def test_highlevel(): array = awkward1.Array([[3.3, 1.1, 5.5, 1.1, 4.4], [4.4, 2.2, 1.1, 6.6], [2.2, 3.3, -1.1]]) assert awkward1.argmin(array) == 11 assert awkward1.argmax(array) == 8 assert awkward1.to_list(awkward1.argmin(array, axis=0)) == [2, 0, 2, 0, 0] assert awkward1.to_list(awkward1.argmax(array, axis=0)) == [1, 2, 0, 1, 0] assert awkward1.to_list(awkward1.argmin(array, axis=1)) == [1, 2, 2] assert awkward1.to_list(awkward1.argmax(array, axis=1)) == [2, 3, 1]
def process(self, events): # Initialize accumulator out = self.accumulator.identity() # Event selection: opposite charged same flavor Electron = events.Electron Electron_mask = (Electron.pt > 20) & (np.abs(Electron.eta) < 2.5) & (Electron.cutBased > 1) Ele_channel_mask = ak.num(Electron[Electron_mask]) > 1 Ele_channel_events = events[Ele_channel_mask] Ele = Ele_channel_events.Electron # All possible pairs of Electron in each event ele_pairs = ak.combinations(Ele, 2, axis=1) # TLorentz vector sum of ele_pairs ele_left, ele_right = ak.unzip(ele_pairs) diele = ele_left + ele_right diffsign_diele = diele[diele.charge == 0] leading_diffsign_diele = diffsign_diele[ak.argmax(diffsign_diele.pt, axis=1, keepdims=True)] #Mee = ak.flatten(leading_diffsign_diele.mass) # This makes type error ( primitive expected but ?float given ) Mee = ak.to_numpy(leading_diffsign_diele.mass) Mee = Mee.flatten() out.fill(dataset=events.metadata["dataset"], mass=Mee) return out
def test_ByteMaskedArray(): content = awkward1.Array([1.1, 2.2, 3.3, 999, 999, 4.4, 5.5]).layout mask = awkward1.layout.Index8( numpy.array([False, False, False, True, True, False, False])) bytemaskedarray = awkward1.layout.ByteMaskedArray(mask, content, valid_when=False) array = awkward1.Array(bytemaskedarray) assert array.tolist() == [1.1, 2.2, 3.3, None, None, 4.4, 5.5] assert awkward1.max(array, axis=0) == 5.5 assert awkward1.argmax(array, axis=0) == 6 offsets = awkward1.layout.Index64( numpy.array([0, 2, 4, 7], dtype=numpy.int64)) listoffsetarray = awkward1.layout.ListOffsetArray64( offsets, bytemaskedarray) array = awkward1.Array(listoffsetarray) assert array.tolist() == [[1.1, 2.2], [3.3, None], [None, 4.4, 5.5]] assert awkward1.max(array, axis=1) == [2.2, 3.3, 5.5] assert awkward1.argmax(array, axis=1) == [1, 0, 2]
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet) > 2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Muons muon = Collections(ev, "Muon", "tightTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) > 0, axis=1) OSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) < 0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() dielectron = choose(electron, 2) SSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) > 0, axis=1) OSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) < 0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 lepton = ak.concatenate([muon, electron], axis=1) dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) > 0, axis=1) OSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) < 0, axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort( jet.pt_nom, ascending=False )] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match( jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta) < 2.4)] btag = getBTagsDeepFlavB( jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets high_p_fwd = fwd[ak.singletons(ak.argmax( fwd.p, axis=1))] # highest momentum spectator high_pt_fwd = fwd[ak.singletons(ak.argmax( fwd.pt_nom, axis=1))] # highest transverse momentum spectator high_eta_fwd = fwd[ak.singletons(ak.argmax(abs( fwd.eta), axis=1))] # most forward spectator ## Get the two leading b-jets in terms of btag score high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:, :2] jf = cross(high_p_fwd, jet) mjf = (jf['0'] + jf['1']).mass deltaEta = abs(high_p_fwd.eta - jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'].eta) deltaEtaMax = ak.max(deltaEta, axis=1) mjf_max = ak.max(mjf, axis=1) jj = choose(jet, 2) mjj_max = ak.max((jj['0'] + jj['1']).mass, axis=1) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) ht_central = ak.sum(central.pt, axis=1) ## event selectors filters = getFilters(ev, year=self.year, dataset=dataset) triggers = getTriggers(ev, year=self.year, dataset=dataset) dilep = ((ak.num(electron) == 1) & (ak.num(muon) == 1)) lep0pt = ((ak.num(electron[(electron.pt > 25)]) + ak.num(muon[(muon.pt > 25)])) > 0) lep1pt = ((ak.num(electron[(electron.pt > 20)]) + ak.num(muon[(muon.pt > 20)])) > 1) lepveto = ((ak.num(vetoelectron) + ak.num(vetomuon)) == 2) # define the weight weight = Weights(len(ev)) if not dataset == 'MuonEG': # lumi weight weight.add("weight", ev.weight * cfg['lumi'][self.year]) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) selection = PackedSelection() selection.add('lepveto', lepveto) selection.add('dilep', dilep) selection.add('trigger', (triggers)) selection.add('filter', (filters)) selection.add('p_T(lep0)>25', lep0pt) selection.add('p_T(lep1)>20', lep1pt) selection.add('OS', OSlepton) selection.add('N_btag=2', (ak.num(btag) == 2)) selection.add('N_jet>2', (ak.num(jet) >= 3)) selection.add('N_central>1', (ak.num(central) >= 2)) selection.add('N_fwd>0', (ak.num(fwd) >= 1)) selection.add('MET>30', (ev.MET.pt > 30)) os_reqs = [ 'lepveto', 'dilep', 'trigger', 'filter', 'p_T(lep0)>25', 'p_T(lep1)>20', 'OS' ] bl_reqs = os_reqs + [ 'N_btag=2', 'N_jet>2', 'N_central>1', 'N_fwd>0', 'MET>30' ] os_reqs_d = {sel: True for sel in os_reqs} os_selection = selection.require(**os_reqs_d) bl_reqs_d = {sel: True for sel in bl_reqs} BL = selection.require(**bl_reqs_d) cutflow = Cutflow(output, ev, weight=weight) cutflow_reqs_d = {} for req in bl_reqs: cutflow_reqs_d.update({req: True}) cutflow.addRow(req, selection.require(**cutflow_reqs_d)) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[os_selection].npvs, weight=weight.weight()[os_selection]) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[os_selection].npvsGood, weight=weight.weight()[os_selection]) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[os_selection], weight=weight.weight()[os_selection]) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[os_selection], weight=weight.weight()[os_selection]) output['N_central'].fill(dataset=dataset, multiplicity=ak.num(central)[os_selection], weight=weight.weight()[os_selection]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[os_selection], weight=weight.weight()[os_selection]) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(electron)[os_selection], weight=weight.weight()[os_selection]) output['N_fwd'].fill(dataset=dataset, multiplicity=ak.num(fwd)[os_selection], weight=weight.weight()[os_selection]) output['MET'].fill(dataset=dataset, pt=ev.MET[os_selection].pt, phi=ev.MET[os_selection].phi, weight=weight.weight()[os_selection]) output['electron'].fill(dataset=dataset, pt=ak.to_numpy(ak.flatten(electron[BL].pt)), eta=ak.to_numpy(ak.flatten(electron[BL].eta)), phi=ak.to_numpy(ak.flatten(electron[BL].phi)), weight=weight.weight()[BL]) output['muon'].fill(dataset=dataset, pt=ak.to_numpy(ak.flatten(muon[BL].pt)), eta=ak.to_numpy(ak.flatten(muon[BL].eta)), phi=ak.to_numpy(ak.flatten(muon[BL].phi)), weight=weight.weight()[BL]) output['lead_lep'].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(leading_lepton[BL].pt)), eta=ak.to_numpy(ak.flatten(leading_lepton[BL].eta)), phi=ak.to_numpy(ak.flatten(leading_lepton[BL].phi)), weight=weight.weight()[BL]) output['trail_lep'].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(trailing_lepton[BL].pt)), eta=ak.to_numpy(ak.flatten(trailing_lepton[BL].eta)), phi=ak.to_numpy(ak.flatten(trailing_lepton[BL].phi)), weight=weight.weight()[BL]) output['fwd_jet'].fill(dataset=dataset, pt=ak.flatten(high_p_fwd[BL].pt_nom), eta=ak.flatten(high_p_fwd[BL].eta), phi=ak.flatten(high_p_fwd[BL].phi), weight=weight.weight()[BL]) output['b1'].fill(dataset=dataset, pt=ak.flatten(high_score_btag[:, 0:1][BL].pt_nom), eta=ak.flatten(high_score_btag[:, 0:1][BL].eta), phi=ak.flatten(high_score_btag[:, 0:1][BL].phi), weight=weight.weight()[BL]) output['b2'].fill(dataset=dataset, pt=ak.flatten(high_score_btag[:, 1:2][BL].pt_nom), eta=ak.flatten(high_score_btag[:, 1:2][BL].eta), phi=ak.flatten(high_score_btag[:, 1:2][BL].phi), weight=weight.weight()[BL]) output['j1'].fill(dataset=dataset, pt=ak.flatten(jet.pt_nom[:, 0:1][BL]), eta=ak.flatten(jet.eta[:, 0:1][BL]), phi=ak.flatten(jet.phi[:, 0:1][BL]), weight=weight.weight()[BL]) output['j2'].fill(dataset=dataset, pt=ak.flatten(jet[:, 1:2][BL].pt_nom), eta=ak.flatten(jet[:, 1:2][BL].eta), phi=ak.flatten(jet[:, 1:2][BL].phi), weight=weight.weight()[BL]) output['j3'].fill(dataset=dataset, pt=ak.flatten(jet[:, 2:3][BL].pt_nom), eta=ak.flatten(jet[:, 2:3][BL].eta), phi=ak.flatten(jet[:, 2:3][BL].phi), weight=weight.weight()[BL]) # Now, take care of systematic unceratinties if not dataset == 'MuonEG': alljets = getJets(ev, minPt=0, maxEta=4.7) alljets = alljets[(alljets.jetId > 1)] for var in self.variations: # get the collections that change with the variations jet = getPtEtaPhi(alljets, pt_var=var) jet = jet[(jet.pt > 25)] jet = jet[~match( jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match( jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta) < 2.4)] btag = getBTagsDeepFlavB( jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets high_p_fwd = fwd[ak.singletons(ak.argmax( fwd.p, axis=1))] # highest momentum spectator high_pt_fwd = fwd[ak.singletons(ak.argmax( fwd.pt, axis=1))] # highest transverse momentum spectator high_eta_fwd = fwd[ak.singletons( ak.argmax(abs(fwd.eta), axis=1))] # most forward spectator ## Get the two leading b-jets in terms of btag score high_score_btag = central[ak.argsort( central.btagDeepFlavB)][:, :2] # get the modified selection -> more difficult selection.add('N_jet>2_' + var, (ak.num(jet.pt) >= 3)) # stupid bug here... selection.add('N_btag=2_' + var, (ak.num(btag) == 2)) selection.add('N_central>1_' + var, (ak.num(central) >= 2)) selection.add('N_fwd>0_' + var, (ak.num(fwd) >= 1)) selection.add('MET>30_' + var, (getattr(ev.MET, var) > 30)) ## Don't change the selection for now... bl_reqs = os_reqs + [ 'N_jet>2_' + var, 'MET>30_' + var, 'N_btag=2_' + var, 'N_central>1_' + var, 'N_fwd>0_' + var ] bl_reqs_d = {sel: True for sel in bl_reqs} BL = selection.require(**bl_reqs_d) # the OS selection remains unchanged output['N_jet_' + var].fill( dataset=dataset, multiplicity=ak.num(jet)[os_selection], weight=weight.weight()[os_selection]) output['N_fwd_' + var].fill( dataset=dataset, multiplicity=ak.num(fwd)[os_selection], weight=weight.weight()[os_selection]) output['N_b_' + var].fill( dataset=dataset, multiplicity=ak.num(btag)[os_selection], weight=weight.weight()[os_selection]) output['N_central_' + var].fill( dataset=dataset, multiplicity=ak.num(central)[os_selection], weight=weight.weight()[os_selection]) # We don't need to redo all plots with variations. E.g., just add uncertainties to the jet plots. output['j1_' + var].fill(dataset=dataset, pt=ak.flatten(jet.pt[:, 0:1][BL]), eta=ak.flatten(jet.eta[:, 0:1][BL]), phi=ak.flatten(jet.phi[:, 0:1][BL]), weight=weight.weight()[BL]) output['b1_' + var].fill( dataset=dataset, pt=ak.flatten(high_score_btag[:, 0:1].pt[:, 0:1][BL]), eta=ak.flatten(high_score_btag[:, 0:1].eta[:, 0:1][BL]), phi=ak.flatten(high_score_btag[:, 0:1].phi[:, 0:1][BL]), weight=weight.weight()[BL]) output['fwd_jet_' + var].fill( dataset=dataset, pt=ak.flatten(high_p_fwd[BL].pt), eta=ak.flatten(high_p_fwd[BL].eta), phi=ak.flatten(high_p_fwd[BL].phi), weight=weight.weight()[BL]) output['MET_' + var].fill(dataset=dataset, pt=getattr(ev.MET, var)[os_selection], phi=ev.MET[os_selection].phi, weight=weight.weight()[os_selection]) return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet) > 2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Muons muon = Collections(ev, "Muon", "tight").get() vetomuon = Collections(ev, "Muon", "veto").