def createConfigFile(datafilename,
sigfilename,
bkgfilename,
hname,
gvfilename=None,
ntrials=100):
data, edata = getYield(datafilename, hname)
ndata = sum(data)
nbins = len(data)
if gvfilename:
gvariates = map(atof, open(gvfilename).readlines())
nsample = min(len(gvariates), ntrials)
else:
gvariates = [1.0]
nsample = 1
os.system('mkdir -p configs')
cfgfilename = 'configs/%s_%s_%4.4d.cfg' % \
(nameonly(sigfilename), hname, nsample)
print '-> config file: %s' % cfgfilename
cfg = open(cfgfilename, 'w')
record = '#' + '-' * 78
cfg.write('%s\n' % record)
record = '# file: %s' % cfgfilename
cfg.write('%s\n' % record)
record = '# created: %s' % ctime()
cfg.write('%s\n' % record)
record = '#' + '-' * 78
cfg.write('%s\n' % record)
# get counts and uncertainty in counts
sig, dsig = getYield(sigfilename, hname)
bkg, dbkg = getYield(bkgfilename, hname)
nsig = sum(sig)
esig = sqrt(sum(map(lambda x: x * x, dsig)))
nbkg = sum(bkg)
ebkg = sqrt(sum(map(lambda x: x * x, dbkg)))
record = '#nbins:\t%9d' % nbins
cfg.write('%s\n' % record)
record = '#data:\t%9d' % ndata
cfg.write('%s\n' % record)
record = '#sig:\t%9.2e' % nsig
cfg.write('%s\n' % record)
record = '#esig:\t%9.2e' % esig
cfg.write('%s\n' % record)
record = '#bkg:\t%9.2e' % nbkg
cfg.write('%s\n' % record)
record = '#ebkg:\t%9.2e' % ebkg
cfg.write('%s\n' % record)
record = '#' + '-' * 78
cfg.write('%s\n' % record)
record = '# number of bins'
cfg.write('%s\n' % record)
record = '%10d' % nbins
cfg.write('%s\n' % record)
record = '# observed counts'
cfg.write('%s\n' % record)
record = ''
for ii in xrange(nbins):
record += ' %9d' % int(data[ii])
cfg.write('%s\n' % record)
record = '# number of sampled points'
cfg.write('%s\n' % record)
cfg.write('\t%d\n' % nsample)
x1 = 0.0
x2 = 0.0
for jj in xrange(nsample):
s = [0] * nbins
es = [0] * nbins
b = [0] * nbins
eb = [0] * nbins
x = gvariates[jj]
x1 += x
x2 += x * x
for ii in xrange(nbins):
s[ii] = x * sig[ii]
es[ii] = x * dsig[ii]
b[ii] = x * bkg[ii]
eb[ii] = x * dbkg[ii]
nn = jj + 1
record = '# signal counts\t%d' % nn
cfg.write('%s\n' % record)
record = ''
for ii in xrange(nbins):
record += ' %9.2e' % s[ii]
cfg.write('%s\n' % record)
record = '# signal uncertainties\t%d' % nn
cfg.write('%s\n' % record)
record = ''
for ii in xrange(nbins):
record += ' %9.2e' % es[ii]
cfg.write('%s\n' % record)
record = '# background counts\t%d' % nn
cfg.write('%s\n' % record)
record = ''
for ii in xrange(nbins):
record += ' %9.2e' % b[ii]
cfg.write('%s\n' % record)
record = '# background uncertainties\t%d' % nn
cfg.write('%s\n' % record)
record = ''
for ii in xrange(nbins):
record += ' %9.2e' % eb[ii]
cfg.write('%s\n' % record)
cfg.close()
x1 /= nsample
x2 /= nsample
x2 = sqrt(x2 - x1 * x1)
print "-> gamma(mean): %5.3f\tgamma(stdev): %5.3f" % (x1, x2)
def main():
# ---------------------------------------
# set up some standard graphics style
# ---------------------------------------
tdrstyle.setTDRStyle()
gStyle.SetPadRightMargin(0.12)
gStyle.SetOptStat('ei')
gStyle.SetStatFont(42)
gStyle.SetStatFontSize(0.03)
gStyle.SetStatBorderSize(1)
gStyle.SetStatH(0.2)
gStyle.SetStatW(0.3)
gStyle.SetStatX(0.83)
gStyle.SetStatY(0.93)
bnn = m4lmela
bnn3 = m4lmelamet
#change the CMS_lumi variables (see CMS_lumi.py)
iPeriod = 4
iPos = 0
CMS_lumi.relPosX = 0.12
CMS_lumi.lumi_13TeV = "36 fb^{-1}"
CMS_lumi.writeExtraText = 1
CMS_lumi.extraText = "Simulation"
if len(sys.argv) > 1:
filenames = sys.argv[1:]
else:
sys.exit('''
Usage:
makeHists.py ntuple-file ...
