def getPlotter(self,analysis,region,runPeriod,mass,runTau,plotName,doFakes):
nl = 3 if analysis=='Hpp3l' or analysis=='WZ' else 4
ntuples = getNtupleDirectory(analysis,region,runPeriod)
saves = '%s_%s_%iTeV' % (analysis,region,runPeriod)
sigMap = getSigMap(nl,mass)
intLumiMap = getIntLumiMap()
mergeDict = getMergeDict(runPeriod)
regionBackground = getChannelBackgrounds(runPeriod)
channels, leptons = getChannels(nl,runTau=runTau)
plotter = Plotter(region,ntupleDir=ntuples,saveDir=saves,period=runPeriod,rootName=plotName,mergeDict=mergeDict,scaleFactor=self.scalefactor)
if not doFakes: plotter.initializeBackgroundSamples([sigMap[runPeriod][x] for x in regionBackground[analysis]])
if runPeriod==8: plotter.initializeDataSamples([sigMap[runPeriod]['data']])
plotter.setIntLumi(intLumiMap[runPeriod])
return plotter
def calculateLeptonSystematic(mass,chanCuts,chanScales,**kwargs):
do4l = kwargs.pop('do4l',False)
analysis = 'Hpp3l'
region = 'Hpp3l'
runPeriod = 8
nl = 3
ntuples = getNtupleDirectory(analysis,region,runPeriod)
saves = '%s_%s_%sTeV' % (analysis,region,runPeriod)
sigMap = getSigMap(4,mass) if do4l else getSigMap(nl,mass)
intLumiMap = getIntLumiMap()
mergeDict = getMergeDict(runPeriod)
regionBackground = {
'Hpp3l' : ['T','TT', 'TTV','W','Z','VVV','WW','ZZ','WZ'],
'Hpp4l' : ['TT','Z','DB']
}
channels, leptons = getChannels(nl)
plotter = Plotter(analysis,ntupleDir=ntuples,saveDir=saves,period=runPeriod,rootName='systematics',mergeDict=mergeDict)
plotter.initializeBackgroundSamples([sigMap[runPeriod][x] for x in regionBackground[analysis]])
plotter.initializeSignalSamples([sigMap[runPeriod]['Sig']])
plotter.initializeDataSamples([sigMap[runPeriod]['data']])
plotter.setIntLumi(intLumiMap[runPeriod])
fullCut = 'finalstate.mass>100 && finalstate.sT>1.1*%f+60. && fabs(z1.mass-%f)>80. && h1.dPhi<%f/600.+1.95' %(mass,ZMASS,mass)
finalSRCut = 'h1.mass>0.9*%f && h1.mass<1.1*%f' %(mass,mass)
totBG = 0
totBG_scaled = 0
for c,s in zip(chanCuts,chanScales):
chanBG = s*plotter.getNumEntries('%s && %s && %s' %(c,fullCut,finalSRCut),plotter.signal[0],scaleup=False)
chanBG_scaled = s*plotter.getNumEntries('%s && %s && %s' %(c,fullCut,finalSRCut),plotter.signal[0],scaleup=True)
totBG += chanBG
totBG_scaled += chanBG_scaled
sigSelSys = (totBG_scaled-totBG)/totBG
return sigSelSys+1
def limit(analysis,region,period,mass,**kwargs):
cut = kwargs.pop('cut','1')
doChannels = kwargs.pop('doChannels',False)
doAlphaTest = kwargs.pop('doAlphaTest',False)
unblind = kwargs.pop('unblind',False)
name = kwargs.pop('name','card')
bp = kwargs.pop('bp','')
directory = kwargs.pop('directory','')
channelScales = kwargs.pop('channelScales',[1.0])
channelCuts = kwargs.pop('channelCuts',['1'])
recoChannels = kwargs.pop('recoChannels',['1'])
genChannels = kwargs.pop('genChannels',['1'])
mode = kwargs.pop('mode','sideband')
scalefactor = kwargs.pop('scalefactor','event.gen_weight*event.pu_weight*event.lep_scale*event.trig_scale')
datacardDir = kwargs.pop('datacardDir','./datacards')
do4l = kwargs.pop('do4l',False)
doBoth = kwargs.pop('doBoth',False)
