def make_fractions_single(output_dir,
channel,
variable,
components_dict,
category='inclusive',
systematic='nominal'):
'''This funciton aims at producing a root file containing all
histograms needed for datacards. To do so, provide a dict of components
(class Component) that have the ROOT histograms to be used.
Gives also the output directory and the variable name, so that you can
make datacards for different variables.'''
rootfilename = '_'.join(['htt', channel, 'for_FF_fractions'])
rootfile = TFile('{}/{}.root'.format(output_dir, rootfilename), 'UPDATE')
rootdirname = '_'.join([channels_names[channel], variable, category])
rootdir = rootfile.GetDirectory(rootdirname)
if not rootdir:
rootdir = TDirectoryFile(rootdirname, rootdirname)
rootdir.cd()
for key, component in components_dict.iteritems():
histname = '_'.join([key, systematic])
if systematic == 'nominal':
histname = key
else:
histname = histname.replace('up', 'Up')
histname = histname.replace('down', 'Down')
if rootdir.Get(histname):
continue
hist = component.histogram.Clone(histname)
if histname[:len("fakes_")] == "fakes_":
hist.Scale(-1)
hist.SetTitle(key)
hist.Write()
rootfile.Close()
def FiltFunc(args):
with open(args.cfgFileName, 'r') as ymlCfgFile:
inputCfg = yaml.load(ymlCfgFile, yaml.FullLoader)
with open(args.cutSetFileNames[0], 'r') as ymlCutSetFile:
cutSetCfg = yaml.load(ymlCutSetFile, yaml.FullLoader)
cutVars = cutSetCfg['cutvars']
axesToKeep = cutSetCfg['axestokeep']
infilenames = inputCfg['filename']
if not isinstance(infilenames, list):
infilenames = [infilenames]
for iFile, infilename in enumerate(infilenames):
sparseReco, sparseGen = LoadSparseFromTask(infilename, inputCfg)
# filter sparses
sparseFiltReco = FilterSparses(sparseReco, cutVars, axesToKeep)
if inputCfg['isMC']:
sparseFiltGen = FilterSparses(sparseGen, cutVars, axesToKeep)
# plot filtered sparses (each variable vs pt)
if args.plot:
PlotFiltVarsVsPt(sparseFiltReco, 'cReco{0}'.format(iFile))
if inputCfg['isMC']:
PlotFiltVarsVsPt(sparseFiltGen, 'cGen{0}'.format(iFile))
# get other objects from original file
inlist = LoadListFromTask(infilename, inputCfg)
_, normCounter = LoadNormObjFromTask(infilename, inputCfg)
cutObj, cutObjName = LoadCutObjFromTask(infilename, inputCfg)
for sparse in sparseFiltReco.values():
sparsetodel = inlist.FindObject(sparse.GetName())
inlist.Remove(sparsetodel)
inlist.Add(sparse)
if inputCfg['isMC']:
for sparse in sparseFiltGen.values():
sparsetodel = inlist.FindObject(sparse.GetName())
inlist.Remove(sparsetodel)
inlist.Add(sparse)
# save new file with filtered sparses
outfilename = infilename
if args.suffix:
outfilename = outfilename.replace(
'.root', '{0}.root'.format(args.suffix))
print('Saving filtered ThnSparses in file', outfilename)
outfile = TFile(outfilename, 'recreate')
outdir = TDirectoryFile(inputCfg['dirname'], inputCfg['dirname'])
outdir.Write(inputCfg['dirname'])
outdir.cd()
inlist.Write(inputCfg['listname'], 1)
cutObj.Write(cutObjName)
normCounter.Write()
outfile.Close()
def FiltFuncV2(args):
with open(args.cfgFileName, 'r') as ymlCfgFile:
inputCfg = yaml.load(ymlCfgFile, yaml.FullLoader)
cutSetsCfg = []
for cutFile in args.cutSetFileNames:
with open(cutFile, 'r') as file:
cutCfg = yaml.load(file, yaml.FullLoader)
cutSetsCfg.append(cutCfg)
if not len(cutSetsCfg) == len(inputCfg['dirname']) == len(
inputCfg['listname']):
print('Wrong number of cut sets, dir names or list names')
return
sparseList = LoadSparseFromTaskV2(inputCfg)
sparseListFilt = []
for sparse, cutSet in zip(sparseList, cutSetsCfg):
sparseFilt = FilterSparsesV2(sparse, cutSet['cutvars'],
cutSet['axestokeep'])
sparseListFilt.append(sparseFilt)
for sparse in sparseListFilt[1:]:
sparseListFilt[0].Add(sparse)
# get other objects from original file
inlist = LoadListFromTaskV2(inputCfg['filename'], inputCfg['dirname'][0],
inputCfg['listname'][0])
sparsetodel = inlist.FindObject(sparseList[0].GetName())
inlist.Remove(sparsetodel)
inlist.Add(sparseListFilt[0])
# save new file with filtered sparses
outfilename = inputCfg['outfilename']
print('Saving filtered ThnSparses in file', outfilename)
outfile = TFile(outfilename, 'recreate')
outdir = TDirectoryFile(inputCfg['outdirname'], inputCfg['outdirname'])
outdir.Write(inputCfg['outdirname'])
outdir.cd()
inlist.Write(inputCfg['outlistname'], 1)
outfile.Close()
def make_datacards(output_dir, channel, variable, components_dict, category='inclusive', systematics=['nominal']):
'''This funciton aims at producing a root file containing all
histograms needed for datacards. To do so, provide a dict of components
(class Component) that have the ROOT histograms to be used.
