removeVars = [ 'tagCatP2VV' ] selection = 'hlt2_biased==1' numDataSets = 40 weightName = '' import P2VV.RooFitWrappers from ROOT import TFile, RooArgSet protoFile = TFile.Open(protoFilePathIn) nTupleFileIn = TFile.Open(nTupleFilePathIn) protoData = protoFile.Get('JpsiKK_sigSWeight') nTupleIn = nTupleFileIn.Get('DecayTree') from ROOT import RooRealVar, RooCategory obsSet = RooArgSet( protoData.get() ) if runPeriods : rp = obsSet.find('runPeriod') if rp : obsSet.remove(rp) rp = RooCategory( 'runPeriod', 'runPeriod' ) for per in runPeriods : rp.defineType( 'p%d' % per, per ) obsSet.add(rp) if KKMassBins : KKCat = obsSet.find('KKMassCat') if KKCat : obsSet.remove(KKCat) KKCat = RooCategory( 'KKMassCat', 'KKMassCat' ) for ind in range( len(KKMassBins) - 1 ) : KKCat.defineType( 'bin%d' % ind, ind ) obsSet.add(KKCat) from array import array KKBinsArray = array( 'd', KKMassBins ) from ROOT import RooBinning
dataNames = [ 'JpsiKK', 'JpsiKK_sigSWeight', 'JpsiKK_cbkgSWeight' ] cut = 'hlt2_biased==1' removeObs = [ 'wMC', 'mdau1', 'tagCatP2VV' ] #, 'polarity', 'hlt2_prescale', 'nPVCat', 'BpTCat' ] dataFilePathIn = 'P2VVDataSets20112012Reco14_I2Mass_6KKMassBins_4TagCats.root' dataFilePathOut = 'P2VVDataSets20112012Reco14_I2Mass_6KKMassBins_4TagCats_HLT2B.root' import P2VV.RooFitWrappers from ROOT import TObject, TFile, RooFit, RooDataSet, RooArgSet dataFile = TFile.Open(dataFilePathIn) newDataFile = TFile.Open( dataFilePathOut, 'RECREATE' ) newData = [ ] print 'read datasets from file "%s"' % dataFile.GetName() for dataName in dataNames : print 'reading dataset "%s"' % dataName data = dataFile.Get(dataName) data.Print() newArgSet = RooArgSet( data.get() ) for name in removeObs : newArgSet.remove( newArgSet.find(name) ) newData.append( RooDataSet( dataName, dataName, newArgSet, RooFit.Import(data), RooFit.Cut(cut) ) ) newData[-1].Print() newDataFile.Add( newData[-1] ) print 'write dataset to file "%s"' % newDataFile.GetName() newDataFile.Write( dataFilePathOut, TObject.kOverwrite )
# create data sets with final columns obsSetMain = obsSetNTuple + [ var for var in weightVars ] mainDataSet = dataTree.buildDataSet( Observables = obsSetMain, Name = 'JpsiKK', Title = 'JpsiKK', IndexName = 'index' , OrigDataSet = preSDataSet ) del preSDataSet del preDataSet dataTreeFile.Close() from ROOT import gROOT gROOT.cd('PyROOT:/') from ROOT import RooArgSet, RooDataSet dataSets = { } for it, var in enumerate(weightVars) : argSet = RooArgSet( mainDataSet.get() ) for remVar in weightVars : if remVar != var : argSet.remove( argSet.find( remVar.GetName() ) ) dataName = dataSetNameOut if it == 0 else 'JpsiKK_%d' % it dataSets[var] = RooDataSet( dataName, dataName, argSet, Import = mainDataSet, WeightVar = ( var.GetName(), True ) ) if not printYields : break print 'P2VV - INFO: createBs2JpsiKKDataSet: produced data sets:' mainDataSet.Print() for var in weightVars : dataSets[var].Print() if not printYields : break print if printYields : # print event yields print 'P2VV - INFO: createBs2JpsiKKDataSet: event yields:' allCats = [ mainDataSet.get().find( obsDict['runPeriod'][0] )
dataSets.pop('preS') dataTreeFile.Close() from ROOT import gROOT gROOT.cd('PyROOT:/') print 'P2VV - INFO: createB2CCFitNTuple: produced data set:\n' + ' ' * 13, dataSets['main'][0].Print() print # create weighted data sets