Docs | All | Real | Category | PDF | DataSet | Plot | Container | Misc | Aux | User

RooFit Toolkit for Data Modeling
#include "RooHist.hh"

RooHist


class description - source file - inheritance tree (.pdf)

class RooHist : public TGraphAsymmErrors, public RooPlotable

Inheritance Chart:
TObject
<-
TNamed
TAttLine
TAttFill
TAttMarker
<-
TGraph
<-
TGraphAsymmErrors
RooPrintable
<-
RooPlotable
<-
RooHist

    protected:
void initialize() Int_t roundBin(Double_t y) public:
RooHist() RooHist(Double_t nominalBinWidth, Double_t nSigma = 1, Double_t xErrorFrac = 1.0) RooHist(const TH1& data, Double_t nominalBinWidth = 0, Double_t nSigma = 1, RooAbsData::ErrorType = RooAbsData::Poisson, Double_t xErrorFrac = 1.0) RooHist(const TH1& data1, const TH1& data2, Double_t nominalBinWidth = 0, Double_t nSigma = 1, Double_t xErrorFrac = 1.0) RooHist(const RooHist& hist1, const RooHist& hist2, Double_t wgt1 = 1.0, Double_t wgt2 = 1.0, RooAbsData::ErrorType etype = RooAbsData::Poisson, Double_t xErrorFrac = 1.0) RooHist(const RooHist&) virtual ~RooHist() void addAsymmetryBin(Axis_t binCenter, Int_t n1, Int_t n2, Double_t binWidth = 0, Double_t xErrorFrac = 1.0) void addBin(Axis_t binCenter, Int_t n, Double_t binWidth = 0, Double_t xErrorFrac = 1.0) void addBinWithError(Axis_t binCenter, Double_t n, Double_t elow, Double_t ehigh, Double_t binWidth = 0, Double_t xErrorFrac = 1.0) static TClass* Class() virtual Double_t getFitRangeBinW() const virtual Double_t getFitRangeNEvt() const virtual Double_t getFitRangeNEvt(Double_t xlo, Double_t xhi) const Double_t getNominalBinWidth() const Bool_t hasIdenticalBinning(const RooHist& other) const virtual TClass* IsA() const RooHist* makePullHist(const RooCurve& curve) const RooHist& operator=(const RooHist&) virtual void Print(Option_t* options = "0") const virtual void printToStream(ostream& os, RooPrintable::PrintOption opt = Standard, TString indent = ) const void setRawEntries(Double_t n) virtual void ShowMembers(TMemberInspector& insp, char* parent) virtual void Streamer(TBuffer& b) void StreamerNVirtual(TBuffer& b)

Data Members

    private:
Double_t _nominalBinWidth Double_t _nSigma Double_t _entries Double_t _rawEntries

Class Description

 A RooHist is a graphical representation of binned data based on the
 TGraphAsymmErrors class. Error bars are calculated using either Poisson
 or Binomial statistics.

RooHist(Double_t nominalBinWidth, Double_t nSigma, Double_t /*xErrorFrac*/) : TGraphAsymmErrors(), _nominalBinWidth(nominalBinWidth), _nSigma(nSigma), _rawEntries(-1)
 Create an empty histogram that can be filled with the addBin()
 and addAsymmetryBin() methods. Use the optional parameter to
 specify the confidence level in units of sigma to use for
 calculating error bars. The nominal bin width specifies the
 default used by addBin(), and is used to set the relative
 normalization of bins with different widths.

RooHist(const TH1 &data, Double_t nominalBinWidth, Double_t nSigma, RooAbsData::ErrorType etype, Double_t xErrorFrac) : TGraphAsymmErrors(), _nominalBinWidth(nominalBinWidth), _nSigma(nSigma), _rawEntries(-1)
 Create a histogram from the contents of the specified TH1 object
 which may have fixed or variable bin widths. Error bars are
 calculated using Poisson statistics. Prints a warning and rounds
 any bins with non-integer contents. Use the optional parameter to
 specify the confidence level in units of sigma to use for
 calculating error bars. The nominal bin width specifies the
 default used by addBin(), and is used to set the relative
 normalization of bins with different widths. If not set, the
 nominal bin width is calculated as range/nbins.

