def GetNminus1Group(self, tagger):
# Use after ApplyTopPickViaMatch
cutgroup = CutGroup('taggingVars')
cutgroup.Add(
'mH_%s_cut' % tagger,
'SubleadHiggs_msoftdrop_corrH > {0} && SubleadHiggs_msoftdrop_corrH < {1}'
.format(*self.cuts['mh']))
cutgroup.Add(
'mt_%s_cut' % tagger,
'LeadTop_msoftdrop_corrT > {0} && LeadTop_msoftdrop_corrT < {1}'.
format(*self.cuts['mt']))
cutgroup.Add(
'%s_H_cut' % tagger, 'SubleadHiggs_{0}MD_HbbvsQCD > {1}'.format(
tagger, self.cuts[tagger + 'MD_HbbvsQCD']))
cutgroup.Add(
'%s_top_cut' % tagger,
'LeadTop_{0}_TvsQCD > {1}'.format(tagger,
self.cuts[tagger + '_TvsQCD']))
return cutgroup
def select(setname, year):
ROOT.ROOT.EnableImplicitMT(
2) # Just use two threads - no need to kill the interactive nodes
# Initialize TIMBER analyzer
file_path = '%s/%s_bstar%s.root' % (rootfile_path, setname, year)
a = analyzer(file_path)
# Determine normalization weight
if not a.isData:
norm = helpers.getNormFactor(setname, year, config)
else:
norm = 1.
# Book actions on the RDataFrame
a.Cut('filters', a.GetFlagString(flags))
a.Cut('trigger', a.GetTriggerString(triggers))
a.Define(
'jetIdx', 'hemispherize(FatJet_phi, FatJet_jetId)'
) # need to calculate if we have two jets (with Id) that are back-to-back
a.Cut(
'nFatJets_cut', 'nFatJet > max(jetIdx[0],jetIdx[1])'
) # If we don't do this, we may try to access variables of jets that don't exist! (leads to seg fault)
a.Cut("hemis",
"(jetIdx[0] != -1)&&(jetIdx[1] != -1)") # cut on that calculation
a.Cut('pt_cut', 'FatJet_pt[jetIdx[0]] > 400 && FatJet_pt[jetIdx[1]] > 400')
a.Cut(
'eta_cut',
'abs(FatJet_eta[jetIdx[0]]) < 2.4 && abs(FatJet_eta[jetIdx[1]]) < 2.4')
a.Define('norm', str(norm))
#################################
# Build some variables for jets #
#################################
# Wtagging decision logic
# Returns 0 for no tag, 1 for lead tag, 2 for sublead tag, and 3 for both tag (which is physics-wise equivalent to 2)
wtag_str = "1*Wtag(FatJet_tau2[jetIdx[0]]/FatJet_tau1[jetIdx[0]],0,{0}, FatJet_msoftdrop[jetIdx[0]],65,105) + 2*Wtag(FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]],0,{0}, FatJet_msoftdrop[jetIdx[1]],65,105)".format(
cuts['tau21'])
jets = VarGroup('jets')
jets.Add('wtag_bit', wtag_str)
jets.Add(
'top_bit', '(wtag_bit & 2)? 0: (wtag_bit & 1)? 1: -1'
) # (if wtag==3 or 2 (subleading w), top_index=0) else (if wtag==1, top_index=1) else (-1)
jets.Add('top_index', 'top_bit >= 0 ? jetIdx[top_bit] : -1')
jets.Add('w_index',
'top_index == 0 ? jetIdx[1] : top_index == 1 ? jetIdx[0] : -1')
# Calculate some new comlumns that we'd like to cut on (that were costly to do before the other filtering)
jets.Add(
"lead_vect",
"hardware::TLvector(FatJet_pt[jetIdx[0]],FatJet_eta[jetIdx[0]],FatJet_phi[jetIdx[0]],FatJet_msoftdrop[jetIdx[0]])"
)
jets.Add(
"sublead_vect",