''')
# name of graphics file
name = nameonly(filenames[0])
plotname = replace(name, 'ntuple_', 'fig_')
plotnameSRCR = replace(name, 'ntuple_', 'fig_regions_')
histfname = replace(name, 'ntuple_', 'histos_')
if len(filenames) > 1:
plotname = stripit.sub('', plotname)
histfname= stripit.sub('', histfname)
outfilename = 'histos/%s.root' % histfname
# change marker size and color depending on filename
isData = False
isHiggs= False
if find(plotname, 'data') > -1:
msize = 0.8
mcolor = kBlack
isData = True
CMS_lumi.extraText = "Preliminary"
elif find(plotname, 'bkg') > -1:
msize = 0.01
mcolor = kMagenta+1
elif find(plotname, 'higgs') > -1:
msize = 0.01
mcolor = kCyan+1
isHiggs = True
else:
msize = 0.01
mcolor = kCyan+2
# ---------------------------------------
# open ntuple file
# ---------------------------------------
ntuple = Ntuple(filenames, treename='HZZ4LeptonsAnalysisReduced')
nevents = ntuple.size()
print '='*80
print 'number of entries: %d' % nevents
print 'output file: %s' % outfilename
print '='*80
# open output root file for histograms
hfile = TFile(outfilename, 'recreate')
hfile.cd()
# ---------------------------------------
# book histograms
# ---------------------------------------
# 2-D plot in (f_mass4l, f_D_bkg_kin) space
cname = 'histos/%s' % plotname
cm4lD = TCanvas(cname, cname, 10, 10, 500, 500)
hm4lD = TH2F('hm4lD', '', MASSBINS, MASSMIN, MASSMAX, DBINS, 0, 1)
hm4lD.SetMarkerSize(msize)
hm4lD.SetMarkerColor(mcolor)
hm4lD.GetXaxis().SetTitle('#font[12]{m}_{4l} (GeV)')
hm4lD.GetYaxis().SetTitle('#font[12]{D}_{bkg}^{kin}')
hm4lD.Sumw2() # needed to handle weights correctly
hm4lD.SetMinimum(0)
hm4lD.GetXaxis().SetNdivisions(505)
hm4lD.GetYaxis().SetNdivisions(505)
# 1-D plot in D(f_mass4l, f_D_bkg_kin) space
cname = 'histos/%s_bnn' % plotname
cbnn = TCanvas(cname, cname, 520, 10, 500, 500)
hbnn = TH1F('hbnn', '', DBINS, 0, 1)
hbnn.SetLineWidth(1)
hbnn.SetFillColor(mcolor)
hbnn.SetFillStyle(3001)
hbnn.GetXaxis().SetTitle('D(#font[12]{m}_{4l}, '\
'#font[12]{D}_{bkg}^{kin})')
hbnn.GetXaxis().SetNdivisions(505)
hbnn.Sumw2()
hbnn.SetMinimum(0)
# 1-D plot in f_mass4l
cname = 'histos/%s_m4l' % plotname
cm4l = TCanvas(cname, cname, 1040, 10, 500, 500)
hm4l = TH1F('hm4l', '', MASSBINS, MASSMIN, MASSMAX)
