Logo ROOT  
Reference Guide
rf402_datahandling.C
Go to the documentation of this file.
1 /// \file
2 /// \ingroup tutorial_roofit
3 /// \notebook -js
4 /// Data and categories: tools for manipulation of (un)binned datasets
5 ///
6 /// \macro_image
7 /// \macro_output
8 /// \macro_code
9 ///
10 /// \date July 2008
11 /// \author Wouter Verkerke
12 
13 #include "RooRealVar.h"
14 #include "RooDataSet.h"
15 #include "RooDataHist.h"
16 #include "RooGaussian.h"
17 #include "RooConstVar.h"
18 #include "RooCategory.h"
19 #include "TCanvas.h"
20 #include "TAxis.h"
21 #include "RooPlot.h"
22 #include "TFile.h"
23 using namespace RooFit;
24 
25 // WVE Add reduction by range
26 
27 void rf402_datahandling()
28 {
29 
30  // Binned (RooDataHist) and unbinned datasets (RooDataSet) share
31  // many properties and inherit from a common abstract base class
32  // (RooAbsData), that provides an interface for all operations
33  // that can be performed regardless of the data format
34 
35  RooRealVar x("x", "x", -10, 10);
36  RooRealVar y("y", "y", 0, 40);
37  RooCategory c("c", "c");
38  c.defineType("Plus", +1);
39  c.defineType("Minus", -1);
40 
41  // B a s i c O p e r a t i o n s o n u n b i n n e d d a t a s e t s
42  // --------------------------------------------------------------
43 
44  // RooDataSet is an unbinned dataset (a collection of points in N-dimensional space)
45  RooDataSet d("d", "d", RooArgSet(x, y, c));
46 
47  // Unlike RooAbsArgs (RooAbsPdf,RooFormulaVar,....) datasets are not attached to
48  // the variables they are constructed from. Instead they are attached to an internal
49  // clone of the supplied set of arguments
50 
51  // Fill d with dummy values
52  Int_t i;
53  for (i = 0; i < 1000; i++) {
54  x = i / 50 - 10;
55  y = sqrt(1.0 * i);
56  c.setLabel((i % 2) ? "Plus" : "Minus");
57 
58  // We must explicitly refer to x,y,c here to pass the values because
59  // d is not linked to them (as explained above)
60  d.add(RooArgSet(x, y, c));
61  }
62  d.Print("v");
63  cout << endl;
64 
65  // The get() function returns a pointer to the internal copy of the RooArgSet(x,y,c)
66  // supplied in the constructor
67  const RooArgSet *row = d.get();
68  row->Print("v");
69  cout << endl;
70 
71  // Get with an argument loads a specific data point in row and returns
72  // a pointer to row argset. get() always returns the same pointer, unless
73  // an invalid row number is specified. In that case a null ptr is returned
74  d.get(900)->Print("v");
75  cout << endl;
76 
77  // R e d u c i n g , A p p e n d i n g a n d M e r g i n g
78  // -------------------------------------------------------------
79 
80  // The reduce() function returns a new dataset which is a subset of the original
81  cout << endl << ">> d1 has only columns x,c" << endl;
82  RooDataSet *d1 = (RooDataSet *)d.reduce(RooArgSet(x, c));
83  d1->Print("v");
84 
85  cout << endl << ">> d2 has only column y" << endl;
86  RooDataSet *d2 = (RooDataSet *)d.reduce(RooArgSet(y));
87  d2->Print("v");
88 
89  cout << endl << ">> d3 has only the points with y>5.17" << endl;
90  RooDataSet *d3 = (RooDataSet *)d.reduce("y>5.17");
91  d3->Print("v");
92 
93  cout << endl << ">> d4 has only columns x,c for data points with y>5.17" << endl;
94  RooDataSet *d4 = (RooDataSet *)d.reduce(RooArgSet(x, c), "y>5.17");
95  d4->Print("v");
96 
97  // The merge() function adds two data set column-wise
98  cout << endl << ">> merge d2(y) with d1(x,c) to form d1(x,c,y)" << endl;
99  d1->merge(d2);
100  d1->Print("v");
101 
102  // The append() function addes two datasets row-wise
103  cout << endl << ">> append data points of d3 to d1" << endl;
104  d1->append(*d3);
105  d1->Print("v");
106 
107  // O p e r a t i o n s o n b i n n e d d a t a s e t s
108  // ---------------------------------------------------------
109 
110  // A binned dataset can be constructed empty, from an unbinned dataset, or
111  // from a ROOT native histogram (TH1,2,3)
112 
113  cout << ">> construct dh (binned) from d(unbinned) but only take the x and y dimensions," << endl
114  << ">> the category 'c' will be projected in the filling process" << endl;
115 
116  // The binning of real variables (like x,y) is done using their fit range
117  // 'get/setRange()' and number of specified fit bins 'get/setBins()'.
