fitConvolution.py File Reference

Detailed Description

Tutorial for convolution of two functions

****************************************
Minimizer is Minuit2 / Migrad
Chi2                      =       298.12
NDf                       =           96
Edm                       =  5.73699e-07
NCalls                    =          446
p0                        =       7.3286   +/-   0.0370542   
p1                        =    0.0733035   +/-   0.00243996  
p2                        =     -2.26419   +/-   0.0491459   
p3                        =      1.12809   +/-   0.0628298   

 
import ROOT
import numpy as np
 
# Construction of histogram to fit.
h_ExpGauss = ROOT.TH1F("h_ExpGauss", "Exponential convoluted by Gaussian", 100, 0.0, 5.0)
h_ExpGauss.Fill(
    np.array(
        [
            # Gives a alpha of -0.3 in the exp.
            # Probability density function of the addition of two variables is the
            # convolution of two density functions.
            ROOT.gRandom.Exp(1.0 / 0.3) + ROOT.gRandom.Gaus(0.0, 3.0)
            for _ in range(1000000)
        ]
    )
)
f_conv = ROOT.TF1Convolution("expo", "gaus", -1, 6, True)
f_conv.SetRange(-1.0, 6.0)
f_conv.SetNofPointsFFT(1000)
f = ROOT.TF1("f", f_conv, 0.0, 5.0, f_conv.GetNpar())
f.SetParameters(1.0, -0.3, 0.0, 1.0)
 
c1 = ROOT.TCanvas("c1", "c1", 800, 1000)
 
# Fit and draw result of the fit
h_ExpGauss.Fit("f")
 
c1.SaveAs("fitConvolution.png")

Author

Jonas Rembser, Aurelie Flandi (C++ version)

Definition in file fitConvolution.py.