def PlotCompare(dataType, outputDir, mcsets, histname, leg, cutoff = -1, precise = False):
#
# plot a set of histograms defined by histname and comparing mc samples
# NOTE: ALL SAMPLES MUST CONTAIN THE EXACT SAME LIST OF HISTOGRAMS, OTHERWISE THIS FUNCTION WILL NOT WORK
#
# this function takes the following parameters:
# dataType....type of the lepton ('mu', 'el')
# outputDir...basic output directory
# mcsets......list of mc samples [mcsample1, mcsample2, ..]
# leg.........legend to be plotted
# cutoff......cutoff for the histogram name (see function getSaveName() in lib.py)
# precise.....True if only the histogram with the name matching histname exactly shall be plotted
# define canvas and pads
canv = helper.makeCanvas(900, 675)
pad_plot = helper.makePad('plot')
pad_ratio = helper.makePad('ratio')
pad_ratio.cd()
# iterate over all histograms in root files
# it does not matter which sample we iterate on, as all samples contain the same list of histograms
for hist in mcsets[0].hists:
# get index of histogram
i = mcsets[0].hists.index(hist)
pad_plot.cd()
# if precise is True, we only plot the histogram with the name matching histname exactly
# else, we plot all histograms which have histname in their name (useful for several versions or bins of a histogram)
if precise and not histname == hist.GetName(): continue
if not precise and not histname in hist.GetName(): continue
# pre- and postpends
prepend = ''
postpend = '_compare'
if '_Loose_' in hist.GetName(): prepend = 'Loose_'
if '_Tight_' in hist.GetName(): prepend = 'Tight_'
# draw first histogram
hist.Draw('hist')
hist.SetFillStyle(0)
hist.Scale(1.0/hist.Integral())
max = hist.GetMaximum()
for j in range(1,len(mcsets)):
mcsets[j].hists[i].Draw('hist same')
mcsets[j].hists[i].SetFillStyle(0)
mcsets[j].hists[i].SetLineStyle(2)
mcsets[j].hists[i].Scale(1.0/mcsets[j].hists[i].Integral())
if max < mcsets[j].hists[i].GetMaximum(): max = mcsets[j].hists[i].GetMaximum()
# do some cosmetics
hist.SetMinimum(0.0001)
hist.SetMaximum(1.5 * max)
hist = helper.set1dPlotStyle(dataType, hist, helper.getColor(mcsets[0].GetName()), '', hist, '1/Integral')
# draw legend
leg.Draw()
# draw ratio plot
pad_ratio.cd()
hist_ratio = copy.deepcopy(hist)
hist_ratio.Divide(copy.deepcopy(mcsets[1].hists[i]))
hist_ratio.Draw("p e1")
hist_ratio = helper.setRatioStyle(dataType, hist_ratio, hist)
line = helper.makeLine(hist_ratio.GetXaxis().GetXmin(), 1.00, hist_ratio.GetXaxis().GetXmax(), 1.00)
line.Draw()
# make plot
helper.saveCanvas(canv, pad_plot, outputDir + "compare/", prepend + helper.getSaveName(hist, cutoff) + postpend)
def PlotJPtZooms(dataType, outputDir, dataset, mcsets, leg):
