rf314_paramfitrange.py File Reference

Detailed Description

Multidimensional models: working with parameterized ranges in a fit.

This an example of a fit with an acceptance that changes per-event

pdf = exp(-t/tau) with t[tmin,5]

where t and tmin are both observables in the dataset

 
import ROOT
 
 
# Define observables and decay pdf
# ---------------------------------------------------------------
 
# Declare observables
t = ROOT.RooRealVar("t", "t", 0, 5)
tmin = ROOT.RooRealVar("tmin", "tmin", 0, 0, 5)
 
# Make parameterized range in t : [tmin,5]
t.setRange(tmin, ROOT.RooFit.RooConst(t.getMax()))
 
# Make pdf
tau = ROOT.RooRealVar("tau", "tau", -1.54, -10, -0.1)
model = ROOT.RooExponential("model", "model", t, tau)
 
# Create input data
# ------------------------------------
 
# Generate complete dataset without acceptance cuts (for reference)
dall = model.generate({t}, 10000)
 
# Generate a (fake) prototype dataset for acceptance limit values
tmp = ROOT.RooGaussian("gmin", "gmin", tmin, 0.0, 0.5).generate({tmin}, 5000)
 
# Generate dataset with t values that observe (t>tmin)
dacc = model.generate({t}, ProtoData=tmp)
 
# Fit pdf to data in acceptance region
# -----------------------------------------------------------------------
 
r = model.fitTo(dacc, Save=True, PrintLevel=-1)
 
# Plot fitted pdf on full and accepted data
# ---------------------------------------------------------------------------------
 
# Make plot frame, datasets and overlay model
frame = t.frame(Title="Fit to data with per-event acceptance")
dall.plotOn(frame, MarkerColor="r", LineColor="r")
model.plotOn(frame)
dacc.plotOn(frame)
 
# Print fit results to demonstrate absence of bias
r.Print("v")
 
c = ROOT.TCanvas("rf314_paramranges", "rf314_paramranges", 600, 600)
ROOT.gPad.SetLeftMargin(0.15)
frame.GetYaxis().SetTitleOffset(1.6)
frame.Draw()
 
c.SaveAs("rf314_paramranges.png")

[#1] INFO:Fitting -- RooAbsPdf::fitTo(model_over_model_Int[t]) fixing normalization set for coefficient determination to observables in data
[#1] INFO:Fitting -- using generic CPU library compiled with no vectorizations
[#1] INFO:Fitting -- Creation of NLL object took 1.02937 ms
[#1] INFO:Fitting -- RooAddition::defaultErrorLevel(nll_model_over_model_Int[t]_modelData) Summation contains a RooNLLVar, using its error level
[#1] INFO:Minimization -- RooAbsMinimizerFcn::setOptimizeConst: activating const optimization
[#1] INFO:Minimization -- [fitFCN] No discrete parameters, performing continuous minimization only
[#1] INFO:Minimization -- RooAbsMinimizerFcn::setOptimizeConst: deactivating const optimization
[#1] INFO:Plotting -- RooPlot::updateFitRangeNorm: New event count of 5000 will supersede previous event count of 10000 for normalization of PDF projections
 
  RooFitResult: minimized FCN value: 2823.97, estimated distance to minimum: 3.17108e-08
                covariance matrix quality: Full, accurate covariance matrix
                Status : MINIMIZE=0 HESSE=0 
 
    Floating Parameter  InitialValue    FinalValue +/-  Error     GblCorr.
  --------------------  ------------  --------------------------  --------
                   tau   -1.5400e+00   -1.5335e+00 +/-  2.22e-02  <none>
 

Date

February 2018

Authors

Clemens Lange, Wouter Verkerke (C++ version)

Definition in file rf314_paramfitrange.py.