def getEfficiency(datasets, numerator="Numerator", denominator="Denominator"):
# statOption = ROOT.TEfficiency.kFNormal
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
# statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
first = True
isData = False
teff = ROOT.TEfficiency()
for dataset in datasets:
n = dataset.getDatasetRootHisto(numerator).getHistogram()
d = dataset.getDatasetRootHisto(denominator).getHistogram()
if d.GetEntries() == 0:
continue
checkNegatives(n, d)
# removeNegatives(n)
# removeNegatives(d)
print dataset.getName(), "entries", n.GetEntries(), d.GetEntries()
print " bins", n.GetNbinsX(), d.GetNbinsX()
print " lowedge", n.GetBinLowEdge(1), d.GetBinLowEdge(1)
eff = ROOT.TEfficiency(n, d)
eff.SetStatisticOption(statOption)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection() / d.GetEntries()
for i in range(1, d.GetNbinsX() + 1):
print " bin", i, d.GetBinLowEdge(i), n.GetBinContent(
i), d.GetBinContent(i)
eff.SetWeight(weight)
if first:
teff = eff
if dataset.isData():
tn = n
td = d
first = False
else:
teff.Add(eff)
if dataset.isData():
tn.Add(n)
td.Add(d)
if isData:
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(self.statOption)
return teff
def getEfficiency(datasets,numerator="Numerator",denominator="Denominator"):
# statOption = ROOT.TEfficiency.kFNormal
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
# statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
first = True
isData = False
teff = ROOT.TEfficiency()
for dataset in datasets:
n = dataset.getDatasetRootHisto(numerator).getHistogram()
d = dataset.getDatasetRootHisto(denominator).getHistogram()
if d.GetEntries() == 0:
continue
checkNegatives(n,d)
# removeNegatives(n)
# removeNegatives(d)
print dataset.getName(),"entries",n.GetEntries(),d.GetEntries()
print " bins",n.GetNbinsX(),d.GetNbinsX()
print " lowedge",n.GetBinLowEdge(1),d.GetBinLowEdge(1)
eff = ROOT.TEfficiency(n,d)
eff.SetStatisticOption(statOption)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()/d.GetEntries()
for i in range(1,d.GetNbinsX()+1):
print " bin",i,d.GetBinLowEdge(i),n.GetBinContent(i),d.GetBinContent(i)
eff.SetWeight(weight)
if first:
teff = eff
if dataset.isData():
tn = n
td = d
first = False
else:
teff.Add(eff)
if dataset.isData():
tn.Add(n)
td.Add(d)
if isData:
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(self.statOption)
return teff
def GetEfficiency(datasetsMgr, datasets, numPath, denPath, intLumi):
# Definitions
myList = []
myList_MC = []
myList_Data = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasets:
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
total = den.Integral(0, den.GetXaxis().GetNbins() + 1)
selected = num.Integral(0, num.GetXaxis().GetNbins() + 1)
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(
selected / total, 3)
print "Pass :"******" events"
if "binList" in _kwargs:
#if len(_kwargs["binList"]) == 1:
# continue
xBins = _kwargs["binList"]
nx = len(xBins) - 1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
#elif "Eta" in numPath or "Phi" in numPath:
# num = num.Rebin(2)
# den = den.Rebin(2)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
eff = convert2TGraph(eff)
return eff
def GetEfficiency(datasetsMgr, datasets, numPath, denPath, intLumi):
# Definitions
myList = []
myList_MC = []
myList_Data = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasets:
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
total = den.Integral(0, den.GetXaxis().GetNbins()+1)
selected = num.Integral(0, num.GetXaxis().GetNbins()+1)
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(selected/total, 3)
print "Pass :"******" events"
if "binList" in _kwargs:
#if len(_kwargs["binList"]) == 1:
# continue
xBins = _kwargs["binList"]
nx = len(xBins)-1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
#elif "Eta" in numPath or "Phi" in numPath:
# num = num.Rebin(2)
# den = den.Rebin(2)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
eff = convert2TGraph(eff)
return eff
def PlotMC_ForEffPlots(datasetsMgr, histoName, intLumi):
index = 0
for dataset in datasetsMgr.getAllDatasets():
datasetName = dataset.getName()
rootHisto = dataset.getDatasetRootHisto(histoName)
rootHisto.normalizeToLuminosity(intLumi)
histo = rootHisto.getHistogram()
kwargs = {}
if index == 0:
# Apply Styles
if "TT" in datasetsMgr.getAllDatasets():
p.histoMgr.setHistoDrawStyle("TT", "AP")
p.histoMgr.setHistoLegendStyle("TT", "LP")
index = 1
else:
# Apply Styles
if "TT" in datasetsMgr.getAllDatasets():
p.histoMgr.setHistoDrawStyle("TTTT", "AP")
p.histoMgr.setHistoLegendStyle("TTTT", "LP")
_xlabel = "p_{T} (GeV/c)"
logY = False
_rebinX = 1
units = "GeV/c"
_format = "%0.1f" + units
_opts = {"ymin": 1e-3, "ymaxfactor": 1.0}
_cutBox = False
# _cutBox = {"cutValue": 0.5, "fillColor": 16, "box": False, "line": False, "greaterThan": True}
plots.drawPlot(p,
histo,
xlabel = _xlabel,
ylabel = "Arbitrary Units / %s" % (_format),
log = logY,
rebinX = _rebinX, cmsExtraText = "Preliminary",
createLegend = {"x1": 0.58, "y1": 0.65, "x2": 0.92, "y2": 0.92},
opts = _opts,
opts2 = {"ymin": 0.6, "ymax": 1.4},
cutBox = _cutBox,
)
# Save plot in all formats
saveName = histo.split("/")[-1]
savePath = os.path.join(opts.saveDir, "HplusMasses", histo.split("/")[0], opts.optMode)
SavePlot(p, saveName, savePath)
return
def main(opts):
# Apply TDR style
style = tdrstyle.TDRStyle()
style.setOptStat(False)
style.setGridX(False)
style.setGridY(False)
# Setup & configure the dataset manager
datasetsMgr = GetDatasetsFromDir(opts, 0)
datasetsMgr.updateNAllEventsToPUWeighted()
datasetsMgr.loadLuminosities() # from lumi.json
if opts.verbose:
datasetsMgr.PrintCrossSections()
datasetsMgr.PrintLuminosities()
# Set/Overwrite cross-sections
for d in datasetsMgr.getAllDatasets():
if "ChargedHiggs" in d.getName():
datasetsMgr.getDataset(d.getName()).setCrossSection(1.0)
# Merge histograms (see NtupleAnalysis/python/tools/plots.py)
if 1:
plots.mergeRenameReorderForDataMC(datasetsMgr)
# Print datasets info summary
datasetsMgr.PrintInfo()
# Define the mapping histograms in numerator->denominator pairs
VariableList = ["TetrajetMass"]
counter = 0
opts.nDatasets = len(datasetsMgr.getAllDatasets())
nPlots = len(VariableList)*opts.nDatasets
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
# For-looop: All variables
for hName in VariableList:
hPath = os.path.join(opts.folder, hName)
counter+=1
msg = "{:<9} {:>3} {:<1} {:<3} {:<50}".format("Histogram", "%i" % counter, "/", "%s:" % (nPlots), "%s" % (dataset.getName()))
aux.Print(ShellStyles.SuccessStyle() + msg + ShellStyles.NormalStyle(), counter==1)
PlotHistos(dataset.getName(), hPath) # For each dataset: Plot histos from different multicrabs on same canvas
aux.Print("All plots saved under directory %s" % (ShellStyles.NoteStyle() + aux.convertToURL(opts.saveDir, opts.url) + ShellStyles.NormalStyle()), True)
return
def Convert2TGraph(tefficiency, dataset, style, titleX, titleY):
'''
'''
x = []
y = []
xerrl = []
xerrh = []
yerrl = []
yerrh = []
h = tefficiency.GetCopyTotalHisto()
n = h.GetNbinsX()
for i in range(1, n + 1):
x.append(h.GetBinLowEdge(i) + 0.5 * h.GetBinWidth(i))
xerrl.append(0.5 * h.GetBinWidth(i))
xerrh.append(0.5 * h.GetBinWidth(i))
y.append(tefficiency.GetEfficiency(i))
yerrl.append(tefficiency.GetEfficiencyErrorLow(i))
# ugly hack to prevent error going above 1
errUp = tefficiency.GetEfficiencyErrorUp(i)
if y[-1] == 1.0:
errUp = 0
yerrh.append(errUp)
tgraph = ROOT.TGraphAsymmErrors(n, array.array("d",
x), array.array("d", y),
array.array("d", xerrl),
array.array("d", xerrh),
array.array("d", yerrl),
array.array("d", yerrh))
tgraph.SetName(dataset.getName())
tgraph.GetXaxis().SetTitle(titleX)
tgraph.GetYaxis().SetTitle(titleY)
style.apply(tgraph)
return tgraph
def Convert2TGraph(tefficiency, dataset, style, titleX, titleY):
'''
'''
x = []
y = []
xerrl = []
xerrh = []
yerrl = []
yerrh = []
h = tefficiency.GetCopyTotalHisto()
n = h.GetNbinsX()
for i in range(1,n+1):
x.append(h.GetBinLowEdge(i)+0.5*h.GetBinWidth(i))
xerrl.append(0.5*h.GetBinWidth(i))
xerrh.append(0.5*h.GetBinWidth(i))
y.append(tefficiency.GetEfficiency(i))
yerrl.append(tefficiency.GetEfficiencyErrorLow(i))
# ugly hack to prevent error going above 1
errUp = tefficiency.GetEfficiencyErrorUp(i)
if y[-1] == 1.0:
errUp = 0
yerrh.append(errUp)
tgraph = ROOT.TGraphAsymmErrors(n,array.array("d",x),
array.array("d",y),
array.array("d",xerrl),
array.array("d",xerrh),
array.array("d",yerrl),
array.array("d",yerrh))
tgraph.SetName(dataset.getName())
tgraph.GetXaxis().SetTitle(titleX)
tgraph.GetYaxis().SetTitle(titleY)
style.apply(tgraph)
return tgraph
def GetEfficiency(datasetsMgr, datasets, numerator="Numerator",denominator="Denominator", **kwargs):
'''
TEfficiency method:
See https://root.cern.ch/doc/master/classTEfficiency.html
'''
lumi = GetLumi(datasetsMgr)
# Select Statistic Options
statOption = ROOT.TEfficiency.kFCP
'''
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
statOption = ROOT.TEfficiency.kFNormal # Normal Approximation
statOption = ROOT.TEfficiency.kFWilson # Wilson
statOption = ROOT.TEfficiency.kFAC # Agresti-Coull
statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
statOption = ROOT.TEfficiency.kBBJeffrey # Jeffrey
statOption = ROOT.TEfficiency.kBBUniform # Uniform Prior
statOption = ROOT.TEfficiency.kBBayesian # Custom Prior
'''
first = True
teff = ROOT.TEfficiency()
# teff.SetStatisticOption(statOption)
# For-loop: All datasets
for dataset in datasets:
num = dataset.getDatasetRootHisto(numerator)
den = dataset.getDatasetRootHisto(denominator)
#
if dataset.isMC():
num.normalizeToLuminosity(lumi)
den.normalizeToLuminosity(lumi)
# Get Numerator and Denominator
n = num.getHistogram()
d = den.getHistogram()
if d.GetEntries() == 0 or n.GetEntries() == 0:
msg = "Denominator Or Numerator has no entries"
Print(ErrorStyle() + msg + NormalStyle(), True)
continue
# Check Negatives
CheckNegatives(n, d, True)
# Remove Negatives
RemoveNegatives(n)
#RemoveNegatives(d)
NumeratorBins = n.GetNbinsX()
DenominatorBins = d.GetNbinsX()
# Sanity Check
if (NumeratorBins != DenominatorBins) :
raise Exception("Numerator and Denominator Bins are NOT equal!")