RooHist(const TH1 &data1, const TH1 &data2, Double_t nominalBinWidth, Double_t nSigma, Double_t xErrorFrac) : TGraphAsymmErrors(), _nominalBinWidth(nominalBinWidth), _nSigma(nSigma), _rawEntries(-1)
 Create a histogram from the asymmetry between the specified TH1 objects
 which may have fixed or variable bin widths, but which must both have
 the same binning. The asymmetry is calculated as (1-2)/(1+2). Error bars are
 calculated using Binomial statistics. Prints a warning and rounds
 any bins with non-integer contents. Use the optional parameter to
 specify the confidence level in units of sigma to use for
 calculating error bars. The nominal bin width specifies the
 default used by addAsymmetryBin(), and is used to set the relative
 normalization of bins with different widths. If not set, the
 nominal bin width is calculated as range/nbins.

RooHist(const RooHist& hist1, const RooHist& hist2, Double_t wgt1, Double_t wgt2, RooAbsData::ErrorType etype, Double_t xErrorFrac) : _rawEntries(-1)
 Create histogram as sum of two existing histograms. If Poisson errors are selected the histograms are
 added and Poisson confidence intervals are calculated for the summed content. If wgt1 and wgt2 are not
 1 in this mode, a warning message is printed. If SumW2 errors are selectd the histograms are added
 and the histograms errors are added in quadrature, taking the weights into account.

void initialize()
 Perform common initialization for all constructors.

Double_t getFitRangeNEvt() const

Double_t getFitRangeNEvt(Double_t xlo, Double_t xhi) const
 Calculate integral of histogram in given range

Double_t getFitRangeBinW() const

Int_t roundBin(Double_t y)
 Return the nearest positive integer to the input value
 and print a warning if an adjustment is required.

void addBin(Axis_t binCenter, Int_t n, Double_t binWidth, Double_t xErrorFrac)
 Add a bin to this histogram with the specified integer bin contents
 and using an error bar calculated with Poisson statistics. The bin width
 is used to set the relative scale of bins with different widths.

void addBinWithError(Axis_t binCenter, Double_t n, Double_t elow, Double_t ehigh, Double_t binWidth, Double_t xErrorFrac)
 Add a bin to this histogram with the specified bin contents
 and error. The bin width is used to set the relative scale of
 bins with different widths.

void addAsymmetryBin(Axis_t binCenter, Int_t n1, Int_t n2, Double_t binWidth, Double_t xErrorFrac)
 Add a bin to this histogram with the value (n1-n2)/(n1+n2)
 using an error bar calculated with Binomial statistics.

~RooHist()

Bool_t hasIdenticalBinning(const RooHist& other) const
 First check if number of bins is the same

void printToStream(ostream& os, PrintOption opt, TString indent) const
 Print info about this histogram to the specified output stream.

   Standard: number of entries
      Shape: error CL and maximum value
    Verbose: print our bin contents and errors

RooHist* makePullHist(const RooCurve& curve) const
 Make histogram of pulls w.r.t to given curve



Inline Functions


            RooHist RooHist(const RooHist& hist1, const RooHist& hist2, Double_t wgt1 = 1.0, Double_t wgt2 = 1.0, RooAbsData::ErrorType etype = RooAbsData::Poisson, Double_t xErrorFrac = 1.0)
               void Print(Option_t* options = "0") const
           Double_t getNominalBinWidth() const
               void setRawEntries(Double_t n)
            TClass* Class()
            TClass* IsA() const
               void ShowMembers(TMemberInspector& insp, char* parent)
               void Streamer(TBuffer& b)
               void StreamerNVirtual(TBuffer& b)
            RooHist RooHist(const RooHist&)
           RooHist& operator=(const RooHist&)
Last CVS Update: v 1.33 2005/07/12 15:43:06 wverkerke Top
Copyright © 2000-2005 University of California, Stanford University

Page maintained by Wouter Verkerke and David Kirkby

SourceForge.net Logo