hm4l.SetLineWidth(1)
hm4l.SetFillColor(mcolor)
hm4l.SetFillStyle(3001)
hm4l.GetXaxis().SetTitle('#font[12]{m}_{4l} (GeV)')
hm4l.GetXaxis().SetNdivisions(505)
hm4l.Sumw2()
hm4l.SetMinimum(0)
# 1-D plot in f_pfmet
cname = 'histos/%s_met' % plotname
cmet = TCanvas(cname, cname, 10, 510, 500, 500)
hmet = TH1F('hmet', '', METBINS, METMIN, METMAX)
hmet.SetLineWidth(1)
hmet.SetFillColor(mcolor)
hmet.SetFillStyle(3001)
hmet.GetXaxis().SetTitle('#font[12]{E}_{T}^{miss} (GeV)')
hmet.GetXaxis().SetNdivisions(505)
hmet.Sumw2()
hmet.SetMinimum(0)
# 1-D plot in D(f_mass4l, f_D_bkg_kin, f_pfmet)
cname = 'histos/%s_bnn3' % plotname
cbnn3 = TCanvas(cname, cname, 510, 510, 500, 500)
hbnn3 = TH1F('hbnn3', '', DBINS, 0, 1)
hbnn3.SetLineWidth(1)
hbnn3.SetFillColor(mcolor)
hbnn3.SetFillStyle(3001)
hbnn3.GetXaxis().SetTitle('D(#font[12]{m}_{4l}, '\
'#font[12]{D}_{bkg}^{kin}, '\
'#font[12]{E}_{T}^{miss})')
hbnn3.GetXaxis().SetNdivisions(505)
hbnn3.Sumw2()
hbnn3.SetMinimum(0)
hbag = []
for ii, (name, xtitle, xoff, yoff, xbins, xmin, xmax) in enumerate(PLOTS):
hbag.append(HistBag(ntuple, plotnameSRCR, name, xtitle, xoff, yoff,
xbins, xmin, xmax))
for ii,(name,xtitle, xoff, yoff, xbins, xmin, xmax) in enumerate(PLOTSZOOM):
hbag.append(HistBag(ntuple, plotnameSRCR, name, xtitle, xoff, yoff,
xbins, xmin, xmax,
ymin=1.e-9,
postfix='_zoom'))
# ---------------------------------------
# Loop over events
# ---------------------------------------
t1 = 0.0
t2 = 0.0
w1 = 0.0
w2 = 0.0
passed = 0
for index, event in enumerate(ntuple):
m4l = event.f_mass4l
if m4l < MASSMIN: continue
if m4l > MASSMAX: continue
#if (m4l >= 100) and (m4l <=150): continue
w = event.f_weight
t1 += w
t2 += w*w
if event.f_outlier: continue
w1 += w
w2 += w*w
Dbkg = event.f_D_bkg_kin
met = event.f_pfmet
Dbnn = bnn(m4l, Dbkg)
Dbnn3= bnn3(m4l, Dbkg, met)
hm4l.Fill(m4l, w)
hm4lD.Fill(m4l, Dbkg, w)
hbnn.Fill(Dbnn, w)
hbnn3.Fill(Dbnn3, w)
hmet.Fill(met, w)
if Dbnn > BNNCUT:
for h in hbag:
h.fillSR()
else:
for h in hbag:
h.fillCR()
if passed % SKIP == 0:
print '%10d %10d' % (passed, index)
cm4lD.cd()
hm4lD.Draw('p')
cm4lD.Update()
gSystem.ProcessEvents()
cbnn.cd()
if isData:
hbnn.Draw('ep')
else:
hbnn.Draw('hist')
cbnn.Update()
gSystem.ProcessEvents()
for h in hbag:
h.draw()