nBins = d.GetNbinsX()
xMin = d.GetXaxis().GetXmin()
xMax = d.GetXaxis().GetXmax()
# ----------------------------------------------------------------------------------------- #
# Ugly hack to ignore EMPTY (in the wanted range) histograms with overflows/underflows
# ----------------------------------------------------------------------------------------- #
if 0:
print "\n"
print "=========== getEfficiency:"
print "Dataset = ", dataset.getName()
print "Numerator :", n.GetName(), " entries=", n.GetEntries(), " Bins=", n.GetNbinsX(), " Low edge=", n.GetBinLowEdge(1)
print "Denominator:", d.GetName(), " entries=", d.GetEntries(), " Bins=", d.GetNbinsX(), " Low edge=", d.GetBinLowEdge(1)
print "\n"
print ">>>>>> Sanity Check: <<<<<<"
print "Numerator Mean = ", n.GetMean()
print "Numerator RMS = ", n.GetRMS()
print "Numerator Integral = ", n.Integral(1, nBins)
print "Denominator Mean = ", d.GetMean()
print "Denominator RMS = ", d.GetRMS()
print "Denominator Integral = ", d.Integral(1, nBins)
if (n.GetMean() == 0 or d.GetMean() == 0): continue
if (n.GetRMS() == 0 or d.GetRMS() == 0): continue
if (n.Integral(1,nBins) == 0 or d.Integral(1,nBins) == 0): continue
Verbose("Passed the sanity check", True)
eff = ROOT.TEfficiency(n, d)
eff.SetStatisticOption(statOption)
# For-loop: All bins
if 0:
for iBin in range(1, nBins+1):
print iBin, "x=", n.GetBinLowEdge(iBin), " Num=", n.GetBinContent(iBin), " Den=", d.GetBinContent(iBin)," Eff=", eff.GetEfficiency(iBin)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
if first:
teff = eff
first = False
if dataset.isData():
tn = n
td = d
else:
teff.Add(eff)
if dataset.isData():
tn.Add(n)
td.Add(d)
if dataset.isData():
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(statOption)
Verbose("Final tEff", True)
if 0:
for iBin in range(1,nBins+1):
print iBin, "x=", n.GetBinLowEdge(iBin)," Efficiency=", teff.GetEfficiency(iBin), " Weight = ", teff.GetWeight()
return convert2TGraph(teff)
def GetCutEfficiencyHisto(dataset, histoName, statOpt, **kwargs):
'''
See https://root.cern.ch/doc/master/classTEfficiency.html
'''
HasKeys(["verbose", "normalizeTo", "cutDirection"], **kwargs)
verbose = kwargs.get("verbose")
normalizeTo = kwargs.get("normalizeTo")
cutDirection= kwargs.get("cutDirection")
Verbose("Calculating the cut-efficiency (%s) for histo with name %s" % (cutDirection, histoName) )
# Choose statistics options
statOpts = ["kFCP", "kFNormal", "KFWilson", "kFAC", "kFFC", "kBJeffrey", "kBUniform", "kBayesian"]
if statOpt not in statOpts:
raise Exception("Invalid statistics option \"%s\". Please choose one from the following:\n\t%s" % (statOpt, "\n\t".join(statOpts)))
if statOpt == "kFCP":
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
elif statOpt == "kFNormal":
statOption = ROOT.TEfficiency.kFNormal # Normal Approximation
elif statOpt == "kFWilson":
statOption = ROOT.TEfficiency.kFWilson # Wilson
elif statOpt == "kFAC":
statOption = ROOT.TEfficiency.kFAC # Agresti-Coull
elif statOpt == "kFFC":
statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
elif statOpt == "kBJeffrey":
statOption = ROOT.TEfficiency.kBJeffrey # Jeffrey
elif statOpt == "kBUniform":
statOption = ROOT.TEfficiency.kBUniform # Uniform Prior
elif statOpt == "kBayesian":
statOption = ROOT.TEfficiency.kBayesian # Custom Prior
else:
raise Exception("This should never be reached")
# Declare variables & options
first = True
isData = False
teff = ROOT.TEfficiency()
# Get the ROOT histogram
rootHisto = dataset.getDatasetRootHisto(histoName)
# Normalise the histogram
NormalizeRootHisto(datasetsMgr, rootHisto, dataset.isMC(), normalizeTo)
#NormalizeRootHisto(datasetsMgr, rootHisto, d.isMC(), normalizeTo)
## Get a clone of the wrapped histogram normalized as requested.
h = rootHisto.getHistogram()
titleX = h.GetXaxis().GetTitle()
binWidth = h.GetXaxis().GetBinWidth(0)
titleY = "efficiency (%s) / %s" % (cutDirection, GetBinwidthDecimals(binWidth) % (binWidth) )
# If empty return
if h.GetEntries() == 0:
return
# Create the numerator/denominator histograms
numerator = h.Clone("Numerator")
denominator = h.Clone("Denominator")
# Reset the numerator/denominator histograms
numerator.Reset()
denominator.Reset()
# Calculate the instances passing a given cut (all bins)
nBinsX = h.GetNbinsX()+1
for iBin in range(1, nBinsX):
nTotal = h.Integral(0, nBinsX)
if cutDirection == ">":
nPass = h.Integral(iBin+1, nBinsX)
elif cutDirection == "<":
nPass = nTotal - h.Integral(iBin+1, nBinsX)
else:
raise Exception("Invalid cut direction \"%s\". Please choose either \">\" or \"<\"" % (cutDirection))
# Sanity check
if nPass < 0:
nPass = 0
# Fill the numerator/denominator histograms
# print "iBin = %s, nPass = %s, nTotal = %s" % (iBin, nPass, nTotal)
numerator.SetBinContent(iBin, nPass)
numerator.SetBinError(iBin, math.sqrt(nPass)/10)
#
denominator.SetBinContent(iBin, nTotal)
denominator.SetBinError(iBin, math.sqrt(nTotal)/10)
# Check for negative values
CheckNegatives(numerator, denominator)
# Create TEfficiency object using the two histos
eff = ROOT.TEfficiency(numerator, denominator)
eff.SetStatisticOption(statOption)
Verbose("The statistic option was set to %s" % (eff.GetStatisticOption()) )
# Save info in a table (debugging)
table = []
hLine = "="*70
msgAlign = '{:<5} {:<20} {:<20} {:<20}'
title = msgAlign.format("Bin", "Efficiency", "Error-Low", "Error-Up")
table.append("\n" + hLine)
table.append(title)
table.append(hLine)
for iBin in range(1, nBinsX):
e = eff.GetEfficiency(iBin)
errLow = eff.GetEfficiencyErrorLow(iBin)
errUp = eff.GetEfficiencyErrorUp(iBin)
values = msgAlign.format(iBin, e, errLow, errUp)
table.append(values)
table.append(hLine)
# Verbose mode
if verbose:
for l in table:
print l
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
if first:
teff = eff
if dataset.isData():
tn = numerator
td = denominator
first = False
else:
teff.Add(eff)
if dataset.isData():
tn.Add(numerator)
td.Add(denominator)
if isData:
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(self.statOption)
style = styleDict[dataset.getName()]
return Convert2TGraph(teff, dataset, style, titleX, titleY)
def PlotEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
myList_MC = []
myList_Data = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if "Fake" in numPath and "TT" in dataset.getName():
continue
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
total = den.Integral(0, den.GetXaxis().GetNbins()+1)
selected = num.Integral(0, num.GetXaxis().GetNbins()+1)
print "Pass :"******" events"
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(selected/total, 3)
if "binList" in _kwargs:
#if len(_kwargs["binList"]) == 1:
# continue
xBins = _kwargs["binList"]
nx = len(xBins)-1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
elif "Eta" in numPath or "Phi" in numPath:
num = num.Rebin(2)
den = den.Rebin(2)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
eff = convert2TGraph(eff)
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Append in list
myList.append(histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P"))
if dataset.isMC():
eff_MC = eff
if "QCD" in dataset.getName():
eff_QCD = eff
elif "TT" in dataset.getName():
eff_TT= eff
myList_MC.append(histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P"))
else:
eff_Data = eff
plots._plotStyles[dataset.getName()].apply(eff_Data)
#styles.dataStyle.apply(eff_Data)
eff_Data.SetMarkerSize(1.2)
myList_Data.append(histograms.HistoGraph(eff_Data, plots._legendLabels[dataset.getName()], "p", "P"))
numPath = numPath.replace("AfterAllSelections_","")
# Define save name
saveName = "Eff_" + numPath.split("/")[-1]
# Plot the efficiency
p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
p1 = plots.ComparisonManyPlot(histograms.HistoGraph(eff_Data, "Data", drawStyle="P"),
myList_MC, saveFormats=[])
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses", numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
print "save_path", save_path
# Draw and save the plot
p1.setLuminosity(intLumi)
_kwargs["ratio"] = True
_kwargs["ratioInvert"] = True
_kwargs["cutBoxY"] = {"cutValue": 1.0, "fillColor": 16, "box": False, "line": True, "greaterThan": True, "mainCanvas": True, "ratioCanvas": True}
plots.drawPlot(p1, save_path1, **_kwargs)
SavePlot(p1, saveName, save_path, saveFormats = [".png", ".pdf", ".C"])
return
def PlotProb(datasets, numPath, denPath):
EfficiencyList = []
index = 0
for dataset in datasets:
datasetName = dataset.getName()
print "Dataset = ", datasetName
statOption = ROOT.TEfficiency.kFNormal
## n = dataset.getDatasetRootHisto(numPath).getHistogram()
# n.normalizeToOne()
## d = dataset.getDatasetRootHisto(denPath).getHistogram()
nn = dataset.getDatasetRootHisto(numPath)
nn.normalizeToLuminosity(35.8*(10**3))
n = nn.getHistogram()
dd = dataset.getDatasetRootHisto(denPath)
# dd.normalizeToOne()
# dd.normalizeToLuminosity(36.3*(10**3))
dd.normalizeToLuminosity(35.8*(10**3))
# dd.normalizeByCrossSection()
d = dd.getHistogram()
# if "TT" in datasetName and ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# continue
# elif "M_" in datasetName and not ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# continue
if "Event" in numPath:
n.Rebin(10)
d.Rebin(10)
else:
n.Rebin(5)
d.Rebin(5)
if d.GetEntries() == 0 or n.GetEntries() == 0:
continue
if n.GetEntries() > d.GetEntries():
continue
# Check Negatives
CheckNegatives(n, d, True)
# Remove Negatives
RemoveNegatives(n)
nBins = d.GetNbinsX()
xMin = d.GetXaxis().GetXmin()
xMax = d.GetXaxis().GetXmax()
binwidth = int(n.GetBinWidth(0))
# ----------------------------------------------------------------------------------------- #
# Ugly hack to ignore EMPTY (in the wanted range) histograms with overflows/underflows
# ----------------------------------------------------------------------------------------- #
if (0):
print "\n"
print "=========== getEfficiency:"