118  // Category dimensions of binned datasets get one bin per defined category state
119  x.setBins(10);
120  y.setBins(10);
121  RooDataHist dh("dh", "binned version of d", RooArgSet(x, y), d);
122  dh.Print("v");
123 
124  RooPlot *yframe = y.frame(Bins(10), Title("Operations on binned datasets"));
125  dh.plotOn(yframe); // plot projection of 2D binned data on y
126 
127  // Examine the statistics of a binned dataset
128  cout << ">> number of bins in dh : " << dh.numEntries() << endl;
129  cout << ">> sum of weights in dh : " << dh.sum(kFALSE) << endl;
130  cout << ">> integral over histogram: " << dh.sum(kTRUE) << endl; // accounts for bin volume
131 
132  // Locate a bin from a set of coordinates and retrieve its properties
133  x = 0.3;
134  y = 20.5;
135  cout << ">> retrieving the properties of the bin enclosing coordinate (x,y) = (0.3,20.5) " << endl;
136  cout << " bin center:" << endl;
137  dh.get(RooArgSet(x, y))->Print("v"); // load bin center coordinates in internal buffer
138  cout << " weight = " << dh.weight() << endl; // return weight of last loaded coordinates
139 
140  // Reduce the 2-dimensional binned dataset to a 1-dimensional binned dataset
141  //
142  // All reduce() methods are interfaced in RooAbsData. All reduction techniques
143  // demonstrated on unbinned datasets can be applied to binned datasets as well.
144  cout << ">> Creating 1-dimensional projection on y of dh for bins with x>0" << endl;
145  RooDataHist *dh2 = (RooDataHist *)dh.reduce(y, "x>0");
146  dh2->Print("v");
147 
148  // Add dh2 to yframe and redraw
149  dh2->plotOn(yframe, LineColor(kRed), MarkerColor(kRed));
150 
151  // S a v i n g a n d l o a d i n g f r o m f i l e
152  // -------------------------------------------------------
153 
154  // Datasets can be persisted with ROOT I/O
155  cout << endl << ">> Persisting d via ROOT I/O" << endl;
156  TFile f("rf402_datahandling.root", "RECREATE");
157  d.Write();
158  f.ls();
159 
160  // To read back in future session:
161  // > TFile f("rf402_datahandling.root") ;
162  // > RooDataSet* d = (RooDataSet*) f.FindObject("d") ;
163 
164  new TCanvas("rf402_datahandling", "rf402_datahandling", 600, 600);
165  gPad->SetLeftMargin(0.15);
166  yframe->GetYaxis()->SetTitleOffset(1.4);
167  yframe->Draw();
168 }
c
#define c(i)
Definition: RSha256.hxx:101
RooPlot::Draw
virtual void Draw(Option_t *options=0)
Draw this plot and all of the elements it contains.