logging.info("Processing BP %s; mass-point %i; card name %s" % (bp,mass,name))
# get the cut maps for each gen channel
genCutMap = {}
alphaGenCuts = {}
for genChan in genChannels:
genCutMap[genChan] = getChannelCutFlowMap(analysis,genChan,mass=mass)
alphaGenCuts[genChan] = getChannelSidebandSignalRegion(analysis,genChan,mass=mass)
# and the reco channel
recoCutMap = {}
alphaRecoCuts = {}
for recoChan in recoChannels:
recoCutMap[recoChan] = getChannelCutFlowMap(analysis,recoChan,mass=mass)
alphaRecoCuts[recoChan] = getChannelSidebandSignalRegion(analysis,recoChan,mass=mass)
# if we are testing a tau hypothesis, explicitly use a wider mass window and the tau cuts
# otherwise we need to just use reco
if bp in ['et100','mt100','tt100']:
theCutMap = getChannelCutFlowMap(analysis,bp[:2]+bp[:2],mass=mass)
theAlphaCuts = getChannelSidebandSignalRegion(analysis,bp[:2]+bp[:2],mass=mass)
else:
theCutMap = recoCutMap[recoChannels[0]] # only support 1 reco channel at a time
theAlphaCuts = alphaRecoCuts[recoChannels[0]]
fullCut = ' && '.join(theCutMap['cuts'])
# setup sideband stuff
chanCuts = '(' + ' || '.join(channelCuts) + ')' # gen cuts for h++ ORed with the default for BG 'aaa'
sbCut = theAlphaCuts['sbcut']
srCut = theAlphaCuts['srcut']
finalSRCut = theAlphaCuts['srcut']
channels, leptons = getChannels(3 if analysis=='Hpp3l' or analysis=='WZ' else 4)
nl = 3 if analysis in ['Hpp3l', 'WZ'] else 4
sigMap = getSigMap(4,mass) if do4l else getSigMap(nl,mass)
intLumiMap = getIntLumiMap()
# setup for final selection
myCut = cut
sbcut = '%s && %s && %s' %(myCut,sbCut,chanCuts)
srcut = '%s && %s && %s && %s' %(myCut,srCut,fullCut, chanCuts)
base_selections = '%s && %s && %s' %(myCut, srCut, fullCut)
if region=='WZ': srcut = '%s && %s && %s' %(myCut,srCut, chanCuts)
if doAlphaTest:
sbcut = '%s && finalstate.sT<150. && z1.mass<110. && h1.mass<130.' %(chanCuts)
srcut = '%s && finalstate.sT<400. && finalstate.sT>150. && z1.mass<110. && h1.mass<130.' %(chanCuts)
if doAlphaTest: unblind = True
logging.debug('Sideband cut: %s' % sbcut)
logging.debug('Signal region cut: %s' % srcut)
logging.debug('Base cut: %s' % base_selections)
# create the limits object
# base_selections is the cut applied on top of individual channel cuts
# sbcut is the sideband selection for alpha calculation
# srcut is the signal ragion selection for alpha calculation
limits = Limits(analysis,region, period, base_selections, getNtupleDirectory(analysis,region,period),
'%s/%s_%itev_%s/%s/%s' % (datacardDir, analysis, period, region, directory, mass),
channels=['dblh%s' % analysis], lumi=intLumiMap[period],
blinded=not unblind, bgMode=mode, scalefactor=scalefactor,
sbcut=sbcut, srcut=srcut)
signal = sigMap[period]['SigPP'] if do4l or analysis in ['Hpp4l'] else sigMap[period]['SigAP']
if mode=='sideband':
# add groups, signal scales must be list of floats with same length as cuts list in gen card
signame = "hpp%i_PP" % mass if do4l or analysis in ['Hpp4l'] else "hpp%i_AP" % mass
limits.add_group(signame, signal, scale=channelScales, isSignal=True)