print "Dataset = ", dataset.getName()
print "Numerator: entries=", n.GetEntries(), " Bins=", n.GetNbinsX(), " Low edge=", n.GetBinLowEdge(1)
print "Denominator: entries=", d.GetEntries(), " Bins=", d.GetNbinsX(), " Low edge=", d.GetBinLowEdge(1)
print "\n"
print ">>>>>> Sanity Check: <<<<<<"
print "Numerator Mean = ", n.GetMean()
print "Numerator RMS = ", n.GetRMS()
print "Numerator Integral = ", n.Integral(1, nBins)
print "Denominator Mean = ", d.GetMean()
print "Denominator RMS = ", d.GetRMS()
print "Denominator Integral = ", d.Integral(1, nBins)
if (n.GetMean() == 0 or d.GetMean() == 0): continue
if (n.GetRMS() == 0 or d.GetRMS() == 0): continue
if (n.Integral(1,nBins) == 0 or d.Integral(1,nBins) == 0): continue
# if not (ROOT.TEfficiency.CheckConsistency(n,d)): continue;
effic = ROOT.TEfficiency(n,d)
effic.SetStatisticOption(statOption)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
effic.SetWeight(weight)
eff = convert2TGraph(effic)
# Apply Styles
if "TT" in datasetName:
if index == 0:
styles.signalStyleHToTB500.apply(eff)
# styles.ttStyle.apply(eff)
eff.SetLineStyle(1)
eff.SetLineWidth(3)
eff.SetLineColor(619)
legend = "Default: t#bar{t}"
index = 1
else:
styles.signalStyleHToTB500.apply(eff)
# styles.ttStyle.apply(eff)
eff.SetLineStyle(1)
eff.SetLineWidth(3)
eff.SetLineColor(417)
legend = "#Delta R(q,q')>0.8: t#bar{t}"
elif "M_500" in datasetName:
styles.signalStyleHToTB500.apply(eff)
legend = "H^{+} m_{H^{+}} = 500 GeV"
elif "M_300" in datasetName:
styles.signalStyleHToTB300.apply(eff)
legend = "H^{+} m_{H^{+}} = 300 GeV"
elif "M_1000" in datasetName:
styles.signalStyleHToTB1000.apply(eff)
legend = "H^{+} m_{H^{+}} = 1000 GeV"
elif "M_800" in datasetName:
styles.signalStyleHToTB800.apply(eff)
legend = "H^{+} m_{H^{+}} = 800 GeV"
elif "M_200" in datasetName:
styles.signalStyleHToTB200.apply(eff)
legend = "H^{+} m_{H^{+}} = 200 GeV"
else:
styles.ttStyle.apply(eff)
legend = "other"
EfficiencyList.append(histograms.HistoGraph(eff, legend, "lp", "P"))
saveName = "Eff_"+numPath.split("/")[-1]+"Over"+denPath.split("/")[-1]
if "Pt" in numPath:
xMin = 0.0
# rebinX = 2
xMax = 805.0
# xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Efficiency / " + str(binwidth) + " "+units
yMin = 0.0
yMax = 1.1
elif "_Eta" in numPath:
xMin = -3.0
xMax = +3.0
xTitle = "#eta"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
elif "_Mass" in numPath:
xMin = 50.0
xMax = 300
xTitle = "M (GeV/c^{2})"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
elif "_Phi" in numPath:
xMin = -3
xMax = +3
xTitle = "#phi"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
else:
xMin = 0.0
xMax = 250.0
xTitle = "xTitle"
yTitle = "yTitle"
yMin = 0.0
yMax = 1.1
if "Fake" in numPath:
# xMin = 95.0
# rebinX = 4
xMax = 805.0
xTitle = "candidate p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Misid rate / " + str(binwidth) + " " +units
yMin = 0.0
yMax = 0.11
if "Event" in numPath:
rebinX = 2
# xMin = 95.0
xMax = 805.0
xTitle = "candidate p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Efficiency / " + str(binwidth) + " "+ units
yMin = 0.0
yMax = 1.1
if "NonMatched" in numPath:
xMin = 90.0
rebinX = 4
xMax = 700.0
xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} (GeV)"
yTitle = "Efficiency"
yMin = 0.0
yMax = 0.15
if "AllTopQuarkPt_MatchedBDT" in numPath and "TopQuarkPt" in denPath:
xMin = 0.0
# rebinX = 4
xMax = 805.0 #705
units = "GeV/c"
xTitle = "generated top p_{T} (GeV/c)"
yTitle = "Efficiency / " + str(binwidth) + " " + units
yMin = 0.0
yMax = 1.1
if "SameFake" in numPath:
xMin = 95.0
rebinX = 4
xMax = 705.0
xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} [GeV]"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
options = {"ymin": yMin , "ymax": yMax, "xmin":xMin, "xMax":xMax}
# if "TT" in datasetName and ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# return
# if "M_" in datasetName and not ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# return
p = plots.PlotBase(datasetRootHistos=EfficiencyList, saveFormats=kwargs.get("saveFormats"))
#p = plots.ComparisonManyPlot(refEff, EfficiencyList, saveFormats=[])
p.createFrame(saveName, opts=options)
# p.histoMgr.forEachHisto(lambda h: h.getRootHisto().RebinX(kwargs.get("rebinX")))
# Set Titles
# p.getFrame().GetYaxis().SetTitle(kwargs.get("ylabel")) #"ylabel"
p.getFrame().GetXaxis().SetTitle(xTitle)
p.getFrame().GetYaxis().SetTitle(yTitle)
# Set range
p.getFrame().GetXaxis().SetRangeUser(xMin, xMax)
moveLegend = {"dx": -0.55, "dy": -0.02, "dh": -0.2}
# moveLegend = {"dx": -0.55, "dy": -0.01, "dh": -0.1}
p.setLegend(histograms.moveLegend(histograms.createLegend(), **moveLegend))
# Add Standard Texts to plot
histograms.addStandardTexts()
p.draw()
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses", numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
# SavePlot(p, saveName, savePath)
SavePlot(p, saveName, save_path)
return
def GetCutEfficiencyHisto(dataset, histoName, statOpt, **kwargs):
'''
See https://root.cern.ch/doc/master/classTEfficiency.html
'''
HasKeys(["verbose", "normalizeTo", "cutDirection"], **kwargs)
verbose = kwargs.get("verbose")
normalizeTo = kwargs.get("normalizeTo")
cutDirection = kwargs.get("cutDirection")
Verbose("Calculating the cut-efficiency (%s) for histo with name %s" %
(cutDirection, histoName))
# Choose statistics options
statOpts = [
"kFCP", "kFNormal", "KFWilson", "kFAC", "kFFC", "kBJeffrey",
"kBUniform", "kBayesian"
]
if statOpt not in statOpts:
raise Exception(
"Invalid statistics option \"%s\". Please choose one from the following:\n\t%s"
% (statOpt, "\n\t".join(statOpts)))
if statOpt == "kFCP":
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
elif statOpt == "kFNormal":
statOption = ROOT.TEfficiency.kFNormal # Normal Approximation
elif statOpt == "kFWilson":
statOption = ROOT.TEfficiency.kFWilson # Wilson
elif statOpt == "kFAC":
statOption = ROOT.TEfficiency.kFAC # Agresti-Coull
elif statOpt == "kFFC":
statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
elif statOpt == "kBJeffrey":
statOption = ROOT.TEfficiency.kBJeffrey # Jeffrey
elif statOpt == "kBUniform":
statOption = ROOT.TEfficiency.kBUniform # Uniform Prior
elif statOpt == "kBayesian":
statOption = ROOT.TEfficiency.kBayesian # Custom Prior
else:
raise Exception("This should never be reached")
# Declare variables & options
first = True
isData = False
teff = ROOT.TEfficiency()
# Get the ROOT histogram
rootHisto = dataset.getDatasetRootHisto(histoName)
# Normalise the histogram
NormalizeRootHisto(datasetsMgr, rootHisto, dataset.isMC(), normalizeTo)
#NormalizeRootHisto(datasetsMgr, rootHisto, d.isMC(), normalizeTo)
## Get a clone of the wrapped histogram normalized as requested.
h = rootHisto.getHistogram()
titleX = h.GetXaxis().GetTitle()
binWidth = h.GetXaxis().GetBinWidth(0)
titleY = "efficiency (%s) / %s" % (cutDirection,
GetBinwidthDecimals(binWidth) %
(binWidth))
# If empty return
if h.GetEntries() == 0:
return
# Create the numerator/denominator histograms
numerator = h.Clone("Numerator")
denominator = h.Clone("Denominator")
# Reset the numerator/denominator histograms
numerator.Reset()
denominator.Reset()
# Calculate the instances passing a given cut (all bins)
nBinsX = h.GetNbinsX() + 1
for iBin in range(1, nBinsX):
nTotal = h.Integral(0, nBinsX)
if cutDirection == ">":
nPass = h.Integral(iBin + 1, nBinsX)
elif cutDirection == "<":
nPass = nTotal - h.Integral(iBin + 1, nBinsX)
else:
raise Exception(
"Invalid cut direction \"%s\". Please choose either \">\" or \"<\""
% (cutDirection))
# Sanity check
if nPass < 0:
nPass = 0
# Fill the numerator/denominator histograms
# print "iBin = %s, nPass = %s, nTotal = %s" % (iBin, nPass, nTotal)
numerator.SetBinContent(iBin, nPass)
numerator.SetBinError(iBin, math.sqrt(nPass) / 10)
#
denominator.SetBinContent(iBin, nTotal)
denominator.SetBinError(iBin, math.sqrt(nTotal) / 10)
# Check for negative values
CheckNegatives(numerator, denominator)
# Create TEfficiency object using the two histos
eff = ROOT.TEfficiency(numerator, denominator)
eff.SetStatisticOption(statOption)
Verbose("The statistic option was set to %s" % (eff.GetStatisticOption()))
# Save info in a table (debugging)
table = []
hLine = "=" * 70
msgAlign = '{:<5} {:<20} {:<20} {:<20}'
title = msgAlign.format("Bin", "Efficiency", "Error-Low", "Error-Up")
table.append("\n" + hLine)
table.append(title)
table.append(hLine)
for iBin in range(1, nBinsX):
e = eff.GetEfficiency(iBin)
errLow = eff.GetEfficiencyErrorLow(iBin)
errUp = eff.GetEfficiencyErrorUp(iBin)
values = msgAlign.format(iBin, e, errLow, errUp)
table.append(values)
table.append(hLine)
# Verbose mode
if verbose:
for l in table:
print l
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
if first:
teff = eff
if dataset.isData():
tn = numerator
td = denominator
first = False
else:
teff.Add(eff)
if dataset.isData():
tn.Add(numerator)
td.Add(denominator)
if isData:
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(self.statOption)
style = styleDict[dataset.getName()]
return Convert2TGraph(teff, dataset, style, titleX, titleY)
def PlotProb(datasets, numPath, denPath):
EfficiencyList = []
index = 0
for dataset in datasets:
datasetName = dataset.getName()
print "Dataset = ", datasetName
statOption = ROOT.TEfficiency.kFNormal
## n = dataset.getDatasetRootHisto(numPath).getHistogram()
# n.normalizeToOne()
## d = dataset.getDatasetRootHisto(denPath).getHistogram()
nn = dataset.getDatasetRootHisto(numPath)
nn.normalizeToLuminosity(35.8 * (10**3))
n = nn.getHistogram()
dd = dataset.getDatasetRootHisto(denPath)
# dd.normalizeToOne()
# dd.normalizeToLuminosity(36.3*(10**3))
dd.normalizeToLuminosity(35.8 * (10**3))
# dd.normalizeByCrossSection()
d = dd.getHistogram()
# if "TT" in datasetName and ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# continue
# elif "M_" in datasetName and not ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# continue
if "Event" in numPath:
