def main():
start_time = time.time()
global ops
ops = options()
global inputpath
inputpath = CONF.inputpath + ops.inputdir + "/"
global outputpath
outputpath = CONF.outputpath + ops.outputdir + "/tempplot/"
helpers.checkpath(outputpath)
#if do eos
eosmcpath = CONF.toppath + "/eos/atlas/user/b/btong/bb/mc/v02-00-00/gridOutput/MiniNTuple/*mc15_13TeV"
eosdatapath = CONF.toppath + "/eos/atlas/user/b/btong/bb/data/v02-00-00/gridOutput/MiniNTuple/*16_*periodB.*.root_skim"
#start analysis on TinyNtuple
mass = 3000
TinyAnalysis(inputpath + "signal_G_hh_c10_M" + str(mass) + "/" +
"hist-MiniNTuple.root", "signal_M" + str(mass)) #MC
#TinyAnalysis(inputpath + "data_test/" + "hist-MiniNTuple.root", "data") #data
#TinyAnalysis(inputpath + "data_test16/" + "hist-MiniNTuple.root", "data") #data
##start analysis on MiniNtuple
#MiniAnalysis(glob.glob(eosmcpath + "*G_hh_bbbb_c10*" + str(mass) + ".hh4b*.root_skim")[0], "signal_M" + str(mass)) #MC
#MiniAnalysis(glob.glob(eosdatapath)[0], "data16") #data
#MiniAnalysis(glob.glob("../test_mini/data-MiniNTuple/*.root_skim")[0], "signal_M" + str(mass)) #MC
#finish
print("--- %s seconds ---" % (time.time() - start_time))
def main():
start_time = time.time()
global ops
ops = options()
global inputpath
inputpath = CONF.inputpath + ops.inputdir + "/"
global outputpath
outputpath = CONF.outputpath + ops.outputdir + "/tempplot/"
helpers.checkpath(outputpath)
#if do eos
eosmcpath = "/eos/atlas/user/b/btong/bb/mc/v02-03-04/gridOutput/MiniNTuple/*mc15_13TeV"
eosdatapath = "/eos/atlas/user/b/btong/bb/data/v02-03-04/gridOutput/MiniNTuple/*16_*periodB.*.root"
#start analysis on TinyNtuple
mass = 3000
#TinyAnalysis(inputpath + "signal_G_hh_c10_M" + str(mass) + "/" + "hist-MiniNTuple.root", "signal_M" + str(mass)) #MC
#TinyAnalysis(inputpath + "data_test/" + "hist-MiniNTuple.root", "data") #data
#TinyAnalysis(inputpath + "data_test16/" + "hist-MiniNTuple.root", "data") #data
##start analysis on MiniNtuple
#MiniAnalysis(glob.glob(eosmcpath + "*G_hh_bbbb_c10*" + str(mass) + ".hh4b*.root")[0], "signal_M" + str(mass)) #MC
MiniAnalysis(glob.glob(eosmcpath + "*G_hh_bbbb_c10*" + str(mass) + ".hh4b*.root")[0], outname="signal_M" + str(mass)) #MC
#MiniAnalysis(glob.glob(eosmcpath + "*410007*ttbar*_allhad.*v1*.root")[0], outname="tthadv1") #MC
#MiniAnalysis(glob.glob(eosmcpath + "*410007*ttbar*_allhad.*v3*.root")[0], outname="tthadv3") #MC
#MiniAnalysis(glob.glob("/afs/cern.ch/work/b/btong/bbbb/MoriondAnalysis/test_mini/data-MiniNTuple/mc15_13TeV.root")[0], outname="tthadv3") #MC
#MiniAnalysis(glob.glob(eosdatapath)[0], "data16") #data
#MiniAnalysis(glob.glob("../test_mini/data-MiniNTuple/*.root_skim")[0], "signal_M" + str(mass)) #MC
#finish
print("--- %s seconds ---" % (time.time() - start_time))
def split(targetpath="data_test"):
start_time = time.time()
ops = options()
nfiles = ops.nfiles
inputdir = ops.inputdir
global inputpath
inputpath = CONF.inputpath + inputdir + "/" + targetpath
global outputpath
outputpath = CONF.inputpath + inputdir + "/" + targetpath
helpers.checkpath(outputpath)
print "split! target: ", targetpath
f = ROOT.TFile(inputpath + "/" + "hist-MiniNTuple.root", "read")
#load the target tree
t = f.Get("TinyTree")
#load the histograms
hist_list = [
"CutFlowWeight", "CutFlowNoWeight", "h_leadHCand_pT_pre_trig",
"h_leadHCand_pT_aft_trig"
]
temp_hist_list = []
for j, hist in enumerate(hist_list):
temp_hist_list.append(f.Get(hist).Clone())
temp_hist_list[j].Scale(1.0 / (nfiles * 1.0))
##correct for the sqrt N error here; this is really stupid
for x_bin in range(0, temp_hist_list[j].GetXaxis().GetNbins() + 1):
temp_hist_list[j].SetBinError(
x_bin,
temp_hist_list[j].GetBinError(x_bin) * ROOT.TMath.Sqrt(nfiles))
outfile = []
outtree = []
for i in range(nfiles):
outfile.append(
ROOT.TFile(inputpath + "/" + "hist-MiniNTuple_%s.root" % (str(i)),
"recreate"))
outtree.append(t.CloneTree(0))
#open and copy
nentries = t.GetEntries()
for n in range(nentries):
t.GetEntry(n)
#print n%nfiles
outtree[n % nfiles].Fill()
for i in range(nfiles):
outfile[i].cd()
outtree[i].Write()
for j, hist in enumerate(temp_hist_list):
hist.Write()
outfile[i].Close()
f.Close()
del (t)
del (outtree)
del (temp_hist_list)
print("--- %s seconds ---" % (time.time() - start_time))
print "Finish!"
def pack_input(inputfile, inputsplit=-1):
dic = {}
dic["inputfile"] = inputfile
dic["inputroot"] = "hist-MiniNTuple" + ("_" + str(inputsplit) if inputsplit >= 0 else "") + ".root"
dic["outputroot"] = "hist-MiniNTuple" + ("_" + str(inputsplit) if inputsplit >= 0 else "") + ".root"
#make sure the output directory exist here; resolve the conflicts
helpers.checkpath(outputpath + inputfile)
return dic
def print_image_checks(img_fpath):
hasimg = helpers.checkpath(img_fpath, verbose=True)
if hasimg:
_tup = (img_fpath, filesize_str(img_fpath))
print('[io] Image %r (%s) exists. Is it corrupted?' % _tup)
else:
print('[io] Image %r does not exists ' (img_fpath, ))
return hasimg
def print_image_checks(img_fpath):
hasimg = helpers.checkpath(img_fpath, verbose=True)
if hasimg:
_tup = (img_fpath, filesize_str(img_fpath))
print('[io] Image %r (%s) exists. Is it corrupted?' % _tup)
else:
print('[io] Image %r does not exists ' (img_fpath,))
return hasimg
def debug_compute_ap_exe(compute_ap_exe,
ground_truth_query,
ranked_list_fpath):
print('================================')
print('Debugging compute_ap executable:')
print('-----------')
print('Path checks: ')
helpers.checkpath(ranked_list_fpath, True)
helpers.checkpath(compute_ap_exe, True)
print('-----------')
print('Command string check:')
args = (compute_ap_exe, ground_truth_query, ranked_list_fpath)
cmdstr = ' '.join(args)
print(cmdstr)
print('-----------')
print('Noargs check:')
(out, err, return_code) = execute(compute_ap_exe)
(out, err, return_code) = popen_communicate(cmdstr)
def skim(targetpath=""):
start_time = time.time()
ops = options()
inputpath = targetpath
outputpath = targetpath
helpers.checkpath(outputpath)
print targetpath
#setup files
files = glob.glob(targetpath + "*.MiniNTuple.root")
config = []
#setup the dictionary
for file in files:
#print file
temp_dic = {}
temp_dic["file"] = file
#add skimming selection now
if ops.file not in file:
continue
#only do skimming once for now!