passed += 1
# now re-scale histograms to compensate for removal of
# outlier events.
scaleFactor = t1 / w1
t2 = sqrt(t2)
w2 = sqrt(w2)
hm4l.Scale(scaleFactor)
hm4lD.Scale(scaleFactor)
hbnn.Scale(scaleFactor)
hbnn3.Scale(scaleFactor)
hmet.Scale(scaleFactor)
for h in hbag:
h.scale(scaleFactor)
s1, s2, c1, c2 = hintegral(hbnn, BNNCUT)
print '='*80
txtfilename = '%s.txt' % plotname
print txtfilename
out = open(txtfilename, 'w')
record = 'number of entries: %d' % nevents
print record
out.write('%s\n' % record)
record = "number of events (with outliers): %10.2e +/- %-10.1e" % \
(t1, t2)
print record
out.write('%s\n' % record)
record = "number of events (without outliers): %10.2e +/- %-10.1e" % \
(w1, w2)
print record
out.write('%s\n' % record)
record = ' '
print record
out.write('%s\n' % record)
record = 'histograms scaled by factor %10.3f' % scaleFactor
print record
out.write('%s\n' % record)
record = "number of events (BNN > %3.1f): %10.2e +/- %-10.1e" % \
(BNNCUT, s1, s2)
print record
out.write('%s\n' % record)
record = "number of events (BNN <= %3.1f): %10.2e +/- %-10.1e" % \
(BNNCUT, c1, c2)
print record
out.write('%s\n' % record)
out.close()
print '='*80
cm4lD.cd()
hm4lD.Draw('p')
CMS_lumi.CMS_lumi(cm4lD, iPeriod, iPos)
cm4lD.Update()
gSystem.ProcessEvents()
cm4lD.SaveAs('.png')
cbnn.cd()
if isData:
hbnn.Draw('ep')
else:
hbnn.Draw('hist')
CMS_lumi.CMS_lumi(cbnn, iPeriod, iPos)
cbnn.Update()
gSystem.ProcessEvents()
cbnn.SaveAs('.png')
cbnn3.cd()
if isData:
hbnn3.Draw('ep')
else:
hbnn3.Draw('hist')
CMS_lumi.CMS_lumi(cbnn3, iPeriod, iPos)
cbnn3.Update()
gSystem.ProcessEvents()
cbnn3.SaveAs('.png')
cmet.cd()
if isData:
hmet.Draw('ep')
else:
hmet.Draw('hist')
CMS_lumi.CMS_lumi(cmet, iPeriod, iPos)
cmet.Update()
gSystem.ProcessEvents()
cmet.SaveAs('.png')
cm4l.cd()
if isData:
hm4l.Draw('ep')
else:
hm4l.Draw('hist')
CMS_lumi.CMS_lumi(cm4l, iPeriod, iPos)
cm4l.Update()
gSystem.ProcessEvents()
cm4l.SaveAs('.png')
for h in hbag:
h.draw(True)
hfile.cd()
cm4lD.Write()
cbnn.Write()
cbnn3.Write()
cmet.Write()
cm4l.Write()
for h in hbag:
h.write()
hfile.Write()
hfile.Close()
sleep(2)
def main():
argv = sys.argv[1:]
argc = len(argv)
if argc < 1:
print '''
Usage:
plot.py <sig-filename1> [SR]
'''
sys.exit()
print "=" * 80
os.system("mkdir -p figures")
SR = argv[-1] == 'SR'
if SR:
argv = argv[:-1]
postfix = '_SR'
else:
postfix = ''
sigfilenames = argv
sigfilenames.sort()
bkgfilename = '../../ntuple_SM.root'
BNNname = BNNNAME
print 'BNN: %s' % BNNname
print
print 'signal file: %s' % sigfilenames
print
print 'background file: %s' % bkgfilename
print "=" * 80
# compile bnn function
#gSystem.Load("libmvd")
gROOT.ProcessLine('.L metd.cpp')
gROOT.ProcessLine('.L m4lmela.cpp')
bnn = eval(BNNname)
# ---------------------------------------
# set up some standard graphics style
# ---------------------------------------
tdrstyle.setTDRStyle()
gStyle.SetPadRightMargin(0.12)
gStyle.SetOptStat('ei')
gStyle.SetStatFont(42)
gStyle.SetStatFontSize(0.03)