n.Rebin(10)
d.Rebin(10)
else:
n.Rebin(5)
d.Rebin(5)
if d.GetEntries() == 0 or n.GetEntries() == 0:
continue
if n.GetEntries() > d.GetEntries():
continue
# Check Negatives
CheckNegatives(n, d, True)
# Remove Negatives
RemoveNegatives(n)
nBins = d.GetNbinsX()
xMin = d.GetXaxis().GetXmin()
xMax = d.GetXaxis().GetXmax()
binwidth = int(n.GetBinWidth(0))
# ----------------------------------------------------------------------------------------- #
# Ugly hack to ignore EMPTY (in the wanted range) histograms with overflows/underflows
# ----------------------------------------------------------------------------------------- #
if (0):
print "\n"
print "=========== getEfficiency:"
print "Dataset = ", dataset.getName()
print "Numerator: entries=", n.GetEntries(
), " Bins=", n.GetNbinsX(), " Low edge=", n.GetBinLowEdge(1)
print "Denominator: entries=", d.GetEntries(
), " Bins=", d.GetNbinsX(), " Low edge=", d.GetBinLowEdge(1)
print "\n"
print ">>>>>> Sanity Check: <<<<<<"
print "Numerator Mean = ", n.GetMean()
print "Numerator RMS = ", n.GetRMS()
print "Numerator Integral = ", n.Integral(1, nBins)
print "Denominator Mean = ", d.GetMean()
print "Denominator RMS = ", d.GetRMS()
print "Denominator Integral = ", d.Integral(1, nBins)
if (n.GetMean() == 0 or d.GetMean() == 0): continue
if (n.GetRMS() == 0 or d.GetRMS() == 0): continue
if (n.Integral(1, nBins) == 0 or d.Integral(1, nBins) == 0): continue
# if not (ROOT.TEfficiency.CheckConsistency(n,d)): continue;
effic = ROOT.TEfficiency(n, d)
effic.SetStatisticOption(statOption)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
effic.SetWeight(weight)
eff = convert2TGraph(effic)
# Apply Styles
if "TT" in datasetName:
if index == 0:
styles.signalStyleHToTB500.apply(eff)
# styles.ttStyle.apply(eff)
eff.SetLineStyle(1)
eff.SetLineWidth(3)
eff.SetLineColor(619)
legend = "Default: t#bar{t}"
index = 1
else:
styles.signalStyleHToTB500.apply(eff)
# styles.ttStyle.apply(eff)
eff.SetLineStyle(1)
eff.SetLineWidth(3)
eff.SetLineColor(417)
legend = "#Delta R(q,q')>0.8: t#bar{t}"
elif "M_500" in datasetName:
styles.signalStyleHToTB500.apply(eff)
legend = "H^{+} m_{H^{+}} = 500 GeV"
elif "M_300" in datasetName:
styles.signalStyleHToTB300.apply(eff)
legend = "H^{+} m_{H^{+}} = 300 GeV"
elif "M_1000" in datasetName:
styles.signalStyleHToTB1000.apply(eff)
legend = "H^{+} m_{H^{+}} = 1000 GeV"
elif "M_800" in datasetName:
styles.signalStyleHToTB800.apply(eff)
legend = "H^{+} m_{H^{+}} = 800 GeV"
elif "M_200" in datasetName:
styles.signalStyleHToTB200.apply(eff)
legend = "H^{+} m_{H^{+}} = 200 GeV"
else:
styles.ttStyle.apply(eff)
legend = "other"
EfficiencyList.append(histograms.HistoGraph(eff, legend, "lp", "P"))
saveName = "Eff_" + numPath.split("/")[-1] + "Over" + denPath.split(
"/")[-1]
if "Pt" in numPath:
xMin = 0.0
# rebinX = 2
xMax = 805.0
# xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Efficiency / " + str(binwidth) + " " + units
yMin = 0.0
yMax = 1.1
elif "_Eta" in numPath:
xMin = -3.0
xMax = +3.0
xTitle = "#eta"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
elif "_Mass" in numPath:
xMin = 50.0
xMax = 300
xTitle = "M (GeV/c^{2})"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
elif "_Phi" in numPath:
xMin = -3
xMax = +3
xTitle = "#phi"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
else:
xMin = 0.0
xMax = 250.0
xTitle = "xTitle"
yTitle = "yTitle"
yMin = 0.0
yMax = 1.1
if "Fake" in numPath:
# xMin = 95.0
# rebinX = 4
xMax = 805.0
xTitle = "candidate p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Misid rate / " + str(binwidth) + " " + units
yMin = 0.0
yMax = 0.11
if "Event" in numPath:
rebinX = 2
# xMin = 95.0
xMax = 805.0
xTitle = "candidate p_{T} (GeV/c)"
units = "GeV/c"
_format = "%0.1f" + units
yTitle = "Efficiency / " + str(binwidth) + " " + units
yMin = 0.0
yMax = 1.1
if "NonMatched" in numPath:
xMin = 90.0
rebinX = 4
xMax = 700.0
xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} (GeV)"
yTitle = "Efficiency"
yMin = 0.0
yMax = 0.15
if "AllTopQuarkPt_MatchedBDT" in numPath and "TopQuarkPt" in denPath:
xMin = 0.0
# rebinX = 4
xMax = 805.0 #705
units = "GeV/c"
xTitle = "generated top p_{T} (GeV/c)"
yTitle = "Efficiency / " + str(binwidth) + " " + units
yMin = 0.0
yMax = 1.1
if "SameFake" in numPath:
xMin = 95.0
rebinX = 4
xMax = 705.0
xMax = 555.0 # For topPt < 500GeV
xTitle = "p_{T} [GeV]"
yTitle = "Efficiency"
yMin = 0.0
yMax = 1.1
options = {"ymin": yMin, "ymax": yMax, "xmin": xMin, "xMax": xMax}
# if "TT" in datasetName and ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# return
# if "M_" in datasetName and not ("Higgs" in numPath or "LdgBjetPt_isLdgFreeBjet" in numPath):
# return
p = plots.PlotBase(datasetRootHistos=EfficiencyList,
saveFormats=kwargs.get("saveFormats"))
#p = plots.ComparisonManyPlot(refEff, EfficiencyList, saveFormats=[])
p.createFrame(saveName, opts=options)
# p.histoMgr.forEachHisto(lambda h: h.getRootHisto().RebinX(kwargs.get("rebinX")))
# Set Titles
# p.getFrame().GetYaxis().SetTitle(kwargs.get("ylabel")) #"ylabel"
p.getFrame().GetXaxis().SetTitle(xTitle)
p.getFrame().GetYaxis().SetTitle(yTitle)
# Set range
p.getFrame().GetXaxis().SetRangeUser(xMin, xMax)
moveLegend = {"dx": -0.55, "dy": -0.02, "dh": -0.2}
# moveLegend = {"dx": -0.55, "dy": -0.01, "dh": -0.1}
p.setLegend(histograms.moveLegend(histograms.createLegend(), **moveLegend))
# Add Standard Texts to plot
histograms.addStandardTexts()
p.draw()
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses",
numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
# SavePlot(p, saveName, savePath)
SavePlot(p, saveName, save_path)
return
def CalcEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
x = []
y = []
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
if "binList" in _kwargs:
xBins = _kwargs["binList"]
nx = len(xBins)-1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
if nbin < 0:
nbin = 0
if dbin < 0:
nbin = 0
dbin = 1
if nbin > dbin:
nbin = dbin
x.append(num.GetBinLowEdge(i)+0.5*num.GetBinWidth(i))
y.append(nbin/dbin)
n = num.GetNbinsX()
eff = ROOT.TGraph(n, array.array("d",x), array.array("d",y))
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Apply random histo styles and append
if "charged" in dataset.getName().lower():
mass = dataset.getName().split("M_")[-1]
s = styles.getSignalStyleHToTB_M(mass)
s.apply(eff)
# Append in list
myList.append(histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P"))
# Define save name
saveName = "Eff_" + numPath.split("/")[-1] + "Over" + denPath.split("/")[-1]
# Plot the efficiency
p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
# Save plot in all formats
savePath = os.path.join(opts.saveDir, numPath.split("/")[0], opts.optMode)
SavePlot(p, saveName, savePath, saveFormats = [".png"])#, ".pdf"])
return
def PlotEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if "Fake" in numPath and "TT" in dataset.getName():
continue
# Get the histograms
#num = dataset.getDatasetRootHisto(numPath).getHistogram()
#den = dataset.getDatasetRootHisto(denPath).getHistogram()
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
if "binList" in _kwargs:
xBins = _kwargs["binList"]
nx = len(xBins)-1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Remove negative bins and ensure numerator bin <= denominator bin
CheckNegatives(num, den, True)
# RemoveNegatives(num)
# RemoveNegatives(den)
# Sanity check (Histograms are valid and consistent) - Always false!
# if not ROOT.TEfficiency.CheckConsistency(num, den):
# continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #
# Set the weights - Why is this needed?
if 0:
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
# Convert to TGraph
eff = convert2TGraph(eff)
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Append in list
myList.append(histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P"))
# Define save name
saveName = "Eff_" + numPath.split("/")[-1] + "Over" + denPath.split("/")[-1]
# Plot the efficiency
p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
# Save plot in all formats
savePath = os.path.join(opts.saveDir, numPath.split("/")[0], opts.optMode)
#savePath = os.path.join(opts.saveDir, numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
SavePlot(p, saveName, save_path, saveFormats = [".png", ".pdf", ".C"])
return
def GetEfficiency(datasetsMgr, datasets, numerator="Numerator",denominator="Denominator", **kwargs):
'''
TEfficiency method:
See https://root.cern.ch/doc/master/classTEfficiency.html
'''
lumi = GetLumi(datasetsMgr)
# Select Statistic Options
statOption = ROOT.TEfficiency.kFCP
'''
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
statOption = ROOT.TEfficiency.kFNormal # Normal Approximation
statOption = ROOT.TEfficiency.kFWilson # Wilson
statOption = ROOT.TEfficiency.kFAC # Agresti-Coull
statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
statOption = ROOT.TEfficiency.kBBJeffrey # Jeffrey
statOption = ROOT.TEfficiency.kBBUniform # Uniform Prior
statOption = ROOT.TEfficiency.kBBayesian # Custom Prior
'''
first = True
teff = ROOT.TEfficiency()
# teff.SetStatisticOption(statOption)
# For-loop: All datasets
for dataset in datasets:
num = dataset.getDatasetRootHisto(numerator)
den = dataset.getDatasetRootHisto(denominator)
#
if dataset.isMC():
num.normalizeToLuminosity(lumi)
den.normalizeToLuminosity(lumi)
# Get Numerator and Denominator
n = num.getHistogram()
d = den.getHistogram()
if d.GetEntries() == 0 or n.GetEntries() == 0:
msg = "Denominator Or Numerator has no entries"
Print(ErrorStyle() + msg + NormalStyle(), True)
continue
# Check Negatives
CheckNegatives(n, d, True)
# Remove Negatives
RemoveNegatives(n)
#RemoveNegatives(d)
NumeratorBins = n.GetNbinsX()
DenominatorBins = d.GetNbinsX()
# Sanity Check
if (NumeratorBins != DenominatorBins) :
raise Exception("Numerator and Denominator Bins are NOT equal!")