if not os.path.isfile(temp_dic["file"] + "_skim"):
config.append(temp_dic)
print config
print " Running %s jobs on %s cores" % (len(config), mp.cpu_count() - 1)
npool = min(len(config), mp.cpu_count() - 1)
pool = mp.Pool(npool)
pool.map(selection, config)
##for debugging
#selection(config[0])
# for conf in config:
# print conf
# selection(conf)
print("--- %s seconds ---" % (time.time() - start_time))
print "Finish!"
def skim(targetpath=""):
start_time = time.time()
ops = options()
inputpath = targetpath
outputpath = targetpath
helpers.checkpath(outputpath)
print targetpath
#setup files
files = glob.glob(targetpath + "*.MiniNTuple.root")
config = []
#setup the dictionary
for file in files:
#print file
temp_dic = {}
temp_dic["file"] = file
#add skimming selection now
if ops.file not in file:
continue
#only do skimming once for now!
if not os.path.isfile(temp_dic["file"] + "_skim"):
config.append(temp_dic)
print config
print " Running %s jobs on %s cores" % (len(config), mp.cpu_count()-1)
npool = min(len(config), mp.cpu_count()-1)
pool = mp.Pool(npool)
pool.map(selection, config)
##for debugging
#selection(config[0])
# for conf in config:
# print conf
# selection(conf)
print("--- %s seconds ---" % (time.time() - start_time))
print "Finish!"
def syst_pipeline(config):
t = config["inputdir"]
print "the directory is: ", t
inputpath = CONF.inputpath + t + "/"
#check if for syst, the data file is there
helpers.checkpath(inputpath + "data_test")
#this is a really bad practice and temp fix now! need to watch this very carfully...
ori_link = CONF.inputpath + ops.inputdir + "/data_test/hist-MiniNTuple.root"
dst_link = inputpath + "data_test/hist-MiniNTuple.root"
#print ori_link, dst_link
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
#for ttbar, also need to link the MCs.
if "syst_tt_" in t:
for i, mass in enumerate(CONF.mass_lst):
#print "creating links of signal samples", "signal_G_hh_c10_M" + str(mass)
#this is a really bad practice and temp fix now! need to watch this very carfully...
ori_link = CONF.inputpath + ops.inputdir + "/signal_G_hh_c10_M" + str(
mass) + "/hist-MiniNTuple.root"
#ori_link = inputpath.replace("TEST", "DS1_cb") + "signal_G_hh_c10_M" + str(mass) + "/hist-MiniNTuple.root"
dst_link = inputpath + "signal_G_hh_c10_M" + str(
mass) + "/hist-MiniNTuple.root"
helpers.checkpath(inputpath + "signal_G_hh_c10_M" + str(mass))
#print ori_link, dst_link
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
#link the 2HDM samples if necessary
if (ops.Xhh):
ori_link = CONF.inputpath + ops.inputdir + "/signal_X_hh_M" + str(
mass) + "/hist-MiniNTuple.root"
dst_link = inputpath + "signal_X_hh_M" + str(
mass) + "/hist-MiniNTuple.root"
helpers.checkpath(inputpath + "signal_X_hh_M" + str(mass))
if os.path.islink(dst_link):
os.unlink(dst_link)
print "linking: ", dst_link
os.symlink(ori_link, dst_link)
#start running programs
#print (inputpath)
os.system("rm " + inputpath + "sum_" + t + ".root")
os.system("rm -r " + inputpath + "Limitinput")
print "done clearing!"
os.system("python get_count.py --dosyst " + " --inputdir " + t +
(" --Xhh " if ops.Xhh else ""))
os.system("python dump_hists.py --dosyst " + " --inputdir " + t +
(" --Xhh " if ops.Xhh else ""))
def oxsty_mAP_results(allres):
print('oxsty_results> Building oxsty results')
hs = allres.hs
qcx2_res = allres.qcx2_res
SV = allres.SV
# Check directorys where ranked lists of images names will be put
oxsty_qres_dname = 'oxsty_ranked_lists' +allres.title_suffix
oxsty_qres_dpath = join(hs.dirs.qres_dir, oxsty_qres_dname)
helpers.ensure_path(oxsty_qres_dpath)
oxford_gt_dir = join(hs.dirs.db_dir, 'oxford_style_gt')
helpers.assertpath(oxford_gt_dir)
compute_ap_exe = normpath(join(oxford_gt_dir, '../compute_ap'))
if not helpers.checkpath(compute_ap_exe):
compute_ap_exe = normpath(join(oxford_gt_dir, '/compute_ap'))
helpers.assertpath(compute_ap_exe)
# Get the mAP scores using philbins program
query_mAP_list = []
query_mAP_cx = []
for qcx in iter(hs.test_sample_cx):
res = qcx2_res[qcx]
mAP = get_oxsty_mAP_score_from_res(hs, res, SV, oxsty_qres_dpath,
compute_ap_exe, oxford_gt_dir)
query_mAP_list.append(mAP)
query_mAP_cx.append(qcx)
print('')
# Calculate the scalar mAP score for the experiemnt
scalar_mAP = np.mean(np.array(query_mAP_list))
scalar_mAP_str = '# mAP score = %r\n' % scalar_mAP
# build a CSV file with the results
header = '# Oxford Style Map Scores: title_suffix=%r\n' % allres.title_suffix
header += scalar_mAP_str
header += helpers.get_timestamp(format='comment')+'\n'
header += '# Full Parameters: \n#' + params.param_string().replace('\n','\n#')+'\n\n'
column_labels = ['QCX', 'mAP']
column_list = [query_mAP_cx, query_mAP_list]
oxsty_map_csv = load_data2.make_csv_table(column_labels, column_list, header)
return oxsty_map_csv, scalar_mAP_str
def DrawSRcomparison(inputname="CR_High",
tag="",
keyword="totalbkg_hh",
prename="",
Xrange=[0, 0],
Yrange=[0, 0],
norm=True,
Logy=0):
#print inputdir, inputname
histdir = inputdir + "_" + inputname
inputroot = ROOT.TFile.Open(CONF.inputpath + "/" + histdir +
"/Limitinput/" + histdir + "_limit_" + tag +
".root")
refroot = ROOT.TFile.Open(CONF.inputpath + "/" + inputdir + reweightpath +
"/Limitinput/" + inputdir + reweightpath +
"_limit_" + tag + ".root")
tempname = inputname + "_" + "compare" + "_" + tag + "_" + keyword + (
"" if Logy == 0 else "_" + str(Logy))
canv = ROOT.TCanvas(tempname, tempname, 800, 800)
canv.SetLogy(Logy)
xleg, yleg = 0.5, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg + 0.15, yleg + 0.2)
counter = 0
maxbincontent = (0.2 if Logy == 0 else 10)
print keyword, histdir
temp_hist = inputroot.Get(keyword)
#print temp_hist.GetName()
temp_hist.SetLineColor(2)
temp_hist.SetMarkerStyle(20)
temp_hist.SetMarkerColor(2)
temp_hist.SetMarkerSize(1)
ref_hist = refroot.Get(keyword)
#print temp_hist.GetName()
ref_hist.SetLineColor(1)
ref_hist.SetMarkerStyle(21)
ref_hist.SetMarkerColor(1)
ref_hist.SetMarkerSize(1)
#scale to correct normalization diff
#temp_hist.Scale(ref_hist.Integral()/temp_hist.Integral())
#continue
maxbincontent = max(maxbincontent, ref_hist.GetMaximum(),
temp_hist.GetMaximum())
temp_hist.SetMaximum(maxbincontent * 1.5 * 100)
ref_hist.SetMaximum(maxbincontent * 1.5 * 100)
legend.AddEntry(temp_hist, inputname.replace("_", " "), "apl")
legend.AddEntry(ref_hist, "Nominal", "apl")
# top pad
pad0 = ROOT.TPad("pad0", "pad0", 0.0, 0.31, 1., 1.)
