def readAndFillHist(filename,
bnn,
c1,
h1,
m4lmela,
step=10000,
SR=False,
treename="HZZ4LeptonsAnalysisReduced"):
# ---------------------------------------
# open ntuple file
# ---------------------------------------
data = Ntuple(filename, treename)
print filename
size = data.size()
if find(filename, 'SM') > 0:
ntrain = 50000
else:
ntrain = 3000
print 'ntrain: %s' % ntrain
fields = [VARNAME]
inputs = vector('double')(len(fields))
count = 0
for row, event in enumerate(data):
if event.f_outlier: continue
if event.f_mass4l < MASSMIN: continue
if event.f_mass4l > MASSMAX: continue
if count % step == 0:
print "%10d\t%10d" % (row, count)
count += 1
if count < ntrain: continue
if SR:
d = m4lmela(event.f_mass4l, event.f_D_bkg_kin)
if d < BNNCUT: continue
w = event.f_weight
for ii in xrange(len(fields)):
inputs[ii] = event.__getattr__(fields[ii])
D = bnn(inputs)
h1.Fill(D, w)
if count % step == 0:
c1.cd()
h1.Draw("hist")
c1.Update()
gSystem.ProcessEvents()
c1.cd()
h1.Scale(1.0 / h1.Integral())
h1.Draw("hist")
c1.Update()
gSystem.ProcessEvents()
def readAndFillHist(filename, bnn,
c1, h1,
c2, h2,
c3, h3,
c4, h4,
treename='HZZ4LeptonsAnalysisReduced'):
# ---------------------------------------
# open ntuple file
# ---------------------------------------
isData = find(filename, 'data') > 0
ntuple = Ntuple(filename, treename)
for row, event in enumerate(ntuple):
o = event.f_outlier
x = event.f_mass4l
if o: continue
if x < MASSMIN: continue
if x > MASSMAX: continue
w = event.f_weight
y = event.f_D_bkg_kin
D = bnn(x, y)
h1.Fill(D, w)
h2.Fill(x, y, w)
h3.Fill(x, w)
h4.Fill(y, w)
if row % 10000 == 0:
for c, h in [(c1, h1),
(c3, h3),
(c4, h4)]:
c.cd()
if isData:
h.Draw('ep')
else:
h.Draw("hist")
c.Update()
gSystem.ProcessEvents()
c2.cd()
h2.Draw("p")
c2.Update()
for c, h in [(c1, h1),
(c2, h2),
(c3, h3),
(c4, h4)]:
c.cd()
if isData:
h.Draw('ep')
else:
h.Scale(1.0/h.Integral())
h.Draw("hist")
c.Update()
gSystem.ProcessEvents()
def main():
print "\n\tmakesimdata.py\n"
treename = "HZZ4LeptonsAnalysisReduced"
# source names
srcnames = ['gg', 'VV', 'bkg']
# ntuple variable names
varnames = ['D_VVgg_MLP', 'D_VVgg_BDT', 'D_bkg', 'weight']
# ---------------------------------------------------
# 1. load data into memory
# 2. create a bootstrap sample of a given size
# by randomly selecting events with a
# probability proportional to event weight
# 3. write out events to an ntuple
# ---------------------------------------------------
records = []
weight = 0.0
for name in srcnames:
filename = 'd_4mu_%s.root' % name
print 'read %s' % filename
ntuple = Ntuple(filename, treename)
for row in ntuple:
rec = []
for varname in varnames:
rec.append(row(varname))
records.append(rec)
weight += records[-1][-1] # weight is last column
print "Total weight (300/fb): %8.2f" % weight
print "\tcompute cdf of weights"
wcdf = len(records) * [0]
wcdf[0] = records[0][-1]
for i in xrange(1, len(records)):
wcdf[i] = wcdf[i - 1] + records[i][-1]
sumw = wcdf[-1]
if sumw != weight:
sys.exit("huh?")