#
# plotting JetPt and JetRawPt distributions in bins of lepton eta and lepton pt (binning according to fake rate maps)
# NOTE: ALL SAMPLES MUST CONTAIN THE EXACT SAME LIST OF HISTOGRAMS, OTHERWISE THIS FUNCTION WILL NOT WORK
#
# this function takes the following parameters:
# dataType....type of the lepton ('mu', 'el')
# outputDir...basic output directory
# datasets....list of data samples [datasample1, datasample2, ..]
# mcsets......list of mc samples [mcsample1, mcsample2, ..]
# leg.........legend to be plotted
# define canvas and pads
canv = helper.makeCanvas(900, 675, 'c1dZ')
pad_plot = helper.makePad('tot')
pad_plot.SetTicks(1,1)
pad_plot.cd()
# text for eta binning
t_eta = ROOT.TLatex()
t_eta.SetNDC()
t_eta.SetTextSize(0.05)
t_eta.SetTextAlign(11)
t_eta.SetTextColor(ROOT.kBlack)
# text for pt binning
t_pt = ROOT.TLatex()
t_pt.SetNDC()
t_pt.SetTextSize(0.05)
t_pt.SetTextAlign(11)
t_pt.SetTextColor(ROOT.kBlack)
# bins in eta and pt, with total number of bins
bins_eta = [0.0, 1.0, 2.4]
#bins_pt = [10.0, 20.0, 30.0, 35.0, 37.5, 40.0, 42.5, 45.0, 47.5, 50.0, 55.0, 60.0, 70.0] # old
bins_pt = [10.0, 20.0, 22.5, 25.0, 27.5, 30.0, 32.5, 35.0, 40.0, 50.0, 60.0, 70.0] # new
bins_tot = (len(bins_eta)-1)*(len(bins_pt)-1)
# iterate over all histograms in root files
# it does not matter which sample we iterate on, as all samples contain the same list of histograms
for hist in dataset.hists:
# get index of the histogram
i = dataset.hists.index(hist)
# only histograms in the parameter histlist are plotted
if not "JPtZoom" in hist.GetName(): continue
# pre- and postpends
prepend = ''
postpend = ''
if '_Loose_' in hist.GetName(): prepend = 'Loose_'
if '_Tight_' in hist.GetName(): prepend = 'Tight_'
# get the id of the plot, i.e. the last number in the name (e.g. '0' in h_Loose_DJPtZoomC_0)
id = hist.GetName().split('_')[-1]
# draw data
hist.Scale(1.0/hist.Integral())
hist.SetFillStyle(0)
hist.SetLineStyle(2)
hist.Draw("HIST")
max = hist.GetMaximum()
# draw mc samples
for mc in mcsets:
mc.hists[i].Scale(1.0/mc.hists[i].Integral())
mc.hists[i].SetFillStyle(0)
mc.hists[i].Draw("HIST SAME")
if mc.hists[i].GetMaximum()>max: max = mc.hists[i].GetMaximum()
# do some cosmetics
hist.SetMaximum(1.5*max)
hist.GetXaxis().SetTitle(helper.getXTitle(dataType, hist))
hist.GetYaxis().SetTitle("1/Integral")
hist.SetTitle("")
hist.GetXaxis().SetTitleSize(0.07)
hist.GetXaxis().SetLabelSize(0.07)
hist.GetYaxis().SetTitleSize(0.07)
hist.GetYaxis().SetLabelSize(0.07)
hist.GetXaxis().SetNdivisions(505)
hist.GetYaxis().SetNdivisions(505)
# draw legend
leg.Draw()
# write bin texts
m = int(id)//(len(bins_pt)-1)
n = int(id)%(len(bins_pt)-1)
if "ZoomC" in hist.GetName(): write = "corr."
else: write = "raw"
text_eta = str(bins_eta[m]) + " #leq jet-|#eta| < " + str(bins_eta[m+1])
text_pt = str(bins_pt[n]) + " #leq jet-p_{T} (" + write + ") < " + str(bins_pt[n+1])
t_eta.DrawLatex(0.22, 0.8, text_eta)
t_pt.DrawLatex(0.22, 0.73, text_pt)
# draw plots
helper.saveCanvas(canv, pad_plot, outputDir + "zoom_jpt/", prepend + helper.getSaveName(hist, '-2:') + postpend, False)
def Plot2d(dataType, outputDir, datasets, mcsets, histlist):
#
# this function is basically the 2d analogon to Plot1d: create 2d plots according to the histograms in the list
# NOTE: ALL SAMPLES MUST CONTAIN THE EXACT SAME LIST OF HISTOGRAMS, OTHERWISE THIS FUNCTION WILL NOT WORK
#
# this function takes the following parameters:
# dataType....type of the lepton ('mu', 'el')
# outputDir...basic output directory
# datasets....list of data samples [datasample1, datasample2, ..]
# mcsets......list of mc samples [mcsample1, mcsample2, ..]
# histlist....list of 1d histogram names ['h_Loose_LepIso', 'h_Loose_LepPhi', ..]
# define canvas and pads
canv = helper.makeCanvas(900, 675, 'c2d')
pad_plot = helper.makePad('tot')
pad_plot.cd()
pad_plot.SetTicks(1,1)
# iterate over all histograms in root files
# it does not matter which sample we iterate on, as all samples contain the same list of histograms
for hist in datasets[0].hists:
# get index of the histogram
i = datasets[0].hists.index(hist)
# only histograms in the parameter histlist are plotted
if not hist.GetName() in histlist: continue
# pre- and postpends
prepend = ''
postpend = ''
if '_Loose_' in hist.GetName(): prepend = 'Loose_'
if '_Tight_' in hist.GetName(): prepend = 'Tight_'
# we stack both data and mc samples (i.e. one may use several data and several mc samples)
data = ROOT.THStack()
mc = ROOT.THStack()
for dataset in datasets: data.Add(dataset.hists[i])
for mcset in mcsets: mc .Add(mcset .hists[i])
# call make2dPlot to make plots for data, total MC, each mc sample
make2dPlot(dataType, canv, pad_plot, outputDir, data.GetStack().Last(), 'data', prepend + helper.getSaveName(hist) + postpend)
make2dPlot(dataType, canv, pad_plot, outputDir, mc .GetStack().Last(), 'MC' , prepend + helper.getSaveName(hist) + postpend)
for mcset in mcsets: make2dPlot(dataType, canv, pad_plot, outputDir, mcset.hists[i], mcset.GetName(), prepend + helper.getSaveName(hist) + postpend)
def PlotMETZooms(dataType, outputDir, datasets, mcsets, leg, grouping = False):
#
# plotting MET distribution in bins of lepton eta and lepton pt (binning according to fake rate maps)
# NOTE: ALL SAMPLES MUST CONTAIN THE EXACT SAME LIST OF HISTOGRAMS, OTHERWISE THIS FUNCTION WILL NOT WORK
#
# dataType....type of the lepton ('mu', 'el')
# outputDir...basic output directory
# datasets....list of data samples [datasample1, datasample2, ..]
# mcsets......list of mc samples [mcsample1, mcsample2, ..]
# leg.........legend to be plotted
# grouping....True if mc samples should be grouped before stacking (useful in case of e.g. several QCD files)
# define canvas and pads
canv = helper.makeCanvas(900, 675, 'c1dM')
pad_plot = helper.makePad('plot')
pad_ratio = helper.makePad('ratio')
pad_plot.SetTicks(1,1)
pad_ratio.SetTicks(1,1)
# text for eta binning
t_eta = ROOT.TLatex()
t_eta.SetNDC()
t_eta.SetTextSize(0.05)
t_eta.SetTextAlign(11)
t_eta.SetTextColor(ROOT.kBlack)
# text for pt binning
t_pt = ROOT.TLatex()
t_pt.SetNDC()
t_pt.SetTextSize(0.05)
t_pt.SetTextAlign(11)
t_pt.SetTextColor(ROOT.kBlack)
# bins in eta and pt, with total number of bins
bins_eta = [0.0, 0.5, 1.0, 1.5, 2.0, 2.5]
bins_pt = [20.0, 25.0, 30.0, 35.0, 40.0, 45.0, 50.0]
bins_tot = (len(bins_eta)-1)*(len(bins_pt)-1)
# iterate over all histograms in root files
# it does not matter which sample we iterate on, as all samples contain the same list of histograms
for hist in datasets[0].hists:
# get index of the histogram
i = datasets[0].hists.index(hist)
pad_plot.cd()
# only histograms in the parameter histlist are plotted
if not "METZoom" in hist.GetName(): continue
# pre- and postpends
prepend = ''
postpend = ''
if '_Loose_' in hist.GetName(): prepend = 'Loose_'
if '_Tight_' in hist.GetName(): prepend = 'Tight_'
# get the id of the plot, i.e. the last number in the name (e.g. '0' in h_Loose_FRMETZoom_0)
id = hist.GetName().split('_')[-1]
# we stack both data and mc samples (i.e. one may use several data and several mc samples)
data = ROOT.THStack()
mc = ROOT.THStack()
for dataset in datasets:
data.Add(dataset.hists[i])
# if grouping is enabled, we first sum all 'similar' mc samples before adding them to the stack
# similar means, that we sum all samples which have the same name up to a few digits at the end
# in this way, e.g., the samples dyjets50 and dyjets10 are stacked together
# if grouping is not enabled, we just stack all mc samples in one stack
if grouping:
mcgroups = []
mcnames = []
for mcset in mcsets:
label = ''.join([j for j in mcset.GetName() if not j.isdigit()])
foundat = -1
for j, mcname in enumerate(mcnames):
if label == mcname: foundat = j
if foundat == -1:
mcgroups.append(ROOT.THStack())
mcgroups[len(mcgroups)-1].Add(mcset.hists[i])
mcnames.append(label)
else:
mcgroups[foundat].Add(mcset.hists[i])
for j, group in enumerate(mcgroups):
group.Draw('hist')
histogram = group.GetStack().Last()
mc.Add(histogram)
else:
for mcset in mcsets:
mc.Add(mcset.hists[i])
# draw histogram
mc.Draw('hist')
# define the list of histograms which shall be plotted
# i.e. one has to take the histogram of the stack, not the stack itself
hists = []
hists.append([data.GetStack().Last(), 'data' ])
hists.append([mc , 'totbg'])
# plot pad_plot first, then we add the texts and plot ratio afterwards
make1dPlot_plot(dataType, pad_plot, hists, hists[0][0], leg)
# write bin texts
m = int(id)//(len(bins_pt)-1)
n = int(id)%(len(bins_pt)-1)
if dataType == 'el': lepton = 'e'
else : lepton = '#mu'
text_eta = str(bins_eta[m]) + " #leq " + lepton + "-|#eta| < " + str(bins_eta[m+1])
text_pt = str(bins_pt[n]) + " #leq " + lepton + "-p_{T} < " + str(bins_pt[n+1])
t_eta.DrawLatex(0.22, 0.8, text_eta)
t_pt.DrawLatex(0.22, 0.73, text_pt)
# plot ratio
#make1dPlot_ratio(dataType, pad_ratio, hists, hists[0][0])
# calling the function to produce the ratio plot results in a malfunction i do not understand properly
# so we copy the lines from make1dPlot_ratio() while we still keep that function for other purposes
pad_ratio.cd()
data_bg_ratio = copy.deepcopy(hists[0][0])
data_bg_ratio.Divide(copy.deepcopy(hists[1][0].GetStack().Last()))
data_bg_ratio.Draw("p e")
data_bg_ratio = helper.setRatioStyle(dataType, data_bg_ratio, hists[0][0])
line = helper.makeLine(data_bg_ratio.GetXaxis().GetXmin(), 1.00, data_bg_ratio.GetXaxis().GetXmax(), 1.00)
line.Draw()
# save plot
ROOT.gPad.RedrawAxis()
helper.saveCanvas(canv, pad_plot, outputDir + "zoom_met/", prepend + helper.getSaveName(hist, '-2:') + postpend)
def Plot1d(dataType, outputDir, datasets, mcsets, histlist, leg, grouping = False):
#
# given data and mc samples, all histograms in histlist are produced with mc samples stacked
# NOTE: ALL SAMPLES MUST CONTAIN THE EXACT SAME LIST OF HISTOGRAMS, OTHERWISE THIS FUNCTION WILL NOT WORK
#
# this function takes the following parameters:
# dataType....type of the lepton ('mu', 'el')
# outputDir...basic output directory
# datasets....list of data samples [datasample1, datasample2, ..]
# mcsets......list of mc samples [mcsample1, mcsample2, ..]
# histlist....list of 1d histogram names ['h_Loose_LepIso', 'h_Loose_LepPhi', ..]
# leg.........legend to be drawn
# grouping....True if mc samples should be grouped before stacking (useful in case of e.g. several QCD files)
# define canvas and pads
canv = helper.makeCanvas(900, 675, 'c1d')
pad_plot = helper.makePad('plot')
pad_ratio = helper.makePad('ratio')
pad_plot.SetTicks(1,1)
pad_ratio.SetTicks(1,1)
# iterate over all histograms in root files
# it does not matter which sample we iterate on, as all samples contain the same list of histograms
for hist in datasets[0].hists:
# get index of the histogram
i = datasets[0].hists.index(hist)
pad_plot.cd()
# only histograms in the parameter histlist are plotted
if not hist.GetName() in histlist: continue
# there are two NVertices plots in the list with different binning
# we only plot the NVertices, but not the NVertices1 (this we use for the fake rate plots, see lib_FakeRate.py)
if hist.GetName()[-10:] == "NVertices1": continue
# pre- and postpends
prepend = ''
postpend = ''
if '_Loose_' in hist.GetName(): prepend = 'Loose_'
if '_Tight_' in hist.GetName(): prepend = 'Tight_'
# we stack both data and mc samples (i.e. one may use several data and several mc samples)
data = ROOT.THStack()
mc = ROOT.THStack()
for dataset in datasets:
data.Add(dataset.hists[i])
# if grouping is enabled, we first sum all 'similar' mc samples before adding them to the stack
# similar means, that we sum all samples which have the same name up to a few digits at the end
# in this way, e.g., the samples dyjets50 and dyjets10 are stacked together
# if grouping is not enabled, we just stack all mc samples in one stack
if grouping:
mcgroups = []
mcnames = []
for mcset in mcsets:
label = ''.join([j for j in mcset.GetName() if not j.isdigit()])
foundat = -1
for j, mcname in enumerate(mcnames):
if label == mcname: foundat = j
if foundat == -1:
mcgroups.append(ROOT.THStack())
mcgroups[len(mcgroups)-1].Add(mcset.hists[i])
mcnames.append(label)
else:
mcgroups[foundat].Add(mcset.hists[i])
for j, group in enumerate(mcgroups):
group.Draw('hist')
histogram = group.GetStack().Last()
mc.Add(histogram)
else:
for mc in mcsets:
mc.Add(mc.hists[i])
# define the list of histograms which shall be plotted
# i.e. one has to take the histogram of the stack, not the stack itself
histstoplot = []
histstoplot.append([data.GetStack().Last(), 'data' ])
histstoplot.append([mc , 'totbg'])
# call make1dPlot to create the plot
make1dPlot(dataType, canv, pad_plot, pad_ratio, outputDir, histstoplot, hist, prepend + helper.getSaveName(hist) + postpend, leg)