if doBoth:
signame_PP = "hpp%i_PP" % mass
signal_PP = sigMap[period]['SigPP']
limits.add_group(signame_PP, signal_PP, scale=channelScales, isSignal=True)
limits.add_group("bg", "bg")
limits.add_group("data", "data_R*", isData=True)
# luminosity systematics, 2.6 % for mc
lumi = {signame: 1.026}
if doBoth: lumi = {signame: 1.026, signame_PP: 1.026}
limits.add_systematics("lumi", "lnN", **lumi)
# lepton systematics, electron and muon separately for mc
chanNames = recoChannels # only one supported for now
scaleMap = calculateChannelLeptonSystematic(mass,chanNames,do4l=do4l,doBoth=doBoth)
eid = {signame: "%0.3f" %scaleMap[chanNames[0]]['e']}
if doBoth: eid = {signame: "%0.3f" %scaleMap[chanNames[0]]['e'], signame_PP: "%0.3f" %scaleMap[chanNames[0]]['e']}
chgid = {signame: "%0.3f" %scaleMap[chanNames[0]]['chg']}
if doBoth: chgid = {signame: "%0.3f" %scaleMap[chanNames[0]]['chg'], signame_PP: "%0.3f" %scaleMap[chanNames[0]]['chg']}
mid = {signame: "%0.3f" %scaleMap[chanNames[0]]['m']}
if doBoth: mid = {signame: "%0.3f" %scaleMap[chanNames[0]]['m'], signame_PP: "%0.3f" %scaleMap[chanNames[0]]['m']}
limits.add_systematics('eid', 'lnN', **eid)
limits.add_systematics('chgid', 'lnN', **chgid)
limits.add_systematics('mid', 'lnN', **mid)
# signal mc uncertainty
sigmc = {signame: 1.15}
if doBoth: sigmc = {signame: 1.15, signame_PP: 1.15}
limits.add_systematics("sig_mc_err", "lnN", **sigmc)
# uncertainty on bg estimation
alpha_str = recoChannels[0] # only one supported for now
alpha_pdf = {'bg': 1.1}
limits.add_systematics("alpha_%s" %alpha_str, "lnN", **alpha_pdf)
# generate the card, passing the cuts to be applied for each gen channel
limits.gen_card("%s.txt" % name, mass=mass, cuts=channelCuts, doAlphaTest=doAlphaTest)
elif mode=='mc':
logging.error('MC needs to be reimplemented')
#add_systematics_mc(limits,mass,signal,name,channelCuts,scale,period,bp,doAlphaTest,do4l)
else:
return 0
def wzlimit(analysis, region, period, chan, **kwargs):
cut = kwargs.pop('cut', '1')
name = kwargs.pop('name', 'card')
scalefactor = kwargs.pop(
'scalefactor',
'event.gen_weight*event.pu_weight*event.lep_scale*event.trig_scale')
datacardDir = kwargs.pop('datacardDir', './datacards')
mode = kwargs.pop('mode',
'all') # all, none, theory, stat, lumi, experimental
logging.info("Processing card name {0}".format(name))
chanCut = '{0} && channel=="{1}"'.format(cut, chan)
#doStat = mode in ['all','experimental','stat']
doStat = mode not in ['nostat']
limits = WZLimits(
analysis,
region,
period,
chanCut,
getNtupleDirectory(analysis, region, period),
'%s/%s_%itev_%s' % (datacardDir, analysis, period, region),
scalefactor=scalefactor,
doStat=doStat)
# add systematic
#bgnames = ['datadriven','ZZ','WW','TTV','VVV','ZG']
bgnames = ['datadriven', 'ZZ', 'TTV', 'VVV', 'ZG']
signames = ['WZ']
#mcnames = ['WZ','ZZ','WW','TTV','VVV','ZG']
mcnames = ['WZ', 'ZZ', 'TTV', 'VVV', 'ZG']
# lumi
# current recommendation: 4.6%
lumi = {}
for b in mcnames:
lumi[b] = 1.046
if mode in ['all', 'lumi', 'nostat']:
limits.add_systematics("lumi", "lnN", **lumi)