# randomly select "N" events according to event weight
N = int(sumw + 0.5) # number of events to select
print "\tselecting %d events" % N
outrecords = []
for i in xrange(N):
w = uniform(0, sumw)
k = binsearch(wcdf, w)
if k < 0:
sys.exit("**error** not found %f *** should not happen!" % w)
outrecords.append(records[k])
outrecords[-1][-1] = 1.0
# write out records to an ntuple
filename = 'd_4mu_simdata.root'
makeTree(filename, treename, outrecords)
def wrout(filename, name):
treename = "HZZ4LeptonsAnalysisReduced" # name of Root tree
weightname = "f_weight" # name of event weight variable
ntuple = Ntuple(filename, treename)
size = len(ntuple)
if find(filename, 'SM') > 0:
ntrain = 50000
else:
ntrain = 3000
print "\n\n==> filename: %s" % filename
total1 = 0.0
total2 = 0.0
etotal2 = 0.0
records = []
fmt = ' %15.3e' * 4 + '\n'
count = 0
for ii, event in enumerate(ntuple):
if ii % 10000 == 0:
print '.',
sys.stdout.flush()
if event.f_outlier: continue
if event.f_mass4l < MASSMIN: continue
if event.f_mass4l > MASSMAX: continue
total1 += 1.0
total2 += event.f_weight
etotal2 += event.f_weight**2
record = fmt % \
(event.f_weight,
event.f_mass4l,
event.f_D_bkg_kin,
event.f_pt4l)
records.append(record)
count += 1
if count >= ntrain: break
shuffle(records)
fmt = ' %s' * 4 + '\n'
record = fmt % ('f_weight', 'f_mass4l', 'f_D_bkg_kin', 'f_pt4l')
records.insert(0, record)
outfilename = '%s_weighted.txt' % name
print
print outfilename
open(outfilename, 'w').writelines(records)
ecount = total2**2 / etotal2
print
print 'training sample from file %s' % filename
print "\ttotal: %10d events" % size
print "\ttotal (without outliers): %10.0f events" % total1
print "\teffective total: %10.0f events" % ecount
print
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 wrout(filename, name):
treename = "HZZ4LeptonsAnalysisReduced" # name of Root tree
weightname = "f_weight" # name of event weight variable
ntuple = Ntuple(filename, treename)
size = len(ntuple)
print "\n\n==> filename: %s" % filename
total1 = 0.0
total2 = 0.0
etotal2 = 0.0
records = []
fmt = ' %15.3e' * 13 + '\n'
count = 0
for ii, event in enumerate(ntuple):
if ii % 10000 == 0:
print '.',
sys.stdout.flush()
if event.f_outlier: continue
if event.f_mass4l < MASSMIN: continue
if event.f_mass4l > MASSMAX: continue
total1 += 1.0
total2 += event.f_weight
etotal2 += event.f_weight**2
record = fmt % \
(event.f_weight,
event.f_D_bkg_kin,
event.f_pt4l,
event.f_pfmet,
event.f_mT,
event.f_mass4l,
event.f_Z1mass,
event.f_Z2mass,
event.f_angle_costhetastar,
event.f_angle_costheta1,
event.f_angle_costheta2,
event.f_angle_phi,
event.f_angle_phistar1)
records.append(record)
shuffle(records)
fmt = ' %s' * 13 + '\n'
record = fmt % ('f_weight',
'f_D_bkg_kin',
'f_pt4l',
'f_pfmet',
'f_mT',
'f_mass4l',
'f_Z1mass',
'f_Z2mass',
'f_angle_costhetastar',
'f_angle_costheta1',
'f_angle_costheta2',
'f_angle_phi',
'f_angle_phistar1')
records.insert(0, record)
outfilename = '%s_weighted.txt' % name
print
print outfilename
open(outfilename, 'w').writelines(records)
ecount = total2**2/etotal2
print
print 'training sample from file %s' % filename
print "\ttotal: %10d events" % size
print "\ttotal (without outliers): %10.0f events" % total1
print "\teffective total: %10.0f events" % ecount
print