Gives also the output directory and the variable name, so that you can
make datacards for different variables.'''
rootfilename = '_'.join(['htt', channel+'.inputs', 'datacards', variable])
rootfile = TFile('{}/{}.root'.format(output_dir, rootfilename), 'UPDATE')
rootdirname = '_'.join([channels_names[channel], category])
rootdir = TDirectoryFile(rootdirname, rootdirname)
rootdir.cd()
for systematic in systematics:
for key, component in components_dict[systematic].iteritems():
histname = '_'.join([key,systematic])
if systematic == 'nominal':
histname = key
elif histname in syst_rename_dir:
histname = syst_rename_dir[histname]
else:
histname = histname.replace('up','Up')
histname = histname.replace('down','Down')
hist = component.histogram.Clone(histname)
hist.SetMinimum(0.000001)
hist.SetTitle(key)
hist.Write()
if systematic in syst_split_list:
hist_list = []
for sys_type in types_dir[key]:
if 'Down' in histname:
new_histname = histname.replace('Down',sys_type+'Down')
elif 'Up' in histname:
new_histname = histname.replace('Up',sys_type+'Up')
hist_list.append(component.histogram.Clone(new_histname))
hist_list[-1].SetTitle(key)
hist_list[-1].Write()
rootfile.Close()
print('Datacards for category {} and variable {} made.'.format(category, variable))
vartitles = {
1: '#it{p}_{T} (GeV/#it{c})',
2: '#Delta#it{M}_{KK} (MeV/#it{c})',
3: 'decay length (#mum #times 0.1)',
4: 'decay length xy (#mum #times 0.1)',
5: 'normalised decay length xy',
6: 'cos(#theta_{p}) #times 100',
7: 'cos(#theta_{p}^{xy}) #times 100',
8: 'sigma vertex (#mum #times 0.1)',
10: '|cos^{3}(#piK#phi)|',
11: 'max norm #it{d}_{0}-#it{d}_{0}^{exp}',
12: 'impact parameter xy'
}
outfile = TFile(ARGS.outFileName, 'recreate')
dir1D = TDirectoryFile('Distr1D', 'Distr1D')
dir1D.Write()
outfile.cd()
dirVsPt = TDirectoryFile('DistrVsPt', 'DistrVsPt')
dirVsPt.Write()
outfile.cd()
dirVsML = TDirectoryFile('DistrVsML', 'DistrVsML')
dirVsML.Write()
cVars, cVarsNorm, cVarsVsPt, cVarsVsML = {}, {}, {}, {}
hVars, hVarsSel, hVarsNorm, hVarsSelNorm, hVarsVsPt, hVarsSelVsPt, hVarsVsML, hVarsSelVsML = (
{} for iDic in range(8))
listoffigures = []
for iPt, (ptmin,
ptmax) in enumerate(zip(cutVars['Pt']['min'], cutVars['Pt']['max'])):
else:
RaaFD = RaaFD_config
# load constant terms
nExpEv = inputCfg['nExpectedEvents']
Taa = inputCfg['Taa']
sigmaMB = inputCfg['sigmaMB']
# set batch mode if enabled
if args.batch:
gROOT.SetBatch(True)
gROOT.ProcessLine("gErrorIgnoreLevel = kFatal;")
# output file with TNtuple
outFile = TFile(args.outFileName, 'recreate')
outDirFitSB = TDirectoryFile('SBfits', 'SBfits')
outDirFitSB.Write()
outDirFitSBPt = []
outFile.cd()
outDirPlots = TDirectoryFile('plots', 'plots')
outDirPlots.Write()
outDirPlotsPt = []