pad0.SetLogy(1)
pad0.SetRightMargin(0.05)
pad0.SetBottomMargin(0.0001)
pad0.SetFrameFillColor(0)
pad0.SetFrameBorderMode(0)
pad0.SetFrameFillColor(0)
pad0.SetBorderMode(0)
pad0.SetBorderSize(0)
pad1 = ROOT.TPad("pad1", "pad1", 0.0, 0.0, 1., 0.30)
pad1.SetRightMargin(0.05)
pad1.SetBottomMargin(0.38)
pad1.SetTopMargin(0.0001)
pad1.SetFrameFillColor(0)
pad1.SetFillStyle(0) # transparent
pad1.SetFrameBorderMode(0)
pad1.SetFrameFillColor(0)
pad1.SetBorderMode(0)
pad1.SetBorderSize(0)
canv.cd()
pad0.Draw()
pad0.cd()
temp_hist.Draw("")
ref_hist.Draw("same")
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas - 0.06, tag.replace("_", " "))
watermarks = [atlas, hh4b]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
canv.cd()
pad1.Draw()
pad1.cd()
#ratio of the two plots
ratiohist = temp_hist.Clone("ratio")
ratiohist.Divide(ref_hist)
ratiohist.GetYaxis().SetRangeUser(0.6, 1.5) #set range for ratio plot
ratiohist.GetYaxis().SetTitle(
"Varaition/Nominal") #set range for ratio plot
ratiohist.GetYaxis().SetTitleFont(43)
ratiohist.GetYaxis().SetTitleSize(28)
ratiohist.GetYaxis().SetLabelFont(43)
ratiohist.GetYaxis().SetLabelSize(28)
ratiohist.GetYaxis().SetNdivisions(405)
ratiohist.GetXaxis().SetTitleFont(43)
ratiohist.GetXaxis().SetTitleOffset(3.5)
ratiohist.GetXaxis().SetTitleSize(28)
ratiohist.GetXaxis().SetLabelFont(43)
ratiohist.GetXaxis().SetLabelSize(28)
ratiohist.Draw("")
xMin = ref_hist.GetXaxis().GetBinLowEdge(1)
xMax = ref_hist.GetXaxis().GetBinUpEdge(ref_hist.GetXaxis().GetNbins())
line = ROOT.TLine(xMin, 1.0, xMax, 1.0)
line.SetLineStyle(1)
line.Draw()
#canv.SetLogy(1)
helpers.checkpath(CONF.inputpath + inputdir + "/Plot/Syst/")
canv.SaveAs(CONF.inputpath + inputdir + "/Plot/Syst/" + canv.GetName() +
".pdf")
pad0.Close()
pad1.Close()
canv.Close()
inputroot.Close()
refroot.Close()
def write_reweight(fname="TEST", reweight_dic={},
region_dic = [("2bs", "TwoTag_split_Sideband"), ("3b","ThreeTag_Sideband"), ("4b","FourTag_Sideband")], split=False, cond=False):
'''write reweight output '''
motherfolder="Moriond"
helpers.checkpath("script")
#building the inputdictionary
#creat an empty dictionary
#ready to dump file
f = open("script/" + fname + ".txt", "w")
#make sure over write everytime!
f.truncate()
f.write( "#reweighting script for hh4b analysis \n")
#iteration; Ntrk; parameter; inputfolder; parameterfile
for i in range(iteration):
f.write( "#iteration:" + str(i) + "\n")
#space is very important!!!!
for region, region_fname in region_dic:
for var, var_fname in reweight_dic.iteritems():
if split: #this is to reweight leading pT and trk pT seperately
if "j0_" in var and i%2 == 1: #for even skip j0_pt
continue
elif "j0_" not in var and i%2 != 1: #for odd, skip other
continue
# if "j0_pt" in var and i%4 > 1: #for even skip j0_pt
# continue
# elif "j0_pt" not in var and i%4 <= 1: #for odd, skip other
# continue
##notice this onlyputs condition on subl, lead reweighting; reweight lead's subl and subl's lead
#print region_fname, var_fname, ("lead_subl" in region_fname), ("lead" in var_fname)
if (("lead_lead" in region_fname) or ("lead_subl" in region_fname)):
if "lead" in var_fname:
continue
elif (("subl_lead" in region_fname) or ("subl_subl" in region_fname)):
if "subl" in var_fname:
continue
elif "lead" in region_fname:
if "lead" in var_fname:
continue
elif "subl" in region_fname:
if "subl" in var_fname:
continue
templine = ""
templine += str(i) + " " #iteration
templine += region + " " #Ntrk
templine += "event." + var + " " #parameter
templine += motherfolder + ("_" + fname + "_" + str(i-1) if i!= 0 else "") + " " #look for the original iteration
templine += "r" + str(i) + "_" + region_fname + "_" + var_fname + ".txt" + " " #parameterfile;
##add in condition; be very careful, this means the TinyNtuple has to be produced with the correct b-tagging MV2Cut
##also the definition of condition needs to agree with the PlotTinyTree region condition!!! STUPID but be very careful!!!
if cond:
if "2Trk_split_lead_Incl" in region_fname:
templine += "((event.j0_nb==1)and(event.j1_nb==0))" + " " #condition
if "2Trk_split_subl_Incl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==1))" + " " #condition
# if "2Trk_split_lead_lead_Incl" in region_fname:
# templine += "((event.j0_nb==1)and(event.j1_nb==0)and(event.j0_trk0_Mv2>0.6455))" + " " #condition
# if "2Trk_split_subl_lead_Incl" in region_fname:
# templine += "((event.j0_nb==0)and(event.j1_nb==1)and(event.j1_trk0_Mv2>0.6455))" + " " #condition
# if "2Trk_split_lead_subl_Incl" in region_fname:
# templine += "((event.j0_nb==1)and(event.j1_nb==0)and(event.j0_trk0_Mv2<0.6455))" + " " #condition
# if "2Trk_split_subl_subl_Incl" in region_fname:
# templine += "((event.j0_nb==0)and(event.j1_nb==1)and(event.j1_trk0_Mv2<0.6455))" + " " #condition
if "3Trk_lead" in region_fname:
templine += "((event.j0_nb==2)and(event.j1_nb==0))" + " " #condition
if "3Trk_subl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==2))" + " " #condition
if "4Trk_lead" in region_fname:
templine += "((event.j0_nb==2)and(event.j1_nb==0))" + " " #condition
if "4Trk_subl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==2))" + " " #condition
templine += "\n"
print templine
f.write(templine)
#finish
f.close()
def analysis_pipeline(config):
#setup the directories
motherdir = config["motherdir"] #the one with TinyTree
reweight = config["reweight"] #this is the reweight method
iter_re = config["iter_re"]
reweightplotdir = config["reweightplotdir"]
outputdir = ops.inputdir + "_" + reweight + "_" + str(iter_re) #the output from Plot TinyTree, input for analysis code
print "the directory is: ", outputdir, " parent dir is: ", motherdir, " reweight: ", reweight, " iteration: ", iter_re
##reweight
#print "python PlotTinyTree.py --inputdir " + motherdir + " --outputdir " + outputdir + " --reweight " + reweight + " --iter " + str(iter_re)
os.system("python PlotTinyTree.py --inputdir " + motherdir + " --outputdir " + outputdir + " --reweight " + reweight + " --iter " + str(iter_re)) #+ " --debug")
# if (iter_re == iter_total - 1): ## reweight the dijet MC for the last iteration
# os.system("python PlotTinyTree.py --inputdir " + motherdir + " --outputdir " + outputdir + " --reweight " + reweight + " --iter " + str(iter_re) + " --dijet")
##fit and produce plot
os.system("python get_count.py --full --inputdir " + outputdir)
os.system("python plot.py --inputdir " + outputdir)
os.system("python reweight.py --inputdir " + outputdir + " --iter " + str(iter_re + 1) + " --var " + reweight) ##+1 because it is really for the next iteration
if ops.publish:
##for publication purpose
homepath="/afs/cern.ch/user/b/btong/"
workpath=CONF.outputpath + outputdir
print "Publish!"
helpers.checkpath(homepath + "/www/share/hh4b/reweight/" + outputdir)
helpers.checkpath(homepath + "/www/share/hh4b/plot/" + outputdir)
helpers.checkpath(homepath + "/www/share/hh4b/express/" + outputdir)
##list of plots
if CONF.fullstudy:
plt_lst = ["mHH_l_1",\
"leadHCand_Pt_m_1", "leadHCand_Eta", "leadHCand_Phi", "leadHCand_Mass", "leadHCand_Mass_s", "leadHCand_trk_dr",\
"sublHCand_Pt_m_1", "sublHCand_Eta", "sublHCand_Phi", "sublHCand_Mass", "sublHCand_Mass_s", "sublHCand_trk_dr",\
"leadHCand_trk0_Pt", "leadHCand_trk1_Pt", "sublHCand_trk0_Pt", "sublHCand_trk1_Pt"]
else:
plt_lst = ["mHH_l_1", \
"leadHCand_Pt_m_1",\
"sublHCand_Pt_m_1",\
"leadHCand_trk0_Pt", "leadHCand_trk1_Pt", "sublHCand_trk0_Pt", "sublHCand_trk1_Pt"]
#"hCandDr", "hCandDeta", "hCandDphi",\
##clean up the current plots
pubDirs = ["reweight", "express", "plot"]
for pubdir in pubDirs:
for pic in glob.glob(homepath + "/www/share/hh4b/" + pubdir + "/" + outputdir +"/*"):
os.remove(pic)
##add description file
descript = open(homepath + "/www/share/hh4b/" + pubdir + "/" + outputdir +"/shortdescription.txt", "w")
descript.write(" reweight: " + reweight + " iteration: " + str(iter_re))
descript.write(" time: " + time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime()))
descript.close()
##copy
for plot in plt_lst:
for pic in glob.glob(workpath + "/Plot_r" + str(iter_re + 1) + "/" + reweightplotdir + "/*" + plot + ".png"):
os.system("cp " + pic + " " + homepath + "/www/share/hh4b/reweight/" + outputdir +"/.")
for pic in glob.glob(workpath + "/Plot" + "/Sideband/*" + plot + ".png"):
os.system("cp " + pic + " " + homepath + "/www/share/hh4b/plot/" + outputdir +"/.")
if "mHH_l_1" in pic:
os.system("cp " + pic + " " + homepath + "/www/share/hh4b/express/" + outputdir +"/.")
for pic in glob.glob(workpath + "/Plot" + "/Control/*" + plot + ".png"):
#print pic
os.system("cp " + pic + " " + homepath + "/www/share/hh4b/plot/" + outputdir +"/.")
if "mHH_l_1" in pic:
os.system("cp " + pic + " " + homepath + "/www/share/hh4b/express/" + outputdir +"/.")
#print "cp " + pic + " " + homepath + "/www/share/hh4b/express/" + outputdir +"/."
##publish
os.chdir(homepath + "/www/share/")
os.system("python createHtmlOverview.py")
os.chdir(CONF.currpath)
print "Done!"
def DrawSignalTruth(outputroot,
dcut_lst,
scut_lst,
inputdir="",
outputname="",
normalization=0):
### the first argument is the input directory
### the second argument is the output prefix name
### the third argument is relative to what normalization: 0 for total number of events
### 1 for signal mass region
# setup basic plot parameters
lowmass = -50
highmass = 3150
# load input MC file
maxbincontent = .4 # approx
minbincontent = -0.01
for i, (dcut, scut) in enumerate(zip(dcut_lst, scut_lst)):
canv = ROOT.TCanvas(inputdir + "_" + outputname + str(normalization),
"Efficiency", 800, 800)
xleg, yleg = 0.55, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg + 0.3, yleg + 0.2)
sfiles = [
"/signal_G_hh_c10_M%i/hist-MiniNTuple.root" % mass
for mass in mass_lst
]
sinfos = ["RSG " + str(m) + " GeV" for m in mass_lst]
dfiles = ["/data_test/hist-MiniNTuple.root"]
dinfos = ["0Tag data"]
allmc = []
for j, (f, info) in enumerate(zip(dfiles + sfiles, dinfos + sinfos)):
cut = dcut if "data" in f else scut
#here could be changed to have more options
input_mc = ROOT.TFile.Open(CONF.inputpath + inputdir + f)
if not input_mc:
print CONF.inputpath + inputdir + f
try:
temp_mc = input_mc.Get(cut).Clone()
#temp_mc = temp_mc.ProjectionY()
except:
print CONF.inputpath + inputdir + f
print cut
raise
# rebin the hist for pt
# set other options
temp_mc.GetYaxis().SetTitle("Normalized")
temp_mc.GetXaxis().SetNdivisions(510)
temp_mc.GetXaxis().SetLabelSize(0.03)
temp_mc.GetYaxis().SetNdivisions(505)
if cut.split("_")[-1] == "pt":
temp_mc.Rebin(10)
temp_mc.GetXaxis().SetTitle(temp_mc.GetXaxis().GetTitle() +
" [GeV]")
elif "deta" in cut.lower():
temp_mc.Rebin(30)
maxbincontent = .6 / 1.5
# draw line at the cut value
cutval = 1.7
line = ROOT.TLine(1.7, 0, 1.7, 0.4)
line.SetLineWidth(3)
line.SetLineStyle(9)
line.Draw()
else:
temp_mc.GetXaxis().SetTitle("#DeltaR between H, child b")
dR_type = cut.split("/")[1][0:4]
if dR_type != "h0h1":
temp_mc.GetXaxis().SetRangeUser(0, 3)
maxbincontent = 1.0 / 1.5
else:
maxbincontent = .5
if dR_type == "h1b2" or dR_type == "h0b0":
dR1_line = ROOT.TLine(1, 0, 1, maxbincontent)
dR04_line = ROOT.TLine(.4, 0, .4, maxbincontent)
dR1_line.Draw("")
dR04_line.Draw("")
elif dR_type == "b0b1" or dR_type == "b2b3":
dR1_line = ROOT.TLine(2, 0, 2, maxbincontent)
dR04_line = ROOT.TLine(.8, 0, .8, maxbincontent)
dR1_line.Draw("")
dR04_line.Draw("")
if temp_mc.GetNbinsX() == 76:
temp_mc.Rebin(4)
elif temp_mc.GetNbinsX() > 20:
temp_mc.Rebin(temp_mc.GetNbinsX() / 20)
if "data" in f:
temp_mc.Sumw2(True)
outputroot.cd()
temp_mc.Scale(1 / temp_mc.Integral())
temp_mc.SetName("RSG_" + info + "_" + cut.replace("/", "_"))
temp_mc.Write()
temp2_mc = outputroot.Get(temp_mc.GetName())
if temp_mc.Integral() < 1e-4:
continue
truth_mc = helpers.TH1toTAsym(temp2_mc, efficiency=False)
truth_mc.SetLineColor(CONF.clr_lst[j])
truth_mc.SetMarkerStyle(20 + j)
truth_mc.SetMarkerColor(CONF.clr_lst[j])
truth_mc.SetMarkerSize(1)
truth_mc.SetMaximum(maxbincontent * 1.5)
truth_mc.SetMinimum(minbincontent)
truth_mc.GetXaxis().SetTitle(cut.split("/")[1].replace("_", " "))
canv.cd()
#reset data style
if "data" in f:
truth_mc.SetLineColor(1)
truth_mc.SetMarkerColor(1)
if j == 0:
truth_mc.Draw("APC")
else:
truth_mc.Draw("PC")
allmc.append(truth_mc)
legend.AddEntry(truth_mc, info, "apl")
input_mc.Close()
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas - 0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas - 0.12, "MC #sqrt{s} = 13 TeV")
watermarks = [atlas, hh4b, lumi]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
outputroot.cd()
helpers.checkpath(CONF.inputpath + inputdir + "/Plot/Truth/")
#print CONF.inputpath + inputdir + "/Plot/Truth/"
canv.SaveAs(CONF.inputpath + inputdir + "/Plot/Truth/" +
canv.GetName() + "_" + cut.replace("/", "_") + ".pdf")
canv.Close()
#Tony: master configuration file, specifies all the necessary paths import ROOT, helpers, os #get current directory currpath = os.path.abspath(os.curdir) #change this to your home directory of everything; should be where the code is checked out toppath = os.path.dirname(currpath) #input top directory for the root files inputpath = toppath + "/Output/" helpers.checkpath(inputpath) #output top directory for the output plots/root files outputpath = toppath +"/Output/" helpers.checkpath(outputpath) #output top directory for only plots outplotpath = toppath +"/Plot/" helpers.checkpath(outplotpath) #put in the working directory name; default b77~ workdir = "Moriond" #"Moriond" #b77 #chosen reweight directory reweightdir = "bkg_9" #"Moriond" #b77 #check if reference folder exists refpath = toppath +"/Output/ref/" #do c20 and 2HDM samples doallsig = True #check if reference folder exists fullstudy = False #check if doing my thesis; if so, disable all the ATLAS labels thesis = True #check if the path exists if not os.path.exists(refpath): print "please copy the directory: /afs/cern.ch/user/b/btong/work/public/RunIIHH4b/ref over to Output/ref!!!" else:
def plot_RSG_syst_detail(masterdic, cut):
canv = ROOT.TCanvas(cut + "_" + "RSG" + "_" + "syst_detail", "Sytematics", 800, 800)
xleg, yleg = 0.52, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.3, yleg+0.2)
# setup basic plot parameters
# load input MC file
mass_lst = [1000, 1100, 1200, 1300, 1400, 1500, 1600, 1800, 2000, 2250, 2500, 2750, 3000]
eff_lst = []
graph_lst = []
maxbincontent = 100.0
minbincontent = -0.001
lowmass = 950
highmass = 3150
#create bsyst list
bsyst_lst = []
for i in bsyst:
if "up" in i:
bsyst_lst.append(i.replace("up", ""))
#now loop
draw_counter = 0
for i, syst in enumerate(bsyst_lst):
eff_lst.append( ROOT.TH1F(syst, "%s; Mass, GeV; Systematic Percentage Diff" %syst, int((highmass-lowmass)/100), lowmass, highmass) )
maxsyst = 0.0
for mass in mass_lst:
temp_col_dic = find_syst(masterdic, cut, syst, "RSG1_" + str(mass))
syst_eff = add_syst(temp_col_dic) #this is a tuple!