nBins = d.GetNbinsX()
xMin = d.GetXaxis().GetXmin()
xMax = d.GetXaxis().GetXmax()
# ----------------------------------------------------------------------------------------- #
# Ugly hack to ignore EMPTY (in the wanted range) histograms with overflows/underflows
# ----------------------------------------------------------------------------------------- #
if 0:
print "\n"
print "=========== getEfficiency:"
print "Dataset = ", dataset.getName()
print "Numerator :", n.GetName(), " entries=", n.GetEntries(), " Bins=", n.GetNbinsX(), " Low edge=", n.GetBinLowEdge(1)
print "Denominator:", d.GetName(), " entries=", d.GetEntries(), " Bins=", d.GetNbinsX(), " Low edge=", d.GetBinLowEdge(1)
print "\n"
print ">>>>>> Sanity Check: <<<<<<"
print "Numerator Mean = ", n.GetMean()
print "Numerator RMS = ", n.GetRMS()
print "Numerator Integral = ", n.Integral(1, nBins)
print "Denominator Mean = ", d.GetMean()
print "Denominator RMS = ", d.GetRMS()
print "Denominator Integral = ", d.Integral(1, nBins)
if (n.GetMean() == 0 or d.GetMean() == 0): continue
if (n.GetRMS() == 0 or d.GetRMS() == 0): continue
if (n.Integral(1,nBins) == 0 or d.Integral(1,nBins) == 0): continue
Verbose("Passed the sanity check", True)
eff = ROOT.TEfficiency(n, d)
eff.SetStatisticOption(statOption)
# For-loop: All bins
if 0:
for iBin in range(1, nBins+1):
print iBin, "x=", n.GetBinLowEdge(iBin), " Num=", n.GetBinContent(iBin), " Den=", d.GetBinContent(iBin)," Eff=", eff.GetEfficiency(iBin)
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
if first:
teff = eff
first = False
if dataset.isData():
tn = n
td = d
else:
teff.Add(eff)
if dataset.isData():
tn.Add(n)
td.Add(d)
if dataset.isData():
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(statOption)
Verbose("Final tEff", True)
if 0:
for iBin in range(1,nBins+1):
print iBin, "x=", n.GetBinLowEdge(iBin)," Efficiency=", teff.GetEfficiency(iBin), " Weight = ", teff.GetWeight()
return convert2TGraph(teff)
def Fit(datasets, histo, function):
FitList = []
for dataset in datasets:
datasetName = dataset.getName()
print "Dataset = ", datasetName
hh = dataset.getDatasetRootHisto(histo)
hh.normalizeToOne()
h = hh.getHistogram()
#h = dataset.getDatasetRootHisto(histo).getHistogram()
xMin = h.GetXaxis().GetXmin()
xMax = h.GetXaxis().GetXmax()
yMin = 0
yMax = 1.2
#statOption = ROOT.TEfficiency.kFNormal
if "TT" in datasetName:
if function == "gaus":
fitGauss = ROOT.TF1("fitGauss", "gaus", -2.5, 2.5)
# TF1 *fitBoFreq = new TF1("fitBoFreq","[0]*x+[1]",0,20);
# h.Fit("gaus")
#fitTest = ROOT.TF1("fitTest", "0.01", -2.5, 2.5)
h.Fit("fitGauss", "SRBM")
#h.GetListOfFunctions().Add(fitTest)
legend = "TT"
legend = "a legend"
print "Legend", legend
saveName = histo.split("/")[-1] + "_Fit"
print saveName
xTitle = "fixXTitle"
yTitle = "fixYTitle"
yMin = 0.
yMax = 0.03
xMin = -2.3
xMax = 2.3
kwargs = {}
options = {"ymin": yMin, "ymax": yMax, "xmin": xMin, "xMax": xMax}
FitList.append(h)
#p = plots.MCPlot(dataset, h, normalizeToLumi=0, saveFormats=[], **kwargs)
p = plots.PlotBase(datasetRootHistos=FitList,
saveFormats=kwargs.get("saveFormats"))
p.createFrame(saveName, opts=options)
p.getFrame().GetXaxis().SetTitle(xTitle)
p.getFrame().GetYaxis().SetTitle(yTitle)
#p.histoMgr.setHistoDrawStyle(datasetName, "AP")
# Set range
p.getFrame().GetXaxis().SetRangeUser(xMin, xMax)
moveLegend = {"dx": -0.55, "dy": -0.01, "dh": -0.1}
p.setLegend(
histograms.moveLegend(histograms.createLegend(), **moveLegend))
# Add Standard Texts to plot
histograms.addStandardTexts()
p.draw()
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses",
histo.split("/")[0], opts.optMode)
save_path = savePath
SavePlot(p, saveName, save_path)
return
def PlotEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
myList_MC = []
myList_Data = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if "Fake" in numPath and "TT" in dataset.getName():
continue
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
total = den.Integral(0, den.GetXaxis().GetNbins() + 1)
selected = num.Integral(0, num.GetXaxis().GetNbins() + 1)
print "Pass :"******" events"
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(
selected / total, 3)
if "binList" in _kwargs:
#if len(_kwargs["binList"]) == 1:
# continue
xBins = _kwargs["binList"]
nx = len(xBins) - 1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
elif "Eta" in numPath or "Phi" in numPath:
num = num.Rebin(2)
den = den.Rebin(2)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
eff = convert2TGraph(eff)
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Append in list
myList.append(
histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()],
"lp", "P"))
if dataset.isMC():
eff_MC = eff
if "QCD" in dataset.getName():
eff_QCD = eff
elif "TT" in dataset.getName():
eff_TT = eff
myList_MC.append(
histograms.HistoGraph(eff,
plots._legendLabels[dataset.getName()],
"lp", "P"))
else:
eff_Data = eff
plots._plotStyles[dataset.getName()].apply(eff_Data)
#styles.dataStyle.apply(eff_Data)
eff_Data.SetMarkerSize(1.2)
myList_Data.append(
histograms.HistoGraph(eff_Data,
plots._legendLabels[dataset.getName()],
"p", "P"))
numPath = numPath.replace("AfterAllSelections_", "")
# Define save name
saveName = "Eff_" + numPath.split("/")[-1]
# Plot the efficiency
p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
p1 = plots.ComparisonManyPlot(histograms.HistoGraph(eff_Data,
"Data",
drawStyle="P"),
myList_MC,
saveFormats=[])
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses",
numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
print "save_path", save_path
# Draw and save the plot
p1.setLuminosity(intLumi)
_kwargs["ratio"] = True
_kwargs["ratioInvert"] = True
_kwargs["cutBoxY"] = {
"cutValue": 1.0,
"fillColor": 16,
"box": False,
"line": True,
"greaterThan": True,
"mainCanvas": True,
"ratioCanvas": True
}
plots.drawPlot(p1, save_path1, **_kwargs)
SavePlot(p1, saveName, save_path, saveFormats=[".png", ".pdf", ".C"])
return
def main(opts):
# Setup & configure the dataset manager
datasetsMgr = GetDatasetsFromDir(opts)
datasetsMgr.updateNAllEventsToPUWeighted()
datasetsMgr.loadLuminosities() # from lumi.json
if opts.verbose:
datasetsMgr.PrintCrossSections()
datasetsMgr.PrintLuminosities()
# Print dataset information
if opts.verbose:
datasetsMgr.PrintInfo()
# Check if path exists
if not os.path.exists(opts.outputDir):
os.makedirs(opts.outputDir)
# Get all files under the input pseudo-multicrab
src_files = os.listdir(opts.mcrabs[0])
nDatasets = len(datasetsMgr.getAllDatasets())
nDirs = len(opts.mcrabs)
# For-loop: All files inside the directory (e.g. multicrab.cfg, lumi.json)
for i, fileName in enumerate(src_files, 1):
filePath = os.path.join(opts.mcrabs[0], fileName)
isFile = os.path.isfile(filePath)
# If not a file skip
if not isFile:
continue
else:
shutil.copy(filePath, opts.outputDir)
# For-loop: All datasets
for i, dataset in enumerate(datasetsMgr.getAllDatasets(), 1):
dsetName = dataset.getName()
# Create new directory with structure of pseudomulticrab
dirTree = os.path.join(opts.outputDir, dsetName, "res")
# Check if path exists
if not os.path.exists(dirTree):
os.makedirs(dirTree)
# Output file Name
outputFileName = "/histograms-%s.root" % (dsetName)
outputFileName = dirTree + outputFileName
Verbose("Creating ROOT file %s" % (outputFileName), True)
outputFile = ROOT.TFile.Open(outputFileName, "RECREATE")
# For-loop: All pseudo-multicrabs in list
for j, dirName in enumerate(opts.mcrabs, 1):
# Get root file from dataset
dirPath = os.path.join(dirName, dsetName, "res")
filePath = "%s/histograms-%s.root" % (dirPath, dsetName)
# Open input root file and change directory
inputFile = ROOT.TFile.Open(filePath)
outputFile.cd()
nFolders = len(inputFile.GetListOfKeys())
# For-loop: All folders in ROOT file
for k, key in enumerate(inputFile.GetListOfKeys(), 1):
folderName = key.GetName()
# Inform user of progress
msg = "{:<10} {:<2} {:>1} {:<2} {:<10} {:<2} {:>1} {:<2} {:<10} {:<2} {:>1} {:<2}".format("%sDataset" % (ShellStyles.HighlightAltStyle()), "%d" % i, "/", "%d" % (nDatasets), "%sPseudomulticrab" % (ShellStyles.NoteStyle()), "%d" % j, "/", "%d" % (nDirs), "%sFolder" % (ShellStyles.HighlightStyle()), "%d" % k, "/", "%d%s" % (nFolders, ShellStyles.NormalStyle()) )
aux.PrintFlushed(msg, i*j*k==1)
# Skip if object already exists
if (folderName in outputFile.GetListOfKeys()):
continue
Verbose("Merging %s" % folderName, False)
MergeFiles(inputFile.Get(folderName), outputFile, msg)
#p = Process(target=MergeFiles(inputFile.Get(folderName), outputFile, msg))
#p.start()
#p.join()
Verbose("Writing & closing file %s" % (outputFile.GetName()), True)
outputFile.Write()
outputFile.Close()
print
Print("Results saved in %s" % (ShellStyles.SuccessStyle() + opts.outputDir + ShellStyles.NormalStyle()), True)
return
def PlotEfficiency(datasetsMgr, numPath, denPath, eff_def):
# Definitions
myList = []
default_eff = None
datasetList = []
ttVariationEff = []
_kwargs = GetHistoKwargs(numPath, opts)
nx = 0
if len(_kwargs["binList"]) > 0:
xBins = _kwargs["binList"]
nx = len(xBins) - 1
counter = 0
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
d = dataset.getDatasetRootHisto(denPath)
num = n.getHistogram()