from ROOT import RooArgSet obsSets = dict( [ ( var.GetName(), RooArgSet( dataSets['main'][0].get() ) ) for var in weightVars ] ) for varName, obsSet in obsSets.iteritems() : for var in weightVars : if var.GetName() == varName : continue obsSet.remove( obsSet.find( var.GetName() ) ) from ROOT import RooDataSet dataSets['sigSWeight'] = ( RooDataSet( 'JpsiKK_sigSWeight', 'JpsiKK_sigSWeight', obsSets['N_sigMass_sw'] , Import = dataSets['main'][0], WeightVar = ( weightVars[0].GetName(), True ) ), [ ] ) dataSets['cbkgSWeight'] = ( RooDataSet( 'JpsiKK_cbkgSWeight', 'JpsiKK_cbkgSWeight', obsSets['N_cbkgMass_sw'] , Import = dataSets['main'][0], WeightVar = ( weightVars[1].GetName(), True ) ), [ ] ) for sample, data in zip( samples, dataSets['main'][1] ) : dataSets['sigSWeight'][1].append( RooDataSet( 'JpsiKK_sigSWeight_' + sample[0], 'JpsiKK_sigSWeight', obsSets['N_sigMass_sw'] , Import = data, WeightVar = ( weightVars[0].GetName(), True ) ) ) dataSets['cbkgSWeight'][1].append( RooDataSet( 'JpsiKK_cbkgSWeight_' + sample[0], 'JpsiKK_cbkgSWeight', obsSets['N_cbkgMass_sw'] , Import = data, WeightVar = ( weightVars[1].GetName(), True ) ) ) print 'P2VV - INFO: createB2CCFitNTuple: signal data set:\n' + ' ' * 13, dataSets['sigSWeight'][0].Print() print
dataNames = [ 'JpsiKK_sigSWeight' ] #[ 'JpsiKK', 'JpsiKK_sigSWeight', 'JpsiKK_cbkgSWeight' ] removeObs = [ 'wMC', 'mdau1', 'tagCatP2VV' ] #, 'polarity', 'hlt2_prescale', 'nPVCat', 'BpTCat' ] dataFilePathIn = 'P2VVDataSets20112012Reco14_I2Mass_6KKMassBins_2TagCats_20140309.root' dataFilePathOut = 'P2VVDataSets2012Reco14_I2Mass_6KKMassBins_2TagCats_20140309.root' import P2VV.RooFitWrappers from ROOT import TObject, TFile, RooFit, RooDataSet, RooArgSet, RooCategory dataFile = TFile.Open(dataFilePathIn) newDataFile = TFile.Open( dataFilePathOut, 'RECREATE' ) newData = [ ] print 'read datasets from file "%s"' % dataFile.GetName() for dataName in dataNames : print 'reading dataset "%s"' % dataName data = dataFile.Get(dataName) data.Print() newArgSet = RooArgSet( data.get() ) for name in removeObs : newArgSet.remove( newArgSet.find(name) ) if runPeriod : newArgSet.remove( newArgSet.find('runPeriod') ) rp = RooCategory( 'runPeriod', 'runPeriod' ) rp.defineType( 'p%d' % runPeriod, runPeriod ) newArgSet.add(rp) newData.append( RooDataSet( dataName, dataName, newArgSet, RooFit.Import(data), RooFit.Cut(cut) ) ) newData[-1].Print() newDataFile.Add( newData[-1] ) print 'write dataset to file "%s"' % newDataFile.GetName() newDataFile.Write( dataFilePathOut, TObject.kOverwrite )
# workspace from P2VV.RooFitWrappers import RooObject ws = RooObject( workspace = 'JpsiphiWorkspace' ).ws() # read data set with events in two asymmetry categories print 'pdfAsymmetry: reading dataset with events in two asymmetry categories' from ROOT import TFile dataFile = TFile.Open(dataSetFilePath) dataSetAsym = dataFile.Get('asymData') dataFile.Close() dataSetAsym.Print() # create weighted data set from ROOT import RooProduct, RooArgSet, RooArgList obsSet = RooArgSet( dataSetAsym.get() ) prodList = RooArgList( obsSet.find('sigWeight') ) if applyPlotWeights : prodList.add( obsSet.find('dilution') ) weightVar = RooProduct( 'weightVar', 'weightVar', prodList ) weightVar = dataSetAsym.addColumn(weightVar) obsSet.add(weightVar) from ROOT import RooDataSet dataSetAsymW = RooDataSet( 'asymDataW', 'asymDataW', obsSet, Import = dataSetAsym, WeightVar = ( 'weightVar', True ) ) del dataSetAsym ws.put(dataSetAsymW) del dataSetAsymW dataSetAsymW = ws['asymDataW'] obsSet = RooArgSet( dataSetAsymW.get() ) dataSetAsymW.Print() # build PDF
dataFile.Write( dataSetFileOut, TObject.kOverwrite ) dataFile.Close() else : # read data set with events in two asymmetry categories print 'plotAsymmetry: reading dataset with events in two asymmetry categories' dataFile = TFile.Open(dataSetFileOut) dataSetAsym = dataFile.Get('asymData') dataFile.Close() dataSetAsym.Print() # create weighted data set from ROOT import RooProduct, RooArgSet, RooArgList obsSet = RooArgSet( dataSetAsym.get() ) prodList = RooArgList( obsSet.find('sigWeight') ) if applyDilWeights : prodList.add( obsSet.find('dilution') ) if applyAngWeights : prodList.add( obsSet.find( 'angWeight_%s' % applyAngWeights ) ) weightVar = RooProduct( 'weightVar', 'weightVar', prodList ) weightVar = dataSetAsym.addColumn(weightVar) obsSet.add(weightVar) dataSetAsymW = RooDataSet( 'asymDataW', 'asymDataW', obsSet, Import = dataSetAsym, WeightVar = ( 'weightVar', True ) ) del dataSetAsym ws.put(dataSetAsymW) del dataSetAsymW dataSetAsymW = ws['asymDataW'] obsSet = RooArgSet( dataSetAsymW.get() ) dataSetAsymW.Print() # get sums of weights
pdfs['cbkg'][stateName] = simMassPdf.getPdf(stateName).pdfList().at(1) else : pdfs['sig'][stateName] = simMassPdf.getPdf(stateName).pdfList().at(0).createIntegral( intSet, normSet ) pdfs['cbkg'][stateName] = simMassPdf.getPdf(stateName).pdfList().at(1).createIntegral( intSet, normSet ) for comp in comps : yields[comp]['total'] = sum( y for y in yields[comp].itervalues() ) print 'P2VV - INFO: signal and background yields:' for comp in comps : print ' %4s: %9.2f' % ( comp, yields[comp]['total'] ) # create datasets from ROOT import RooFit, RooDataSet, RooRealVar dataObs = RooArgSet( dataSet.get() ) if genMass : var = dataObs.find('mass') if var : dataObs.remove(var) splitData = dict( [ ( comp, dict( [ ( state.GetName(), RooDataSet('%s_%s' % (dataSet.GetName(), comp), dataSet.GetTitle(), dataObs) )\ for state in splitCat ] ) ) for comp in comps ] ) else : sigWeight = RooRealVar( 'sigWeight', 'sigWeight', 1. ) dataObs.add(sigWeight) if weightData : splitData = dict( [ ( comp, dict( [ ( 'total', RooDataSet( '%s_%s' % ( dataSet.GetName(), comp ), dataSet.GetTitle() , dataObs, RooFit.WeightVar(sigWeight) ) ) ] ) ) for comp in comps ] ) else : splitData = dict( [ ( comp, dict( [ ( 'total', RooDataSet( '%s_%s' % ( dataSet.GetName(), comp ), dataSet.GetTitle() , dataObs ) ) ] ) ) for comp in comps ] ) # function to get observable value from dataset def getObsVal( names, obsSet ) :
def readDataSet( config, # configuration dictionary ws, # workspace to which to add data set observables, # observables rangeName = None # name of range to clip dataset to ): """ read data set from given Ntuple (or a RooDataSet inside a workspace) into a RooDataSet arguments: config -- configuration dictionary (see below for relevant keys) ws -- workspace into which to import data from tuple observables -- RooArgSet containing the observables to be read rangeName -- optional, can be the name of a range of one observable, if the data read from the tuple needs to be explicitly clipped to that