"hardware::TLvector(FatJet_pt[jetIdx[1]],FatJet_eta[jetIdx[1]],FatJet_phi[jetIdx[1]],FatJet_msoftdrop[jetIdx[1]])"
)
jets.Add("deltaY", "abs(lead_vect.Rapidity()-sublead_vect.Rapidity())")
jets.Add("mtw", "hardware::invariantMass({lead_vect,sublead_vect})")
#########
# N - 1 #
#########
plotting_vars = VarGroup(
'plotting_vars') # assume leading is top and subleading is W
plotting_vars.Add("mtop", "FatJet_msoftdrop[jetIdx[0]]")
plotting_vars.Add("mW", "FatJet_msoftdrop[jetIdx[1]]")
plotting_vars.Add("tau32", "FatJet_tau3[jetIdx[0]]/FatJet_tau2[jetIdx[0]]")
plotting_vars.Add(
"subjet_btag",
"max(SubJet_btagDeepB[FatJet_subJetIdx1[jetIdx[0]]],SubJet_btagDeepB[FatJet_subJetIdx2[jetIdx[0]]])"
)
plotting_vars.Add("tau21", "FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]]")
plotting_vars.Add("lead_jet_deepAK8_MD_WvsQCD",
"FatJet_deepTagMD_WvsQCD[jetIdx[0]]")
plotting_vars.Add("sublead_jet_deepAK8_MD_WvsQCD",
"FatJet_deepTagMD_WvsQCD[jetIdx[1]]")
plotting_vars.Add("lead_jet_deepAK8_MD_TvsQCD",
"FatJet_deepTagMD_TvsQCD[jetIdx[0]]")
plotting_vars.Add("sublead_jet_deepAK8_MD_TvsQCD",
"FatJet_deepTagMD_TvsQCD[jetIdx[1]]")
N_cuts = CutGroup('Ncuts') # cuts
N_cuts.Add("deltaY_cut", "deltaY<1.6")
N_cuts.Add("mtop_cut", "(mtop > 105.)&&(mtop < 220.)")
N_cuts.Add("mW_cut", "(mW > 65.)&&(mW < 105.)")
#N_cuts.Add("tau32_cut", "(tau32 > 0.0)&&(tau32 < %s)"%(cuts['tau32']))
#N_cuts.Add("subjet_btag_cut", "(subjet_btag > %s)&&(subjet_btag < 1.)"%(cuts['sjbtag']))
#N_cuts.Add("tau21_cut", "(tau21 > 0.0)&&(tau21 < %s)"%(cuts['tau21']))
N_cuts.Add("lead_jet_deepAK8_MD_WvsQCD_cut",
"lead_jet_deepAK8_MD_WvsQCD > 0.9")
N_cuts.Add("sublead_jet_deepAK8_MD_WvsQCD_cut",
"sublead_jet_deepAK8_MD_WvsQCD > 0.9")
N_cuts.Add("lead_jet_deepAK8_MD_TvsQCD_cut",
"lead_jet_deepAK8_MD_TvsQCD > 0.9")
N_cuts.Add("sublead_jet_deepAK8_MD_TvsQCD_cut",
"sublead_jet_deepAK8_MD_TvsQCD > 0.9")
# Organize N-1 of tagging variables when assuming top is always leading
nodeToPlot = a.Apply([jets, plotting_vars])
nminus1Nodes = a.Nminus1(
N_cuts, nodeToPlot
) # constructs N nodes with a different N-1 selection for each
nminus1Hists = HistGroup('nminus1Hists')
binning = {
'mtop': [25, 50, 300],
'mW': [25, 30, 270],
'tau32': [20, 0, 1],
'tau21': [20, 0, 1],
'subjet_btag': [20, 0, 1],
'deltaY': [20, 0, 2.0],
'lead_jet_deepAK8_MD_WvsQCD': [20, 0, 1],
'sublead_jet_deepAK8_MD_WvsQCD': [20, 0, 1],
'lead_jet_deepAK8_MD_TvsQCD': [20, 0, 1],
'sublead_jet_deepAK8_MD_TvsQCD': [20, 0, 1]
}
# Add hists to group and write out
for nkey in nminus1Nodes.keys():
if nkey == 'full': continue
var = nkey.replace('_cut', '').replace('minus_', '')
hist_tuple = (var, var, binning[var][0], binning[var][1],
binning[var][2])
hist = nminus1Nodes[nkey].DataFrame.Histo1D(hist_tuple, var, 'norm')
hist.GetValue()
nminus1Hists.Add(var, hist)
a.PrintNodeTree('exercises/nminus1_tree.dot')
# Return the group
return nminus1Hists