den = d.getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Calculations
total = den.Integral(0, den.GetXaxis().GetNbins() + 1)
selected = num.Integral(0, num.GetXaxis().GetNbins() + 1)
if 0:
print "Numerical Efficiency", numPath, dataset.getName(
), ":", round(selected / total, 3)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den)
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
datasetTT = datasetsMgr.getDataset("TT")
# Get the histograms
numTT = datasetTT.getDatasetRootHisto(numPath).getHistogram()
denTT = datasetTT.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
numTT = numTT.Rebin(nx, "", xBins) #num.Rebin(nx, "", xBins)
denTT = denTT.Rebin(nx, "", xBins) #den.Rebin(nx, "", xBins)
'''
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
nbinTT = numTT.GetBinContent(i)
dbinTT = denTT.GetBinContent(i)
eps = nbin/dbin
epsTT = nbinTT/dbinTT
ratioTT = eps/epsTT
if ratioTT > 1:
ratioTT = 1/ratioTT
#print "bin: ", i, "eps: ", round(eps,5) , "epsTT: ", round(epsTT,5)
#print "bin: ", i, "eps/epsTT: ", (1.0 - round(ratioTT, 3))*100
'''
eff_ref = ROOT.TEfficiency(numTT, denTT)
eff_ref.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
gEff = convert2TGraph(eff)
gEffRef = convert2TGraph(eff_ref)
# Keep the default tt and variations tt efficiency plots
if dataset.getName() == "TT":
default_eff = gEffRef.Clone()
else:
datasetList.append(dataset.getName())
ttVariationEff.append(gEff)
# Style definitions
stylesDef = styles.ttStyle
styles0 = styles.signalStyleHToTB300
styles1 = styles.signalStyleHToTB500
styles2 = styles.signalStyleHToTB800
styles3 = styles.signalStyleHToTB500
styles4 = styles.signalStyleHToTB1000
styles5 = styles.signalStyleHToTB2000
styles6 = styles.signalStyleHToTB180
styles7 = styles.signalStyleHToTB3000
styles8 = styles.signalStyleHToTB200
if dataset.getName() == "TT":
styles.ttStyle.apply(gEffRef)
legend_ref = "t#bar{t}"
if opts.type == "partonShower":
legend_ref = "t#bar{t} (Pythia8)"
elif opts.type == "evtGen":
legend_ref = "t#bar{t} (Powheg)"
refGraph = histograms.HistoGraph(gEffRef, legend_ref, "p", "P")
else:
styles.markerStyles[counter].apply(gEff)
legend = dataset.getName().replace("TT_", "t#bar{t} (").replace(
"isr", "ISR ").replace("fsr", "FSR ")
legend = legend.replace("hdamp", "hdamp ").replace("DOWN",
"down").replace(
"UP", "up")
legend = legend.replace("mtop1665", "m_{t} = 166.5 GeV")
legend = legend.replace("mtop1695", "m_{t} = 169.5 GeV")
legend = legend.replace("mtop1715", "m_{t} = 171.5 GeV")
legend = legend.replace("mtop1735", "m_{t} = 173.5 GeV")
legend = legend.replace("mtop1755", "m_{t} = 175.5 GeV")
legend = legend.replace("mtop1785", "m_{t} = 178.5 GeV")
legend = legend.replace("TuneEE5C", "Herwig++")
legend += ")"
counter += 1
#myList.append(histograms.HistoGraph(gEff, legend, "lp", "P"))
myList.append(histograms.HistoGraph(gEff, legend, "p", "P"))
units = "GeV/c"
if eff_def == "fakeTop":
_kwargs["xlabel"] = "candidate p_{T} (%s)" % (units)
elif eff_def == "inclusiveTop" or eff_def == "genuineTop":
_kwargs["xlabel"] = "generated top p_{T} (%s)" % (units)
else:
_kwargs["xlabel"] = "p_{T} (%s)" % (units)
# Define stuff
numPath = numPath.replace("AfterAllSelections_", "")
saveName = "Efficiency_%s_%s" % (eff_def, opts.type)
#saveName = saveName.replace("__", "_Inclusive_")
# Plot the efficiency
p = plots.ComparisonManyPlot(refGraph, myList, saveFormats=[])
savePath = os.path.join(opts.saveDir, opts.optMode)
plots.drawPlot(p, savePath, **_kwargs)
# Save plot in all formats
SavePlot(p, saveName, savePath, saveFormats=[".png", ".pdf", ".C"])
# ==============================================================================
# I need the uncertainties from the ratio of all plots (ONLY for Genuine)
# ==============================================================================
if eff_def == "genuineTop":
uncWriter = UncertaintyWriter()
jsonName = "uncertainties_%s_BDT_%s.json" % (opts.type, opts.BDT)
analysis = opts.analysisName
saveDir = os.path.join("", jsonName)
for i in range(0, len(datasetList)):
uncWriter.addParameters(datasetList[i], analysis, saveDir,
default_eff, ttVariationEff[i])
#print "i = ", i, " Dataset = ", datasetList[i]
#for iBin in range(1, len(xBins)):
#ratio = float(default_eff.GetEfficiency(iBin))/float(ttVariationEff[i].GetEfficiency(iBin))
#unc = 0.5*(1.0 - ratio)
#print "iBin = ", iBin, " Default TT=", default_eff.GetEfficiency(iBin), " Variation (", datasetList[i], ") =", ttVariationEff[i].GetEfficiency(iBin), " Uncertainty =", unc
uncWriter.writeJSON(jsonName)
return
def PlotEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
index = 0
_kwargs = GetHistoKwargs(numPath, opts)
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
#if "Fake" in numPath and "TT" in dataset.getName():
# continue
# Get the histograms
#num = dataset.getDatasetRootHisto(numPath).getHistogram()
#den = dataset.getDatasetRootHisto(denPath).getHistogram()
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
if "binList" in _kwargs:
xBins = _kwargs["binList"]
nx = len(xBins) - 1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Remove negative bins and ensure numerator bin <= denominator bin
CheckNegatives(num, den, True)
# RemoveNegatives(num)
# RemoveNegatives(den)
# Sanity check (Histograms are valid and consistent) - Always false!
# if not ROOT.TEfficiency.CheckConsistency(num, den):
# continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #
# Set the weights - Why is this needed?
if 0:
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
# Convert to TGraph
eff = convert2TGraph(eff)
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Append in list
myList.append(
histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()],
"lp", "P"))
# Define save name
saveName = "Eff_" + numPath.split("/")[-1] + "Over" + denPath.split(
"/")[-1]
# Plot the efficiency
p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses",
numPath.split("/")[0], opts.optMode)
#savePath = os.path.join(opts.saveDir, numPath.split("/")[0], opts.optMode)
save_path = savePath + opts.MVAcut
SavePlot(p, saveName, save_path, saveFormats=[".png", ".pdf", ".C"])
return
def PlotEfficiency(datasetsMgr, numPath, denPath, eff_def):
# Definitions
myList = []
default_eff = None
datasetList = []
ttVariationEff = []
_kwargs = GetHistoKwargs(numPath, opts)
nx = 0
if len(_kwargs["binList"]) > 0:
xBins = _kwargs["binList"]
nx = len(xBins)-1
counter = 0
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
d = dataset.getDatasetRootHisto(denPath)
num = n.getHistogram()
den = d.getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Calculations
total = den.Integral(0, den.GetXaxis().GetNbins()+1)
selected = num.Integral(0, num.GetXaxis().GetNbins()+1)
if 0:
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(selected/total, 3)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den)
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
datasetTT = datasetsMgr.getDataset("TT")
# Get the histograms
numTT = datasetTT.getDatasetRootHisto(numPath).getHistogram()
denTT = datasetTT.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
numTT = numTT.Rebin(nx, "", xBins) #num.Rebin(nx, "", xBins)
denTT = denTT.Rebin(nx, "", xBins) #den.Rebin(nx, "", xBins)
'''
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
nbinTT = numTT.GetBinContent(i)
dbinTT = denTT.GetBinContent(i)
eps = nbin/dbin
epsTT = nbinTT/dbinTT
ratioTT = eps/epsTT
if ratioTT > 1:
ratioTT = 1/ratioTT
#print "bin: ", i, "eps: ", round(eps,5) , "epsTT: ", round(epsTT,5)
#print "bin: ", i, "eps/epsTT: ", (1.0 - round(ratioTT, 3))*100
'''
eff_ref = ROOT.TEfficiency(numTT, denTT)
eff_ref.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
gEff = convert2TGraph(eff)
gEffRef = convert2TGraph(eff_ref)
# Keep the default tt and variations tt efficiency plots
if dataset.getName() == "TT":
default_eff = gEffRef.Clone()
else:
datasetList.append(dataset.getName())
ttVariationEff.append(gEff)
# Style definitions
stylesDef = styles.ttStyle
styles0 = styles.signalStyleHToTB300
styles1 = styles.signalStyleHToTB500
styles2 = styles.signalStyleHToTB800
styles3 = styles.signalStyleHToTB500
styles4 = styles.signalStyleHToTB1000
styles5 = styles.signalStyleHToTB2000
styles6 = styles.signalStyleHToTB180
styles7 = styles.signalStyleHToTB3000
styles8 = styles.signalStyleHToTB200
if dataset.getName() == "TT":
styles.ttStyle.apply(gEffRef)
legend_ref = "t#bar{t}"
if opts.type == "partonShower":
legend_ref = "t#bar{t} (Pythia8)"
elif opts.type == "evtGen":
legend_ref = "t#bar{t} (Powheg)"
refGraph = histograms.HistoGraph(gEffRef, legend_ref, "p", "P")
else:
styles.markerStyles[counter].apply(gEff)
legend = dataset.getName().replace("TT_", "t#bar{t} (").replace("isr", "ISR ").replace("fsr", "FSR ")
legend = legend.replace("hdamp", "hdamp ").replace("DOWN", "down").replace("UP", "up")
legend = legend.replace("mtop1665", "m_{t} = 166.5 GeV")
legend = legend.replace("mtop1695", "m_{t} = 169.5 GeV")
legend = legend.replace("mtop1715", "m_{t} = 171.5 GeV")
legend = legend.replace("mtop1735", "m_{t} = 173.5 GeV")
legend = legend.replace("mtop1755", "m_{t} = 175.5 GeV")
legend = legend.replace("mtop1785", "m_{t} = 178.5 GeV")
legend = legend.replace("TuneEE5C", "Herwig++")
legend += ")"
counter+=1
#myList.append(histograms.HistoGraph(gEff, legend, "lp", "P"))
myList.append(histograms.HistoGraph(gEff, legend, "p", "P"))
units = "GeV/c"
if eff_def == "fakeTop":
_kwargs["xlabel"] = "candidate p_{T} (%s)" % (units)
elif eff_def == "inclusiveTop" or eff_def == "genuineTop":
_kwargs["xlabel"] = "generated top p_{T} (%s)" % (units)
else:
_kwargs["xlabel"] = "p_{T} (%s)" % (units)
# Define stuff
numPath = numPath.replace("AfterAllSelections_","")
saveName = "Efficiency_%s_%s" % (eff_def, opts.type)
#saveName = saveName.replace("__", "_Inclusive_")
# Plot the efficiency
p = plots.ComparisonManyPlot(refGraph, myList, saveFormats=[])
savePath = os.path.join(opts.saveDir, opts.optMode)
plots.drawPlot(p, savePath, **_kwargs)
# Save plot in all formats
SavePlot(p, saveName, savePath, saveFormats = [".png", ".pdf", ".C"])
# ==============================================================================
# I need the uncertainties from the ratio of all plots (ONLY for Genuine)
# ==============================================================================
if eff_def == "genuineTop":
uncWriter = UncertaintyWriter()
jsonName = "uncertainties_%s_BDT_%s.json" % (opts.type, opts.BDT)
analysis = opts.analysisName
saveDir = os.path.join("", jsonName)
for i in range(0, len(datasetList)):
uncWriter.addParameters(datasetList[i], analysis, saveDir, default_eff, ttVariationEff[i])
#print "i = ", i, " Dataset = ", datasetList[i]
#for iBin in range(1, len(xBins)):
#ratio = float(default_eff.GetEfficiency(iBin))/float(ttVariationEff[i].GetEfficiency(iBin))
#unc = 0.5*(1.0 - ratio)
#print "iBin = ", iBin, " Default TT=", default_eff.GetEfficiency(iBin), " Variation (", datasetList[i], ") =", ttVariationEff[i].GetEfficiency(iBin), " Uncertainty =", unc
uncWriter.writeJSON(jsonName)
return
def PlotEfficiency(datasetsMgr, numPath, denPath):
# Definitions
myList = []
_kwargs = GetHistoKwargs(numPath, opts)
nx = 0
if len(_kwargs["binList"]) > 0:
xBins = _kwargs["binList"]
nx = len(xBins) - 1
counter = 0
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
d = dataset.getDatasetRootHisto(denPath)
num = n.getHistogram()
den = d.getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Calculations
total = den.Integral(0, den.GetXaxis().GetNbins() + 1)
selected = num.Integral(0, num.GetXaxis().GetNbins() + 1)
if 0:
print "Numerical Efficiency", numPath, dataset.getName(
), ":", round(selected / total, 3)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den)
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
datasetTT = datasetsMgr.getDataset("TT")
# Get the histograms
numTT = datasetTT.getDatasetRootHisto(numPath).getHistogram()
denTT = datasetTT.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
numTT = numTT.Rebin(nx, "", xBins) #num.Rebin(nx, "", xBins)
denTT = denTT.Rebin(nx, "", xBins) #den.Rebin(nx, "", xBins)
'''
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
nbinTT = numTT.GetBinContent(i)
dbinTT = denTT.GetBinContent(i)
eps = nbin/dbin
epsTT = nbinTT/dbinTT
ratioTT = eps/epsTT
if ratioTT > 1:
ratioTT = 1/ratioTT
#print "bin: ", i, "eps: ", round(eps,5) , "epsTT: ", round(epsTT,5)
#print "bin: ", i, "eps/epsTT: ", (1.0 - round(ratioTT, 3))*100
'''
eff_ref = ROOT.TEfficiency(numTT, denTT)
eff_ref.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
gEff = convert2TGraph(eff)
gEffRef = convert2TGraph(eff_ref)
# Style definitions
stylesDef = styles.ttStyle
styles0 = styles.signalStyleHToTB300
styles1 = styles.signalStyleHToTB500
styles2 = styles.signalStyleHToTB800
styles3 = styles.signalStyleHToTB500
styles4 = styles.signalStyleHToTB1000
styles5 = styles.signalStyleHToTB2000
styles6 = styles.signalStyleHToTB180
styles7 = styles.signalStyleHToTB3000
styles8 = styles.signalStyleHToTB200
if dataset.getName() == "TT":
styles.ttStyle.apply(gEffRef)
legend_ref = "t#bar{t}"
if opts.type == "partonShower":
legend_ref = "t#bar{t} (Pythia8)"
elif opts.type == "evtGen":
legend_ref = "t#bar{t} (Powheg)"
refGraph = histograms.HistoGraph(gEffRef, legend_ref, "p", "P")
else:
styles.markerStyles[counter].apply(gEff)
legend = dataset.getName().replace("TT_", "t#bar{t} (").replace(
"isr", "ISR ").replace("fsr", "FSR ")
legend = legend.replace("hdamp", "hdamp ").replace("DOWN",
"down").replace(
"UP", "up")
legend = legend.replace("mtop1665", "m_{t} = 166.5 GeV")
legend = legend.replace("mtop1695", "m_{t} = 169.5 GeV")
legend = legend.replace("mtop1715", "m_{t} = 171.5 GeV")
legend = legend.replace("mtop1735", "m_{t} = 173.5 GeV")
legend = legend.replace("mtop1755", "m_{t} = 175.5 GeV")
legend = legend.replace("mtop1785", "m_{t} = 178.5 GeV")
legend = legend.replace("TuneEE5C", "Herwig++")
legend += ")"
counter += 1
#myList.append(histograms.HistoGraph(gEff, legend, "lp", "P"))
myList.append(histograms.HistoGraph(gEff, legend, "p", "P"))
# Define stuff
numPath = numPath.replace("AfterAllSelections_", "")
saveName = "Efficiency_%s_%s" % (opts.folder, opts.type)
saveName = saveName.replace("__", "_Inclusive_")
# Plot the efficiency
p = plots.ComparisonManyPlot(refGraph, myList, saveFormats=[])
savePath = os.path.join(opts.saveDir, opts.optMode)
plots.drawPlot(p, savePath, **_kwargs)
# Save plot in all formats
SavePlot(p, saveName, savePath, saveFormats=[".png", ".pdf", ".C"])
return
def Fit (datasets, histo, function):
FitList = []
for dataset in datasets:
datasetName = dataset.getName()
print "Dataset = ", datasetName
hh = dataset.getDatasetRootHisto(histo)
hh.normalizeToOne()
h = hh.getHistogram()
#h = dataset.getDatasetRootHisto(histo).getHistogram()
xMin = h.GetXaxis().GetXmin()
xMax = h.GetXaxis().GetXmax()
yMin = 0
yMax = 1.2
#statOption = ROOT.TEfficiency.kFNormal
if "TT" in datasetName:
if function == "gaus":
fitGauss = ROOT.TF1("fitGauss", "gaus", -2.5, 2.5)
# TF1 *fitBoFreq = new TF1("fitBoFreq","[0]*x+[1]",0,20);
# h.Fit("gaus")
#fitTest = ROOT.TF1("fitTest", "0.01", -2.5, 2.5)
h.Fit("fitGauss","SRBM")
#h.GetListOfFunctions().Add(fitTest)
legend = "TT"
legend = "a legend"
print "Legend", legend
saveName = histo.split("/")[-1]+"_Fit"
print saveName
xTitle = "fixXTitle"
yTitle = "fixYTitle"
yMin = 0.
yMax = 0.03
xMin = -2.3
xMax = 2.3
kwargs = {}
options = {"ymin": yMin , "ymax": yMax, "xmin":xMin, "xMax":xMax}
FitList.append(h)
#p = plots.MCPlot(dataset, h, normalizeToLumi=0, saveFormats=[], **kwargs)
p = plots.PlotBase(datasetRootHistos=FitList, saveFormats=kwargs.get("saveFormats"))
p.createFrame(saveName, opts=options)
p.getFrame().GetXaxis().SetTitle(xTitle)
p.getFrame().GetYaxis().SetTitle(yTitle)
#p.histoMgr.setHistoDrawStyle(datasetName, "AP")
# Set range
p.getFrame().GetXaxis().SetRangeUser(xMin, xMax)
moveLegend = {"dx": -0.55, "dy": -0.01, "dh": -0.1}
p.setLegend(histograms.moveLegend(histograms.createLegend(), **moveLegend))
# Add Standard Texts to plot
histograms.addStandardTexts()
p.draw()
# Save plot in all formats
savePath = os.path.join(opts.saveDir, "HplusMasses", histo.split("/")[0], opts.optMode)
save_path = savePath
SavePlot(p, saveName, save_path)
return
def getEfficiency2D(datasetsMgr,
datasets,
numerator="Numerator",
denominator="Denominator",
**kwargs):
'''
TEfficiency method:
See https://root.cern.ch/doc/master/classTEfficiency.html
'''
HasKeys(["verbose"], **kwargs)
verbose = True #kwargs.get("verbose")
lumi = GetLumi(datasetsMgr)
# Select Statistic Options
statOption = ROOT.TEfficiency.kFCP
'''
statOption = ROOT.TEfficiency.kFCP # Clopper-Pearson
statOption = ROOT.TEfficiency.kFNormal # Normal Approximation
statOption = ROOT.TEfficiency.kFWilson # Wilson
statOption = ROOT.TEfficiency.kFAC # Agresti-Coull
statOption = ROOT.TEfficiency.kFFC # Feldman-Cousins
statOption = ROOT.TEfficiency.kBBJeffrey # Jeffrey
statOption = ROOT.TEfficiency.kBBUniform # Uniform Prior
statOption = ROOT.TEfficiency.kBBayesian # Custom Prior
'''
print "getEfficiency function"
first = True
teff = ROOT.TEfficiency()
# teff.SetStatisticOption(statOption)
print "Loop over Datasets"
for dataset in datasets:
print "Datasets"
#datasets.normalizeMCByLuminosity()
for dataset in datasets:
num = dataset.getDatasetRootHisto(numerator)
den = dataset.getDatasetRootHisto(denominator)
if dataset.isMC():
num.normalizeToLuminosity(lumi)
den.normalizeToLuminosity(lumi)
#num.normalizeMCByLuminosity()
#den.normalizeMCByLuminosity()
# Get Numerator and Denominator
n = num.getHistogram()
d = den.getHistogram()
#tn = None
#td = None
#n.normalizeMCByLuminosity()
#d.normalizeMCByLuminosity()
#n = dataset.getDatasetRootHisto(numerator).getHistogram()
#d = dataset.getDatasetRootHisto(denominator).getHistogram()
if d.GetEntries() == 0 or n.GetEntries() == 0:
print "Denominator Or Numerator has no entries"
continue
# Check Negatives
CheckNegatives(n, d, True)
# Remove Negatives
RemoveNegatives(n)
#RemoveNegatives(d)
NumeratorBins = n.GetNbinsX()
DenominatorBins = d.GetNbinsX()
# Sanity Check
if (NumeratorBins != DenominatorBins):
raise Exception("Numerator and Denominator Bins are NOT equal!")
nBinsX = d.GetNbinsX()
xMin = d.GetXaxis().GetXmin()
xMax = d.GetXaxis().GetXmax()
nBinsY = d.GetNbinsY()
#yMin = d.GetYaxis().GetYmin()
#yMax = d.GetYaxis().GetYmax()
print("NoProblem till here asdasd...")