range for some reason the routine returns the data set that has been read in and stored inside ws. relevant configuration dictionary keys: 'DataFileName' -- file name of data file from which to read ntuple or data set 'DataSetNames' -- name (TTree or RooDataSet) of the data set to be read; more than one can be given in a dictionary, providing a mapping between the sample name and the data set to be read (see below for an explanation) 'DataWorkSpaceName' -- name of workspace to read data from (if any - leave None for reading tuples) 'DataSetCuts' -- cuts to apply to data sets on import - anything that RooDataSet.reduce will understand is permissible here (set to None to not apply any cuts on import) 'DataSetVarNameMapping' -- mapping from variable names in set of observables to what these variable names are called in the tuple/workspace to be imported "special" observable names: The routine treats some variable names special on import based on their likely meaning: 'weight' -- this variable name must be used to read in (s)weighted events 'qf' -- final state charge (e.g. +1 for K+ vs -1 for K-); only the sign is important here, and the import code enforces that 'qt' -- tagging decision; this can be any integer number (positive or negative); if the tuple should contain a float/double with that information, it is rounded appropriately 'mistag' -- predicted mistag; the import code makes sure that events with qt == 0 have mistag = 0.5 'sample' -- if more than one final state is studied (e.g. Ds final states phipi, kstk, nonres, kpipi, pipipi), the events for these subsamples often reside in different samples; therefore the config dictionary entry 'DataSetNames' can contain a dictionary which maps the category labels (phipi etc) to the names of the data samples in the ROOT file/workspace The config dict key 'DataSetVarNameMapping' contains a useful feature: Instead of providing a one-to-one-mapping of observables to tuple/data set names, an observable can be calculated from more than one tuple column. This is useful e.g. to convert a tuple that's stored the tagging decision as untagged/mixed/unmixed, or to sum up sweights for the different samples. Most simple formulae should be supported, but constants in scientific notation (1.0E+00) are not for now (until someone write a better parser for this). Example: @code seed = 42 # it's easy to modify the filename depending on the seed number configdict = { # file to read from 'DataFileName': '/some/path/to/file/with/toy_%04d.root' % seed, # data set is in a workspace already 'DataWorkSpaceName': 'FitMeToolWS', # name of data set inside workspace 'DataSetNames': 'combData', # mapping between observables and variable name in data set 'DataSetVarNameMapping': { 'sample': 'sample', 'mass': 'lab0_MassFitConsD_M', 'pidk': 'lab1_PIDK', 'dsmass': 'lab2_MM', 'time': 'lab0_LifetimeFit_ctau', 'timeerr': 'lab0_LifetimeFit_ctauErr', 'mistag': 'tagOmegaComb', 'qf': 'lab1_ID', 'qt': ' tagDecComb', # sweights need to be combined from different branches in this # case, only one of the branches is ever set to a non-zero value, # depending on which subsample the event is in 'weight': ('nSig_both_nonres_Evts_sw+nSig_both_phipi_Evts_sw+' 'nSig_both_kstk_Evts_sw+nSig_both_kpipi_Evts_sw+' 'nSig_both_pipipi_Evts_sw') } } # define all observables