# datadriven
# assume 40%
fake = {'datadriven': 1.4}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('fake_rate_unc', 'lnN', **fake)
# ZZ cross section
zzxsec = {'ZZ': 1.16}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('zz_xsec', 'lnN', **zzxsec)
# ZG cross section theory
zgxsec = {'ZG': 1.06}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('zg_xsec_theory', 'lnN', **zgxsec)
# TTZ cross section theory
ttzxsec = {'TTV': 1.15}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('ttz_xsec_theory', 'lnN', **ttzxsec)
# diboson cross section theory
wwxsec = {'WW': 1.06}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('ww_xsec_theory', 'lnN', **wwxsec)
# VVV cross section theory
vvvxsec = {'VVV': 1.06}
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('vvv_xsec_theory', 'lnN', **vvvxsec)
# eff uncertainty
# take scale factors for leptons, propagate up and down based on statistical uncertainty
lepvals = {
'eee': 1.019,
'eem': 1.016,
'mme': 1.016,
'mmm': 1.016,
}
lep = {}
for m in mcnames:
lep[m] = lepvals[chan]
#limits.add_systematics('lep_eff_unc','lnN',**lep)
elepvals = {
'eee': 1.018,
'eem': 1.012,
'mme': 1.005,
'mmm': 1.000,
}
if 'e' in chan:
elep = {}
for m in mcnames:
elep[m] = elepvals[chan]
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('lep_eff_unc_e', 'lnN', **elep)
mlepvals = {
'eee': 1.000,
'eem': 1.004,
'mme': 1.011,
'mmm': 1.016,
}
if 'm' in chan:
mlep = {}
for m in mcnames:
mlep[m] = mlepvals[chan]
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('lep_eff_unc_m', 'lnN', **mlep)
# pu
# assume 10% uncertainty on min bias cross section, scale up and down, take largest difference in wz yield
puvals = {
'eee': 1.0064,
'eem': 1.0088,
'mme': 1.0124,
'mmm': 1.0020,
}
pu = {}
for m in mcnames:
pu[m] = puvals[chan]
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('PU_unc', 'lnN', **pu)
# met
# scale all components up and down independently, add in quadrature the largest
metvals = {
#'eee' : 1.0146, # placeholder from 8 tev
#'eem' : 1.0150,
#'mme' : 1.0159,
#'mmm' : 1.0117,
'eee': 1.019, # 13 tev mes, ees, jes
'eem': 1.013,
'mme': 1.033,
'mmm': 1.017,
}
met = {}
for m in mcnames:
met[m] = metvals[chan]
if mode in ['all', 'experimental', 'nostat']:
limits.add_systematics('met_unc', 'lnN', **met)
# pdf
# propagate pdf ucnertainties through the selection, scale up and down, take largest
pdfvals = {
'eee':
1.01407, # for now just taking gen, figure it out later after new fsa
'eem': 1.01394,
'mme': 1.01399,
'mmm': 1.01395,
}
pdf = {}
for s in signames:
pdf[s] = pdfvals[chan]
if mode in ['all', 'theory', 'nostat']:
limits.add_systematics('pdf_unc', 'lnN', **pdf)
# scale
# propagate scale uncertainties through the selection, scale up and down, take largest
scalevals = {
'eee': 1.04296, # again, now just taking gen, fix fsa later
'eem': 1.04298,
'mme': 1.04285,
'mmm': 1.04298,
}
scale = {}
for s in signames:
scale[s] = scalevals[chan]
if mode in ['all', 'theory', 'nostat']:
limits.add_systematics('scale_unc', 'lnN', **scale)
# gen card
limits.gen_card("{0}.txt".format(name))