This is a standard demo that can be used with any ROOT file prepared in the standard way. You specify:

  • name for input ROOT file
  • name of workspace inside ROOT file that holds model and data
  • name of ModelConfig that specifies details for calculator tools
  • name of dataset

    With default parameters the macro will attempt to run the standard hist2workspace example and read the ROOT file that it produces.

Author: Sven Kreiss, Kyle Cranmer
This notebook tutorial was automatically generated with ROOTBOOK-izer from the macro found in the ROOT repository on Saturday, September 24, 2022 at 09:49 AM.

In [ ]:
%%cpp -d
#include "TFile.h"
#include "TROOT.h"
#include "TH1F.h"
#include "TF1.h"
#include "TCanvas.h"
#include "TStopwatch.h"

#include "RooWorkspace.h"
#include "RooAbsData.h"
#include "RooRandom.h"
#include "RooRealSumPdf.h"
#include "RooNumIntConfig.h"

#include "RooStats/ModelConfig.h"
#include "RooStats/ToyMCImportanceSampler.h"
#include "RooStats/HypoTestResult.h"
#include "RooStats/HypoTestPlot.h"
#include "RooStats/SamplingDistribution.h"
#include "RooStats/ProfileLikelihoodTestStat.h"
#include "RooStats/SimpleLikelihoodRatioTestStat.h"
#include "RooStats/ProfileLikelihoodCalculator.h"
#include "RooStats/LikelihoodInterval.h"
#include "RooStats/LikelihoodIntervalPlot.h"

#include "RooStats/FrequentistCalculator.h"
#include "TSystem.h"

#include <vector>

using namespace RooFit;
using namespace RooStats;

Arguments are defined.

In [ ]:
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

In [ ]:
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;
      // 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

In [ ]:
TFile *file = TFile::Open(filename);

if input file was specified byt not found, quit

In [ ]:
if (!file) {
   cout << "StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
   return -1;

Tutorial starts here

In [ ]:
TStopwatch *mn_t = new TStopwatch;

get the workspace out of the file

In [ ]:
RooWorkspace *w = (RooWorkspace *)file->Get(workspaceName);
if (!w) {
   cout << "workspace not found" << endl;
   return -1.0;

get the modelConfig out of the file

In [ ]:
ModelConfig *mc = (ModelConfig *)w->obj(modelConfigNameSB);

get the data out of the file

In [ ]:
RooAbsData *data = w->data(dataName);

make sure ingredients are found

In [ ]:
if (!data || !mc) {
   cout << "data or ModelConfig was not found" << endl;
   return -1.0;

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

create null model

In [ ]:
ModelConfig *mcNull = mc->Clone("ModelConfigNull");
mcNull->SetSnapshot(*(RooArgSet *)mcNull->GetParametersOfInterest()->snapshot());

Configure a ProfileLikelihoodTestStat and a SimpleLikelihoodRatioTestStat to use simultaneously with ToyMCSampler

In [ ]:
ProfileLikelihoodTestStat *plts = new ProfileLikelihoodTestStat(*mc->GetPdf());

configure the ToyMCImportanceSampler with two test statistics

In [ ]:
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.

In [ ]:
if (!mc->GetPdf()->canBeExtended()) {
   if (data->numEntries() == 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, "[email protected]", false);

In [ ]:
ProofConfig pc(*w, 2, "", false);

toymcs.SetProofConfig(&pc); // enable proof

instantiate the calculator

In [ ]:
FrequentistCalculator freqCalc(*data, *mc, *mcNull, &toymcs);
freqCalc.SetToys(toys, toys); // null toys, alt toys

Run the calculator and print result

In [ ]:
HypoTestResult *freqCalcResult = freqCalc.GetHypoTest();
freqCalcResult->GetNullDistribution()->SetTitle("b only");
double pvalue = freqCalcResult->NullPValue();

stop timing

In [ ]:
cout << "total CPU time: " << mn_t->CpuTime() << endl;
cout << "total real time: " << mn_t->RealTime() << endl;


In [ ]:
TCanvas *c1 = new TCanvas();
HypoTestPlot *plot = new HypoTestPlot(*freqCalcResult, 100, -0.49, 9.51);

add chi2 to plot

In [ ]:
int nPOI = 1;
TF1 *f = new TF1("f", TString::Format("1*ROOT::Math::chisquared_pdf(2*x,%d,0)", nPOI), 0, 20);
plot->AddTF1(f, TString::Format("#chi^{2}(2x,%d)", nPOI));


return pvalue;

Draw all canvases

In [ ]: