def _doCalculate(self, shape, moduleInfoString, normFactors, optionPrintPurityByBins, optionDoNQCDByBinHistograms):
'''
Calculates the result
'''
Verbose("Calculate final shape in signal region (shape * w_QCD) & initialize result containers", True)
nSplitBins = shape.getNumberOfPhaseSpaceSplitBins()
Verbose("Create Shape", True)
self._resultShape = aux.Clone(shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShape.Reset()
self._resultShape.SetTitle("NQCDFinal_Total_%s"%moduleInfoString)
self._resultShape.SetName("NQCDFinal_Total_%s"%moduleInfoString)
Verbose("Create EWK shape", True)
self._resultShapeEWK = aux.Clone(shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShapeEWK.Reset()
self._resultShapeEWK.SetTitle("NQCDFinal_EWK_%s"%moduleInfoString)
self._resultShapeEWK.SetName("NQCDFinal_EWK_%s"%moduleInfoString)
Verbose("Create Purity shape", True)
self._resultShapePurity = aux.Clone(shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShapePurity.Reset()
self._resultShapePurity.SetTitle("NQCDFinal_Purity_%s"%moduleInfoString)
self._resultShapePurity.SetName("NQCDFinal_Purity_%s"%moduleInfoString)
self._histogramsList = []
myUncertaintyLabels = ["statData", "statEWK"]
self._resultCountObject = extendedCount.ExtendedCount(0.0, [0.0, 0.0], myUncertaintyLabels)
if optionDoNQCDByBinHistograms:
for i in range(0, nSplitBins):
hBin = aux.Clone(self._resultShape)
hBin.SetTitle("NQCDFinal_%s_%s"%(shape.getPhaseSpaceBinFileFriendlyTitle(i).replace(" ",""), moduleInfoString))
hBin.SetName("NQCDFinal_%s_%s"%(shape.getPhaseSpaceBinFileFriendlyTitle(i).replace(" ",""), moduleInfoString))
self._histogramsList.append(hBin)
if isinstance(self._resultShape, ROOT.TH2):
self._doCalculate2D(nSplitBins, shape, normFactors, optionPrintPurityByBins, optionDoNQCDByBinHistograms, myUncertaintyLabels)
return
# Intialize counters for purity calculation in final shape binning
myShapeDataSum = []
myShapeDataSumUncert = []
myShapeEwkSum = []
myShapeEwkSumUncert = []
# For-loop: All Bins
for j in range(1,self._resultShape.GetNbinsX()+1):
myShapeDataSum.append(0.0)
myShapeDataSumUncert.append(0.0)
myShapeEwkSum.append(0.0)
myShapeEwkSumUncert.append(0.0)
Verbose("Calculate results separately for each phase-space bin and then combine", True)
# For-loop: All measurement bins (e.g. tau pT bins for HToTauNu)
for i in range(0, nSplitBins):
# N.B: The \"Inclusive\" value is in the zeroth bin
Verbose("Get data-driven QCD, data, and MC EWK shape histogram for the phase-space bin", True)
h = shape.getDataDrivenQCDHistoForSplittedBin(i)
hData = shape.getDataHistoForSplittedBin(i)
hEwk = shape.getEwkHistoForSplittedBin(i)
Verbose("Get normalization factor", True)
wQCDLabel = shape.getPhaseSpaceBinFileFriendlyTitle(i)
if self._optionUseInclusiveNorm:
wQCDLabel = "Inclusive"
wQCD = 0.0
if not wQCDLabel in normFactors.keys():
msg = "No normalization factors available for bin '%s' when accessing histogram %s! Ignoring this bin..." % (wQCDLabel,shape.getHistoName())
Print(ShellStyles.WarningLabel() + msg, True)
else:
wQCD = normFactors[wQCDLabel]
msg = "Weighting bin \"%i\" (label=\"%s\") with normFactor \"%s\"" % (i, wQCDLabel, wQCD)
Verbose(ShellStyles.NoteLabel() + msg, True)
# Construct info table (debugging)
table = []
align = "{:>6} {:^10} {:^15} {:>10} {:>10} {:>10} {:^3} {:^8} {:^3} {:^8}"
header = align.format("Bin", "Width", "Range", "Content", "NormFactor", "QCD", "+/-", "Data", "+/-", "EWK")
hLine = "="*90
table.append("{:^90}".format(shape.getHistoName()))
table.append(hLine)
table.append(header)
table.append(hLine)
binSum = 0.0
nBins = h.GetNbinsX()
binWidth = hData.GetBinWidth(0)
xMin = hData.GetXaxis().GetBinCenter(0)
xMax = hData.GetXaxis().GetBinCenter(nBins+1)
# For-Loop (nested): All bins in the shape histogram
for j in range(1, nBins+1):
# Initialise values
myResult = 0.0
myStatDataUncert = 0.0
myStatEwkUncert = 0.0
# Ignore zero bins
if abs(h.GetBinContent(j)) > 0.00001:
Verbose("Calculating the result")
binContent = h.GetBinContent(j)
binRange = "%.1f -> %.1f" % (h.GetXaxis().GetBinLowEdge(j), h.GetXaxis().GetBinUpEdge(j) )
binWidth = GetTH1BinWidthString(h, j)
binSum += binContent
myResult = binContent * wQCD #apply normalisation factor (transfer from CR to SR))
Verbose("Calculate abs. stat. uncert. for data and for MC EWK (Do not calculate here MC EWK syst.)", True)
myStatDataUncert = hData.GetBinError(j) * wQCD
myStatEwkUncert = hEwk.GetBinError(j) * wQCD
table.append(align.format(j, binWidth, binRange, "%0.1f" % binContent, wQCD, "%.1f" % myResult, "+/-", "%.1f" % myStatDataUncert, "+/-", "%.1f" % myStatEwkUncert))
# Get count object
myCountObject = extendedCount.ExtendedCount(myResult, [myStatDataUncert, myStatEwkUncert], myUncertaintyLabels)
self._resultCountObject.add(myCountObject)
if optionDoNQCDByBinHistograms:
Verbose("Setting bin content \"%i\"" % (j), True)
self._histogramsList[i].SetBinContent(j, myCountObject.value())
self._histogramsList[i].SetBinError(j, myCountObject.statUncertainty())
binContent = self._resultShape.GetBinContent(j) + myCountObject.value()
binError = self._resultShape.GetBinError(j) + myCountObject.statUncertainty()**2
Verbose("Setting bin %i to content %0.1f +/- %0.1f" % (j, binContent, binError), j==0)
self._resultShape.SetBinContent(j, binContent)
self._resultShape.SetBinError(j, binError) # Sum squared (take sqrt outside loop on final squared sum)
Verbose("Sum items for purity calculation", True)
myShapeDataSum[j-1] += hData.GetBinContent(j)*wQCD
myShapeDataSumUncert[j-1] += (hData.GetBinError(j)*wQCD)**2
myShapeEwkSum[j-1] += hEwk.GetBinContent(j)*wQCD
myShapeEwkSumUncert[j-1] += (hEwk.GetBinError(j)*wQCD)**2
# Delete the shape histograms
h.Delete()
hData.Delete()
hEwk.Delete()
# For-loop: All shape bins
for j in range(1,self._resultShape.GetNbinsX()+1):
# Take square root of uncertainties
self._resultShape.SetBinError(j, math.sqrt(self._resultShape.GetBinError(j)))
# Print detailed results in a formatted table
qcdResults = self._resultCountObject.getResultAndStatErrorsDict()
bins = "%0.f-%.0f" % (1, nBins)
binRange = "%.1f -> %.1f" % (xMin, xMax)
binSum = "%.1f" % binSum
nQCD = "%.1f" % qcdResults["value"]
dataStat = "%.1f" % qcdResults["statData"]
ewkStat = "%.1f" % qcdResults["statEWK"]
table.append(align.format(bins, binWidth, binRange, binSum, wQCD, nQCD, "+/-", dataStat, "+/-", ewkStat))
table.append(hLine)
for i, line in enumerate(table):
if i == len(table)-2:
Verbose(ShellStyles.TestPassedStyle()+line+ShellStyles.NormalStyle(), i==0)
else:
Verbose(line, i==0)
if optionPrintPurityByBins:
Verbose("Printing Shape Purity bin-by-bin.", True)
self.PrintPurityByBins(nBins, shape, myShapeDataSum, myShapeDataSumUncert, myShapeEwkSum, myShapeEwkSumUncert)
return
def _doCalculate(self, shape, moduleInfoString, normFactors,
optionPrintPurityByBins, optionDoNQCDByBinHistograms):
# Calculate final shape in signal region (shape * w_QCD)
nSplitBins = shape.getNumberOfPhaseSpaceSplitBins()
# Initialize result containers
self._resultShape = aux.Clone(
shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShape.Reset()
self._resultShape.SetTitle("NQCDFinal_Total_%s" % moduleInfoString)
self._resultShape.SetName("NQCDFinal_Total_%s" % moduleInfoString)
self._resultShapeEWK = aux.Clone(
shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShapeEWK.Reset()
self._resultShapeEWK.SetTitle("NQCDFinal_EWK_%s" % moduleInfoString)
self._resultShapeEWK.SetName("NQCDFinal_EWK_%s" % moduleInfoString)
self._resultShapePurity = aux.Clone(
shape.getDataDrivenQCDHistoForSplittedBin(0))
self._resultShapePurity.Reset()
self._resultShapePurity.SetTitle("NQCDFinal_Purity_%s" %
moduleInfoString)
self._resultShapePurity.SetName("NQCDFinal_Purity_%s" %
moduleInfoString)
self._histogramsList = []
myUncertaintyLabels = ["statData", "statEWK"]
self._resultCountObject = extendedCount.ExtendedCount(
0.0, [0.0, 0.0], myUncertaintyLabels)
if optionDoNQCDByBinHistograms:
for i in range(0, nSplitBins):
hBin = aux.Clone(self._resultShape)
hBin.SetTitle(
"NQCDFinal_%s_%s" %
(shape.getPhaseSpaceBinFileFriendlyTitle(i).replace(
" ", ""), moduleInfoString))
hBin.SetName(
"NQCDFinal_%s_%s" %
(shape.getPhaseSpaceBinFileFriendlyTitle(i).replace(
" ", ""), moduleInfoString))
self._histogramsList.append(hBin)
if isinstance(self._resultShape, ROOT.TH2):
self._doCalculate2D(nSplitBins, shape, normFactors,
optionPrintPurityByBins,
optionDoNQCDByBinHistograms,
myUncertaintyLabels)
return
# Intialize counters for purity calculation in final shape binning
myShapeDataSum = []
myShapeDataSumUncert = []
myShapeEwkSum = []
myShapeEwkSumUncert = []
for j in range(1, self._resultShape.GetNbinsX() + 1):
myShapeDataSum.append(0.0)
myShapeDataSumUncert.append(0.0)
myShapeEwkSum.append(0.0)
myShapeEwkSumUncert.append(0.0)
# Calculate results separately for each phase space bin and then combine
for i in range(0, nSplitBins):
# Get data-driven QCD, data, and MC EWK shape histogram for the phase space bin
h = shape.getDataDrivenQCDHistoForSplittedBin(i)
hData = shape.getDataHistoForSplittedBin(i)
hEwk = shape.getEwkHistoForSplittedBin(i)
# Get normalization factor
wQCDLabel = shape.getPhaseSpaceBinFileFriendlyTitle(i)
if self._optionUseInclusiveNorm:
wQCDLabel = "Inclusive"
wQCD = 0.0
if not wQCDLabel in normFactors.keys():
print ShellStyles.WarningLabel(
) + "No normalization factors available for bin '%s' when accessing histogram %s! Ignoring this bin..." % (
wQCDLabel, shape.getHistoName())
else:
wQCD = normFactors[wQCDLabel]
# Loop over bins in the shape histogram
for j in range(1, h.GetNbinsX() + 1):
myResult = 0.0
myStatDataUncert = 0.0
myStatEwkUncert = 0.0
if abs(h.GetBinContent(j)) > 0.00001: # Ignore zero bins
# Calculate result
myResult = h.GetBinContent(j) * wQCD
# Calculate abs. stat. uncert. for data and for MC EWK
myStatDataUncert = hData.GetBinError(j) * wQCD
myStatEwkUncert = hEwk.GetBinError(j) * wQCD
#errorPropagation.errorPropagationForProduct(hLeg1.GetBinContent(j), hLeg1Data.GetBinError(j), myEffObject.value(), myEffObject.uncertainty("statData"))
# Do not calculate here MC EWK syst.
myCountObject = extendedCount.ExtendedCount(
myResult, [myStatDataUncert, myStatEwkUncert],
myUncertaintyLabels)
self._resultCountObject.add(myCountObject)
if optionDoNQCDByBinHistograms:
self._histogramsList[i].SetBinContent(
j, myCountObject.value())
self._histogramsList[i].SetBinError(
j, myCountObject.statUncertainty())
self._resultShape.SetBinContent(
j,
self._resultShape.GetBinContent(j) + myCountObject.value())
self._resultShape.SetBinError(
j,
self._resultShape.GetBinError(j) +
myCountObject.statUncertainty()**2) # Sum squared
# Sum items for purity calculation
myShapeDataSum[j - 1] += hData.GetBinContent(j) * wQCD
myShapeDataSumUncert[j - 1] += (hData.GetBinError(j) * wQCD)**2
myShapeEwkSum[j - 1] += hEwk.GetBinContent(j) * wQCD
myShapeEwkSumUncert[j - 1] += (hEwk.GetBinError(j) * wQCD)**2
h.Delete()
hData.Delete()
hEwk.Delete()
# Take square root of uncertainties
for j in range(1, self._resultShape.GetNbinsX() + 1):
self._resultShape.SetBinError(
j, math.sqrt(self._resultShape.GetBinError(j)))
# Print result
print "NQCD Integral(%s) = %s " % (
shape.getHistoName(),
self._resultCountObject.getResultStringFull("%.1f"))
# Print purity as function of final shape bins
if optionPrintPurityByBins:
print "Purity of shape %s" % shape.getHistoName()
print "shapeBin purity purityUncert"
for j in range(1, self._resultShape.GetNbinsX() + 1):
myPurity = 0.0
myPurityUncert = 0.0
if abs(myShapeDataSum[j - 1]) > 0.000001:
myPurity = 1.0 - myShapeEwkSum[j - 1] / myShapeDataSum[j - 1]
myPurityUncert = errorPropagation.errorPropagationForDivision(
myShapeEwkSum[j - 1],
math.sqrt(myShapeEwkSumUncert[j - 1]),
myShapeDataSum[j - 1],
math.sqrt(myShapeDataSumUncert[j - 1]))
# Store MC EWK content
self._resultShapeEWK.SetBinContent(j, myShapeEwkSum[j - 1])
self._resultShapeEWK.SetBinError(
j, math.sqrt(myShapeEwkSumUncert[j - 1]))
self._resultShapePurity.SetBinContent(j, myPurity)
self._resultShapePurity.SetBinError(j, myPurityUncert)
# Print purity info of final shape
if optionPrintPurityByBins:
myString = ""
if j < self._resultShape.GetNbinsX():
myString = "%d..%d" % (
self._resultShape.GetXaxis().GetBinLowEdge(j),
self._resultShape.GetXaxis().GetBinUpEdge(j))
else:
myString = ">%d" % (
self._resultShape.GetXaxis().GetBinLowEdge(j))
myString += " %.3f %.3f" % (myPurity, myPurityUncert)
print myString
def _doCalculate2D(self, nSplitBins, shape, normFactors, optionPrintPurityByBins, optionDoNQCDByBinHistograms, myUncertaintyLabels):
'''
Calculates the result for 2D histograms
'''
# Intialize counters for purity calculation in final shape binning
myShapeDataSum = []
myShapeDataSumUncert = []
myShapeEwkSum = []
myShapeEwkSumUncert = []
myList = []
for k in range(1,self._resultShape.GetNbinsY()+1):
myList.append(0.0)
for j in range(1,self._resultShape.GetNbinsX()+1):
myShapeDataSum.append(myList[:])
myShapeDataSumUncert.append(myList[:])
myShapeEwkSum.append(myList[:])
myShapeEwkSumUncert.append(myList[:])
# Calculate results separately for each phase-space bin, and then combine them to get inclusive result
for i in range(0, nSplitBins):
# Get data-driven QCD, data, and MC EWK shape histogram for the phase space bin
h = shape.getDataDrivenQCDHistoForSplittedBin(i)
hData = shape.getDataHistoForSplittedBin(i)
hEwk = shape.getEwkHistoForSplittedBin(i)
# Get normalization factor
wQCDLabel = shape.getPhaseSpaceBinFileFriendlyTitle(i)
if self._optionUseInclusiveNorm:
wQCDLabel = "Inclusive"
wQCD = 0.0
if not wQCDLabel in normFactors.keys():
msg = "No normalization factors available for bin '%s' when accessing histogram %s! Ignoring this bin..." % (wQCDLabel, shape.getHistoName())
print ShellStyles.WarningLabel() + msg
else:
wQCD = normFactors[wQCDLabel]
# Loop over bins in the shape histogram
for j in range(1,h.GetNbinsX()+1):
for k in range(1,h.GetNbinsY()+1):
myResult = 0.0
myStatDataUncert = 0.0
myStatEwkUncert = 0.0
if abs(h.GetBinContent(j,k)) > 0.00001: # Ignore zero bins
# Calculate result
myResult = h.GetBinContent(j,k) * wQCD
# Calculate abs. stat. uncert. for data and for MC EWK
myStatDataUncert = hData.GetBinError(j,k) * wQCD
myStatEwkUncert = hEwk.GetBinError(j,k) * wQCD
#errorPropagation.errorPropagationForProduct(hLeg1.GetBinContent(j), hLeg1Data.GetBinError(j), myEffObject.value(), myEffObject.uncertainty("statData"))
# Do not calculate here MC EWK syst.
myCountObject = extendedCount.ExtendedCount(myResult, [myStatDataUncert, myStatEwkUncert], myUncertaintyLabels)
self._resultCountObject.add(myCountObject)
if optionDoNQCDByBinHistograms:
self._histogramsList[i].SetBinContent(j, k, myCountObject.value())
self._histogramsList[i].SetBinError(j, k, myCountObject.statUncertainty())
self._resultShape.SetBinContent(j, k, self._resultShape.GetBinContent(j, k) + myCountObject.value())
self._resultShape.SetBinError(j, k, self._resultShape.GetBinError(j, k) + myCountObject.statUncertainty()**2) # Sum squared
# Sum items for purity calculation
myShapeDataSum[j-1][k-1] += hData.GetBinContent(j,k)*wQCD
myShapeDataSumUncert[j-1][k-1] += (hData.GetBinError(j,k)*wQCD)**2
myShapeEwkSum[j-1][k-1] += hEwk.GetBinContent(j,k)*wQCD
myShapeEwkSumUncert[j-1][k-1] += (hEwk.GetBinError(j,k)*wQCD)**2
h.Delete()
hData.Delete()
hEwk.Delete()
# Take square root of uncertainties
for j in range(1,self._resultShape.GetNbinsX()+1):
for k in range(1,self._resultShape.GetNbinsY()+1):
self._resultShape.SetBinError(j, k, math.sqrt(self._resultShape.GetBinError(j, k)))
# Print result
print "NQCD Integral(%s) = %s "%(shape.getHistoName(), self._resultCountObject.getResultStringFull("%.1f"))
# Print purity as function of final shape bins
if optionPrintPurityByBins:
print "Purity of shape %s"%shape.getHistoName()
print "shapeBin purity purityUncert"
for j in range (1,self._resultShape.GetNbinsX()+1):
for k in range(1,self._resultShape.GetNbinsY()+1):
myPurity = 0.0
myPurityUncert = 0.0
if abs(myShapeDataSum[j-1][k-1]) > 0.000001:
myPurity = 1.0 - myShapeEwkSum[j-1][k-1] / myShapeDataSum[j-1][k-1]
myPurityUncert = errorPropagation.errorPropagationForDivision(myShapeEwkSum[j-1][k-1], math.sqrt(myShapeEwkSumUncert[j-1][k-1]), myShapeDataSum[j-1][k-1], math.sqrt(myShapeDataSumUncert[j-1][k-1]))
# Store MC EWK content
self._resultShapeEWK.SetBinContent(j, k, myShapeEwkSum[j-1][k-1])
self._resultShapeEWK.SetBinError(j, k, math.sqrt(myShapeEwkSumUncert[j-1][k-1]))
self._resultShapePurity.SetBinContent(j, k, myPurity)
self._resultShapePurity.SetBinError(j, k, myPurityUncert)
# Print purity info of final shape
if optionPrintPurityByBins:
myString = ""
if j < self._resultShape.GetNbinsX():
myString = "%d..%d, "%(self._resultShape.GetXaxis().GetBinLowEdge(j),self._resultShape.GetXaxis().GetBinUpEdge(j))
else:
myString = ">%d, "%(self._resultShape.GetXaxis().GetBinLowEdge(j))
if k < self._resultShape.GetNbinsY():
myString = "%d..%d"%(self._resultShape.GetYaxis().GetBinLowEdge(k),self._resultShape.GetYaxis().GetBinUpEdge(k))
else:
myString = ">%d"%(self._resultShape.GetYaxis().GetBinLowEdge(k))
myString += " %.3f %.3f"%(myPurity, myPurityUncert)
print myString
return