# if (syst_eff[0] * 100 < 3): #if the systematic contribution is less than 3 percent
# continue
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), syst_eff[0] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
#print syst, syst_eff[0]
maxbincontent = max(maxbincontent, syst_eff[0] * 100)
maxsyst = max(maxsyst, syst_eff[0] * 100)
#print maxsyst, i
#start the canvas
canv.cd()
#convert it to a graph
if maxsyst < 3: #don't draw everything
print syst
continue
graph_lst.append(helpers.TH1toTAsym(eff_lst[i]))
graph_lst[-1].SetLineColor(CONF.clr_lst[draw_counter])
graph_lst[-1].SetMarkerStyle(20 + draw_counter)
graph_lst[-1].SetMarkerColor(CONF.clr_lst[draw_counter])
graph_lst[-1].SetMarkerSize(1)
graph_lst[-1].SetMaximum(maxbincontent * 1.5)
graph_lst[-1].SetMinimum(minbincontent)
legend.AddEntry(graph_lst[-1], syst.replace("_", " "), "apl")
if draw_counter==0:
graph_lst[-1].Draw("APC")
draw_counter += 1
else:
graph_lst[-1].Draw("PC")
draw_counter += 1
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw reference lines
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas-0.12, "MC #sqrt{s} = 13 TeV")
watermarks = [atlas, hh4b, lumi]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
helpers.checkpath(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/")
canv.SaveAs(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/" + canv.GetName() + ".pdf")
canv.Close()
def plot_RSG_syst(masterdic, cut):
### the first argument is the input dictionary
### the second argument is the 2b/3b/4b regions
canv = ROOT.TCanvas(cut + "_" + "RSG" + "_" + "syst", "Sytematics", 800, 800)
xleg, yleg = 0.52, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.3, yleg+0.2)
# setup basic plot parameters
# load input MC file
#mass_lst = [1000, 1100, 1200, 1300, 1400, 1500, 1600, 1800, 2000, 2250, 2500, 2750, 3000]
mass_lst = [1000, 1100, 1200, 1300, 1400, 1500, 1600, 1800, 2000, 2250, 2500, 2750, 3000, 3500, 4000, 4500, 5000]
systag_lst = ["JER", "JMR", "Rtrk", "EFF", "Stat"]
systag_dic = {"JER":"JER", "JMR":"JMR", "Rtrk":"JES/JMS", "EFF":"b-tag SF", "Stat":"Stats"}
eff_lst = []
graph_lst = []
maxbincontent = 40.0
minbincontent = -0.001
lowmass = 950
#highmass = 3150
highmass = 5050
for i, syst in enumerate(systag_lst):
eff_lst.append( ROOT.TH1F(syst, "%s; Mass, GeV; Systematic Percentage Diff" %syst, int((highmass-lowmass)/100), lowmass, highmass) )
for mass in mass_lst:
#print mass
if syst is "Stat":
for key2 in masterdic[cut]:
if "RSG1_" + str(mass) in key2:
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), masterdic[cut][key2]["int_err"]/masterdic[cut][key2]["int"] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
else:
temp_col_dic = find_syst(masterdic, cut, syst, "RSG1_" + str(mass))
syst_eff = add_syst(temp_col_dic) #this is a tuple!
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), syst_eff[0] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
#print syst_eff[0]
maxbincontent = max(maxbincontent, syst_eff[0])
#start the canvas
canv.cd()
#convert it to a TGraph
graph_lst.append(helpers.TH1toTAsym(eff_lst[i]))
graph_lst[i].SetLineColor(CONF.clr_lst[i])
graph_lst[i].SetMarkerStyle(20 + i)
graph_lst[i].SetMarkerColor(CONF.clr_lst[i])
graph_lst[i].SetMarkerSize(1)
graph_lst[i].SetMaximum(maxbincontent * 1.5)
graph_lst[i].SetMinimum(minbincontent)
legend.AddEntry(graph_lst[i], systag_dic[syst].replace("_", " "), "apl")
if syst==systag_lst[0]:
graph_lst[i].Draw("APC")
#gr.Draw("same L hist")
else:
graph_lst[i].Draw("PC")
#gr.Draw("same L hist")
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw reference lines
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas-0.12, "MC #sqrt{s} = 13 TeV")
watermarks = [atlas, hh4b, lumi]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
helpers.checkpath(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/")
canv.SaveAs(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/" + canv.GetName() + ".pdf")
canv.Close()
#Tony: master configuration file, specifies all the necessary paths
import ROOT, helpers, os
#get current directory
currpath = os.path.abspath(os.curdir)
#change this to your home directory of everything; should be where the code is checked out
toppath = os.path.dirname(currpath)
#input top directory for the root files
inputpath = toppath + "/Output/"
helpers.checkpath(inputpath)
#output top directory for the output plots/root files
outputpath = toppath + "/Output/"
helpers.checkpath(outputpath)
#output top directory for only plots
outplotpath = toppath + "/Plot/"
helpers.checkpath(outplotpath)
#put in the working directory name; default b77~
workdir = "Moriond" #"Moriond" #b77
#chosen reweight directory
reweightdir = "bkg_9" #"Moriond" #b77
#check if reference folder exists
refpath = toppath + "/Output/ref/"
#do c20 and 2HDM samples
doallsig = True
#check if reference folder exists
fullstudy = False
#check if doing my thesis; if so, disable all the ATLAS labels
thesis = True
#check if the path exists
if not os.path.exists(refpath):
print "please copy the directory: /afs/cern.ch/user/b/btong/work/public/RunIIHH4b/ref over to Output/ref!!!"
else:
def DrawSignalTruth(outputroot, dcut_lst, scut_lst, inputdir="", outputname="", normalization=0):
### the first argument is the input directory
### the second argument is the output prefix name
### the third argument is relative to what normalization: 0 for total number of events
### 1 for signal mass region
# setup basic plot parameters
lowmass = -50
highmass = 3150
# load input MC file
maxbincontent = .4 # approx
minbincontent = -0.01
for i, (dcut, scut) in enumerate(zip(dcut_lst, scut_lst)):
canv = ROOT.TCanvas(inputdir + "_" + outputname + str(normalization), "Efficiency", 800, 800)
xleg, yleg = 0.55, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.3, yleg+0.2)
sfiles = ["/signal_G_hh_c10_M%i/hist-MiniNTuple.root" % mass for mass in mass_lst]
#sfiles = ["/signal_X_hh_M%i/hist-MiniNTuple.root" % mass for mass in mass_lst]
sinfos = ["RSG " + str(m) + " GeV" for m in mass_lst]
dfiles = ["/data_test/hist-MiniNTuple.root"]
dinfos = ["0Tag data"]
allmc = []
for j,(f,info) in enumerate(zip(dfiles + sfiles, dinfos + sinfos)):
cut = dcut if "data" in f else scut
#here could be changed to have more options
input_mc = ROOT.TFile.Open(CONF.inputpath + inputdir + f)
if not input_mc:
print CONF.inputpath + inputdir + f
try:
temp_mc = input_mc.Get(cut).Clone()
#temp_mc = temp_mc.ProjectionY()
except:
print CONF.inputpath + inputdir + f
print cut
raise
# rebin the hist for pt
# set other options
temp_mc.GetYaxis().SetTitle("Normalized")
temp_mc.GetXaxis().SetNdivisions(510)
temp_mc.GetXaxis().SetLabelSize(0.03)
temp_mc.GetYaxis().SetNdivisions(505)