gStyle.SetStatBorderSize(1)
gStyle.SetStatH(0.2)
gStyle.SetStatW(0.3)
gStyle.SetStatX(0.83)
gStyle.SetStatY(0.93)
#change the CMS_lumi variables (see CMS_lumi.py)
iPeriod = 4
iPos = 0
CMS_lumi.relPosX = 0.12
CMS_lumi.lumi_13TeV = "36.0 fb^{-1}"
CMS_lumi.writeExtraText = 1
CMS_lumi.extraText = "Simulation"
hfile = TFile("figures/h_%s.root" % BNNname, "RECREATE")
hfile.cd()
nbins = 100
kolors = [
kRed, kOrange, kYellow + 2, kGreen + 1, kBlue, kMagenta + 1, kCyan + 1
]
icolor = 0
h = []
# SIGNAL
for ii, sigfilename in enumerate(sigfilenames):
color = kolors[icolor]
icolor += 1
if icolor >= len(kolors):
icolor = 0
name = replace(nameonly(sigfilename), 'ntuple_', '')
hs1 = TH1F(name, '', nbins, 0, 1)
hs1.GetXaxis().SetTitle('D_{%s}' % name)
hs1.Sumw2() # needed to handle weights correctly
hs1.SetMinimum(1.e-6)
hs1.GetXaxis().SetNdivisions(505)
hs1.GetYaxis().SetNdivisions(505)
hs1.SetFillColor(color)
hs1.SetFillStyle(3001)
h.append(hs1)
# BACKGROUND
mcolor = kMagenta + 1
hb1 = TH1F('hb1', '', nbins, 0, 1)
hb1.GetXaxis().SetTitle('D_{bkg}')
hb1.Sumw2() # needed to handle weights correctly
hb1.SetMinimum(1.e-6)
hb1.GetXaxis().SetNdivisions(505)
hb1.GetYaxis().SetNdivisions(505)
hb1.SetFillColor(mcolor)
hb1.SetFillStyle(3003)
h.append(hb1)
# ---------------------------------------------------------
# Fill
# ---------------------------------------------------------
cbnn1 = TCanvas("figures/f_%s_lin%s" % (BNNname, postfix), BNNname, 10, 10,
500, 500)
# plot
for ii, sigfilename in enumerate(sigfilenames):
name = h[ii].GetName()
cbnn1.SetTitle(name)
print name
readAndFillHist(sigfilename, bnn, cbnn1, h[ii], m4lmela, 500, SR)
readAndFillHist(bkgfilename, bnn, cbnn1, hb1, m4lmela, 10000, SR)
icolor = 0
hroc = []
for ii, sigfilename in enumerate(sigfilenames):
name = '%s_roc' % h[ii].GetName()
color = kolors[icolor]
icolor += 1
if icolor >= len(kolors):
icolor = 0
hroc.append(mkroc(name, h[ii], h[-1], lcolor=color))
# ---------------------------------------------------------
# Plot
# ---------------------------------------------------------
cbnn1.cd()
h[0].SetMaximum(1.0)
h[-1].SetMaximum(1.0)
h[-1].Draw('hist')
for hist in h:
hist.Draw("histsame")
cbnn1.Update()
gSystem.ProcessEvents()
cbnn1.SaveAs('.png')
cbnn1log = TCanvas("figures/f_%s_log%s" % (BNNname, postfix), BNNname, 520,
10, 500, 500)
cbnn1log.cd()
cbnn1log.SetLogy()
h[-1].Draw('hist')
for hist in h:
hist.Draw("histsame")
cbnn1log.Update()
gSystem.ProcessEvents()
cbnn1log.SaveAs('.png')
croc = TCanvas("figures/f_%s_roc%s" % (BNNname, postfix), BNNname, 1040,
10, 500, 500)
croc.cd()
hroc[0].Draw('al')
for hist in hroc:
hist.Draw("lsame")
croc.Update()
gSystem.ProcessEvents()
croc.SaveAs('.png')
sleep(5)
def main():
# ---------------------------------------
# set up some standard graphics style
# ---------------------------------------
tdrstyle.setTDRStyle()
gStyle.SetPadRightMargin(0.12)
gStyle.SetOptStat('ei')
gStyle.SetStatFont(42)
gStyle.SetStatFontSize(0.03)
gStyle.SetStatBorderSize(1)
