/////////////////////////////////////////////////////////////////
//
// rs102_hypotestwithshapes for RooStats project
// Author: Kyle Cranmer <cranmer@cern.ch>
//
// Modified from version of February 29, 2008
//
// This tutorial macro shows a typical search for a new particle
// by studying an invariant mass distribution.
// The macro creates a simple signal model and two background models,
// which are added to a RooWorkspace.
// The macro creates a toy dataset, and then uses a RooStats
// ProfileLikleihoodCalculator to do a hypothesis test of the
// background-only and signal+background hypotheses.
// In this example, shape uncertainties are not taken into account, but
// normalization uncertainties are.
//
/////////////////////////////////////////////////////////////////

#ifndef __CINT__
#include "RooGlobalFunc.h"
#endif
#include "RooDataSet.h"
#include "RooRealVar.h"
#include "RooGaussian.h"
#include "RooAddPdf.h"
#include "RooProdPdf.h"
#include "RooAddition.h"
#include "RooProduct.h"
#include "TCanvas.h"
#include "RooChebychev.h"
#include "RooAbsPdf.h"
#include "RooFit.h"
#include "RooFitResult.h"
#include "RooPlot.h"
#include "RooAbsArg.h"
#include "RooWorkspace.h"
#include "RooStats/ProfileLikelihoodCalculator.h"
#include "RooStats/HypoTestResult.h"
#include <string>


// use this order for safety on library loading
using namespace RooFit;
using namespace RooStats;

// see below for implementation
void AddModel(RooWorkspace*);
void AddData(RooWorkspace*);
void DoHypothesisTest(RooWorkspace*);
void MakePlots(RooWorkspace*);

//____________________________________
void rs102_hypotestwithshapes() {

  // The main macro.

  // Create a workspace to manage the project.

  // add the signal and background models to the workspace

  // add some toy data to the workspace

  // inspect the workspace if you wish
  //  wspace->Print();

  // do the hypothesis test

  // make some plots

  // cleanup

}

//____________________________________
void AddModel(RooWorkspace* wks){

  // Make models for signal (Higgs) and background (Z+jets and QCD)
  // In real life, this part requires an intellegent modeling
  // of signal and background -- this is only an example.

  // set range of observable

  // make a RooRealVar for the observable


  /////////////////////////////////////////////
  // make a simple signal model.



  // we will test this specific mass point for the signal


  // and we assume we know the mass resolution

  /////////////////////////////////////////////
  // make zjj model.  Just like signal model


  // we know Z mass

  // assume we know resolution too



  //////////////////////////////////////////////
  // make QCD model



  // let's assume this shape is known, but the normalization is not

  //////////////////////////////////////////////
  // combined model

  // Setting the fraction of Zjj to be 40% for initial guess.

  // Set the expected fraction of signal to 20%.


  // Introduce mu: the signal strength in units of the expectation.
  // eg. mu = 1 is the SM, mu = 0 is no signal, mu=2 is 2x the SM

  // Introduce ratio of signal efficiency to nominal signal efficiency.
  // This is useful if you want to do limits on cross section.

  // finally the signal fraction is the product of the terms above.

  // full model

  // interesting for debugging and visualizing the model
  //  model.printCompactTree("","fullModel.txt");
  //  model.graphVizTree("fullModel.dot");


}

//____________________________________
void AddData(RooWorkspace* wks){
  // Add a toy dataset

}

//____________________________________
void DoHypothesisTest(RooWorkspace* wks){


  // Use a RooStats ProfileLikleihoodCalculator to do the hypothesis test.

  //plc.SetData("data");


  // here we explicitly set the value of the parameters for the null.
  // We want no signal contribution, eg. mu = 0


  //   RooArgSet* nullParams = new RooArgSet("nullParams");
  //   nullParams->addClone(*mu);


  //plc.SetNullParameters(*nullParams);


  // NOTE: using snapshot will import nullparams
  // in the WS and merge with existing "mu"
  // model.SetSnapshot(*nullParams);

  //use instead setNuisanceParameters

// 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 MakePlots(RooWorkspace* wks) {

  // Make plots of the data and the best fit model in two cases:
  // first the signal+background case
  // second the background-only case.

  // get some things out of workspace


  //////////////////////////////////////////////////////////
  // Make plots for the Alternate hypothesis, eg. let mu float



  //plot sig candidates, full model, and individual componenets


  //  cdata->SaveAs("alternateFit.gif");

  //////////////////////////////////////////////////////////
  // Do Fit to the Null hypothesis.  Eg. fix mu=0


  // plot signal candidates with background model and components


  //  cbkgonly->SaveAs("nullFit.gif");

}