# ----------------------------------------------------------------------------------------- #
# Ugly hack to ignore EMPTY (in the wanted range) histograms with overflows/underflows
# ----------------------------------------------------------------------------------------- #
print "\n"
print "=========== getEfficiency:"
print "Dataset = ", dataset.getName()
#print "Numerator :", n.GetName(), " entries=", n.GetEntries(), " Bins=", n.GetNbinsX(), " Low edge=", n.GetBinLowEdge(1)
#print "Denominator:", d.GetName(), " entries=", d.GetEntries(), " Bins=", d.GetNbinsX(), " Low edge=", d.GetBinLowEdge(1)
print "\n"
print ">>>>>> Sanity Check: <<<<<<"
print "Numerator Mean = ", n.GetMean()
print "Numerator RMS = ", n.GetRMS()
print "Numerator Integral = ", n.Integral()
print "Denominator Mean = ", d.GetMean()
print "Denominator RMS = ", d.GetRMS()
print "Denominator Integral = ", d.Integral()
if (n.GetMean() == 0 or d.GetMean() == 0): continue
if (n.GetRMS() == 0 or d.GetRMS() == 0): continue
if (n.Integral() == 0 or d.Integral() == 0): continue
print "Passed the sanity check"
eff = ROOT.TEfficiency(n, d)
eff.SetStatisticOption(statOption)
# if "TT" in dataset.getName():
# print " "
# print " TT sample"
#for iBin in range(1, nBins+1):
# print iBin, "x=", n.GetBinLowEdge(iBin), " Num=", n.GetBinContent(iBin), " Den=", d.GetBinContent(iBin)," Eff=", eff.GetEfficiency(iBin)
# "Contrib. =", d.GetBinContent(iBin)/d.Integral(1, nBins)*100.0, "Contrib. = ", n.GetBinContent(iBin)/n.Integral(1, nBins)*100.0,
'''
#if (verbose):
print "\n"
for iBin in range(1,nBins+1):
#print iBin, "x=", n.GetBinLowEdge(iBin), " Numerator=", n.GetBinContent(iBin), " Denominator=", d.GetBinContent(iBin), " Efficiency=", eff.GetEfficiency(iBin\
), " Weight=", eff.GetWeight()
print "\n"
'''
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
#print "dataset=", dataset.getName(), "has weight=", weight
#print " Efficiency plot has weight=", eff.GetWeight()
if first:
teff = eff
first = False
if dataset.isData():
tn = n
td = d
else:
teff.Add(eff)
#print " "
#print "Adding eff to TEfficiency="
#for iBin in range(1, nBins+1):
# print iBin, "x=", n.GetBinLowEdge(iBin), " Numerator=", n.GetBinContent(iBin), "Contrib. = ", n.GetBinContent(iBin)/n.Integral(1, nBins)*100.0, " Denominator=", d.GetBinContent(iBin), "Contrib. =", d.GetBinContent(iBin)/d.Integral(1, nBins)*100.0, " Efficiency=", teff.GetEfficiency(iBin), " Weight=", teff.GetWeight()
if dataset.isData():
tn.Add(n)
td.Add(d)
if dataset.isData():
teff = ROOT.TEfficiency(tn, td)
teff.SetStatisticOption(statOption)
'''
print " ------------------------- Final Data Plot ------------------------- "
print "Integral = ", tn.Integral(1, nBins)
print "Numerator:"
for iBin in range(1, nBins+1):
print iBin, "x=", tn.GetBinLowEdge(iBin), " Bin Content = ", tn.GetBinContent(iBin), " Percentage=", tn.GetBinContent(iBin)/tn.Integral(1, nBins)*100.0
print "Denominator: "
print "Integral = ", td.Integral(1,nBins)
for iBin in range(1, nBins+1):
print iBin, "x=", td.GetBinLowEdge(iBin), " Bin Content = ", td.GetBinContent(iBin), " Percentage=", td.GetBinContent(iBin)/td.Integral(1, nBins)*100
print "-------------------------------------------------------------------- "
'''
print " -----------------> Final tEff"
#for iBin in range(1,nBins+1):
# print iBin, "x=", n.GetBinLowEdge(iBin)," Efficiency=", teff.GetEfficiency(iBin), " Weight = ", teff.GetWeight()
return teff
def PlotMC_ForEffPlots(datasetsMgr, histoName, intLumi):
index = 0
for dataset in datasetsMgr.getAllDatasets():
datasetName = dataset.getName()
rootHisto = dataset.getDatasetRootHisto(histoName)
rootHisto.normalizeToLuminosity(intLumi)
histo = rootHisto.getHistogram()
kwargs = {}
if index == 0:
# Apply Styles
if "TT" in datasetsMgr.getAllDatasets():
p.histoMgr.setHistoDrawStyle("TT", "AP")
p.histoMgr.setHistoLegendStyle("TT", "LP")
index = 1
else:
# Apply Styles
if "TT" in datasetsMgr.getAllDatasets():
p.histoMgr.setHistoDrawStyle("TTTT", "AP")
p.histoMgr.setHistoLegendStyle("TTTT", "LP")
_xlabel = "p_{T} (GeV/c)"
logY = False
_rebinX = 1
units = "GeV/c"
_format = "%0.1f" + units
_opts = {"ymin": 1e-3, "ymaxfactor": 1.0}
_cutBox = False
# _cutBox = {"cutValue": 0.5, "fillColor": 16, "box": False, "line": False, "greaterThan": True}
plots.drawPlot(
p,
histo,
xlabel=_xlabel,
ylabel="Arbitrary Units / %s" % (_format),
log=logY,
rebinX=_rebinX,
cmsExtraText="Preliminary",
createLegend={
"x1": 0.58,
"y1": 0.65,
"x2": 0.92,
"y2": 0.92
},
opts=_opts,
opts2={
"ymin": 0.6,
"ymax": 1.4
},
cutBox=_cutBox,
)
# Save plot in all formats
saveName = histo.split("/")[-1]
savePath = os.path.join(opts.saveDir, "HplusMasses",
histo.split("/")[0], opts.optMode)
SavePlot(p, saveName, savePath)
return
def PlotEfficiency(datasetsMgr, numPath, denPath):
# Definitions
myList = []
_kwargs = GetHistoKwargs(numPath, opts)
nx = 0
if len(_kwargs["binList"]) > 0:
xBins = _kwargs["binList"]
nx = len(xBins)-1
counter = 0
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
if dataset.isMC():
n = dataset.getDatasetRootHisto(numPath)
d = dataset.getDatasetRootHisto(denPath)
num = n.getHistogram()
den = d.getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
else:
num = dataset.getDatasetRootHisto(numPath).getHistogram()
den = dataset.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
# Calculations
total = den.Integral(0, den.GetXaxis().GetNbins()+1)
selected = num.Integral(0, num.GetXaxis().GetNbins()+1)
if 0:
print "Numerical Efficiency", numPath, dataset.getName(), ":", round(selected/total, 3)
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den)
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
datasetTT = datasetsMgr.getDataset("TT")
# Get the histograms
numTT = datasetTT.getDatasetRootHisto(numPath).getHistogram()
denTT = datasetTT.getDatasetRootHisto(denPath).getHistogram()
if nx > 0:
numTT = numTT.Rebin(nx, "", xBins) #num.Rebin(nx, "", xBins)
denTT = denTT.Rebin(nx, "", xBins) #den.Rebin(nx, "", xBins)
'''
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
nbinTT = numTT.GetBinContent(i)
dbinTT = denTT.GetBinContent(i)
eps = nbin/dbin
epsTT = nbinTT/dbinTT
ratioTT = eps/epsTT
if ratioTT > 1:
ratioTT = 1/ratioTT
#print "bin: ", i, "eps: ", round(eps,5) , "epsTT: ", round(epsTT,5)
#print "bin: ", i, "eps/epsTT: ", (1.0 - round(ratioTT, 3))*100
'''
eff_ref = ROOT.TEfficiency(numTT, denTT)
eff_ref.SetStatisticOption(ROOT.TEfficiency.kFCP) #FCP
# Convert to TGraph
gEff = convert2TGraph(eff)
gEffRef = convert2TGraph(eff_ref)
# Style definitions
stylesDef = styles.ttStyle
styles0 = styles.signalStyleHToTB300
styles1 = styles.signalStyleHToTB500
styles2 = styles.signalStyleHToTB800
styles3 = styles.signalStyleHToTB500
styles4 = styles.signalStyleHToTB1000
styles5 = styles.signalStyleHToTB2000
styles6 = styles.signalStyleHToTB180
styles7 = styles.signalStyleHToTB3000
styles8 = styles.signalStyleHToTB200
if dataset.getName() == "TT":
styles.ttStyle.apply(gEffRef)
legend_ref = "t#bar{t}"
if opts.type == "partonShower":
legend_ref = "t#bar{t} (Pythia8)"
elif opts.type == "evtGen":
legend_ref = "t#bar{t} (Powheg)"
refGraph = histograms.HistoGraph(gEffRef, legend_ref, "p", "P")
else:
styles.markerStyles[counter].apply(gEff)
legend = dataset.getName().replace("TT_", "t#bar{t} (").replace("isr", "ISR ").replace("fsr", "FSR ")
legend = legend.replace("hdamp", "hdamp ").replace("DOWN", "down").replace("UP", "up")
legend = legend.replace("mtop1665", "m_{t} = 166.5 GeV")
legend = legend.replace("mtop1695", "m_{t} = 169.5 GeV")
legend = legend.replace("mtop1715", "m_{t} = 171.5 GeV")
legend = legend.replace("mtop1735", "m_{t} = 173.5 GeV")
legend = legend.replace("mtop1755", "m_{t} = 175.5 GeV")
legend = legend.replace("mtop1785", "m_{t} = 178.5 GeV")
legend = legend.replace("TuneEE5C", "Herwig++")
legend += ")"
counter+=1
#myList.append(histograms.HistoGraph(gEff, legend, "lp", "P"))
myList.append(histograms.HistoGraph(gEff, legend, "p", "P"))
# Define stuff
numPath = numPath.replace("AfterAllSelections_","")
saveName = "Efficiency_%s_%s" % (opts.folder, opts.type)
saveName = saveName.replace("__", "_Inclusive_")
# Plot the efficiency
p = plots.ComparisonManyPlot(refGraph, myList, saveFormats=[])
savePath = os.path.join(opts.saveDir, opts.optMode)
plots.drawPlot(p, savePath, **_kwargs)
# Save plot in all formats
SavePlot(p, saveName, savePath, saveFormats = [".png", ".pdf", ".C"])
return
def PlotEfficiency(datasetsMgr, numPath, denPath, intLumi):
# Definitions
myList = []
myBckList = []
index = 0
_kwargs = GetHistoKwargs(denPath, opts)
counter = 0
# For-loop: All datasets
for dataset in datasetsMgr.getAllDatasets():
name_N = numPath
name_D = denPath
# Get the histograms
#num = dataset.getDatasetRootHisto(numPath).getHistogram()
#den = dataset.getDatasetRootHisto(denPath).getHistogram()
#if "TT" in dataset.getName():
# numPath = numPath.replace("HiggsTop", "AllTop")
# denPath = denPath.replace("HiggsTop", "AllTop")
# numPath = numPath.replace("AssocTop", "AllTop")
# denPath = denPath.replace("AssocTop", "AllTop")
n = dataset.getDatasetRootHisto(numPath)
n.normalizeToLuminosity(intLumi)
num = n.getHistogram()
d = dataset.getDatasetRootHisto(denPath)
d.normalizeToLuminosity(intLumi)
den = d.getHistogram()
if "binList" in _kwargs:
xBins = _kwargs["binList"]
nx = len(xBins)-1
num = num.Rebin(nx, "", xBins)
den = den.Rebin(nx, "", xBins)
for i in range(1, num.GetNbinsX()+1):
nbin = num.GetBinContent(i)
dbin = den.GetBinContent(i)
#print dataset.getName(), nbin, dbin
if (nbin > dbin):
print "error"
# Sanity checks
if den.GetEntries() == 0 or num.GetEntries() == 0:
continue
if num.GetEntries() > den.GetEntries():
continue
# Remove negative bins and ensure numerator bin <= denominator bin
#CheckNegatives(num, den, False)
#CheckNegatives(num, den, True)
#RemoveNegatives(num)
#RemoveNegatives(den)
# Sanity check (Histograms are valid and consistent) - Always false!
# if not ROOT.TEfficiency.CheckConsistency(num, den):
# continue
# Create Efficiency plots with Clopper-Pearson stats
eff = ROOT.TEfficiency(num, den) # fixme: investigate warnings
eff.SetStatisticOption(ROOT.TEfficiency.kFCP) #
# Set the weights - Why is this needed?
if 0:
weight = 1
if dataset.isMC():
weight = dataset.getCrossSection()
eff.SetWeight(weight)
# Convert to TGraph
eff = convert2TGraph(eff)
# Apply default style (according to dataset name)
plots._plotStyles[dataset.getName()].apply(eff)
# Apply random histo styles and append
if "charged" in dataset.getName().lower():
counter +=1
mass = dataset.getName().split("M_")[-1]
styles.markerStyles[counter].apply(eff)
if "300" in mass or "650" in mass:
s = styles.getSignalStyleHToTB_M(mass)
s.apply(eff)
eff.SetLineStyle(ROOT.kSolid)
eff.SetLineWidth(3)
eff.SetMarkerSize(1.2)
'''
mass = dataset.getName().split("M_")[-1]
mass = mass.replace("650", "1000")
s = styles.getSignalStyleHToTB_M(mass)
s.apply(eff)
'''
'''
ttStyle = styles.getEWKLineStyle()
if "tt" in dataset.getName().lower():
ttStyle.apply(eff)
'''
# Append in list
#if "charged" in dataset.getName().lower():
# if "m_500" in dataset.getName().lower():
if 1:
#if "tt" in dataset.getName().lower():
if "m_500" in dataset.getName().lower():
eff_ref = histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P")
else:
myList.append(histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P"))
#elif "tt" in dataset.getName().lower():
# eff_ref = histograms.HistoGraph(eff, plots._legendLabels[dataset.getName()], "lp", "P")
# Define save name
saveName = "Eff_" + name_N.split("/")[-1] + "Over"+ name_D.split("/")[-1]
# Plot the efficiency
#p = plots.PlotBase(datasetRootHistos=myList, saveFormats=[])
p = plots.ComparisonManyPlot(eff_ref, myList, saveFormats=[])
plots.drawPlot(p, saveName, **_kwargs)
# Save plot in all formats
savePath = os.path.join(opts.saveDir, name_N.split("/")[0], opts.optMode)
SavePlot(p, saveName, savePath, saveFormats = [".png", ".C", ".pdf"])#, ".pdf"])
return