temp_mc.GetXaxis().SetNdivisions(505)
#print(cut)
if cut.split("_")[-1] == "pt":
temp_mc.Rebin(10)
temp_mc.GetXaxis().SetTitle( temp_mc.GetXaxis().GetTitle() + " [GeV]")
else:
temp_mc.GetXaxis().SetTitle( "#DeltaR between H, child b")
dR_type = cut.split("/")[1][0:4]
if dR_type != "h0h1":
temp_mc.GetXaxis().SetRangeUser(0, 3)
maxbincontent = 1.0/1.5
else:
maxbincontent = .5
if dR_type == "h1b2" or dR_type == "h0b0":
dR1_line = ROOT.TLine(1, 0, 1, maxbincontent)
dR04_line = ROOT.TLine(.4, 0, .4, maxbincontent)
dR1_line.Draw("")
dR04_line.Draw("")
elif dR_type == "b0b1" or dR_type == "b2b3":
dR1_line = ROOT.TLine(2, 0, 2, maxbincontent)
dR04_line = ROOT.TLine(.8, 0, .8, maxbincontent)
dR1_line.Draw("")
dR04_line.Draw("")
if temp_mc.GetNbinsX() == 76:
temp_mc.Rebin(4)
elif temp_mc.GetNbinsX() > 20:
temp_mc.Rebin(temp_mc.GetNbinsX() / 20)
if "data" in f:
temp_mc.Sumw2(True)
outputroot.cd()
temp_mc.Scale(1/temp_mc.Integral())
temp_mc.SetName("RSG_" + info + "_" + cut.replace("/", "_"))
temp_mc.Write()
temp2_mc = outputroot.Get(temp_mc.GetName())
if temp_mc.Integral() < 1e-4:
continue
truth_mc = helpers.TH1toTAsym(temp2_mc, efficiency=False)
truth_mc.SetLineColor(CONF.clr_lst[j])
truth_mc.SetMarkerStyle(20 + j)
truth_mc.SetMarkerColor(CONF.clr_lst[j])
truth_mc.SetMarkerSize(1)
truth_mc.SetMaximum(maxbincontent * 1.5)
truth_mc.SetMinimum(minbincontent)
truth_mc.GetXaxis().SetTitle(cut.split("/")[1].replace("_", " "))
canv.cd()
#reset data style
if "data" in f:
truth_mc.SetLineColor(1)
truth_mc.SetMarkerColor(1)
if j==0:
truth_mc.Draw("APC")
else:
truth_mc.Draw("PC")
allmc.append(truth_mc)
legend.AddEntry(truth_mc, info, "apl")
input_mc.Close()
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas-0.12, "MC #sqrt{s} = 13 TeV")
taglabel = ROOT.TLatex(xatlas, yatlas-0.18, scut.split("_")[0])
watermarks = [atlas, hh4b, lumi, taglabel]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
outputroot.cd()
helpers.checkpath(CONF.inputpath + inputdir + "/Plot/Truth/")
#print CONF.inputpath + inputdir + "/Plot/Truth/"
canv.SaveAs(CONF.inputpath + inputdir + "/Plot/Truth/" + canv.GetName() + "_" + cut.replace("/", "_") + ".pdf")
canv.Close()
def main():
start_time = time.time()
ops = options()
global blinded
blinded = True
global iter_reweight
iter_reweight = int(ops.iter)
#setup basics
inputdir = ops.inputdir
inputroot = ops.inputroot
inputpath = CONF.inputpath + inputdir + "/"
rootinputpath = inputpath + inputroot + "_"
print "input root file is: ", rootinputpath
global StatusLabel
StatusLabel = "Internal" ##StatusLabel = "Preliminary"
global reweightfolder
reweightfolder = inputpath + "Reweight/"
helpers.checkpath(reweightfolder)
global outputroot
outputroot = ROOT.TFile(reweightfolder + "reweights.root", "recreate")
# plot in the control region #
# outputFolder = inputpath + inputroot + "Plot/" + "Sideband"
# plotRegion(rootinputpath, inputdir, cut="FourTag" + "_" + "Sideband" + "_" + "mHH_l", xTitle="m_{2J} [GeV]")
# plotRegion(rootinputpath, inputdir, cut="FourTag" + "_" + "Sideband" + "_" + "mHH_l", xTitle="m_{2J} [GeV]", Logy=1)
##comp_lst are the distributios we want to look like
##cut_lst are the disbrituions we are changing
##this is the default
if "j0pT" in ops.var:
region_lst = ["Sideband"]
cut_lst = ["TwoTag_split", "ThreeTag", "FourTag"]
#this is the one tag rewieght
if "bkg" in ops.var:
region_lst = ["Incl"]
comp_region_lst = ["Incl"]
cut_lst = ["NoTag_2Trk_split_lead", "NoTag_2Trk_split_subl", "NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead", "NoTag_4Trk_subl"]
comp_lst = ["OneTag_subl", "OneTag_lead", "OneTag_subl", "OneTag_lead", "TwoTag_subl", "TwoTag_lead"]
##this is to the sidebands rewieght
if "bkgsb" in ops.var:
region_lst = ["Sideband"]
comp_region_lst = ["Sideband"]
cut_lst = ["NoTag_2Trk_split_lead", "NoTag_2Trk_split_subl", "NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead", "NoTag_4Trk_subl"]
comp_lst = ["TwoTag_split", "TwoTag_split", "ThreeTag", "ThreeTag", "FourTag", "FourTag"]
##this is the detailed trk reweight
# region_lst = ["Incl"]
# cut_lst = ["NoTag_2Trk_split_lead_lead", "NoTag_2Trk_split_subl_lead", "NoTag_2Trk_split_lead_subl", "NoTag_2Trk_split_subl_subl", "NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead", "NoTag_4Trk_subl"]
# comp_lst = ["OneTag_subl_lead", "OneTag_lead_subl", "OneTag_subl_subl", "OneTag_lead_lead", "OneTag_subl", "OneTag_lead", "TwoTag_subl", "TwoTag_lead"]
# comp_region_lst = ["Incl"]
#create master list
inputtasks = []
#fill the task list
for i, region in enumerate(region_lst):
if inputroot == "sum":
inputroot = ""
outputFolder = inputpath + inputroot + "Plot_r" + str(iter_reweight) + "/" + region
helpers.checkpath(outputFolder)
for j, cut in enumerate(cut_lst):
config = {}
config["root"] = rootinputpath
config["inputdir"] = inputdir
config["outputdir"] = outputFolder
config["cut"] = cut + "_" + region + "_"
try:
config["compcut"] = comp_lst[j] + "_" + comp_region_lst[i] + "_" ##change this to be flexiable to regions
except NameError:
config["compcut"] = "" ##by default this is disabled
inputtasks.append(config)
#parallel compute!
print " Running %s jobs on %s cores" % (len(inputtasks), mp.cpu_count()-1)
npool = min(len(inputtasks), mp.cpu_count()-1)
pool = mp.Pool(npool)
pool.map(dumpRegion, inputtasks)
##for debug
# for task in inputtasks:
# dumpRegion(task)
# dumpRegion(inputtasks[0])
outputroot.Close()
print("--- %s seconds ---" % (time.time() - start_time))
def plot_RSG_syst(masterdic, cut):
### the first argument is the input dictionary
### the second argument is the 2b/3b/4b regions
canv = ROOT.TCanvas(cut + "_" + "RSG" + "_" + "syst", "Sytematics", 800, 800)
xleg, yleg = 0.52, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.3, yleg+0.2)
# setup basic plot parameters
# load input MC file
mass_lst = [1000, 1100, 1200, 1300, 1400, 1500, 1600, 1800, 2000, 2250, 2500, 2750, 3000]
systag_lst = ["JER", "JMR", "Rtrk", "EFF", "Stat"]
systag_dic = {"JER":"JER", "JMR":"JMR", "Rtrk":"JES/JMS", "EFF":"b-tag SF", "Stat":"Stats"}
eff_lst = []
graph_lst = []
maxbincontent = 40.0
minbincontent = -0.001
lowmass = 950
highmass = 3150
for i, syst in enumerate(systag_lst):
eff_lst.append( ROOT.TH1F(syst, "%s; Mass, GeV; Systematic Percentage Diff" %syst, int((highmass-lowmass)/100), lowmass, highmass) )
for mass in mass_lst:
if syst is "Stat":
for key2 in masterdic[cut]:
if "RSG1_" + str(mass) in key2:
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), masterdic[cut][key2]["int_err"]/masterdic[cut][key2]["int"] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
else:
temp_col_dic = find_syst(masterdic, cut, syst, "RSG1_" + str(mass))
syst_eff = add_syst(temp_col_dic) #this is a tuple!