gStyle.SetStatH(0.2)
gStyle.SetStatW(0.3)
gStyle.SetStatX(0.83)
gStyle.SetStatY(0.93)
#change the CMS_lumi variables (see CMS_lumi.py)
iPeriod = 4
iPos = 0
CMS_lumi.relPosX = 0.12
CMS_lumi.lumi_13TeV = "36 fb^{-1}"
CMS_lumi.writeExtraText = 1
CMS_lumi.extraText = "Simulation"
filename, options = decodeCommandLine()
# name of graphics file
name = nameonly(filename)
plotname = replace(name, 'ntuple_', '')
histfname = replace(name, 'ntuple_', 'histos_')
os.system('mkdir -p histos')
outfilename = 'histos/%s.root' % histfname
# ---------------------------------------
# open ntuple file
# ---------------------------------------
ntuple = getNtuple(filename)
nevents = ntuple.nevents
SKIP = nevents / 10
print '=' * 80
print 'number of entries: %d' % nevents
print 'output file: %s' % outfilename
print '=' * 80
# open output root file for histograms
hfile = TFile(outfilename, 'recreate')
hfile.cd()
CRbag = []
for ii, (field, hname, xtitle, xoff, yoff, xbins, xmin,
xmax) in enumerate(CRPLOTS):
CRbag.append(
HistBag(CMS_lumi, iPeriod, iPos, 'CR', plotname, ntuple, field,
hname, xtitle, xoff, yoff, xbins, xmin, xmax))
SRbag = []
for ii, (field, hname, xtitle, xoff, yoff, xbins, xmin,
xmax) in enumerate(SRPLOTS):
SRbag.append(
HistBag(CMS_lumi, iPeriod, iPos, 'SR', plotname, ntuple, field,
hname, xtitle, xoff, yoff, xbins, xmin, xmax))
# ---------------------------------------
# Loop over events
# ---------------------------------------
t1 = 0.0
t2 = 0.0
w1 = 0.0
w2 = 0.0
swatch = TStopwatch()
swatch.Start()
passed = 0
for index in xrange(nevents):
ntuple.read(index)
if index % SKIP == 0: print index
m4l = ntuple.f_mass4l
if m4l < CRMASSMIN: continue
if m4l > CRMASSMAX: continue
w = ntuple.f_weight
t1 += w
t2 += w * w
if ntuple.f_outlier: continue
w1 += w
w2 += w * w
SR = (m4l >= SRMASSMIN) and (m4l <= SRMASSMAX)
if SR:
for h in SRbag:
h.fill()
else:
for h in CRbag:
h.fill()
if passed % SKIP == 0:
for h in SRbag:
h.draw()
passed += 1
t = swatch.RealTime()
t /= nevents
t *= 1e6
print 'execution time: %10.2f microsecond/event' % t
# now re-scale histograms to compensate for removal of
# outlier events.
scaleFactor = t1 / w1
t2 = sqrt(t2)
w2 = sqrt(w2)
for h in SRbag:
h.scale(scaleFactor)
for h in CRbag:
h.scale(scaleFactor)
print '=' * 80
txtfilename = '%s.txt' % plotname
print txtfilename
out = open(txtfilename, 'w')
record = 'number of entries: %d' % nevents
print record
out.write('%s\n' % record)
record = "number of events (with outliers): %10.2e +/- %-10.1e" % \
(t1, t2)
print record
out.write('%s\n' % record)
record = "number of events (without outliers): %10.2e +/- %-10.1e" % \
(w1, w2)
print record
out.write('%s\n' % record)
record = ' '
print record
out.write('%s\n' % record)
record = 'histograms scaled by factor %10.3f' % scaleFactor
print record
out.write('%s\n' % record)
out.close()
print '=' * 80
for h in CRbag:
h.draw()
h.save()
h.write()
for h in SRbag:
h.draw()
h.save()
h.write()
hfile.Write()
hfile.Close()
sleep(2)