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) > 0, axis=1) OSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) < 0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tight").get() vetoelectron = Collections(ev, "Electron", "veto").get() dielectron = choose(electron, 2) SSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) > 0, axis=1) OSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) < 0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 lepton = ak.concatenate([muon, electron], axis=1) dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) > 0, axis=1) OSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) < 0, axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] ## Jets jet = getJets(ev, minPt=25, maxEta=4.7) jet = jet[(jet.pt > 25) & (jet.jetId > 1)] jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match( jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons ## event selectors filters = getFilters(ev, year=self.year, dataset=dataset) triggers = getTriggers(ev, year=self.year, dataset=dataset) dilep = ((ak.num(electron) == 1) & (ak.num(muon) == 1)) lep0pt = ((ak.num(electron[(electron.pt > 25)]) + ak.num(muon[(muon.pt > 25)])) > 0) lep1pt = ((ak.num(electron[(electron.pt > 20)]) + ak.num(muon[(muon.pt > 20)])) > 1) lepveto = ((ak.num(vetoelectron) + ak.num(vetomuon)) == 2) # define the weight weight = Weights(len(ev)) if not dataset == 'MuonEG': # lumi weight weight.add("weight", ev.weight * cfg['lumi'][self.year]) ## PU weight - not in the babies... #weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs #weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) selection = PackedSelection() selection.add('lepveto', lepveto) selection.add('dilep', dilep) selection.add('trigger', (triggers)) selection.add('filter', (filters)) selection.add('p_T(lep0)>25', lep0pt) selection.add('p_T(lep1)>20', lep1pt) selection.add('OS', OSlepton) selection.add('N_jet>2', (ak.num(jet) >= 3)) selection.add('MET>30', (ev.MET.pt > 30)) os_reqs = [ 'lepveto', 'dilep', 'trigger', 'filter', 'p_T(lep0)>25', 'p_T(lep1)>20', 'OS' ] bl_reqs = os_reqs + ['N_jet>2', 'MET>30'] os_reqs_d = {sel: True for sel in os_reqs} os_selection = selection.require(**os_reqs_d) bl_reqs_d = {sel: True for sel in bl_reqs} BL = selection.require(**bl_reqs_d) cutflow = Cutflow(output, ev, weight=weight) cutflow_reqs_d = {} for req in bl_reqs: cutflow_reqs_d.update({req: True}) cutflow.addRow(req, selection.require(**cutflow_reqs_d)) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[os_selection].npvs, weight=weight.weight()[os_selection]) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[os_selection].npvsGood, weight=weight.weight()[os_selection]) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[os_selection], weight=weight.weight()[os_selection]) output['MET'].fill(dataset=dataset, pt=ev.MET[os_selection].pt, phi=ev.MET[os_selection].phi, weight=weight.weight()[os_selection]) output['j1'].fill(dataset=dataset, pt=ak.flatten(jet.pt[:, 0:1][BL]), eta=ak.flatten(jet.eta[:, 0:1][BL]), phi=ak.flatten(jet.phi[:, 0:1][BL]), weight=weight.weight()[BL]) # Now, take care of systematic unceratinties if not dataset == 'MuonEG': alljets = getJets(ev, minPt=0, maxEta=4.7) alljets = alljets[(alljets.jetId > 1)] for var in self.variations: # get the collections that change with the variations jet_var = getPtEtaPhi(alljets, pt_var=var) jet_var = jet_var[(jet_var.pt > 25)] jet_var = jet_var[~match( jet_var, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet_var = jet_var[~match( jet_var, electron, deltaRCut=0.4)] # remove jets that overlap with electrons # get the modified selection -> more difficult selection.add( 'N_jet>2_' + var, (ak.num(jet_var.pt) > 3) ) # something needs to be improved with getPtEtaPhi function selection.add('MET>30_' + var, (getattr(ev.MET, var) > 30)) bl_reqs = os_reqs + ['N_jet>2_' + var, 'MET>30_' + var] bl_reqs_d = {sel: True for sel in bl_reqs} BL = selection.require(**bl_reqs_d) # the OS selection remains unchanged output['N_jet_' + var].fill( dataset=dataset, multiplicity=ak.num(jet_var)[os_selection], weight=weight.weight()[os_selection]) # We don't need to redo all plots with variations. E.g., just add uncertainties to the jet plots. output['j1_' + var].fill(dataset=dataset, pt=ak.flatten(jet_var.pt[:, 0:1][BL]), eta=ak.flatten(jet_var.eta[:, 0:1][BL]), phi=ak.flatten(jet_var.phi[:, 0:1][BL]), weight=weight.weight()[BL]) return output
def process(self, events): output = self.accumulator.identity() # we can use a very loose preselection to filter the events. nothing is done with this presel, though presel = ak.num(events.Jet) > 0 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Electrons electron = Collections(ev, "Electron", "tight").get() electron = electron[(electron.miniPFRelIso_all < 0.12) & (electron.pt > 20) & (abs(electron.eta) < 2.4)] gen_matched_electron = electron[((electron.genPartIdx >= 0) & (abs( electron.matched_gen.pdgId) == 11))] n_gen = ak.num(gen_matched_electron) is_flipped = ((gen_matched_electron.matched_gen.pdgId * (-1) == gen_matched_electron.pdgId) & (abs(gen_matched_electron.pdgId) == 11)) #is_flipped = (abs(ev.GenPart[gen_matched_electron.genPartIdx].pdgId) == abs(gen_matched_electron.pdgId))&(ev.GenPart[gen_matched_electron.genPartIdx].pdgId/abs(ev.GenPart[gen_matched_electron.genPartIdx].pdgId) != gen_matched_electron.pdgId/abs(gen_matched_electron.pdgId)) flipped_electron = gen_matched_electron[is_flipped] n_flips = ak.num(flipped_electron) sielectron = choose(electron, 1) dielectron = choose(electron, 2) SSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) > 0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi # setting up the various weights weight = Weights(len(ev)) weight2 = Weights(len(ev)) if not dataset == 'MuonEG': # generator weight weight.add("weight", ev.genWeight) weight2.add("weight", ev.genWeight) weight2.add("charge flip", self.charge_flip_ratio.flip_ratio(sielectron['0'])) #selections filters = getFilters(ev, year=self.year, dataset=dataset) electr = ((ak.num(electron) == 2)) ss = (SSelectron) gen = (n_gen >= 1) flip = (n_flips >= 1) selection = PackedSelection() selection.add('filter', (filters)) selection.add('electr', electr) selection.add('ss', ss) selection.add('flip', flip) selection.add('gen', gen) bl_reqs = ['filter', 'electr'] bl_reqs_d = {sel: True for sel in bl_reqs} baseline = selection.require(**bl_reqs_d) s_reqs = bl_reqs + ['ss'] s_reqs_d = {sel: True for sel in s_reqs} ss_sel = selection.require(**s_reqs_d) f_reqs = bl_reqs + ['gen', 'flip'] f_reqs_d = {sel: True for sel in f_reqs} flip_sel = selection.require(**f_reqs_d) #outputs output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[flip_sel], weight=weight.weight()[flip_sel]) output['electron_flips'].fill(dataset=dataset, multiplicity=n_flips[flip_sel], weight=weight.weight()[flip_sel]) output['N_ele2'].fill(dataset=dataset, multiplicity=ak.num(electron)[baseline], weight=weight2.weight()[baseline]) output['electron_flips2'].fill(dataset=dataset, multiplicity=n_flips[baseline], weight=weight2.weight()[baseline]) output["electron"].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(flipped_electron[flip_sel].pt)), eta=ak.to_numpy(ak.flatten(abs(flipped_electron[flip_sel].eta))), #phi = ak.to_numpy(ak.flatten(leading_electron[baseline].phi)), weight=weight.weight()[flip_sel]) output["electron2"].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(leading_electron[baseline].pt)), eta=ak.to_numpy(ak.flatten(abs(leading_electron[baseline].eta))), #phi = ak.to_numpy(ak.flatten(leading_electron[baseline].phi)), weight=weight2.weight()[baseline]) return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet)>2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Generated leptons gen_lep = ev.GenL leading_gen_lep = gen_lep[ak.singletons(ak.argmax(gen_lep.pt, axis=1))] trailing_gen_lep = gen_lep[ak.singletons(ak.argmin(gen_lep.pt, axis=1))] ## Muons muon = Collections(ev, "Muon", "tightSSTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge)>0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightSSTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() dielectron = choose(electron, 2) SSelectron = ak.any((dielectron['0'].charge * dielectron['1'].charge)>0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge)>0, axis=1) lepton = ak.concatenate([muon, electron], axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] n_nonprompt = getNonPromptFromFlavour(electron) + getNonPromptFromFlavour(muon) n_chargeflip = getChargeFlips(electron, ev.GenPart) + getChargeFlips(muon, ev.GenPart) ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort(jet.pt_nom, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets j_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator jf = cross(j_fwd, jet) mjf = (jf['0']+jf['1']).mass j_fwd2 = jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'] # this is the jet that forms the largest invariant mass with j_fwd delta_eta = abs(j_fwd2.eta - j_fwd.eta) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) ## event selectors filters = getFilters(ev, year=self.year, dataset=dataset) dilep = ((ak.num(electron) + ak.num(muon))==2) pos_charge = ((ak.sum(electron.pdgId, axis=1) + ak.sum(muon.pdgId, axis=1))<0) neg_charge = ((ak.sum(electron.pdgId, axis=1) + ak.sum(muon.pdgId, axis=1))>0) lep0pt = ((ak.num(electron[(electron.pt>25)]) + ak.num(muon[(muon.pt>25)]))>0) lep0pt_40 = ((ak.num(electron[(electron.pt>40)]) + ak.num(muon[(muon.pt>40)]))>0) lep0pt_100 = ((ak.num(electron[(electron.pt>100)]) + ak.num(muon[(muon.pt>100)]))>0) lep1pt = ((ak.num(electron[(electron.pt>20)]) + ak.num(muon[(muon.pt>20)]))>1) lep1pt_30 = ((ak.num(electron[(electron.pt>30)]) + ak.num(muon[(muon.pt>30)]))>1) lepveto = ((ak.num(vetoelectron) + ak.num(vetomuon))==2) # define the weight weight = Weights( len(ev) ) #mult = 1 #if dataset=='inclusive': mult = 0.0478/47.448 #if dataset=='plus': mult = 0.0036/7.205 if not dataset=='MuonEG': # lumi weight weight.add("weight", ev.weight*cfg['lumi'][self.year]) #weight.add("weight", ev.genWeight*cfg['lumi'][self.year]*mult) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) selection = PackedSelection() selection.add('lepveto', lepveto) selection.add('dilep', dilep ) selection.add('filter', (filters) ) selection.add('p_T(lep0)>25', lep0pt ) selection.add('p_T(lep0)>40', lep0pt_40 ) selection.add('p_T(lep1)>20', lep1pt ) selection.add('p_T(lep1)>30', lep1pt_30 ) selection.add('SS', ( SSlepton | SSelectron | SSmuon) ) selection.add('pos', ( pos_charge ) ) selection.add('neg', ( neg_charge ) ) selection.add('N_jet>3', (ak.num(jet)>=4) ) selection.add('N_jet>4', (ak.num(jet)>=5) ) selection.add('N_central>2', (ak.num(central)>=3) ) selection.add('N_central>3', (ak.num(central)>=4) ) selection.add('N_btag>0', (ak.num(btag)>=1) ) selection.add('MET>50', (ev.MET.pt>50) ) selection.add('ST', (st>600) ) selection.add('N_fwd>0', (ak.num(fwd)>=1 )) selection.add('delta_eta', (ak.any(delta_eta>2, axis=1) ) ) selection.add('fwd_p>500', (ak.any(j_fwd.p>500, axis=1) ) ) ss_reqs = ['lepveto', 'dilep', 'SS', 'filter', 'p_T(lep0)>25', 'p_T(lep1)>20', 'N_jet>3', 'N_central>2', 'N_btag>0'] bl_reqs = ss_reqs + ['N_fwd>0', 'N_jet>4', 'N_central>3', 'ST', 'MET>50', 'delta_eta'] sr_reqs = bl_reqs + ['fwd_p>500', 'p_T(lep0)>40', 'p_T(lep1)>30'] ss_reqs_d = { sel: True for sel in ss_reqs } ss_selection = selection.require(**ss_reqs_d) bl_reqs_d = { sel: True for sel in bl_reqs } BL = selection.require(**bl_reqs_d) sr_reqs_d = { sel: True for sel in sr_reqs } SR = selection.require(**sr_reqs_d) cutflow = Cutflow(output, ev, weight=weight) cutflow_reqs_d = {} for req in sr_reqs: cutflow_reqs_d.update({req: True}) cutflow.addRow( req, selection.require(**cutflow_reqs_d) ) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[ss_selection].npvs, weight=weight.weight()[ss_selection]) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[ss_selection].npvsGood, weight=weight.weight()[ss_selection]) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[ss_selection], weight=weight.weight()[ss_selection]) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[ss_selection], weight=weight.weight()[ss_selection]) output['N_central'].fill(dataset=dataset, multiplicity=ak.num(central)[ss_selection], weight=weight.weight()[ss_selection]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[ss_selection], weight=weight.weight()[ss_selection]) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(electron)[ss_selection], weight=weight.weight()[ss_selection]) output['N_fwd'].fill(dataset=dataset, multiplicity=ak.num(fwd)[ss_selection], weight=weight.weight()[ss_selection]) output['nLepFromTop'].fill(dataset=dataset, multiplicity=ev[BL].nLepFromTop, weight=weight.weight()[BL]) output['nLepFromTau'].fill(dataset=dataset, multiplicity=ev.nLepFromTau[BL], weight=weight.weight()[BL]) output['nLepFromZ'].fill(dataset=dataset, multiplicity=ev.nLepFromZ[BL], weight=weight.weight()[BL]) output['nLepFromW'].fill(dataset=dataset, multiplicity=ev.nLepFromW[BL], weight=weight.weight()[BL]) output['nGenTau'].fill(dataset=dataset, multiplicity=ev.nGenTau[BL], weight=weight.weight()[BL]) output['nGenL'].fill(dataset=dataset, multiplicity=ak.num(ev.GenL[BL], axis=1), weight=weight.weight()[BL]) output['chargeFlip_vs_nonprompt'].fill(dataset=dataset, n1=n_chargeflip[ss_selection], n2=n_nonprompt[ss_selection], n_ele=ak.num(electron)[ss_selection], weight=weight.weight()[ss_selection]) output['MET'].fill( dataset = dataset, pt = ev.MET[ss_selection].pt, phi = ev.MET[ss_selection].phi, weight = weight.weight()[ss_selection] ) output['lead_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_gen_lep[BL].phi)), weight = weight.weight()[BL] ) output['trail_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].phi)), weight = weight.weight()[BL] ) output['lead_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_lepton[BL].phi)), weight = weight.weight()[BL] ) output['trail_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_lepton[BL].phi)), weight = weight.weight()[BL] ) output['j1'].fill( dataset = dataset, pt = ak.flatten(jet.pt_nom[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight.weight()[BL] ) output['j2'].fill( dataset = dataset, pt = ak.flatten(jet[:, 1:2][BL].pt_nom), eta = ak.flatten(jet[:, 1:2][BL].eta), phi = ak.flatten(jet[:, 1:2][BL].phi), weight = weight.weight()[BL] ) output['j3'].fill( dataset = dataset, pt = ak.flatten(jet[:, 2:3][BL].pt_nom), eta = ak.flatten(jet[:, 2:3][BL].eta), phi = ak.flatten(jet[:, 2:3][BL].phi), weight = weight.weight()[BL] ) return output
def process(self, events): dataset = events.metadata['dataset'] isRealData = not hasattr(events, "genWeight") selection = PackedSelection() weights = Weights(len(events)) output = self.accumulator.identity() if not isRealData: output['sumw'][dataset] += ak.sum(events.genWeight) if isRealData: trigger = np.zeros(len(events), dtype='bool') for t in self._triggers[self._year]: trigger = trigger | events.HLT[t] else: trigger = np.ones(len(events), dtype='bool') selection.add('trigger', trigger) if isRealData: trigger = np.zeros(len(events), dtype='bool') for t in self._muontriggers[self._year]: trigger = trigger | events.HLT[t] else: trigger = np.ones(len(events), dtype='bool') selection.add('muontrigger', trigger) fatjets = events.FatJet fatjets['msdcorr'] = corrected_msoftdrop(fatjets) fatjets['qcdrho'] = 2 * np.log(fatjets.msdcorr / fatjets.pt) fatjets['n2ddt'] = fatjets.n2b1 - n2ddt_shift(fatjets, year=self._year) fatjets['msdcorr_full'] = fatjets['msdcorr'] * self._msdSF[self._year] candidatejet = fatjets[ # https://github.com/DAZSLE/BaconAnalyzer/blob/master/Analyzer/src/VJetLoader.cc#L269 (fatjets.pt > 200) & (abs(fatjets.eta) < 2.5) & fatjets.isTight # this is loose in sampleContainer ] if self._jet_arbitration == 'pt': candidatejet = ak.firsts(candidatejet) elif self._jet_arbitration == 'mass': candidatejet = candidatejet[ak.argmax(candidatejet.msdcorr)] elif self._jet_arbitration == 'n2': candidatejet = candidatejet[ak.argmin(candidatejet.n2ddt)] elif self._jet_arbitration == 'ddb': candidatejet = candidatejet[ak.argmax(candidatejet.btagDDBvL)] else: raise RuntimeError("Unknown candidate jet arbitration") selection.add('minjetkin', (candidatejet.pt >= 450) & (candidatejet.msdcorr >= 40.) & (abs(candidatejet.eta) < 2.5)) selection.add('jetacceptance', (candidatejet.msdcorr >= 47.) & (candidatejet.pt < 1200) & (candidatejet.msdcorr < 201.)) selection.add('jetid', candidatejet.isTight) selection.add('n2ddt', (candidatejet.n2ddt < 0.)) selection.add('ddbpass', (candidatejet.btagDDBvL >= 0.89)) jets = events.Jet[(events.Jet.pt > 30.) & (abs(events.Jet.eta) < 2.5) & events.Jet.isTight] # only consider first 4 jets to be consistent with old framework jets = jets[:, :4] dphi = abs(jets.delta_phi(candidatejet)) selection.add( 'antiak4btagMediumOppHem', ak.max( jets[dphi > np.pi / 2].btagDeepB, axis=1, mask_identity=False) < BTagEfficiency.btagWPs[self._year]['medium']) ak4_away = jets[dphi > 0.8] selection.add( 'ak4btagMedium08', ak.max(ak4_away.btagDeepB, axis=1, mask_identity=False) > BTagEfficiency.btagWPs[self._year]['medium']) selection.add('met', events.MET.pt < 140.) goodmuon = ((events.Muon.pt > 10) & (abs(events.Muon.eta) < 2.4) & (events.Muon.pfRelIso04_all < 0.25) & events.Muon.looseId) nmuons = ak.sum(goodmuon, axis=1) leadingmuon = ak.firsts(events.Muon[goodmuon]) nelectrons = ak.sum( (events.Electron.pt > 10) & (abs(events.Electron.eta) < 2.5) & (events.Electron.cutBased >= events.Electron.LOOSE), axis=1, ) ntaus = ak.sum( (events.Tau.pt > 20) & events.Tau.idDecayMode, # bacon iso looser than Nano selection axis=1, ) selection.add('noleptons', (nmuons == 0) & (nelectrons == 0) & (ntaus == 0)) selection.add('onemuon', (nmuons == 1) & (nelectrons == 0) & (ntaus == 0)) selection.add('muonkin', (leadingmuon.pt > 55.) & (abs(leadingmuon.eta) < 2.1)) selection.add('muonDphiAK8', abs(leadingmuon.delta_phi(candidatejet)) > 2 * np.pi / 3) if isRealData: genflavor = 0 else: weights.add('genweight', events.genWeight) add_pileup_weight(weights, events.Pileup.nPU, self._year, dataset) bosons = getBosons(events.GenPart) matchedBoson = candidatejet.nearest(bosons, axis=None, threshold=0.8) genflavor = bosonFlavor(matchedBoson) genBosonPt = ak.fill_none(ak.firsts(bosons.pt), 0) add_VJets_NLOkFactor(weights, genBosonPt, self._year, dataset) add_jetTriggerWeight(weights, candidatejet.msdcorr, candidatejet.pt, self._year) output['btagWeight'].fill(dataset=dataset, val=self._btagSF.addBtagWeight( weights, ak4_away)) logger.debug("Weight statistics: %r" % weights.weightStatistics) msd_matched = candidatejet.msdcorr * self._msdSF[self._year] * ( genflavor > 0) + candidatejet.msdcorr * (genflavor == 0) regions = { 'signal': [ 'trigger', 'minjetkin', 'jetacceptance', 'jetid', 'n2ddt', 'antiak4btagMediumOppHem', 'met', 'noleptons' ], 'muoncontrol': [ 'muontrigger', 'minjetkin', 'jetacceptance', 'jetid', 'n2ddt', 'ak4btagMedium08', 'onemuon', 'muonkin', 'muonDphiAK8' ], 'noselection': [], } for region, cuts in regions.items(): allcuts = set() output['cutflow'].fill(dataset=dataset, region=region, genflavor=genflavor, cut=0, weight=weights.weight()) for i, cut in enumerate(cuts + ['ddbpass']): allcuts.add(cut) cut = selection.all(*allcuts) output['cutflow'].fill(dataset=dataset, region=region, genflavor=genflavor[cut], cut=i + 1, weight=weights.weight()[cut]) systematics = [ None, 'jet_triggerUp', 'jet_triggerDown', 'btagWeightUp', 'btagWeightDown', 'btagEffStatUp', 'btagEffStatDown', ] def normalize(val, cut): return ak.to_numpy(ak.fill_none(val[cut], np.nan)) def fill(region, systematic, wmod=None): selections = regions[region] cut = selection.all(*selections) sname = 'nominal' if systematic is None else systematic if wmod is None: weight = weights.weight(modifier=systematic)[cut] else: weight = weights.weight()[cut] * wmod[cut] output['templates'].fill( dataset=dataset, region=region, systematic=sname, genflavor=genflavor[cut], pt=normalize(candidatejet.pt, cut), msd=normalize(msd_matched, cut), ddb=normalize(candidatejet.btagDDBvL, cut), weight=weight, ) if wmod is not None: output['genresponse_noweight'].fill( dataset=dataset, region=region, systematic=sname, pt=normalize(candidatejet.pt, cut), genpt=normalize(genBosonPt, cut), weight=events.genWeight[cut] * wmod[cut], ) output['genresponse'].fill( dataset=dataset, region=region, systematic=sname, pt=normalize(candidatejet.pt, cut), genpt=normalize(genBosonPt, cut), weight=weight, ) for region in regions: cut = selection.all(*(set(regions[region]) - {'n2ddt'})) output['nminus1_n2ddt'].fill( dataset=dataset, region=region, n2ddt=normalize(candidatejet.n2ddt, cut), weight=weights.weight()[cut], ) for systematic in systematics: fill(region, systematic) if 'GluGluHToBB' in dataset: for i in range(9): fill(region, 'LHEScale_%d' % i, events.LHEScaleWeight[:, i]) for c in events.LHEWeight.columns[1:]: fill(region, 'LHEWeight_%s' % c, events.LHEWeight[c]) output["weightStats"] = weights.weightStatistics return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet)>2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Generated leptons gen_lep = ev.GenL leading_gen_lep = gen_lep[ak.singletons(ak.argmax(gen_lep.pt, axis=1))] trailing_gen_lep = gen_lep[ak.singletons(ak.argmin(gen_lep.pt, axis=1))] ## Muons muon = Collections(ev, "Muon", "tightTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 dilepton = cross(muon, electron) dimuon = choose(muon,2) OS_dimuon = dimuon[(dimuon['0'].charge*dimuon['1'].charge < 0)] dielectron = choose(electron) OS_dielectron = dielectron[(dielectron['0'].charge*dielectron['1'].charge < 0)] OS_dimuon_bestZmumu = OS_dimuon[ak.singletons(ak.argmin(abs(OS_dimuon.mass-91.2), axis=1))] OS_dielectron_bestZee = OS_dielectron[ak.singletons(ak.argmin(abs(OS_dielectron.mass-91.2), axis=1))] OS_dilepton_mass = ak.fill_none(ak.pad_none(ak.concatenate([OS_dimuon_bestZmumu.mass, OS_dielectron_bestZee.mass], axis=1), 1, clip=True), -1) lepton = ak.concatenate([muon, electron], axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort(jet.pt_nom, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets j_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator jf = cross(j_fwd, jet) mjf = (jf['0']+jf['1']).mass j_fwd2 = jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'] # this is the jet that forms the largest invariant mass with j_fwd delta_eta = abs(j_fwd2.eta - j_fwd.eta) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) # define the weight weight = Weights( len(ev) ) if not dataset=='MuonEG': # lumi weight weight.add("weight", ev.weight*cfg['lumi'][self.year]) #weight.add("weight", ev.genWeight*cfg['lumi'][self.year]*mult) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) ## lepton SFs #weight.add("lepton", self.leptonSF.get(electron, muon)) cutflow = Cutflow(output, ev, weight=weight) sel = Selection( dataset = dataset, events = ev, year = self.year, ele = electron, ele_veto = vetoelectron, mu = muon, mu_veto = vetomuon, jet_all = jet, jet_central = central, jet_btag = btag, jet_fwd = fwd, met = ev.MET, ) BL = sel.trilep_baseline(cutflow=cutflow) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvs, weight=weight.weight()[BL]) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvsGood, weight=weight.weight()[BL]) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[BL], weight=weight.weight()[BL]) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[BL], weight=weight.weight()[BL]) output['N_central'].fill(dataset=dataset, multiplicity=ak.num(central)[BL], weight=weight.weight()[BL]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight.weight()[BL]) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight.weight()[BL]) output['N_fwd'].fill(dataset=dataset, multiplicity=ak.num(fwd)[BL], weight=weight.weight()[BL]) output['nLepFromTop'].fill(dataset=dataset, multiplicity=ev[BL].nLepFromTop, weight=weight.weight()[BL]) output['nLepFromTau'].fill(dataset=dataset, multiplicity=ev.nLepFromTau[BL], weight=weight.weight()[BL]) output['nLepFromZ'].fill(dataset=dataset, multiplicity=ev.nLepFromZ[BL], weight=weight.weight()[BL]) output['nLepFromW'].fill(dataset=dataset, multiplicity=ev.nLepFromW[BL], weight=weight.weight()[BL]) output['nGenTau'].fill(dataset=dataset, multiplicity=ev.nGenTau[BL], weight=weight.weight()[BL]) output['nGenL'].fill(dataset=dataset, multiplicity=ak.num(ev.GenL[BL], axis=1), weight=weight.weight()[BL]) # make a plot of the dilepton mass, but without applying the cut on the dilepton mass itself (N-1 plot) output['dilep_mass'].fill(dataset=dataset, mass=ak.flatten(OS_dilepton_mass[sel.trilep_baseline(omit=['offZ'])]), weight=weight.weight()[sel.trilep_baseline(omit=['offZ'])]) output['MET'].fill( dataset = dataset, pt = ev.MET[BL].pt, phi = ev.MET[BL].phi, weight = weight.weight()[BL] ) output['lead_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_gen_lep[BL].phi)), weight = weight.weight()[BL] ) output['trail_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].phi)), weight = weight.weight()[BL] ) output['lead_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_lepton[BL].phi)), weight = weight.weight()[BL] ) output['trail_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_lepton[BL].phi)), weight = weight.weight()[BL] ) output['j1'].fill( dataset = dataset, pt = ak.flatten(jet.pt_nom[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight.weight()[BL] ) output['j2'].fill( dataset = dataset, pt = ak.flatten(jet[:, 1:2][BL].pt_nom), eta = ak.flatten(jet[:, 1:2][BL].eta), phi = ak.flatten(jet[:, 1:2][BL].phi), weight = weight.weight()[BL] ) #output['j3'].fill( # dataset = dataset, # pt = ak.flatten(jet[:, 2:3][BL].pt_nom), # eta = ak.flatten(jet[:, 2:3][BL].eta), # phi = ak.flatten(jet[:, 2:3][BL].phi), # weight = weight.weight()[BL] #) output['fwd_jet'].fill( dataset = dataset, pt = ak.flatten(j_fwd[BL].pt), eta = ak.flatten(j_fwd[BL].eta), phi = ak.flatten(j_fwd[BL].phi), weight = weight.weight()[BL] ) output['high_p_fwd_p'].fill(dataset=dataset, p = ak.flatten(j_fwd[BL].p), weight = weight.weight()[BL]) return output
def make_leading_pair(target,base): return target[ak.argmax(base.pt,axis=1,keepdims=True)]
def test_issue434(): a = awkward1.Array([[0.0, 1.1, 2.2], [3.3, 4.4], [5.5]]) b = awkward1.Array([[9.9, 8.8, 7.7], [6.6, 5.5], [4.4]]) assert awkward1.to_list(b[awkward1.argmin(a, axis=1, keepdims=True)]) == [[9.9], [6.6], [4.4]] assert awkward1.to_list(b[awkward1.argmax(a, axis=1, keepdims=True)]) == [[7.7], [5.5], [4.4]]
def process(self, events): output = self.accumulator.identity() # we can use a very loose preselection to filter the events. nothing is done with this presel, though presel = ak.num(events.Jet) >= 0 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Muons muon = ev.Muon ## Electrons electron = ev.Electron ## Merge electrons and muons - this should work better now in ak1 dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) > 0, axis=1) lepton = ak.concatenate([muon, electron], axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi # define the weight weight = Weights(len(ev)) if not dataset == 'MuonEG': # generator weight weight.add("weight", ev.genWeight) filters = getFilters(ev, year=self.year, dataset=dataset) dilep = ((ak.num(electron) + ak.num(muon)) == 2) selection = PackedSelection() selection.add('dilep', dilep) selection.add('filter', (filters)) bl_reqs = ['dilep', 'filter'] bl_reqs_d = {sel: True for sel in bl_reqs} baseline = selection.require(**bl_reqs_d) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[baseline], weight=weight.weight()[baseline]) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(muon)[baseline], weight=weight.weight()[baseline]) output['lead_lep'].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(leading_lepton[baseline].pt)), eta=ak.to_numpy(ak.flatten(leading_lepton[baseline].eta)), phi=ak.to_numpy(ak.flatten(leading_lepton[baseline].phi)), weight=weight.weight()[baseline]) return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet)>2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): ## Generated leptons gen_lep = ev.GenL leading_gen_lep = gen_lep[ak.singletons(ak.argmax(gen_lep.pt, axis=1))] trailing_gen_lep = gen_lep[ak.singletons(ak.argmin(gen_lep.pt, axis=1))] # Get the leptons. This has changed a couple of times now, but we are using fakeable objects as baseline leptons. # The added p4 instance has the corrected pt (conePt for fakeable) and should be used for any following selection or calculation # Any additional correction (if we choose to do so) should be added here, e.g. Rochester corrections, ... ## Muons mu_v = Collections(ev, "Muon", "vetoTTH", year=year).get() # these include all muons, tight and fakeable mu_t = Collections(ev, "Muon", "tightSSTTH", year=year).get() mu_f = Collections(ev, "Muon", "fakeableSSTTH", year=year).get() muon = ak.concatenate([mu_t, mu_f], axis=1) muon['p4'] = get_four_vec_fromPtEtaPhiM(muon, get_pt(muon), muon.eta, muon.phi, muon.mass, copy=False) #FIXME new ## Electrons el_v = Collections(ev, "Electron", "vetoTTH", year=year).get() el_t = Collections(ev, "Electron", "tightSSTTH", year=year).get() el_f = Collections(ev, "Electron", "fakeableSSTTH", year=year).get() electron = ak.concatenate([el_t, el_f], axis=1) electron['p4'] = get_four_vec_fromPtEtaPhiM(electron, get_pt(electron), electron.eta, electron.phi, electron.mass, copy=False) #FIXME new if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): el_t_p = prompt(el_t) el_t_np = nonprompt(el_t) el_f_p = prompt(el_f) el_f_np = nonprompt(el_f) mu_t_p = prompt(mu_t) mu_t_np = nonprompt(mu_t) mu_f_p = prompt(mu_f) mu_f_np = nonprompt(mu_f) is_flipped = ( (el_t_p.matched_gen.pdgId*(-1) == el_t_p.pdgId) & (abs(el_t_p.pdgId) == 11) ) el_t_p_cc = el_t_p[~is_flipped] # this is tight, prompt, and charge consistent el_t_p_cf = el_t_p[is_flipped] # this is tight, prompt, and charge flipped ## Merge electrons and muons. These are fakeable leptons now lepton = ak.concatenate([muon, electron], axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.p4.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.p4.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] dilepton_mass = (leading_lepton.p4 + trailing_lepton.p4).mass dilepton_pt = (leading_lepton.p4 + trailing_lepton.p4).pt #dilepton_dR = delta_r(leading_lepton, trailing_lepton) dilepton_dR = leading_lepton.p4.delta_r(trailing_lepton.p4) lepton_pdgId_pt_ordered = ak.fill_none(ak.pad_none(lepton[ak.argsort(lepton.p4.pt, ascending=False)].pdgId, 2, clip=True), 0) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): n_nonprompt = getNonPromptFromFlavour(electron) + getNonPromptFromFlavour(muon) n_chargeflip = getChargeFlips(electron, ev.GenPart) + getChargeFlips(muon, ev.GenPart) gp = ev.GenPart gp_e = gp[((abs(gp.pdgId)==11)&(gp.status==1)&((gp.statusFlags&(1<<0))==1)&(gp.statusFlags&(1<<8)==256))] gp_m = gp[((abs(gp.pdgId)==13)&(gp.status==1)&((gp.statusFlags&(1<<0))==1)&(gp.statusFlags&(1<<8)==256))] n_gen_lep = ak.num(gp_e) + ak.num(gp_m) else: n_gen_lep = np.zeros(len(ev)) LL = (n_gen_lep > 2) # this is the classifier for LL events (should mainly be ttZ/tZ/WZ...) mt_lep_met = mt(lepton.p4.pt, lepton.p4.phi, ev.MET.pt, ev.MET.phi) min_mt_lep_met = ak.min(mt_lep_met, axis=1) ## Tau and other stuff tau = getTaus(ev) tau = tau[~match(tau, muon, deltaRCut=0.4)] tau = tau[~match(tau, electron, deltaRCut=0.4)] track = getIsoTracks(ev) ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort(jet.pt_nom, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:,:2] bl = cross(lepton, high_score_btag) bl_dR = delta_r(bl['0'], bl['1']) min_bl_dR = ak.min(bl_dR, axis=1) ## forward jets j_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator # try to get either the most forward light jet, or if there's more than one with eta>1.7, the highest pt one most_fwd = light[ak.argsort(abs(light.eta))][:,0:1] #most_fwd = light[ak.singletons(ak.argmax(abs(light.eta)))] best_fwd = ak.concatenate([j_fwd, most_fwd], axis=1)[:,0:1] jf = cross(j_fwd, jet) mjf = (jf['0']+jf['1']).mass j_fwd2 = jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'] # this is the jet that forms the largest invariant mass with j_fwd delta_eta = abs(j_fwd2.eta - j_fwd.eta) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) #st = met_pt + ht + ak.sum(get_pt(muon), axis=1) + ak.sum(get_pt(electron), axis=1) st = met_pt + ht + ak.sum(lepton.p4.pt, axis=1) # define the weight weight = Weights( len(ev) ) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): # lumi weight weight.add("weight", ev.weight*cfg['lumi'][self.year]) # PU weight weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) cutflow = Cutflow(output, ev, weight=weight) # slightly restructured # calculate everything from loose, require two tights on top # since n_tight == n_loose == 2, the tight and loose leptons are the same in the end # in this selection we'll get events with exactly two fakeable+tight and two loose leptons. sel = Selection( dataset = dataset, events = ev, year = self.year, ele = electron, ele_veto = el_v, mu = muon, mu_veto = mu_v, jet_all = jet, jet_central = central, jet_btag = btag, jet_fwd = fwd, jet_light = light, met = ev.MET, ) baseline = sel.dilep_baseline(cutflow=cutflow, SS=True, omit=['N_fwd>0']) baseline_OS = sel.dilep_baseline(cutflow=cutflow, SS=False, omit=['N_fwd>0']) # this is for charge flip estimation if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): BL = (baseline & ((ak.num(el_t_p_cc)+ak.num(mu_t_p))==2)) # this is the MC baseline for events with two tight prompt leptons BL_incl = (baseline & ((ak.num(el_t)+ak.num(mu_t))==2)) # this is the MC baseline for events with two tight leptons np_est_sel_mc = (baseline & \ ((((ak.num(el_t_p_cc)+ak.num(mu_t_p))==1) & ((ak.num(el_f_np)+ak.num(mu_f_np))==1)) | (((ak.num(el_t_p_cc)+ak.num(mu_t_p))==0) & ((ak.num(el_f_np)+ak.num(mu_f_np))==2)) )) # no overlap between tight and nonprompt, and veto on additional leptons. this should be enough np_obs_sel_mc = (baseline & ((ak.num(el_t)+ak.num(mu_t))==2) & ((ak.num(el_t_np)+ak.num(mu_t_np))>=1) ) # two tight leptons, at least one nonprompt np_est_sel_data = (baseline & ~baseline) # this has to be false cf_est_sel_mc = (baseline_OS & ((ak.num(el_t_p)+ak.num(mu_t_p))==2)) cf_obs_sel_mc = (baseline & ((ak.num(el_t)+ak.num(mu_t))==2) & ((ak.num(el_t_p_cf))>=1) ) # two tight leptons, at least one electron charge flip cf_est_sel_data = (baseline & ~baseline) # this has to be false weight_np_mc = self.nonpromptWeight.get(el_f_np, mu_f_np, meas='TT') weight_cf_mc = self.chargeflipWeight.flip_weight(el_t_p) else: BL = (baseline & ((ak.num(el_t)+ak.num(mu_t))==2)) BL_incl = BL np_est_sel_mc = (baseline & ~baseline) np_obs_sel_mc = (baseline & ~baseline) np_est_sel_data = (baseline & (ak.num(el_t)+ak.num(mu_t)==1) & (ak.num(el_f)+ak.num(mu_f)==1) ) cf_est_sel_mc = (baseline & ~baseline) cf_obs_sel_mc = (baseline & ~baseline) cf_est_sel_data = (baseline_OS & ((ak.num(el_t)+ak.num(mu_t))==2) ) weight_np_mc = np.zeros(len(ev)) weight_cf_mc = np.zeros(len(ev)) #rle = ak.to_numpy(ak.zip([ev.run, ev.luminosityBlock, ev.event])) run_ = ak.to_numpy(ev.run) lumi_ = ak.to_numpy(ev.luminosityBlock) event_ = ak.to_numpy(ev.event) if False: output['%s_run'%dataset] += processor.column_accumulator(run_[BL]) output['%s_lumi'%dataset] += processor.column_accumulator(lumi_[BL]) output['%s_event'%dataset] += processor.column_accumulator(event_[BL]) weight_BL = weight.weight()[BL] # this is just a shortened weight list for the two prompt selection weight_np_data = self.nonpromptWeight.get(el_f, mu_f, meas='data') weight_cf_data = self.chargeflipWeight.flip_weight(el_t) out_sel = (BL | np_est_sel_mc | cf_est_sel_mc) dummy = (np.ones(len(ev))==1) def fill_multiple_np(hist, arrays, add_sel=dummy): #reg_sel = [BL, np_est_sel_mc, np_obs_sel_mc, np_est_sel_data, cf_est_sel_mc, cf_obs_sel_mc, cf_est_sel_data], #print ('len', len(reg_sel[0])) #print ('sel', reg_sel[0]) reg_sel = [BL&add_sel, BL_incl&add_sel, np_est_sel_mc&add_sel, np_obs_sel_mc&add_sel, np_est_sel_data&add_sel, cf_est_sel_mc&add_sel, cf_obs_sel_mc&add_sel, cf_est_sel_data&add_sel], fill_multiple( hist, datasets=[ dataset, # only prompt contribution from process dataset+"_incl", # everything from process (inclusive MC truth) "np_est_mc", # MC based NP estimate "np_obs_mc", # MC based NP observation "np_est_data", "cf_est_mc", "cf_obs_mc", "cf_est_data", ], arrays=arrays, selections=reg_sel[0], # no idea where the additional dimension is coming from... weights=[ weight.weight()[reg_sel[0][0]], weight.weight()[reg_sel[0][1]], weight.weight()[reg_sel[0][2]]*weight_np_mc[reg_sel[0][2]], weight.weight()[reg_sel[0][3]], weight.weight()[reg_sel[0][4]]*weight_np_data[reg_sel[0][4]], weight.weight()[reg_sel[0][5]]*weight_cf_mc[reg_sel[0][5]], weight.weight()[reg_sel[0][6]], weight.weight()[reg_sel[0][7]]*weight_cf_data[reg_sel[0][7]], ], ) if self.evaluate or self.dump: # define the inputs to the NN # this is super stupid. there must be a better way. # used a np.stack which is ok performance wise. pandas data frame seems to be slow and memory inefficient #FIXME no n_b, n_fwd back in v13/v14 of the DNN NN_inputs_d = { 'n_jet': ak.to_numpy(ak.num(jet)), 'n_fwd': ak.to_numpy(ak.num(fwd)), 'n_b': ak.to_numpy(ak.num(btag)), 'n_tau': ak.to_numpy(ak.num(tau)), #'n_track': ak.to_numpy(ak.num(track)), 'st': ak.to_numpy(st), 'met': ak.to_numpy(ev.MET.pt), 'mjj_max': ak.to_numpy(ak.fill_none(ak.max(mjf, axis=1),0)), 'delta_eta_jj': ak.to_numpy(pad_and_flatten(delta_eta)), 'lead_lep_pt': ak.to_numpy(pad_and_flatten(leading_lepton.p4.pt)), 'lead_lep_eta': ak.to_numpy(pad_and_flatten(leading_lepton.p4.eta)), 'sublead_lep_pt': ak.to_numpy(pad_and_flatten(trailing_lepton.p4.pt)), 'sublead_lep_eta': ak.to_numpy(pad_and_flatten(trailing_lepton.p4.eta)), 'dilepton_mass': ak.to_numpy(pad_and_flatten(dilepton_mass)), 'dilepton_pt': ak.to_numpy(pad_and_flatten(dilepton_pt)), 'fwd_jet_pt': ak.to_numpy(pad_and_flatten(best_fwd.pt)), 'fwd_jet_p': ak.to_numpy(pad_and_flatten(best_fwd.p)), 'fwd_jet_eta': ak.to_numpy(pad_and_flatten(best_fwd.eta)), 'lead_jet_pt': ak.to_numpy(pad_and_flatten(jet[:, 0:1].pt)), 'sublead_jet_pt': ak.to_numpy(pad_and_flatten(jet[:, 1:2].pt)), 'lead_jet_eta': ak.to_numpy(pad_and_flatten(jet[:, 0:1].eta)), 'sublead_jet_eta': ak.to_numpy(pad_and_flatten(jet[:, 1:2].eta)), 'lead_btag_pt': ak.to_numpy(pad_and_flatten(high_score_btag[:, 0:1].pt)), 'sublead_btag_pt': ak.to_numpy(pad_and_flatten(high_score_btag[:, 1:2].pt)), 'lead_btag_eta': ak.to_numpy(pad_and_flatten(high_score_btag[:, 0:1].eta)), 'sublead_btag_eta': ak.to_numpy(pad_and_flatten(high_score_btag[:, 1:2].eta)), 'min_bl_dR': ak.to_numpy(ak.fill_none(min_bl_dR, 0)), 'min_mt_lep_met': ak.to_numpy(ak.fill_none(min_mt_lep_met, 0)), } if self.dump: for k in NN_inputs_d.keys(): output[k] += processor.column_accumulator(NN_inputs_d[k][out_sel]) if self.evaluate: NN_inputs = np.stack( [NN_inputs_d[k] for k in NN_inputs_d.keys()] ) NN_inputs = np.nan_to_num(NN_inputs, 0, posinf=1e5, neginf=-1e5) # events with posinf/neginf/nan will not pass the BL selection anyway NN_inputs = np.moveaxis(NN_inputs, 0, 1) # this is needed for a np.stack (old version) model, scaler = load_onnx_model(self.training) try: NN_inputs_scaled = scaler.transform(NN_inputs) NN_pred = predict_onnx(model, NN_inputs_scaled) best_score = np.argmax(NN_pred, axis=1) except ValueError: print ("Problem with prediction. Showing the shapes here:") print (np.shape(NN_inputs)) print (np.shape(weight_BL)) NN_pred = np.array([]) best_score = np.array([]) NN_inputs_scaled = NN_inputs raise ##k.clear_session() #FIXME below needs to be fixed again with changed NN evaluation. Should work now fill_multiple_np(output['node'], {'multiplicity':best_score}) fill_multiple_np(output['node0_score_incl'], {'score':NN_pred[:,0]}) fill_multiple_np(output['node1_score_incl'], {'score':NN_pred[:,1]}) fill_multiple_np(output['node2_score_incl'], {'score':NN_pred[:,2]}) fill_multiple_np(output['node3_score_incl'], {'score':NN_pred[:,3]}) fill_multiple_np(output['node4_score_incl'], {'score':NN_pred[:,4]}) fill_multiple_np(output['node0_score'], {'score':NN_pred[:,0]}, add_sel=(best_score==0)) fill_multiple_np(output['node1_score'], {'score':NN_pred[:,1]}, add_sel=(best_score==1)) fill_multiple_np(output['node2_score'], {'score':NN_pred[:,2]}, add_sel=(best_score==2)) fill_multiple_np(output['node3_score'], {'score':NN_pred[:,3]}, add_sel=(best_score==3)) fill_multiple_np(output['node4_score'], {'score':NN_pred[:,4]}, add_sel=(best_score==4)) #SR_sel_pp = ((best_score==0) & ak.flatten((leading_lepton[BL].pdgId<0))) #SR_sel_mm = ((best_score==0) & ak.flatten((leading_lepton[BL].pdgId>0))) #leading_lepton_BL = leading_lepton[BL] #output['lead_lep_SR_pp'].fill( # dataset = dataset, # pt = ak.to_numpy(ak.flatten(leading_lepton_BL[SR_sel_pp].pt)), # weight = weight_BL[SR_sel_pp] #) #output['lead_lep_SR_mm'].fill( # dataset = dataset, # pt = ak.to_numpy(ak.flatten(leading_lepton_BL[SR_sel_mm].pt)), # weight = weight_BL[SR_sel_mm] #) del model del scaler del NN_inputs, NN_inputs_scaled, NN_pred labels = {'topW_v3': 0, 'TTW':1, 'TTZ': 2, 'TTH': 3, 'ttbar': 4, 'rare':5, 'diboson':6} # these should be all? if dataset in labels: label_mult = labels[dataset] else: label_mult = 7 # data or anything else if self.dump: output['label'] += processor.column_accumulator(np.ones(len(ev[out_sel])) * label_mult) output['SS'] += processor.column_accumulator(ak.to_numpy(BL[out_sel])) output['OS'] += processor.column_accumulator(ak.to_numpy(cf_est_sel_mc[out_sel])) output['AR'] += processor.column_accumulator(ak.to_numpy(np_est_sel_mc[out_sel])) output['LL'] += processor.column_accumulator(ak.to_numpy(LL[out_sel])) output['weight'] += processor.column_accumulator(ak.to_numpy(weight.weight()[out_sel])) output['weight_np'] += processor.column_accumulator(ak.to_numpy(weight_np_mc[out_sel])) output['weight_cf'] += processor.column_accumulator(ak.to_numpy(weight_cf_mc[out_sel])) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvs, weight=weight_BL) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvsGood, weight=weight_BL) fill_multiple_np(output['N_jet'], {'multiplicity': ak.num(jet)}) fill_multiple_np(output['N_b'], {'multiplicity': ak.num(btag)}) fill_multiple_np(output['N_central'], {'multiplicity': ak.num(central)}) fill_multiple_np(output['N_ele'], {'multiplicity':ak.num(electron)}) fill_multiple_np(output['N_mu'], {'multiplicity':ak.num(muon)}) fill_multiple_np(output['N_fwd'], {'multiplicity':ak.num(fwd)}) fill_multiple_np(output['ST'], {'ht': st}) fill_multiple_np(output['HT'], {'ht': ht}) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): output['nLepFromTop'].fill(dataset=dataset, multiplicity=ev[BL].nLepFromTop, weight=weight_BL) output['nLepFromTau'].fill(dataset=dataset, multiplicity=ev.nLepFromTau[BL], weight=weight_BL) output['nLepFromZ'].fill(dataset=dataset, multiplicity=ev.nLepFromZ[BL], weight=weight_BL) output['nLepFromW'].fill(dataset=dataset, multiplicity=ev.nLepFromW[BL], weight=weight_BL) output['nGenTau'].fill(dataset=dataset, multiplicity=ev.nGenTau[BL], weight=weight_BL) output['nGenL'].fill(dataset=dataset, multiplicity=ak.num(ev.GenL[BL], axis=1), weight=weight_BL) output['chargeFlip_vs_nonprompt'].fill(dataset=dataset, n1=n_chargeflip[BL], n2=n_nonprompt[BL], n_ele=ak.num(electron)[BL], weight=weight_BL) fill_multiple_np(output['MET'], {'pt':ev.MET.pt, 'phi':ev.MET.phi}) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): output['lead_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_gen_lep[BL].phi)), weight = weight_BL ) output['trail_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].phi)), weight = weight_BL ) fill_multiple_np( output['lead_lep'], { 'pt': pad_and_flatten(leading_lepton.p4.pt), 'eta': pad_and_flatten(leading_lepton.eta), 'phi': pad_and_flatten(leading_lepton.phi), }, ) fill_multiple_np( output['trail_lep'], { 'pt': pad_and_flatten(trailing_lepton.p4.pt), 'eta': pad_and_flatten(trailing_lepton.eta), 'phi': pad_and_flatten(trailing_lepton.phi), }, ) output['j1'].fill( dataset = dataset, pt = ak.flatten(jet.pt_nom[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight_BL ) output['j2'].fill( dataset = dataset, pt = ak.flatten(jet[:, 1:2][BL].pt_nom), eta = ak.flatten(jet[:, 1:2][BL].eta), phi = ak.flatten(jet[:, 1:2][BL].phi), weight = weight_BL ) output['j3'].fill( dataset = dataset, pt = ak.flatten(jet[:, 2:3][BL].pt_nom), eta = ak.flatten(jet[:, 2:3][BL].eta), phi = ak.flatten(jet[:, 2:3][BL].phi), weight = weight_BL ) fill_multiple_np( output['fwd_jet'], { 'pt': pad_and_flatten(best_fwd.pt), 'eta': pad_and_flatten(best_fwd.eta), 'phi': pad_and_flatten(best_fwd.phi), }, ) #output['fwd_jet'].fill( # dataset = dataset, # pt = ak.flatten(j_fwd[BL].pt), # eta = ak.flatten(j_fwd[BL].eta), # phi = ak.flatten(j_fwd[BL].phi), # weight = weight_BL #) output['high_p_fwd_p'].fill(dataset=dataset, p = ak.flatten(best_fwd[BL].p), weight = weight_BL) return output
def argon_kshell_cuts_3kV(events): #4) largest_s2_amplitude_pmt < 11600 events = events[ak.all(events.s2.height_mvdc_bot < 11600, axis=1)] #5)second_largest_s2_area_pmt = 0 events = events[events.s2s_per_waveform == 1] #6)largest_s1_area_pmt >0 events = events[ak.any(events.s1.area_pe_bot > 0, axis=1)] #7)largest_s2_area_pmt > largest_s1_area_pmt event = events[ak.max(events.s2.area_pe_bot, axis=1) > ak.max( events.s1.area_pe_bot, axis=1)] #8) 0.20 < s2_frt < 0.34 events["s2", "s2_frt"] = events.s2.area_pe_top / (events.s2.area_pe_top + events.s2.area_pe_bot) mask = ak.any(events.s2.s2_frt > 0.16, axis=1) & ak.any( events.s2.s2_frt < 0.34, axis=1) events = events[mask] #9)s2_area+s1_area>1175 mask = ak.max(events.s2.area_pe_top,axis=1)+ak.max(events.s2.area_pe_bot,axis=1)+ak.max(events.s1.area_pe_top,axis=1)+\ ak.max(events.s1.area_pe_bot,axis=1)>1175 events = events[mask] #print("Length array pos 1") #print(ak.num(events,axis=0)) if ak.num(events, axis=0) == 0: return ak.Array([]) #Add the drifttime mask_s1_before_s2 = events.s1.pos_bot < ak.flatten(events.s2.pos_bot) #Cut away the event which don't have an s1 befor the s2. these are s2 only. events = events[ak.any(events.s1.area_pe_bot[mask_s1_before_s2], axis=1)] #print("Length array pos 2") #print(ak.num(events,axis=0)) if ak.num(events, axis=0) == 0: return ak.Array([]) mask_s1_before_s2 = events.s1.pos_bot < ak.flatten(events.s2.pos_bot) max_s1_before_s2 = ak.argmax(events.s1.area_pe_bot[mask_s1_before_s2], axis=1, keepdims=True) events["mask_max_s1_before_s2"] = max_s1_before_s2 events["drifttime_musec"] = ak.flatten( (ak.max(events.s2.pos_bot, axis=1) - events.s1.pos_bot[max_s1_before_s2]) / 100) #10) S2 width cut lower_width = 34.5 + 0.22 * events["drifttime_musec"] + np.sqrt( 32.6 * events["drifttime_musec"]) upper_width = 48.2 + 0.19 * events["drifttime_musec"] + np.sqrt( 47.3 * events["drifttime_musec"]) upper_mask = ak.any(events.s2.width_bot < upper_width, axis=1) lower_mask = ak.any(events.s2.width_bot > lower_width, axis=1) events = events[upper_mask & lower_mask] #11)FDV cut v = 1.9608556663165941 gate_time = 1.537109944449019 events["z"] = -v * (events["drifttime_musec"] - gate_time) events = events[events.z < -2] events = events[events.z > -28] events["r_s2"] = ak.flatten( np.sqrt(np.square(events.s2.x_corr) + np.square(events.s2.y_corr))) events = events[events.r_s2 < 10] return events