somewhere, and put the into a RooArgSet called obs # import observables in to a workspace saved in ws # now read the data set data = readDataSet(configdict, ws, observables) @endcode """ from ROOT import ( TFile, RooWorkspace, RooRealVar, RooCategory, RooBinningCategory, RooUniformBinning, RooMappedCategory, RooDataSet, RooArgSet, RooArgList ) import sys, math # local little helper routine def round_to_even(x): xfl = int(math.floor(x)) rem = x - xfl if rem < 0.5: return xfl elif rem > 0.5: return xfl + 1 else: if xfl % 2: return xfl + 1 else: return xfl # another small helper routine def tokenize(s, delims = '+-*/()?:'): # FIXME: this goes wrong for numerical constants like 1.4e-3 # proposed solution: regexp for general floating point constants, # replace occurences of matches with empty string delims = [ c for c in delims ] delims.insert(0, None) for delim in delims: tmp = s.split(delim) tmp = list(set(( s + ' ' for s in tmp))) s = ''.join(tmp) tmp = list(set(s.split(None))) return tmp # figure out which names from the mapping we need - look at the observables names = () for n in config['DataSetVarNameMapping'].keys(): if None != observables.find(n): names += (n,) # build RooArgSets and maps with source and destination variables dmap = { } for k in names: dmap[k] = observables.find(k) if None in dmap.values(): raise NameError('Some variables not found in destination: %s' % str(dmap)) dset = RooArgSet() for v in dmap.values(): dset.add(v) if None != dset.find('weight'): # RooFit insists on weight variable being first in set tmpset = RooArgSet() tmpset.add(dset.find('weight')) it = dset.fwdIterator() while True: obj = it.next() if None == obj: break if 'weight' == obj.GetName(): continue tmpset.add(obj) dset = tmpset del tmpset ddata = RooDataSet('agglomeration', 'of positronic circuits', dset, 'weight') else: ddata = RooDataSet('agglomeration', 'of positronic circuits', dset) # open file with data sets f = TFile(config['DataFileName'], 'READ') # get workspace fws = f.Get(config['DataWorkSpaceName']) ROOT.SetOwnership(fws, True) if None == fws or not fws.InheritsFrom('RooWorkspace'): # ok, no workspace, so try to read a tree of the same name and # synthesize a workspace from ROOT import RooWorkspace, RooDataSet, RooArgList fws = RooWorkspace(config['DataWorkSpaceName']) iset = RooArgSet() addiset = RooArgList() it = observables.fwdIterator() while True: obj = it.next() if None == obj: break name = config['DataSetVarNameMapping'][obj.GetName()] vnames = tokenize(name) if len(vnames) > 1 and not obj.InheritsFrom('RooAbsReal'): print 'Error: Formulae not supported for categories' return None if obj.InheritsFrom('RooAbsReal'): if 1 == len(vnames): # simple case, just add variable var = WS(fws, RooRealVar(name, name, -sys.float_info.max, sys.float_info.max)) iset.addClone(var) else: # complicated case - add a bunch of observables, and # compute something in a RooFormulaVar from ROOT import RooFormulaVar args = RooArgList() for n in vnames: try: # skip simple numerical factors float(n) except: var = iset.find(n) if None == var: var = WS(fws, RooRealVar(n, n, -sys.float_info.max, sys.float_info.max)) iset.addClone(var) args.add(iset.find(n)) var = WS(fws, RooFormulaVar(name, name, name, args)) addiset.addClone(var) else: for dsname in ((config['DataSetNames'], ) if