Definition: RooPlot.cxx:691
kTRUE
const Bool_t kTRUE
Definition: RtypesCore.h:91
f
#define f(i)
Definition: RSha256.hxx:104
RooFit::Bins
RooCmdArg Bins(Int_t nbin)
Definition: RooGlobalFunc.cxx:177
RooGaussian.h
RooAbsData::Print
virtual void Print(Option_t *options=0) const
Print TNamed name and title.
Definition: RooAbsData.h:191
x
Double_t x[n]
Definition: legend1.C:17
RooDataSet::merge
Bool_t merge(RooDataSet *data1, RooDataSet *data2=0, RooDataSet *data3=0, RooDataSet *data4=0, RooDataSet *data5=0, RooDataSet *data6=0)
Definition: RooDataSet.cxx:1326
RooDataSet::append
void append(RooDataSet &data)
Add all data points of given data set to this data set.
Definition: RooDataSet.cxx:1386
TCanvas.h
RooDataSet.h
TFile.h
RooDataHist
The RooDataHist is a container class to hold N-dimensional binned data.
Definition: RooDataHist.h:39
RooFit
The namespace RooFit contains mostly switches that change the behaviour of functions of PDFs (or othe...
Definition: RooCFunction1Binding.h:29
kFALSE
const Bool_t kFALSE
Definition: RtypesCore.h:92
RooDataHist.h
RooPlot.h
RooPlot::GetYaxis
TAxis * GetYaxis() const
Definition: RooPlot.cxx:1258
RooPlot
A RooPlot is a plot frame and a container for graphics objects within that frame.
Definition: RooPlot.h:44
RooCategory.h
y
Double_t y[n]
Definition: legend1.C:17
sqrt
double sqrt(double)
RooRealVar.h
kRed
@ kRed
Definition: Rtypes.h:66
TFile
A ROOT file is a suite of consecutive data records (TKey instances) with a well defined format.
Definition: TFile.h:54
RooConstVar.h
rf402_datahandling
Definition: rf402_datahandling.py:1
RooFit::LineColor
RooCmdArg LineColor(Color_t color)
Definition: RooGlobalFunc.cxx:57
TCanvas
The Canvas class.
Definition: TCanvas.h:23
RooCategory
RooCategory is an object to represent discrete states.
Definition: RooCategory.h:27
RooAbsData::reduce
RooAbsData * reduce(const RooCmdArg &arg1, const RooCmdArg &arg2=RooCmdArg(), const RooCmdArg &arg3=RooCmdArg(), const RooCmdArg &arg4=RooCmdArg(), const RooCmdArg &arg5=RooCmdArg(), const RooCmdArg &arg6=RooCmdArg(), const RooCmdArg &arg7=RooCmdArg(), const RooCmdArg &arg8=RooCmdArg())
Create a reduced copy of this dataset.
Definition: RooAbsData.cxx:382
TAxis.h
d
#define d(i)
Definition: RSha256.hxx:102
gPad
#define gPad
Definition: TVirtualPad.h:287
RooDataSet
RooDataSet is a container class to hold unbinned data.
Definition: RooDataSet.h:33
RooFit::MarkerColor
RooCmdArg MarkerColor(Color_t color)
Definition: RooGlobalFunc.cxx:88
RooAbsCollection::Print
virtual void Print(Option_t *options=0) const
This method must be overridden when a class wants to print itself.
Definition: RooAbsCollection.h:200
TAttAxis::SetTitleOffset
virtual void SetTitleOffset(Float_t offset=1)
Set distance between the axis and the axis title.
Definition: TAttAxis.cxx:293
RooRealVar
RooRealVar represents a variable that can be changed from the outside.
Definition: RooRealVar.h:37
RooDataHist::plotOn
virtual RooPlot * plotOn(RooPlot *frame, PlotOpt o) const
Back end function to plotting functionality.
Definition: RooDataHist.cxx:1014
RooFit::Title
RooCmdArg Title(const char *name)
Definition: RooGlobalFunc.cxx:176
RooArgSet
RooArgSet is a container object that can hold multiple RooAbsArg objects.
Definition: RooArgSet.h:29
int