
pSbModel->SetObservables(obs);
pSbModel->SetGlobalObservables(globalObs);
// set all but obs, poi and nuisance to const
SetConstants(newworkspace, pSbModel);
newworkspace->import(*pSbModel);
// background-only model
// use the same PDF as s+b, with sig=0
// POI value under the background hypothesis
// (We will set the value to 0 later)
Double_t poiValueForBModel = 0.0;
ModelConfig* pBModel = new ModelConfig(*(RooStats::ModelConfig *)newworkspace->obj("SbModel"));
pBModel->SetName("BModel");
pBModel->SetWorkspace(*newworkspace);
newworkspace->import(*pBModel);
// find global maximum with the signal+background model
// with conditional MLEs for nuisance parameters
// and save the parameter point snapshot in the Workspace
// - safer to keep a default name because some RooStats calculators
// will anticipate it
RooAbsReal * pNll = pSbModel->GetPdf()->createNLL(*pData);
RooAbsReal * pProfile = pNll->createProfile(RooArgSet());
pProfile->getVal(); // this will do fit and set POI and nuisance parameters to fitted values
RooArgSet * pPoiAndNuisance = new RooArgSet();
if(pSbModel->GetNuisanceParameters())
pPoiAndNuisance->add(*pSbModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pSbModel->GetParametersOfInterest());
cout << "\nWill save these parameter points that correspond to the fit to data" << endl;
pPoiAndNuisance->Print("v");
pSbModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
// Find a parameter point for generating pseudo-data
// with the background-only data.
// Save the parameter point snapshot in the Workspace
pNll = pBModel->GetPdf()->createNLL(*pData);
pProfile = pNll->createProfile(poi);
((RooRealVar *)poi.first())->setVal(poiValueForBModel);
pProfile->getVal(); // this will do fit and set nuisance parameters to profiled values
pPoiAndNuisance = new RooArgSet();
if(pBModel->GetNuisanceParameters())
pPoiAndNuisance->add(*pBModel->GetNuisanceParameters());
pPoiAndNuisance->add(*pBModel->GetParametersOfInterest());
cout << "\nShould use these parameter points to generate pseudo data for bkg only" << endl;
pPoiAndNuisance->Print("v");
pBModel->SetSnapshot(*pPoiAndNuisance);
delete pProfile;
delete pNll;
delete pPoiAndNuisance;
// save workspace to file
newworkspace->writeToFile("ws_twobin.root");
// clean up
delete newworkspace;
delete pData;
delete pSbModel;
delete pBModel;
} // ----- end of tutorial ----------------------------------------
void StandardBayesianNumericalDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData"){
/////////////////////////////////////////////////////////////
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
////////////////////////////////////////////////////////////
TString filename = infile;
if (filename.IsNull()) {
filename = "results/example_combined_GaussExample_model.root";
std::cout << "Use standard file generated with HistFactory : " << filename << std::endl;
}
// Check if example input file exists
TFile *file = TFile::Open(filename);
// if input file was specified but not found, quit
if(!file && !TString(infile).IsNull()){
cout <<"file " << filename << " 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;
}
// 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;
}
/////////////////////////////////////////////
// create and use the BayesianCalculator
// to find and plot the 95% credible interval
// on the parameter of interest as specified
// in the model config
// before we do that, we must specify our prior
// it belongs in the model config, but it may not have
// been specified
RooUniform prior("prior","",*mc->GetParametersOfInterest());
w->import(prior);
mc->SetPriorPdf(*w->pdf("prior"));
// do without systematics
//mc->SetNuisanceParameters(RooArgSet() );
BayesianCalculator bayesianCalc(*data,*mc);
bayesianCalc.SetConfidenceLevel(0.95); // 95% interval