type(config['DataSetNames']) == str else config['DataSetNames']): break leaf = f.Get(dsname).GetLeaf(name) if None == leaf: leaf = f.Get(dsname).GetLeaf(name + '_idx') if leaf.GetTypeName() in ( 'char', 'unsigned char', 'Char_t', 'UChar_t', 'short', 'unsigned short', 'Short_t', 'UShort_t', 'int', 'unsigned', 'unsigned int', 'Int_t', 'UInt_t', 'long', 'unsigned long', 'Long_t', 'ULong_t', 'Long64_t', 'ULong64_t', 'long long', 'unsigned long long'): var = WS(fws, RooCategory(name, name)) tit = obj.typeIterator() ROOT.SetOwnership(tit, True) while True: tobj = tit.Next() if None == tobj: break var.defineType(tobj.GetName(), tobj.getVal()) else: var = WS(fws, RooRealVar(name, name, -sys.float_info.max, sys.float_info.max)) iset.addClone(var) for dsname in ((config['DataSetNames'], ) if type(config['DataSetNames']) == str else config['DataSetNames']): tmpds = WS(fws, RooDataSet(dsname, dsname,f.Get(dsname), iset), []) if 0 != addiset.getSize(): # need to add columns with RooFormulaVars tmpds.addColumns(addiset) del tmpds # local data conversion routine def doIt(config, rangeName, dsname, sname, names, dmap, dset, ddata, fws): sdata = fws.obj(dsname) if None == sdata: return 0 if None != config['DataSetCuts']: # apply any user-supplied cuts newsdata = sdata.reduce(config['DataSetCuts']) ROOT.SetOwnership(newsdata, True) del sdata sdata = newsdata del newsdata sset = sdata.get() smap = { } for k in names: smap[k] = sset.find(config['DataSetVarNameMapping'][k]) if 'sample' in smap.keys() and None == smap['sample'] and None != sname: smap.pop('sample') dmap['sample'].setLabel(sname) if None in smap.values(): raise NameError('Some variables not found in source: %s' % str(smap)) # # additional complication: toys save decay time in ps, data is in nm # # figure out which time conversion factor to use # timeConvFactor = 1e9 / 2.99792458e8 # meantime = sdata.mean(smap['time']) # if ((dmap['time'].getMin() <= meantime and # meantime <= dmap['time'].getMax() and config['IsToy']) or # not config['IsToy']): # timeConvFactor = 1. # print 'DEBUG: Importing data sample meantime = %f, timeConvFactor = %f' % ( # meantime, timeConvFactor) timeConvFactor = 1. # loop over all entries of data set ninwindow = 0 if None != sname: sys.stdout.write('Dataset conversion and fixup: %s: progress: ' % sname) else: sys.stdout.write('Dataset conversion and fixup: progress: ') for i in xrange(0, sdata.numEntries()): sdata.get(i) if 0 == i % 128: sys.stdout.write('*') vals = { } for vname in smap.keys(): obj = smap[vname] if obj.InheritsFrom('RooAbsReal'): val = obj.getVal() vals[vname] = val else: val = obj.getIndex() vals[vname] = val # first fixup: apply time/timeerr conversion factor if 'time' in dmap.keys(): vals['time'] *= timeConvFactor if 'timeerr' in dmap.keys(): vals['timeerr'] *= timeConvFactor # second fixup: only sign of qf is important if 'qf' in dmap.keys(): vals['qf'] = 1 if vals['qf'] > 0.5 else (-1 if vals['qf'] < -0.5 else 0.) # third fixup: untagged events are forced to 0.5 mistag if ('qt' in dmap.keys() and 'mistag' in dmap.keys() and 0 == vals['qt']): vals['mistag'] = 0.5 # apply cuts inrange = True for vname in dmap.keys(): if not dmap[vname].InheritsFrom('RooAbsReal'): continue # no need to cut on untagged events if 'mistag' == vname and 0 == vals['qt']: continue if None != rangeName and dmap[vname].hasRange(rangeName): if (dmap[vname].getMin(rangeName) > vals[vname] or vals[vname] >= dmap[vname].getMax(rangeName)): inrange = False break else: if (dmap[vname].getMin() > vals[vname] or vals[vname] >= dmap[vname].getMax()): inrange = False break # skip cuts which are not within the allowed range if not inrange: continue # copy values over, doing real-category conversions as needed for vname in smap.keys(): dvar, svar = dmap[vname], vals[vname] if dvar.InheritsFrom('RooAbsRealLValue'): if float == type(svar): dvar.setVal(svar) elif int == type(svar): dvar.setVal(svar) elif dvar.InheritsFrom('RooAbsCategoryLValue'): if int == type(svar): dvar.setIndex(svar) elif float == type(svar): dvar.setIndex(round_to_even(svar)) if 'weight' in dmap: ddata.add(dset, vals['weight']) else: ddata.add(dset) ninwindow = ninwindow + 1 del sdata sys.stdout.write(', done - %d events\n' % ninwindow) return ninwindow ninwindow = 0 if type(config['DataSetNames']) == str: ninwindow += doIt(config, rangeName, config['DataSetNames'], None, names, dmap, dset, ddata, fws) else: for sname in config['DataSetNames'].keys(): ninwindow += doIt(config, rangeName, config['DataSetNames'][sname], sname, names, dmap, dset, ddata, fws) # free workspace and close file del fws f.Close() del f # put the new dataset into our proper workspace ddata = WS(ws, ddata, []) # for debugging if config['Debug']: ddata.Print('v') if 'qt' in dmap.keys(): data.table(dmap['qt']).Print('v') if 'qf' in dmap.keys(): data.table(dmap['qf']).Print('v') if 'qf' in dmap.keys() and 'qt' in dmap.keys(): data.table(RooArgSet(dmap['qt'], dmap['qf'])).Print('v') if 'sample' in dmap.keys(): data.table(dmap['sample']).Print('v') # all done, return Data to the bridge return ddata
from ROOT import TFile, RooArgSet dataFile = TFile.Open('P2VVDataSets20112012Reco14_I2Mass_6KKMassBins_2TagCats_kinematics.root') data = dataFile.Get('JpsiKK_sigSWeight') dataFile.Close() varSet = RooArgSet( data.get() ) for var in [ 'wMC', 'hlt2_prescale', 'polarity', 'tagCatP2VV', 'nPVCat', 'BpTCat', 'runPeriod' ] : varSet.remove( varSet.find(var) ) from ROOT import RooCategory varSet11 = RooArgSet(varSet) varSet12 = RooArgSet(varSet) runPeriod11 = RooCategory( 'runPeriod', 'runPeriod' ) runPeriod12 = RooCategory( 'runPeriod', 'runPeriod' ) runPeriod11.defineType( 'p2011', 2011 ) runPeriod12.defineType( 'p2012', 2012 ) varSet11.add(runPeriod11) varSet12.add(runPeriod12) from ROOT import RooFit, RooDataSet data11 = RooDataSet( data.GetName(), data.GetTitle(), varSet11, RooFit.Import(data), RooFit.Cut('hlt2_biased==1 && runPeriod==2011') ) data12 = RooDataSet( data.GetName(), data.GetTitle(), varSet12, RooFit.Import(data), RooFit.Cut('hlt2_biased==1 && runPeriod==2012') ) from ROOT import TObject dataFile11 = TFile.Open( 'P2VVDataSets2011Reco14_I2Mass_6KKMassBins_2TagCats_kinematics_HLT2B.root', 'RECREATE' ) dataFile11.Add(data11) dataFile11.Write( 'P2VVDataSets2011Reco14_I2Mass_6KKMassBins_2TagCats_kinematics_HLT2B.root', TObject.kOverwrite ) dataFile11.Close() dataFile12 = TFile.Open( 'P2VVDataSets2012Reco14_I2Mass_6KKMassBins_2TagCats_kinematics_HLT2B.root', 'RECREATE' ) dataFile12.Add(data12) dataFile12.Write( 'P2VVDataSets2012Reco14_I2Mass_6KKMassBins_2TagCats_kinematics_HLT2B.root', TObject.kOverwrite ) dataFile12.Close()