estNames = {
'Signif': 'expected significance',
'SoverB': 'S/B',
'S': 'expected signal',
'B': 'expected background',
'EffAccPrompt': '(Acc#times#font[152]{e})_{prompt}',
'EffAccFD': '(Acc#times#font[152]{e})_{FD}',
def main(args):
print(args)
channels = args.channels.split(',')
categories = args.categories.split(',')
nickname = os.path.basename(args.input).replace(".root", "")
DNN_jsons = args.DNNs.split(',')
DNN_jsons = [f for f in DNN_jsons if f != ""]
models = {}
inputs = []
model_number = 1
for DNN_json in DNN_jsons:
DNN_object = DNN_model_from_json(DNN_json)
models["DNN{}".format(model_number)] = DNN_object
model_number += 1
inputs += DNN_object.inputs
# load root file and create friend tree
root_file_input = args.input
output_path = os.path.join(args.output_dir, nickname)
if not os.path.exists(output_path):
os.makedirs(output_path)
root_file_output = os.path.join(
output_path,
"_".join(
filter(
None,
[
nickname,
args.pipeline,
str(args.first_entry),
str(args.last_entry),
],
)) + ".root",
)
root_file_in = TFile.Open(root_file_input, 'read')
if 'all' in channels:
channels = set(
[k.GetName().split('_')[0] for k in root_file_in.GetListOfKeys()])
if 'all' in categories:
categories = set([
k.GetName().split('_')[-1] for k in root_file_in.GetListOfKeys()
if any([c == k.GetName().split('_')[0] for c in channels])
])
if not args.dry:
root_file_out = TFile.Open(root_file_output, 'recreate')
print("Opened new file")
first_pass = True
for channel in channels:
for cat in categories:
rootdirname = '{}_{}'.format(channel, cat)
print(rootdirname)
if rootdirname not in [
k.GetName() for k in root_file_in.GetListOfKeys()
]:
continue
if rootdirname != args.pipeline and args.pipeline != None:
continue
print('process pipeline: %s_%s' % (channel, cat))
if not first_pass and not args.dry:
root_file_out = TFile.Open(root_file_output, 'update')
first_pass = False
if not args.dry:
rootdir = TDirectoryFile(rootdirname, rootdirname)
rootdir.cd()
tree = TTree(args.tree, args.tree)
leafValues = {}
for model in models:
leafValues[model] = array.array("f", [0])
tree_from_root_file_in = root_file_in.Get(rootdirname).Get(
args.tree)
if not args.dry:
print("Filling new branch in tree...")
for model in models:
print(model)
newBranch = tree.Branch(model, leafValues[model],
"{}/F".format(model))
first_entry = args.first_entry
last_entry = tree_from_root_file_in.GetEntries()
if args.last_entry >= first_entry and args.last_entry < last_entry:
last_entry = args.last_entry
k = 0
for evt in tree_from_root_file_in:
if k >= first_entry and k <= last_entry:
for model in models:
leafValues[model][0] = models[model].predict(
evt, channel)
tree.Fill()
elif k > last_entry:
break
k += 1
print("Filled.")