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet)>2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Muons muon = Collections(ev, "Muon", "tightSSTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge)>0, axis=1) OSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge)<0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightSSTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() dielectron = choose(electron, 2) SSelectron = ak.any((dielectron['0'].charge * dielectron['1'].charge)>0, axis=1) OSelectron = ak.any((dielectron['0'].charge * dielectron['1'].charge)<0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 lepton = ak.concatenate([muon, electron], axis=1) dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge)>0, axis=1) OSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge)<0, axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort(jet.pt_nom, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets high_p_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator high_pt_fwd = fwd[ak.singletons(ak.argmax(fwd.pt_nom, axis=1))] # highest transverse momentum spectator high_eta_fwd = fwd[ak.singletons(ak.argmax(abs(fwd.eta), axis=1))] # most forward spectator ## Get the two leading b-jets in terms of btag score high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:,:2] jf = cross(high_p_fwd, jet) mjf = (jf['0']+jf['1']).mass deltaEta = abs(high_p_fwd.eta - jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'].eta) deltaEtaMax = ak.max(deltaEta, axis=1) mjf_max = ak.max(mjf, axis=1) jj = choose(jet, 2) mjj_max = ak.max((jj['0']+jj['1']).mass, axis=1) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) ht_central = ak.sum(central.pt, axis=1) # define the weight weight = Weights( len(ev) ) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): # lumi weight weight.add("weight", ev.weight*cfg['lumi'][self.year]) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) cutflow = Cutflow(output, ev, weight=weight) sel = Selection( dataset = dataset, events = ev, year = self.year, ele = electron, ele_veto = vetoelectron, mu = muon, mu_veto = vetomuon, jet_all = jet, jet_central = central, jet_btag = btag, jet_fwd = fwd, met = ev.MET, ) BL = sel.dilep_baseline(cutflow=cutflow, SS=False) # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvs, weight=weight.weight()[BL]) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvsGood, weight=weight.weight()[BL]) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[BL], weight=weight.weight()[BL]) BL_minusNb = sel.dilep_baseline(SS=False, omit=['N_btag>0']) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[BL_minusNb], weight=weight.weight()[BL_minusNb]) output['N_central'].fill(dataset=dataset, multiplicity=ak.num(central)[BL], weight=weight.weight()[BL]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight.weight()[BL]) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight.weight()[BL]) BL_minusFwd = sel.dilep_baseline(SS=False, omit=['N_fwd>0']) output['N_fwd'].fill(dataset=dataset, multiplicity=ak.num(fwd)[BL_minusFwd], weight=weight.weight()[BL_minusFwd]) BL_minusMET = sel.dilep_baseline(SS=False, omit=['MET>50']) output['MET'].fill( dataset = dataset, pt = ev.MET[BL_minusMET].pt, phi = ev.MET[BL_minusMET].phi, weight = weight.weight()[BL_minusMET] ) #output['electron'].fill( # dataset = dataset, # pt = ak.to_numpy(ak.flatten(electron[BL].pt)), # eta = ak.to_numpy(ak.flatten(electron[BL].eta)), # phi = ak.to_numpy(ak.flatten(electron[BL].phi)), # weight = weight.weight()[BL] #) # #output['muon'].fill( # dataset = dataset, # pt = ak.to_numpy(ak.flatten(muon[BL].pt)), # eta = ak.to_numpy(ak.flatten(muon[BL].eta)), # phi = ak.to_numpy(ak.flatten(muon[BL].phi)), # weight = weight.weight()[BL] #) output['lead_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_lepton[BL].phi)), weight = weight.weight()[BL] ) output['trail_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_lepton[BL].phi)), weight = weight.weight()[BL] ) output['fwd_jet'].fill( dataset = dataset, pt = ak.flatten(high_p_fwd[BL].pt_nom), eta = ak.flatten(high_p_fwd[BL].eta), phi = ak.flatten(high_p_fwd[BL].phi), weight = weight.weight()[BL] ) output['b1'].fill( dataset = dataset, pt = ak.flatten(high_score_btag[:, 0:1][BL].pt_nom), eta = ak.flatten(high_score_btag[:, 0:1][BL].eta), phi = ak.flatten(high_score_btag[:, 0:1][BL].phi), weight = weight.weight()[BL] ) output['b2'].fill( dataset = dataset, pt = ak.flatten(high_score_btag[:, 1:2][BL].pt_nom), eta = ak.flatten(high_score_btag[:, 1:2][BL].eta), phi = ak.flatten(high_score_btag[:, 1:2][BL].phi), weight = weight.weight()[BL] ) output['j1'].fill( dataset = dataset, pt = ak.flatten(jet.pt_nom[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight.weight()[BL] ) output['j2'].fill( dataset = dataset, pt = ak.flatten(jet[:, 1:2][BL].pt_nom), eta = ak.flatten(jet[:, 1:2][BL].eta), phi = ak.flatten(jet[:, 1:2][BL].phi), weight = weight.weight()[BL] ) output['j3'].fill( dataset = dataset, pt = ak.flatten(jet[:, 2:3][BL].pt_nom), eta = ak.flatten(jet[:, 2:3][BL].eta), phi = ak.flatten(jet[:, 2:3][BL].phi), weight = weight.weight()[BL] ) if re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): #rle = ak.to_numpy(ak.zip([ev.run, ev.luminosityBlock, ev.event])) run_ = ak.to_numpy(ev.run) lumi_ = ak.to_numpy(ev.luminosityBlock) event_ = ak.to_numpy(ev.event) output['%s_run'%dataset] += processor.column_accumulator(run_[BL]) output['%s_lumi'%dataset] += processor.column_accumulator(lumi_[BL]) output['%s_event'%dataset] += processor.column_accumulator(event_[BL]) # Now, take care of systematic unceratinties if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): alljets = getJets(ev, minPt=0, maxEta=4.7) alljets = alljets[(alljets.jetId>1)] for var in self.variations: # get the collections that change with the variations jet = getPtEtaPhi(alljets, pt_var=var) jet = jet[(jet.pt>25)] jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets high_p_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator high_pt_fwd = fwd[ak.singletons(ak.argmax(fwd.pt, axis=1))] # highest transverse momentum spectator high_eta_fwd = fwd[ak.singletons(ak.argmax(abs(fwd.eta), axis=1))] # most forward spectator ## Get the two leading b-jets in terms of btag score high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:,:2] met = ev.MET met['pt'] = getattr(met, var) sel = Selection( dataset = dataset, events = ev, year = self.year, ele = electron, ele_veto = vetoelectron, mu = muon, mu_veto = vetomuon, jet_all = jet, jet_central = central, jet_btag = btag, jet_fwd = fwd, met = met, ) BL = sel.dilep_baseline(SS=False) # get the modified selection -> more difficult #selection.add('N_jet>2_'+var, (ak.num(jet.pt)>=3)) # stupid bug here... #selection.add('N_btag=2_'+var, (ak.num(btag)==2) ) #selection.add('N_central>1_'+var, (ak.num(central)>=2) ) #selection.add('N_fwd>0_'+var, (ak.num(fwd)>=1) ) #selection.add('MET>30_'+var, (getattr(ev.MET, var)>30) ) ### Don't change the selection for now... #bl_reqs = os_reqs + ['N_jet>2_'+var, 'MET>30_'+var, 'N_btag=2_'+var, 'N_central>1_'+var, 'N_fwd>0_'+var] #bl_reqs_d = { sel: True for sel in bl_reqs } #BL = selection.require(**bl_reqs_d) # the OS selection remains unchanged output['N_jet_'+var].fill(dataset=dataset, multiplicity=ak.num(jet)[BL], weight=weight.weight()[BL]) BL_minusFwd = sel.dilep_baseline(SS=False, omit=['N_fwd>0']) output['N_fwd_'+var].fill(dataset=dataset, multiplicity=ak.num(fwd)[BL_minusFwd], weight=weight.weight()[BL_minusFwd]) BL_minusNb = sel.dilep_baseline(SS=False, omit=['N_btag>0']) output['N_b_'+var].fill(dataset=dataset, multiplicity=ak.num(btag)[BL_minusNb], weight=weight.weight()[BL_minusNb]) output['N_central_'+var].fill(dataset=dataset, multiplicity=ak.num(central)[BL], weight=weight.weight()[BL]) # We don't need to redo all plots with variations. E.g., just add uncertainties to the jet plots. output['j1_'+var].fill( dataset = dataset, pt = ak.flatten(jet.pt[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight.weight()[BL] ) output['b1_'+var].fill( dataset = dataset, pt = ak.flatten(high_score_btag[:, 0:1].pt[:, 0:1][BL]), eta = ak.flatten(high_score_btag[:, 0:1].eta[:, 0:1][BL]), phi = ak.flatten(high_score_btag[:, 0:1].phi[:, 0:1][BL]), weight = weight.weight()[BL] ) output['fwd_jet_'+var].fill( dataset = dataset, pt = ak.flatten(high_p_fwd[BL].pt), #p = ak.flatten(high_p_fwd[BL].p), eta = ak.flatten(high_p_fwd[BL].eta), phi = ak.flatten(high_p_fwd[BL].phi), weight = weight.weight()[BL] ) BL_minusMET = sel.dilep_baseline(SS=False, omit=['MET>50']) output['MET_'+var].fill( dataset = dataset, pt = getattr(ev.MET, var)[BL_minusMET], phi = ev.MET[BL_minusMET].phi, weight = weight.weight()[BL_minusMET] ) return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet) > 2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Muons muon = Collections(ev, "Muon", "tightSSTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) > 0, axis=1) OSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge) < 0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightSSTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() dielectron = choose(electron, 2) SSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) > 0, axis=1) OSelectron = ak.any( (dielectron['0'].charge * dielectron['1'].charge) < 0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 lepton = ak.concatenate([muon, electron], axis=1) dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) > 0, axis=1) OSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge) < 0, axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] second_lepton = lepton[~(trailing_lepton_idx & leading_lepton_idx)] ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort( jet.pt_nom, ascending=False )] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match( jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta) < 2.4)] btag = getBTagsDeepFlavB( jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) ## forward jets high_p_fwd = fwd[ak.singletons(ak.argmax( fwd.p, axis=1))] # highest momentum spectator high_pt_fwd = fwd[ak.singletons(ak.argmax( fwd.pt_nom, axis=1))] # highest transverse momentum spectator high_eta_fwd = fwd[ak.singletons(ak.argmax(abs( fwd.eta), axis=1))] # most forward spectator ## Get the two leading b-jets in terms of btag score high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:, :2] jf = cross(high_p_fwd, jet) mjf = (jf['0'] + jf['1']).mass deltaEta = abs(high_p_fwd.eta - jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'].eta) deltaEtaMax = ak.max(deltaEta, axis=1) mjf_max = ak.max(mjf, axis=1) jj = choose(jet, 2) mjj_max = ak.max((jj['0'] + jj['1']).mass, axis=1) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) lt = met_pt + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) ht_central = ak.sum(central.pt, axis=1) # define the weight weight = Weights(len(ev)) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): # lumi weight weight.add("weight", ev.weight * cfg['lumi'][self.year]) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add( "btag", self.btagSF.Method1a(btag, light, b_direction='central', c_direction='central')) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) sel = Selection( dataset=dataset, events=ev, year=self.year, ele=electron, ele_veto=vetoelectron, mu=muon, mu_veto=vetomuon, jet_all=jet, jet_central=central, jet_btag=btag, jet_fwd=fwd, met=ev.MET, ) BL = sel.dilep_baseline(SS=False) BL_minusNb = sel.dilep_baseline(SS=False, omit=['N_btag>0']) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[BL_minusNb], weight=weight.weight()[BL_minusNb]) if re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): #rle = ak.to_numpy(ak.zip([ev.run, ev.luminosityBlock, ev.event])) run_ = ak.to_numpy(ev.run) lumi_ = ak.to_numpy(ev.luminosityBlock) event_ = ak.to_numpy(ev.event) output['%s_run' % dataset] += processor.column_accumulator( run_[BL]) output['%s_lumi' % dataset] += processor.column_accumulator( lumi_[BL]) output['%s_event' % dataset] += processor.column_accumulator( event_[BL]) # Now, take care of systematic unceratinties if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): alljets = getJets(ev, minPt=0, maxEta=4.7) alljets = alljets[(alljets.jetId > 1)] for var in self.variations: # get the collections that change with the variations btag = getBTagsDeepFlavB( jet, year=self.year) # should study working point for DeepJet weight = Weights(len(ev)) weight.add("weight", ev.weight * cfg['lumi'][self.year]) weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) if var == 'centralUp': weight.add( "btag", self.btagSF.Method1a(btag, light, b_direction='central', c_direction='up')) elif var == 'centralDown': weight.add( "btag", self.btagSF.Method1a(btag, light, b_direction='central', c_direction='down')) elif var == 'upCentral': weight.add( "btag", self.btagSF.Method1a(btag, light, b_direction='up', c_direction='central')) elif var == 'downCentral': weight.add( "btag", self.btagSF.Method1a(btag, light, b_direction='down', c_direction='central')) weight.add("lepton", self.leptonSF.get(electron, muon)) met = ev.MET sel = Selection( dataset=dataset, events=ev, year=self.year, ele=electron, ele_veto=vetoelectron, mu=muon, mu_veto=vetomuon, jet_all=jet, jet_central=central, jet_btag=btag, jet_fwd=fwd, met=met, ) BL = sel.dilep_baseline(SS=False) BL_minusNb = sel.dilep_baseline(SS=False, omit=['N_btag>0']) output['N_b_' + var].fill( dataset=dataset, multiplicity=ak.num(btag)[BL_minusNb], weight=weight.weight()[BL_minusNb]) return output
def process(self, events): output = self.accumulator.identity() # we can use a very loose preselection to filter the events. nothing is done with this presel, though presel = ak.num(events.Jet)>=2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Electrons electron = Collections(ev, "Electron", "tightFCNC", 0, self.year).get() electron = electron[(electron.pt > 15) & (np.abs(electron.eta) < 2.4)] electron = electron[(electron.genPartIdx >= 0)] electron = electron[(np.abs(electron.matched_gen.pdgId)==11)] #from here on all leptons are gen-matched electron = electron[( (electron.genPartFlav==1) | (electron.genPartFlav==15) )] #and now they are all prompt leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] trailing_electron_idx = ak.singletons(ak.argmin(electron.pt, axis=1)) trailing_electron = electron[trailing_electron_idx] leading_parent = find_first_parent(leading_electron.matched_gen) trailing_parent = find_first_parent(trailing_electron.matched_gen) is_flipped = ( ( (electron.matched_gen.pdgId*(-1) == electron.pdgId) | (find_first_parent(electron.matched_gen)*(-1) == electron.pdgId) ) & (np.abs(electron.pdgId) == 11) ) flipped_electron = electron[is_flipped] flipped_electron = flipped_electron[(ak.fill_none(flipped_electron.pt, 0)>0)] flipped_electron = flipped_electron[~(ak.is_none(flipped_electron))] n_flips = ak.num(flipped_electron) ##Muons muon = Collections(ev, "Muon", "tightFCNC").get() muon = muon[(muon.pt > 15) & (np.abs(muon.eta) < 2.4)] muon = muon[(muon.genPartIdx >= 0)] muon = muon[(np.abs(muon.matched_gen.pdgId)==13)] #from here, all muons are gen-matched muon = muon[( (muon.genPartFlav==1) | (muon.genPartFlav==15) )] #and now they are all prompt ##Leptons lepton = ak.concatenate([muon, electron], axis=1) SSlepton = (ak.sum(lepton.charge, axis=1) != 0) & (ak.num(lepton)==2) OSlepton = (ak.sum(lepton.charge, axis=1) == 0) & (ak.num(lepton)==2) emulepton = (ak.num(electron) == 1) & (ak.num(muon) == 1) no_mumu = (ak.num(muon) <= 1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] #jets jet = getJets(ev, minPt=40, maxEta=2.4, pt_var='pt') jet = jet[ak.argsort(jet.pt, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi # setting up the various weights weight = Weights( len(ev) ) weight2 = Weights( len(ev)) if not dataset=='MuonEG': # generator weight weight.add("weight", ev.genWeight) weight2.add("weight", ev.genWeight) weight2.add("charge flip", self.charge_flip_ratio.flip_weight(electron)) #selections filters = getFilters(ev, year=self.year, dataset=dataset) ss = (SSlepton) os = (OSlepton) jet_all = (ak.num(jet) >= 2) diele = (ak.num(electron) == 2) emu = (emulepton) flips = (n_flips == 1) no_flips = (n_flips == 0) nmm = no_mumu selection = PackedSelection() selection.add('filter', (filters) ) selection.add('ss', ss ) selection.add('os', os ) selection.add('jet', jet_all ) selection.add('ee', diele) selection.add('emu', emu) selection.add('flip', flips) selection.add('nflip', no_flips) selection.add('no_mumu', nmm) bl_reqs = ['filter'] + ['jet'] bl_reqs_d = { sel: True for sel in bl_reqs } baseline = selection.require(**bl_reqs_d) f_reqs = bl_reqs + ['flip'] + ['ss'] + ['ee'] f_reqs_d = {sel: True for sel in f_reqs} flip_sel = selection.require(**f_reqs_d) f2_reqs = bl_reqs + ['flip'] + ['ss'] + ['emu'] f2_reqs_d = {sel: True for sel in f2_reqs} flip_sel2 = selection.require(**f2_reqs_d) f3_reqs = bl_reqs + ['flip'] + ['ss'] + ['no_mumu'] f3_reqs_d = {sel: True for sel in f3_reqs} flip_sel3 = selection.require(**f3_reqs_d) nf_reqs = bl_reqs + ['nflip'] + ['os'] + ['ee'] nf_reqs_d = {sel: True for sel in nf_reqs} n_flip_sel = selection.require(**nf_reqs_d) nf2_reqs = bl_reqs + ['nflip'] + ['os'] + ['emu'] nf2_reqs_d = {sel: True for sel in nf2_reqs} n_flip_sel2 = selection.require(**nf2_reqs_d) nf3_reqs = bl_reqs + ['nflip'] + ['os'] + ['no_mumu'] nf3_reqs_d = {sel: True for sel in nf3_reqs} n_flip_sel3 = selection.require(**nf3_reqs_d) s_reqs = bl_reqs + ['ss'] + ['no_mumu'] s_reqs_d = { sel: True for sel in s_reqs } ss_sel = selection.require(**s_reqs_d) o_reqs = bl_reqs + ['os'] + ['no_mumu'] o_reqs_d = {sel: True for sel in o_reqs } os_sel = selection.require(**o_reqs_d) ees_reqs = bl_reqs + ['ss'] + ['ee'] ees_reqs_d = { sel: True for sel in ees_reqs } eess_sel = selection.require(**ees_reqs_d) eeo_reqs = bl_reqs + ['os'] + ['ee'] eeo_reqs_d = {sel: True for sel in eeo_reqs } eeos_sel = selection.require(**eeo_reqs_d) ems_reqs = bl_reqs + ['ss'] + ['emu'] ems_reqs_d = { sel: True for sel in ems_reqs } emss_sel = selection.require(**ems_reqs_d) emo_reqs = bl_reqs + ['os'] + ['emu'] emo_reqs_d = {sel: True for sel in emo_reqs } emos_sel = selection.require(**emo_reqs_d) #outputs output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[baseline], weight=weight.weight()[baseline]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(lepton)[ss_sel], weight=weight.weight()[ss_sel]) output['N_ele2'].fill(dataset=dataset, multiplicity=ak.num(lepton)[os_sel], weight=weight2.weight()[os_sel]) output['electron_flips'].fill(dataset=dataset, multiplicity = n_flips[flip_sel], weight=weight.weight()[flip_sel]) output['electron_flips2'].fill(dataset=dataset, multiplicity = n_flips[n_flip_sel], weight=weight2.weight()[n_flip_sel]) output['electron_flips3'].fill(dataset=dataset, multiplicity = n_flips[flip_sel2], weight=weight.weight()[flip_sel2]) output['electron_flips4'].fill(dataset=dataset, multiplicity = n_flips[n_flip_sel2], weight=weight2.weight()[n_flip_sel2]) output["electron"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[flip_sel3].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[flip_sel3].eta))), weight = weight.weight()[flip_sel3] ) output["electron2"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[n_flip_sel3].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[n_flip_sel3].eta))), weight = weight2.weight()[n_flip_sel3] ) output["flipped_electron"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[flip_sel].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[flip_sel].eta))), weight = weight.weight()[flip_sel] ) output["flipped_electron2"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[n_flip_sel].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[n_flip_sel].eta))), weight = weight2.weight()[n_flip_sel] ) output["flipped_electron3"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[flip_sel2].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[flip_sel2].eta))), weight = weight.weight()[flip_sel2] ) output["flipped_electron4"].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_electron[n_flip_sel2].pt)), eta = np.abs(ak.to_numpy(ak.flatten(leading_electron[n_flip_sel2].eta))), weight = weight2.weight()[n_flip_sel2] ) #output["lepton_parent"].fill( # dataset = dataset, # pdgID = np.abs(ak.to_numpy(ak.flatten(leading_parent[ss_sel]))), # weight = weight.weight()[ss_sel] #) # #output["lepton_parent2"].fill( # dataset = dataset, # pdgID = np.abs(ak.to_numpy(ak.flatten(trailing_parent[ss_sel]))), # weight = weight.weight()[ss_sel] #) return output
def process(self, events): output = self.accumulator.identity() # use a very loose preselection to filter the events presel = ak.num(events.Jet)>2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): ## Generated leptons gen_lep = ev.GenL leading_gen_lep = gen_lep[ak.singletons(ak.argmax(gen_lep.pt, axis=1))] trailing_gen_lep = gen_lep[ak.singletons(ak.argmin(gen_lep.pt, axis=1))] ## Muons muon = Collections(ev, "Muon", "tightSSTTH").get() vetomuon = Collections(ev, "Muon", "vetoTTH").get() dimuon = choose(muon, 2) SSmuon = ak.any((dimuon['0'].charge * dimuon['1'].charge)>0, axis=1) leading_muon_idx = ak.singletons(ak.argmax(muon.pt, axis=1)) leading_muon = muon[leading_muon_idx] ## Electrons electron = Collections(ev, "Electron", "tightSSTTH").get() vetoelectron = Collections(ev, "Electron", "vetoTTH").get() dielectron = choose(electron, 2) SSelectron = ak.any((dielectron['0'].charge * dielectron['1'].charge)>0, axis=1) leading_electron_idx = ak.singletons(ak.argmax(electron.pt, axis=1)) leading_electron = electron[leading_electron_idx] ## Merge electrons and muons - this should work better now in ak1 dilepton = cross(muon, electron) SSlepton = ak.any((dilepton['0'].charge * dilepton['1'].charge)>0, axis=1) lepton = ak.concatenate([muon, electron], axis=1) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] trailing_lepton_idx = ak.singletons(ak.argmin(lepton.pt, axis=1)) trailing_lepton = lepton[trailing_lepton_idx] dilepton_mass = (leading_lepton+trailing_lepton).mass dilepton_pt = (leading_lepton+trailing_lepton).pt dilepton_dR = delta_r(leading_lepton, trailing_lepton) lepton_pdgId_pt_ordered = ak.fill_none(ak.pad_none(lepton[ak.argsort(lepton.pt, ascending=False)].pdgId, 2, clip=True), 0) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): n_nonprompt = getNonPromptFromFlavour(electron) + getNonPromptFromFlavour(muon) n_chargeflip = getChargeFlips(electron, ev.GenPart) + getChargeFlips(muon, ev.GenPart) mt_lep_met = mt(lepton.pt, lepton.phi, ev.MET.pt, ev.MET.phi) min_mt_lep_met = ak.min(mt_lep_met, axis=1) ## Tau and other stuff tau = getTaus(ev) track = getIsoTracks(ev) ## Jets jet = getJets(ev, minPt=25, maxEta=4.7, pt_var='pt_nom') jet = jet[ak.argsort(jet.pt_nom, ascending=False)] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] # remove jets that overlap with electrons central = jet[(abs(jet.eta)<2.4)] btag = getBTagsDeepFlavB(jet, year=self.year) # should study working point for DeepJet light = getBTagsDeepFlavB(jet, year=self.year, invert=True) fwd = getFwdJet(light) fwd_noPU = getFwdJet(light, puId=False) high_score_btag = central[ak.argsort(central.btagDeepFlavB)][:,:2] bl = cross(lepton, high_score_btag) bl_dR = delta_r(bl['0'], bl['1']) min_bl_dR = ak.min(bl_dR, axis=1) ## forward jets j_fwd = fwd[ak.singletons(ak.argmax(fwd.p, axis=1))] # highest momentum spectator jf = cross(j_fwd, jet) mjf = (jf['0']+jf['1']).mass j_fwd2 = jf[ak.singletons(ak.argmax(mjf, axis=1))]['1'] # this is the jet that forms the largest invariant mass with j_fwd delta_eta = abs(j_fwd2.eta - j_fwd.eta) ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi ## other variables ht = ak.sum(jet.pt, axis=1) st = met_pt + ht + ak.sum(muon.pt, axis=1) + ak.sum(electron.pt, axis=1) # define the weight weight = Weights( len(ev) ) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): # lumi weight weight.add("weight", ev.weight*cfg['lumi'][self.year]) #weight.add("weight", ev.genWeight*cfg['lumi'][self.year]*mult) # PU weight - not in the babies... weight.add("PU", ev.puWeight, weightUp=ev.puWeightUp, weightDown=ev.puWeightDown, shift=False) # b-tag SFs weight.add("btag", self.btagSF.Method1a(btag, light)) # lepton SFs weight.add("lepton", self.leptonSF.get(electron, muon)) cutflow = Cutflow(output, ev, weight=weight) sel = Selection( dataset = dataset, events = ev, year = self.year, ele = electron, ele_veto = vetoelectron, mu = muon, mu_veto = vetomuon, jet_all = jet, jet_central = central, jet_btag = btag, jet_fwd = fwd, met = ev.MET, ) BL = sel.dilep_baseline(cutflow=cutflow, SS=True) weight_BL = weight.weight()[BL] if True: # define the inputs to the NN # this is super stupid. there must be a better way. NN_inputs = np.stack([ ak.to_numpy(ak.num(jet[BL])), ak.to_numpy(ak.num(tau[BL])), ak.to_numpy(ak.num(track[BL])), ak.to_numpy(st[BL]), ak.to_numpy(ev.MET[BL].pt), ak.to_numpy(ak.max(mjf[BL], axis=1)), ak.to_numpy(pad_and_flatten(delta_eta[BL])), ak.to_numpy(pad_and_flatten(leading_lepton[BL].pt)), ak.to_numpy(pad_and_flatten(leading_lepton[BL].eta)), ak.to_numpy(pad_and_flatten(trailing_lepton[BL].pt)), ak.to_numpy(pad_and_flatten(trailing_lepton[BL].eta)), ak.to_numpy(pad_and_flatten(dilepton_mass[BL])), ak.to_numpy(pad_and_flatten(dilepton_pt[BL])), ak.to_numpy(pad_and_flatten(j_fwd[BL].pt)), ak.to_numpy(pad_and_flatten(j_fwd[BL].p)), ak.to_numpy(pad_and_flatten(j_fwd[BL].eta)), ak.to_numpy(pad_and_flatten(jet[:, 0:1][BL].pt)), ak.to_numpy(pad_and_flatten(jet[:, 1:2][BL].pt)), ak.to_numpy(pad_and_flatten(jet[:, 0:1][BL].eta)), ak.to_numpy(pad_and_flatten(jet[:, 1:2][BL].eta)), ak.to_numpy(pad_and_flatten(high_score_btag[:, 0:1][BL].pt)), ak.to_numpy(pad_and_flatten(high_score_btag[:, 1:2][BL].pt)), ak.to_numpy(pad_and_flatten(high_score_btag[:, 0:1][BL].eta)), ak.to_numpy(pad_and_flatten(high_score_btag[:, 1:2][BL].eta)), ak.to_numpy(min_bl_dR[BL]), ak.to_numpy(min_mt_lep_met[BL]), ]) NN_inputs = np.moveaxis(NN_inputs, 0, 1) model, scaler = load_onnx_model('v8') try: NN_inputs_scaled = scaler.transform(NN_inputs) NN_pred = predict_onnx(model, NN_inputs_scaled) best_score = np.argmax(NN_pred, axis=1) except ValueError: #print ("Empty NN_inputs") NN_pred = np.array([]) best_score = np.array([]) NN_inputs_scaled = NN_inputs #k.clear_session() output['node'].fill(dataset=dataset, multiplicity=best_score, weight=weight_BL) output['node0_score_incl'].fill(dataset=dataset, score=NN_pred[:,0] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL) output['node0_score'].fill(dataset=dataset, score=NN_pred[best_score==0][:,0] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL[best_score==0]) output['node1_score'].fill(dataset=dataset, score=NN_pred[best_score==1][:,1] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL[best_score==1]) output['node2_score'].fill(dataset=dataset, score=NN_pred[best_score==2][:,2] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL[best_score==2]) output['node3_score'].fill(dataset=dataset, score=NN_pred[best_score==3][:,3] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL[best_score==3]) output['node4_score'].fill(dataset=dataset, score=NN_pred[best_score==4][:,4] if np.shape(NN_pred)[0]>0 else np.array([]), weight=weight_BL[best_score==4]) SR_sel_pp = ((best_score==0) & ak.flatten((leading_lepton[BL].pdgId<0))) SR_sel_mm = ((best_score==0) & ak.flatten((leading_lepton[BL].pdgId>0))) leading_lepton_BL = leading_lepton[BL] output['lead_lep_SR_pp'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton_BL[SR_sel_pp].pt)), weight = weight_BL[SR_sel_pp] ) output['lead_lep_SR_mm'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton_BL[SR_sel_mm].pt)), weight = weight_BL[SR_sel_mm] ) del model del scaler del NN_inputs, NN_inputs_scaled, NN_pred # first, make a few super inclusive plots output['PV_npvs'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvs, weight=weight_BL) output['PV_npvsGood'].fill(dataset=dataset, multiplicity=ev.PV[BL].npvsGood, weight=weight_BL) output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[BL], weight=weight_BL) output['N_b'].fill(dataset=dataset, multiplicity=ak.num(btag)[BL], weight=weight_BL) output['N_central'].fill(dataset=dataset, multiplicity=ak.num(central)[BL], weight=weight_BL) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight_BL) output['N_mu'].fill(dataset=dataset, multiplicity=ak.num(electron)[BL], weight=weight_BL) output['N_fwd'].fill(dataset=dataset, multiplicity=ak.num(fwd)[BL], weight=weight_BL) output['ST'].fill(dataset=dataset, pt=st[BL], weight=weight_BL) output['HT'].fill(dataset=dataset, pt=ht[BL], weight=weight_BL) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): output['nLepFromTop'].fill(dataset=dataset, multiplicity=ev[BL].nLepFromTop, weight=weight_BL) output['nLepFromTau'].fill(dataset=dataset, multiplicity=ev.nLepFromTau[BL], weight=weight_BL) output['nLepFromZ'].fill(dataset=dataset, multiplicity=ev.nLepFromZ[BL], weight=weight_BL) output['nLepFromW'].fill(dataset=dataset, multiplicity=ev.nLepFromW[BL], weight=weight_BL) output['nGenTau'].fill(dataset=dataset, multiplicity=ev.nGenTau[BL], weight=weight_BL) output['nGenL'].fill(dataset=dataset, multiplicity=ak.num(ev.GenL[BL], axis=1), weight=weight_BL) output['chargeFlip_vs_nonprompt'].fill(dataset=dataset, n1=n_chargeflip[BL], n2=n_nonprompt[BL], n_ele=ak.num(electron)[BL], weight=weight_BL) output['MET'].fill( dataset = dataset, pt = ev.MET[BL].pt, phi = ev.MET[BL].phi, weight = weight_BL ) if not re.search(re.compile('MuonEG|DoubleMuon|DoubleEG|EGamma'), dataset): output['lead_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_gen_lep[BL].phi)), weight = weight_BL ) output['trail_gen_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_gen_lep[BL].phi)), weight = weight_BL ) output['lead_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(leading_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(leading_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(leading_lepton[BL].phi)), weight = weight_BL ) output['trail_lep'].fill( dataset = dataset, pt = ak.to_numpy(ak.flatten(trailing_lepton[BL].pt)), eta = ak.to_numpy(ak.flatten(trailing_lepton[BL].eta)), phi = ak.to_numpy(ak.flatten(trailing_lepton[BL].phi)), weight = weight_BL ) output['j1'].fill( dataset = dataset, pt = ak.flatten(jet.pt_nom[:, 0:1][BL]), eta = ak.flatten(jet.eta[:, 0:1][BL]), phi = ak.flatten(jet.phi[:, 0:1][BL]), weight = weight_BL ) output['j2'].fill( dataset = dataset, pt = ak.flatten(jet[:, 1:2][BL].pt_nom), eta = ak.flatten(jet[:, 1:2][BL].eta), phi = ak.flatten(jet[:, 1:2][BL].phi), weight = weight_BL ) output['j3'].fill( dataset = dataset, pt = ak.flatten(jet[:, 2:3][BL].pt_nom), eta = ak.flatten(jet[:, 2:3][BL].eta), phi = ak.flatten(jet[:, 2:3][BL].phi), weight = weight_BL ) output['fwd_jet'].fill( dataset = dataset, pt = ak.flatten(j_fwd[BL].pt), eta = ak.flatten(j_fwd[BL].eta), phi = ak.flatten(j_fwd[BL].phi), weight = weight_BL ) output['high_p_fwd_p'].fill(dataset=dataset, p = ak.flatten(j_fwd[BL].p), weight = weight_BL) return output
def process(self, events): output = self.accumulator.identity() # we can use a very loose preselection to filter the events. nothing is done with this presel, though presel = ak.num(events.Jet) >= 2 ev = events[presel] dataset = ev.metadata['dataset'] # load the config - probably not needed anymore cfg = loadConfig() output['totalEvents']['all'] += len(events) output['skimmedEvents']['all'] += len(ev) ## Electrons electron = Collections(ev, "Electron", "tight").get() electron = electron[(electron.pt > 20) & (abs(electron.eta) < 2.4)] electron = electron[((electron.genPartIdx >= 0) & (np.abs(electron.matched_gen.pdgId) == 11) )] #from here on all leptons are gen-matched ##Muons muon = Collections(ev, "Muon", "tight").get() muon = muon[(muon.pt > 20) & (abs(muon.eta) < 2.4)] muon = muon[((muon.genPartIdx >= 0) & (np.abs(muon.matched_gen.pdgId) == 13))] ##Leptons lepton = ak.concatenate([muon, electron], axis=1) SSlepton = (ak.sum(lepton.charge, axis=1) != 0) & (ak.num(lepton) == 2) OSlepton = (ak.sum(lepton.charge, axis=1) == 0) & (ak.num(lepton) == 2) leading_lepton_idx = ak.singletons(ak.argmax(lepton.pt, axis=1)) leading_lepton = lepton[leading_lepton_idx] #jets jet = getJets(ev, minPt=40, maxEta=2.4, pt_var='pt') jet = jet[ak.argsort( jet.pt, ascending=False )] # need to sort wrt smeared and recorrected jet pt jet = jet[~match(jet, muon, deltaRCut=0.4)] # remove jets that overlap with muons jet = jet[~match(jet, electron, deltaRCut=0.4)] ## MET -> can switch to puppi MET met_pt = ev.MET.pt met_phi = ev.MET.phi # setting up the various weights weight = Weights(len(ev)) weight2 = Weights(len(ev)) if not dataset == 'MuonEG': # generator weight weight.add("weight", ev.genWeight) weight2.add("weight", ev.genWeight) weight2.add("charge flip", self.charge_flip_ratio.flip_weight(electron)) #selections filters = getFilters(ev, year=self.year, dataset=dataset) ss = (SSlepton) os = (OSlepton) jet_all = (ak.num(jet) >= 2) selection = PackedSelection() selection.add('filter', (filters)) selection.add('ss', ss) selection.add('os', os) selection.add('jet', jet_all) bl_reqs = ['filter', 'jet'] bl_reqs_d = {sel: True for sel in bl_reqs} baseline = selection.require(**bl_reqs_d) s_reqs = bl_reqs + ['ss'] s_reqs_d = {sel: True for sel in s_reqs} ss_sel = selection.require(**s_reqs_d) o_reqs = bl_reqs + ['os'] o_reqs_d = {sel: True for sel in o_reqs} os_sel = selection.require(**o_reqs_d) #outputs output['N_jet'].fill(dataset=dataset, multiplicity=ak.num(jet)[baseline], weight=weight.weight()[baseline]) output['N_ele'].fill(dataset=dataset, multiplicity=ak.num(lepton)[ss_sel], weight=weight.weight()[ss_sel]) output['N_ele2'].fill(dataset=dataset, multiplicity=ak.num(lepton)[os_sel], weight=weight2.weight()[os_sel]) output["electron"].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(leading_lepton[ss_sel].pt)), eta=abs(ak.to_numpy(ak.flatten(leading_lepton[ss_sel].eta))), phi=ak.to_numpy(ak.flatten(leading_lepton[ss_sel].phi)), weight=weight.weight()[ss_sel]) output["electron2"].fill( dataset=dataset, pt=ak.to_numpy(ak.flatten(leading_lepton[os_sel].pt)), eta=abs(ak.to_numpy(ak.flatten(leading_lepton[os_sel].eta))), phi=ak.to_numpy(ak.flatten(leading_lepton[os_sel].phi)), weight=weight2.weight()[os_sel]) return output