// default of the calculator is central interval. here use shortest , central or upper limit depending on input
// doing a shortest interval might require a longer time since it requires a scan of the posterior function
if (intervalType == 0) bayesianCalc.SetShortestInterval(); // for shortest interval
if (intervalType == 1) bayesianCalc.SetLeftSideTailFraction(0.5); // for central interval
if (intervalType == 2) bayesianCalc.SetLeftSideTailFraction(0.); // for upper limit
if (!integrationType.IsNull() ) {
bayesianCalc.SetIntegrationType(integrationType); // set integrationType
bayesianCalc.SetNumIters(nToys); // set number of ietrations (i.e. number of toys for MC integrations)
}
// compute interval by scanning the posterior function
if (scanPosterior)
bayesianCalc.SetScanOfPosterior(nScanPoints);
SimpleInterval* interval = bayesianCalc.GetInterval();
// print out the iterval on the first Parameter of Interest
RooRealVar* firstPOI = (RooRealVar*) mc->GetParametersOfInterest()->first();
cout << "\n95% interval on " <<firstPOI->GetName()<<" is : ["<<
interval->LowerLimit() << ", "<<
interval->UpperLimit() <<"] "<<endl;
// make a plot
// since plotting may take a long time (it requires evaluating
// the posterior in many points) this command will speed up
// by reducing the number of points to plot - do 50
cout << "\nDrawing plot of posterior function....." << endl;
bayesianCalc.SetScanOfPosterior(nScanPoints);
RooPlot * plot = bayesianCalc.GetPosteriorPlot();
plot->Draw();
}
void StandardBayesianNumericalDemo(const char* infile = "",
const char* workspaceName = "combined",
const char* modelConfigName = "ModelConfig",
const char* dataName = "obsData") {
// option definitions
double confLevel = optBayes.confLevel;
TString integrationType = optBayes.integrationType;
int nToys = optBayes.nToys;
bool scanPosterior = optBayes.scanPosterior;
int nScanPoints = optBayes.nScanPoints;
int intervalType = optBayes.intervalType;
int maxPOI = optBayes.maxPOI;
double nSigmaNuisance = optBayes.nSigmaNuisance;
/////////////////////////////////////////////////////////////
// First part is just to access a user-defined file
// or create the standard example file if it doesn't exist
////////////////////////////////////////////////////////////
const char* filename = "";
if (!strcmp(infile,"")) {
filename = "results/example_combined_GaussExample_model.root";
bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
// if file does not exists generate with histfactory
if (!fileExist) {
#ifdef _WIN32
cout << "HistFactory file cannot be generated on Windows - exit" << endl;
return;
#endif
// Normally this would be run on the command line
cout <<"will run standard hist2workspace example"<<endl;
gROOT->ProcessLine(".! prepareHistFactory .");
gROOT->ProcessLine(".! hist2workspace config/example.xml");
cout <<"\n\n---------------------"<<endl;
cout <<"Done creating example input"<<endl;
cout <<"---------------------\n\n"<<endl;
}
}
else
filename = infile;
// Try to open the file
TFile *file = TFile::Open(filename);
// if input file was specified byt not found, quit
if(!file ){
cout <<"StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
return;
}
/////////////////////////////////////////////////////////////
// Tutorial starts here
////////////////////////////////////////////////////////////
// get the workspace out of the file
RooWorkspace* w = (RooWorkspace*) file->Get(workspaceName);
if(!w){
cout <<"workspace not found" << endl;
return;
}
// get the modelConfig out of the file
ModelConfig* mc = (ModelConfig*) w->obj(modelConfigName);
// get the modelConfig out of the file
RooAbsData* data = w->data(dataName);
// make sure ingredients are found
if(!data || !mc){
w->Print();
cout << "data or ModelConfig was not found" <<endl;
return;
}
/////////////////////////////////////////////
// create and use the BayesianCalculator
// to find and plot the 95% credible interval