if not args.dry:
tree.Write(args.tree, kOverwrite)
root_file_out.Close()
print("Done")
hRawYieldsFracGaus2.Write()
hRawYieldsSecPeak.Write()
hRawYieldsMeanSecPeak.Write()
hRawYieldsSigmaSecPeak.Write()
hRawYieldsSignificanceSecPeak.Write()
hRawYieldsSigmaRatioSecondFirstPeak.Write()
hRawYieldsSoverBSecPeak.Write()
hRawYieldsSignalSecPeak.Write()
hRawYieldsBkgSecPeak.Write()
hRawYieldsTrue.Write()
hRawYieldsSecPeakTrue.Write()
hRelDiffRawYieldsFitTrue.Write()
hRelDiffRawYieldsSecPeakFitTrue.Write()
hEv.Write()
if not args.isMC:
dirSB = TDirectoryFile('SandBDiffNsigma', 'SandBDiffNsigma')
dirSB.Write()
dirSB.cd()
for iS, _ in enumerate(nSigma4SandB):
hRawYieldsSignalDiffSigma[iS].Write()
hRawYieldsBkgDiffSigma[iS].Write()
hRawYieldsSoverBDiffSigma[iS].Write()
hRawYieldsSignifDiffSigma[iS].Write()
dirSB.Close()
outFile.Close()
outFileNamePDF = args.outFileName.replace('.root', '.pdf')
outFileNameResPDF = outFileNamePDF.replace('.pdf', '_Residuals.pdf')
for iCanv, (cM, cR) in enumerate(zip(cMass, cResiduals)):
if iCanv == 0 and nCanvases > 1:
cM.SaveAs(f'{outFileNamePDF}[')
leg2D.SetTextSize(0.045)
leg2D.SetFillStyle(0)
leg2D.AddEntry(list(hNsigma['TPC']['Pi']['0'].values())[0], 'w/o ML sel', 'fp')
leg2D.AddEntry(
list(hNsigmaSel['TPC']['Pi']['0'].values())[0], 'w/ ML sel', 'fp')
#plot on canvases and save on root file
listoffigures = []
outfile = TFile(ARGS.outFileName, 'recreate')
cNsigma, cNsigma02, cNsigmaNorm, dirNsigma = {}, {}, {}, {}
for iDet, det in enumerate(hNsigma):
cNsigma[det] = {}
cNsigmaNorm[det] = {}
cNsigma02[det] = {}
outfile.cd()
dirNsigma[det] = TDirectoryFile(det, det)
dirNsigma[det].Write()
dirNsigma[det].cd()
for iPt, (ptmin, ptmax) in enumerate(
zip(cutVars['Pt']['min'], cutVars['Pt']['max'])):
cNsigma[det]['Pt{:.0f}_{:.0f}'.format(ptmin, ptmax)] = \
TCanvas('cNsigma{:s}_Pt{:.0f}_{:.0f}'.format(
det, ptmin, ptmax), '', 1920, 1080)
cNsigma[det]['Pt{:.0f}_{:.0f}'.format(ptmin, ptmax)].Divide(3, 2)
cNsigmaNorm[det]['Pt{:.0f}_{:.0f}'.format(ptmin, ptmax)] = \
TCanvas('cNsigmaNorm{:s}_Pt{:.0f}_{:.0f}'.format(
det, ptmin, ptmax), '', 1920, 1080)
cNsigmaNorm[det]['Pt{:.0f}_{:.0f}'.format(ptmin, ptmax)].Divide(3, 2)
if det != 'TPCTOF':
cNsigma02[det]['Pt{:.0f}_{:.0f}'.format(ptmin, ptmax)] = \
TCanvas('cNsigma02{:s}_Pt{:.0f}_{:.0f}'.format(
def main(args):
print(args)
channels = args.channels.split(',')
categories = args.categories.split(',')
nickname = os.path.basename(args.input).replace(".root", "")
XGB_jsons = args.XGBs.split(',')
XGB_jsons = [f for f in XGB_jsons if f != ""]
models = {}
inputs = []
for XGB_json in XGB_jsons:
XGB_object = XGB_model_from_json(XGB_json)
models[XGB_object.name] = XGB_object
inputs += XGB_object.inputs
# load root file and create friend tree
root_file_input = args.input
output_path = os.path.join(args.output_dir, nickname)
if not os.path.exists(output_path):
os.makedirs(output_path)
root_file_output = os.path.join(
output_path,
"_".join(
filter(
None,
[
nickname,
args.pipeline,
str(args.first_entry),
str(args.last_entry),
],
)) + ".root",
)
root_file_in = uproot.open(root_file_input)
if 'all' in channels:
channels = set([k.split('_')[0] for k in root_file_in.keys()])
if 'all' in categories:
categories = set([
k.split('_')[-1].split(';')[0] for k in root_file_in.keys()
if any([c in k for c in channels])
])
if not args.dry:
root_file_old = None
if not args.recreate:
os.system(
"if [[ -e {root_file_output} ]] ; then mv {root_file_output} {root_file_output}_to_update ; fi"
.format(root_file_output=root_file_output))
root_file_old = TFile("{}_to_update".format(root_file_output),
'read')
root_file_out = TFile(root_file_output, 'recreate')
print("Opened new file")
first_pass = True
for channel in channels:
for cat in categories:
