Logo ROOT  
Reference Guide
rf514_RooCustomizer.C
Go to the documentation of this file.
1/// \file
2/// \ingroup tutorial_roofit
3/// \notebook -nodraw
4/// Using the RooCustomizer to create multiple PDFs that share a lot of properties, but have unique parameters for each category.
5/// As an extra complication, some of the new parameters need to be functions
6/// of a mass parameter.
7///
8/// \macro_output
9/// \macro_code
10///
11/// \author Stephan Hageboeck, CERN
12
13
14#include "RooRealVar.h"
15#include "RooGaussian.h"
16#include "RooPolynomial.h"
17#include "RooAddPdf.h"
18#include "RooCustomizer.h"
19#include "RooCategory.h"
20#include "RooFormulaVar.h"
21#include <iostream>
22
24
25 // Define a proto model that will be used as the template for each category
26 // ---------------------------------------------------------------------------
27
28 RooRealVar E("Energy","Energy",0,3000);
29
30 RooRealVar meanG("meanG","meanG", 100., 0., 3000.);
31 RooRealVar sigmaG("sigmaG","sigmaG", 3.);
32 RooGaussian gauss("gauss", "gauss", E, meanG, sigmaG);
33
34 RooRealVar pol1("pol1", "Constant of the polynomial", 1, -10, 10);
35 RooPolynomial linear("linear", "linear", E, pol1);
36
37 RooRealVar yieldSig("yieldSig", "yieldSig", 1, 0, 1.E4);
38 RooRealVar yieldBkg("yieldBkg", "yieldBkg", 1, 0, 1.E4);
39
40 RooAddPdf model("model", "S + B model",
41 RooArgList(gauss,linear),
42 RooArgList(yieldSig, yieldBkg));
43
44 std::cout << "The proto model before customisation:" << std::endl;
45 model.Print("T"); // "T" prints the model as a tree
46
47
48 // Build the categories
49 RooCategory sample("sample","sample");
50 sample["Sample1"] = 1;
51 sample["Sample2"] = 2;
52 sample["Sample3"] = 3;
53
54
55 // Start to customise the proto model that was defined above.
56 // ---------------------------------------------------------------------------
57
58 // We need two sets for bookkeeping of PDF nodes:
59 RooArgSet newLeafs; // This set collects leafs that are created in the process.
60 RooArgSet allCustomiserNodes; // This set lists leafs that have been used in a replacement operation.
61
62
63 // 1. Each sample should have its own mean for the gaussian
64 // The customiser will make copies of `meanG` for each category.
65 // These will all appear in the set `newLeafs`, which will own the new nodes.
66 RooCustomizer cust(model, sample, newLeafs, &allCustomiserNodes);
67 cust.splitArg(meanG, sample);
68
69
70 // 2. Each sample should have its own signal yield, but there is an extra complication:
71 // We need the yields 1 and 2 to be a function of the variable "mass".
72 // For this, we pre-define nodes with exacly the names that the customiser would have created automatically,
73 // that is, "<nodeName>_<categoryName>", and we register them in the set of customiser nodes.
74 // The customiser will pick them up instead of creating new ones.
75 // If we don't provide one (e.g. for "yieldSig_Sample3"), it will be created automatically by cloning `yieldSig`.
76 RooRealVar mass("M", "M", 1, 0, 12000);
77 RooFormulaVar yield1("yieldSig_Sample1", "Signal yield in the first sample", "M/3.360779", mass);
78 RooFormulaVar yield2("yieldSig_Sample2", "Signal yield in the second sample", "M/2", mass);
79 allCustomiserNodes.add(yield1);
80 allCustomiserNodes.add(yield2);
81
82 // Instruct the customiser to replace all yieldSig nodes for each sample:
83 cust.splitArg(yieldSig, sample);
84
85
86 // Now we can start building the PDFs for all categories:
87 auto pdf1 = cust.build("Sample1");
88 auto pdf2 = cust.build("Sample2");
89 auto pdf3 = cust.build("Sample3");
90
91 // And we inspect the two PDFs
92 std::cout << "\nPDF 1 with a yield depending on M:" << std::endl;
93 pdf1->Print("T");
94 std::cout << "\nPDF 2 with a yield depending on M:" << std::endl;
95 pdf2->Print("T");
96 std::cout << "\nPDF 3 with a free yield:" << std::endl;
97 pdf3->Print("T");
98
99 std::cout << "\nThe following leafs have been created automatically while customising:" << std::endl;
100 newLeafs.Print("V");
101
102
103 // If we needed to set reasonable values for the means of the gaussians, this could be done as follows:
104 auto& meanG1 = static_cast<RooRealVar&>(allCustomiserNodes["meanG_Sample1"]);
105 meanG1.setVal(200);
106 auto& meanG2 = static_cast<RooRealVar&>(allCustomiserNodes["meanG_Sample2"]);
107 meanG2.setVal(300);
108
109 std::cout << "\nThe following leafs have been used while customising"
110 << "\n\t(partial overlap with the set of automatically created leaves."
111 << "\n\ta new customiser for a different PDF could reuse them if necessary.):" << std::endl;
112 allCustomiserNodes.Print("V");
113
114
115}
void Print(Option_t *options=0) const override
This method must be overridden when a class wants to print itself.
virtual bool add(const RooAbsArg &var, bool silent=false)
Add the specified argument to list.
RooAddPdf is an efficient implementation of a sum of PDFs of the form.
Definition: RooAddPdf.h:34
RooArgList is a container object that can hold multiple RooAbsArg objects.
Definition: RooArgList.h:22
RooArgSet is a container object that can hold multiple RooAbsArg objects.
Definition: RooArgSet.h:56
RooCategory is an object to represent discrete states.
Definition: RooCategory.h:28
RooCustomizer is a factory class to produce clones of a prototype composite PDF object with the same ...
Definition: RooCustomizer.h:35
A RooFormulaVar is a generic implementation of a real-valued object, which takes a RooArgList of serv...
Definition: RooFormulaVar.h:30
Plain Gaussian p.d.f.
Definition: RooGaussian.h:24
RooPolynomial implements a polynomial p.d.f of the form.
Definition: RooPolynomial.h:28
RooRealVar represents a variable that can be changed from the outside.
Definition: RooRealVar.h:40
void setVal(double value) override
Set value of variable to 'value'.
Definition: RooRealVar.cxx:254
static constexpr double gauss
constexpr Double_t E()
Base of natural log: .
Definition: TMath.h:93