// on the parameter of interest as specified
// in the model config
// before we do that, we must specify our prior
// it belongs in the model config, but it may not have
// been specified
RooUniform prior("prior","",*mc->GetParametersOfInterest());
w->import(prior);
mc->SetPriorPdf(*w->pdf("prior"));
// do without systematics
//mc->SetNuisanceParameters(RooArgSet() );
if (nSigmaNuisance > 0) {
RooAbsPdf * pdf = mc->GetPdf();
assert(pdf);
RooFitResult * res = pdf->fitTo(*data, Save(true), Minimizer(ROOT::Math::MinimizerOptions::DefaultMinimizerType().c_str()), Hesse(true),
PrintLevel(ROOT::Math::MinimizerOptions::DefaultPrintLevel()-1) );
res->Print();
RooArgList nuisPar(*mc->GetNuisanceParameters());
for (int i = 0; i < nuisPar.getSize(); ++i) {
RooRealVar * v = dynamic_cast<RooRealVar*> (&nuisPar[i] );
assert( v);
v->setMin( TMath::Max( v->getMin(), v->getVal() - nSigmaNuisance * v->getError() ) );
v->setMax( TMath::Min( v->getMax(), v->getVal() + nSigmaNuisance * v->getError() ) );
std::cout << "setting interval for nuisance " << v->GetName() << " : [ " << v->getMin() << " , " << v->getMax() << " ]" << std::endl;
}
}
BayesianCalculator bayesianCalc(*data,*mc);
bayesianCalc.SetConfidenceLevel(confLevel); // 95% interval
// default of the calculator is central interval. here use shortest , central or upper limit depending on input
// doing a shortest interval might require a longer time since it requires a scan of the posterior function
if (intervalType == 0) bayesianCalc.SetShortestInterval(); // for shortest interval
if (intervalType == 1) bayesianCalc.SetLeftSideTailFraction(0.5); // for central interval
if (intervalType == 2) bayesianCalc.SetLeftSideTailFraction(0.); // for upper limit
if (!integrationType.IsNull() ) {
bayesianCalc.SetIntegrationType(integrationType); // set integrationType
bayesianCalc.SetNumIters(nToys); // set number of ietrations (i.e. number of toys for MC integrations)
}
// in case of toyMC make a nnuisance pdf
if (integrationType.Contains("TOYMC") ) {
RooAbsPdf * nuisPdf = RooStats::MakeNuisancePdf(*mc, "nuisance_pdf");
cout << "using TOYMC integration: make nuisance pdf from the model " << std::endl;
nuisPdf->Print();
bayesianCalc.ForceNuisancePdf(*nuisPdf);
scanPosterior = true; // for ToyMC the posterior is scanned anyway so used given points
}
// compute interval by scanning the posterior function
if (scanPosterior)
bayesianCalc.SetScanOfPosterior(nScanPoints);
RooRealVar* poi = (RooRealVar*) mc->GetParametersOfInterest()->first();
if (maxPOI != -999 && maxPOI > poi->getMin())
poi->setMax(maxPOI);
SimpleInterval* interval = bayesianCalc.GetInterval();
// print out the iterval on the first Parameter of Interest
cout << "\n>>>> RESULT : " << confLevel*100 << "% interval on " << poi->GetName()<<" is : ["<<
interval->LowerLimit() << ", "<<
interval->UpperLimit() <<"] "<<endl;
// make a plot
// since plotting may take a long time (it requires evaluating
// the posterior in many points) this command will speed up
// by reducing the number of points to plot - do 50
// ignore errors of PDF if is zero
RooAbsReal::setEvalErrorLoggingMode(RooAbsReal::Ignore) ;
cout << "\nDrawing plot of posterior function....." << endl;
// always plot using numer of scan points
bayesianCalc.SetScanOfPosterior(nScanPoints);
RooPlot * plot = bayesianCalc.GetPosteriorPlot();
plot->Draw();
}
// internal routine to run the inverter
HypoTestInverterResult * RunInverter(RooWorkspace * w, const char * modelSBName, const char * modelBName,
const char * dataName, int type, int testStatType,
int npoints, double poimin, double poimax,
int ntoys, bool useCls )
{
std::cout << "Running HypoTestInverter on the workspace " << w->GetName() << std::endl;
w->Print();
RooAbsData * data = w->data(dataName);
if (!data) {
Error("RA2bHypoTestDemo","Not existing data %s",dataName);
return 0;
}
else
std::cout << "Using data set " << dataName << std::endl;
// 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("RA2bHypoTestDemo","Not existing ModelConfig %s",modelSBName);
return 0;
}
// check the model
if (!sbModel->GetPdf()) {
Error("RA2bHypoTestDemo","Model %s has no pdf ",modelSBName);
return 0;
}
if (!sbModel->GetParametersOfInterest()) {
Error("RA2bHypoTestDemo","Model %s has no poi ",modelSBName);
return 0;
}
if (!sbModel->GetParametersOfInterest()) {
Error("RA2bHypoTestInvDemo","Model %s has no poi ",modelSBName);
return 0;
}
if (!sbModel->GetSnapshot() ) {
Info("RA2bHypoTestInvDemo","Model %s has no snapshot - make one using model poi",modelSBName);
sbModel->SetSnapshot( *sbModel->GetParametersOfInterest() );
}
if (!bModel || bModel == sbModel) {
Info("RA2bHypoTestInvDemo","The background model %s does not exist",modelBName);
Info("RA2bHypoTestInvDemo","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("RA2bHypoTestInvDemo","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("RA2bHypoTestInvDemo","Model %s has no valid poi",modelBName);
return 0;
}
}
}
SimpleLikelihoodRatioTestStat slrts(*sbModel->GetPdf(),*bModel->GetPdf());
if (sbModel->GetSnapshot()) slrts.SetNullParameters(*sbModel->GetSnapshot());
if (bModel->GetSnapshot()) slrts.SetAltParameters(*bModel->GetSnapshot());
// ratio of profile likelihood - need to pass snapshot for the alt
RatioOfProfiledLikelihoodsTestStat
ropl(*sbModel->GetPdf(), *bModel->GetPdf(), bModel->GetSnapshot());
ropl.SetSubtractMLE(false);
//MyProfileLikelihoodTestStat profll(*sbModel->GetPdf());
ProfileLikelihoodTestStat profll(*sbModel->GetPdf());
if (testStatType == 3) profll.SetOneSided(1);
if (optimize) profll.SetReuseNLL(true);
TestStatistic * testStat = &slrts;
if (testStatType == 1) testStat = &ropl;
if (testStatType == 2 || testStatType == 3) testStat = &profll;
HypoTestCalculatorGeneric * hc = 0;
if (type == 0) hc = new FrequentistCalculator(*data, *bModel, *sbModel);
else hc = new HybridCalculator(*data, *bModel, *sbModel);
ToyMCSampler *toymcs = (ToyMCSampler*)hc->GetTestStatSampler();
//=== DEBUG
///// toymcs->SetWS( w ) ;
//=== DEBUG
toymcs->SetNEventsPerToy(1);
toymcs->SetTestStatistic(testStat);
if (optimize) toymcs->SetUseMultiGen(true);
if (type == 1) {
HybridCalculator *hhc = (HybridCalculator*) hc;
hhc->SetToys(ntoys,ntoys);
// check for nuisance prior pdf
if (bModel->GetPriorPdf() && sbModel->GetPriorPdf() ) {
hhc->ForcePriorNuisanceAlt(*bModel->GetPriorPdf());
hhc->ForcePriorNuisanceNull(*sbModel->GetPriorPdf());
}
else {
if (bModel->GetNuisanceParameters() || sbModel->GetNuisanceParameters() ) {
Error("RA2bHypoTestInvDemo","Cannnot run Hybrid calculator because no prior on the nuisance parameter is specified");
return 0;
}
}
}
else
((FrequentistCalculator*) hc)->SetToys(ntoys,ntoys);
// Get the result
RooMsgService::instance().getStream(1).removeTopic(RooFit::NumIntegration);
TStopwatch tw; tw.Start();
const RooArgSet * poiSet = sbModel->GetParametersOfInterest();
RooRealVar *poi = (RooRealVar*)poiSet->first();
// fit the data first
sbModel->GetPdf()->fitTo(*data);
double poihat = poi->getVal();
HypoTestInverter calc(*hc);
calc.SetConfidenceLevel(0.95);
calc.UseCLs(useCls);
calc.SetVerbose(true);
// can speed up using proof-lite
if (useProof && nworkers > 1) {
ProofConfig pc(*w, nworkers, "", kFALSE);
toymcs->SetProofConfig(&pc); // enable proof
}
printf(" npoints = %d, poimin = %7.2f, poimax = %7.2f\n\n", npoints, poimin, poimax ) ;
cout << flush ;
if ( npoints==1 ) {
std::cout << "Evaluating one point : " << poimax << std::endl;
calc.RunOnePoint(poimax);
} else 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;
}
cout << "\n\n right before calc.GetInterval(), ntoys = " << ntoys << " \n\n" << flush ;
HypoTestInverterResult * r = calc.GetInterval();
return r;
}