rootdirname = '{}_{}'.format(channel, cat)
if rootdirname not in root_file_in.keys() and "{};1".format(
rootdirname) not in root_file_in.keys():
continue
if rootdirname != args.pipeline and args.pipeline != None:
continue
print('process pipeline: %s_%s' % (channel, cat))
if not first_pass and not args.dry:
root_file_out = TFile(root_file_output, 'update')
first_pass = False
if not args.dry:
rootdir_old = False
if root_file_old:
rootdir_old = root_file_old.GetDirectory(rootdirname)
if not rootdir_old:
already_rootdir = False
else:
already_rootdir = True
rootdir = TDirectoryFile(rootdirname, rootdirname)
rootdir.cd()
tree_old = False
if already_rootdir:
if not args.recreate:
tree_old = rootdir_old.Get(args.tree)
tree = TTree(args.tree, args.tree)
old_models = []
if tree_old:
old_models = [
model.GetName()
for model in [tree_old.GetListOfBranches()][0]
]
if len(old_models) > 0:
root_file_out_old = uproot.open(
"{}_to_update".format(root_file_output))
models = {i: models[i] for i in models if i not in old_models}
all_models = old_models + [k for k in models]
leafValues = {}
for model in all_models:
leafValues[model] = array.array("f", [0])
if args.pandas:
df = root_file_in[rootdirname][args.tree].pandas.df()
if tree_old:
df_old = root_file_out_old[rootdirname][
args.tree].pandas.df()
else:
_df = root_file_in[rootdirname][args.tree].arrays()
df = pandas.DataFrame()
keys_to_export = set(inputs +
["pt_1", "pt_2", "phi_1", "phi_2"])
for key in ["N_neutrinos_reco", "mt_tt"]:
if key in keys_to_export:
keys_to_export.remove(key)
for k in keys_to_export:
df[k] = _df[str.encode(k)]
if tree_old:
_df_old = root_file_out_old[rootdirname][
args.tree].arrays()
df_old = pandas.DataFrame()
keys_to_export = old_models
for k in keys_to_export:
df_old[k] = _df_old[str.encode(k)]
df["mt_tt"] = (2 * df["pt_1"] * df["pt_2"] *
(1 - np.cos(df["phi_1"] - df["phi_2"])))**.5
df["N_neutrinos_reco"] = N_neutrinos_in_channel[channel] * np.ones(
len(df[inputs[0]]), dtype='int')
# remove values set at -10 by default to match training settings
for variable in ["jpt_r", "jeta_r", "jphi_r", "Njet_r"]:
if variable in inputs:
df[variable].values[df[variable].values < 0] = 0
for model in models:
print("Predicting with {}...".format(model))
df[model] = models[model].predict(df)
if not args.dry:
print("Filling new branch in tree...")
for model in all_models:
newBranch = tree.Branch(model, leafValues[model],
"prediction/F")
first_entry = args.first_entry
last_entry = len(df[model].values)
if args.last_entry > first_entry and args.last_entry < len(
df[model].values):
last_entry = args.last_entry
for k in range(first_entry, last_entry + 1):
for model in all_models:
if model in old_models:
leafValues[model][0] = df_old[model].values[k]
else:
leafValues[model][0] = df[model].values[k]
tree.Fill()
print("Filled.")
rootdir.Remove(rootdir.Get(args.tree))
tree.Write(args.tree, kOverwrite)
root_file_out.Close()
os.system("rm -rf {}_to_update".format(root_file_output))
hSgn[-1].SetDirectory(0)
hBkg[-1].SetDirectory(0)
hSgnMin[-1].SetDirectory(0)
hSgnMax[-1].SetDirectory(0)
hSignif[-1].SetDirectory(0)
hSignifMin[-1].SetDirectory(0)
hSignifMax[-1].SetDirectory(0)
hSoverB[-1].SetDirectory(0)
hSoverBMin[-1].SetDirectory(0)
hSoverBMax[-1].SetDirectory(0)
hEff[-1].SetDirectory(0)
hAcc[-1].SetDirectory(0)
hEffAcc[-1].SetDirectory(0)
outFile.cd()
outDir = TDirectoryFile(meson, meson)
outDir.Write()
outDir.cd()
hSgn[-1].Write()
hSgnMin[-1].Write()
hSgnMax[-1].Write()
for iPt, _ in enumerate(hMassSignal):
hMassSignal[iPt].Write()
hMassSignalMin[iPt].Write()
hMassSignalMax[iPt].Write()
hBkg[-1].Write()
for iPt, _ in enumerate(hMassSignal):
hMassBkg[iPt].Write()
hMassBkgMin[iPt].Write()
hMassBkgMax[iPt].Write()
hSignif[-1].Write()