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), syst_eff[0] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
#print syst_eff[0]
maxbincontent = max(maxbincontent, syst_eff[0])
#start the canvas
canv.cd()
#convert it to a TGraph
graph_lst.append(helpers.TH1toTAsym(eff_lst[i]))
graph_lst[i].SetLineColor(CONF.clr_lst[i])
graph_lst[i].SetMarkerStyle(20 + i)
graph_lst[i].SetMarkerColor(CONF.clr_lst[i])
graph_lst[i].SetMarkerSize(1)
graph_lst[i].SetMaximum(maxbincontent * 1.5)
graph_lst[i].SetMinimum(minbincontent)
legend.AddEntry(graph_lst[i], systag_dic[syst].replace("_", " "), "apl")
if syst==systag_lst[0]:
graph_lst[i].Draw("APC")
#gr.Draw("same L hist")
else:
graph_lst[i].Draw("PC")
#gr.Draw("same L hist")
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw reference lines
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas-0.12, "MC #sqrt{s} = 13 TeV")
watermarks = [atlas, hh4b, lumi]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
helpers.checkpath(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/")
canv.SaveAs(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/" + canv.GetName() + ".pdf")
canv.Close()
def DrawSRcomparison(inputname="CR_High", tag="", keyword="totalbkg_hh", prename="", Xrange=[0, 0], Yrange=[0, 0], norm=True, Logy=0):
#print inputdir, inputname
histdir = inputdir + "_" + inputname
inputroot = ROOT.TFile.Open(CONF.inputpath + "/" + histdir + "/Limitinput/" + histdir + "_limit_" + tag + ".root")
refroot = ROOT.TFile.Open(CONF.inputpath + "/" + inputdir + reweightpath + "/Limitinput/" + inputdir + reweightpath + "_limit_" + tag + ".root")
tempname = inputname + "_" + "compare" + "_" + tag + "_" + keyword + ("" if Logy == 0 else "_" + str(Logy))
canv = ROOT.TCanvas(tempname, tempname, 800, 800)
canv.SetLogy(Logy)
xleg, yleg = 0.5, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.15, yleg+0.2)
counter = 0
maxbincontent = (0.2 if Logy ==0 else 10)
print keyword, histdir
temp_hist = inputroot.Get(keyword)
#print temp_hist.GetName()
temp_hist.SetLineColor(2)
temp_hist.SetMarkerStyle(20)
temp_hist.SetMarkerColor(2)
temp_hist.SetMarkerSize(1)
ref_hist = refroot.Get(keyword)
#print temp_hist.GetName()
ref_hist.SetLineColor(1)
ref_hist.SetMarkerStyle(21)
ref_hist.SetMarkerColor(1)
ref_hist.SetMarkerSize(1)
#scale to correct normalization diff
#temp_hist.Scale(ref_hist.Integral()/temp_hist.Integral())
#continue
maxbincontent = max(maxbincontent, ref_hist.GetMaximum(), temp_hist.GetMaximum())
temp_hist.SetMaximum(maxbincontent * 1.5 * 100)
ref_hist.SetMaximum(maxbincontent * 1.5 * 100)
legend.AddEntry(temp_hist, inputname.replace("_", " "), "apl")
legend.AddEntry(ref_hist, "Nominal", "apl")
# top pad
pad0 = ROOT.TPad("pad0", "pad0", 0.0, 0.31, 1., 1.)
pad0.SetLogy(1)
pad0.SetRightMargin(0.05)
pad0.SetBottomMargin(0.0001)
pad0.SetFrameFillColor(0)
pad0.SetFrameBorderMode(0)
pad0.SetFrameFillColor(0)
pad0.SetBorderMode(0)
pad0.SetBorderSize(0)
pad1 = ROOT.TPad("pad1", "pad1", 0.0, 0.0, 1., 0.30)
pad1.SetRightMargin(0.05)
pad1.SetBottomMargin(0.38)
pad1.SetTopMargin(0.0001)
pad1.SetFrameFillColor(0)
pad1.SetFillStyle(0) # transparent
pad1.SetFrameBorderMode(0)
pad1.SetFrameFillColor(0)
pad1.SetBorderMode(0)
pad1.SetBorderSize(0)
canv.cd()
pad0.Draw()
pad0.cd()
temp_hist.Draw("")
ref_hist.Draw("same")
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, tag.replace("_", " "))
watermarks = [atlas, hh4b]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
canv.cd()
pad1.Draw()
pad1.cd()
#ratio of the two plots
ratiohist = temp_hist.Clone("ratio")
ratiohist.Divide(ref_hist)
ratiohist.GetYaxis().SetRangeUser(0.6, 1.5) #set range for ratio plot
ratiohist.GetYaxis().SetTitle("Varaition/Nominal") #set range for ratio plot
ratiohist.GetYaxis().SetTitleFont(43)
ratiohist.GetYaxis().SetTitleSize(28)
ratiohist.GetYaxis().SetLabelFont(43)
ratiohist.GetYaxis().SetLabelSize(28)
ratiohist.GetYaxis().SetNdivisions(405)
ratiohist.GetXaxis().SetTitleFont(43)
ratiohist.GetXaxis().SetTitleOffset(3.5)
ratiohist.GetXaxis().SetTitleSize(28)
ratiohist.GetXaxis().SetLabelFont(43)
ratiohist.GetXaxis().SetLabelSize(28)
ratiohist.Draw("")
xMin = ref_hist.GetXaxis().GetBinLowEdge(1)
xMax = ref_hist.GetXaxis().GetBinUpEdge(ref_hist.GetXaxis().GetNbins())
line = ROOT.TLine(xMin, 1.0, xMax, 1.0)
line.SetLineStyle(1)
line.Draw()
#canv.SetLogy(1)
helpers.checkpath(CONF.inputpath + inputdir + "/Plot/Syst/")
canv.SaveAs(CONF.inputpath + inputdir + "/Plot/Syst/" + canv.GetName() + ".pdf")
pad0.Close()
pad1.Close()
canv.Close()
inputroot.Close()
refroot.Close()
def syst_pipeline(config):
t = config["inputdir"]
print "the directory is: ", t
inputpath = CONF.inputpath + t + "/"
#check if for syst, the data file is there
helpers.checkpath(inputpath + "data_test")
#this is a really bad practice and temp fix now! need to watch this very carfully...
ori_link = CONF.inputpath + ops.inputdir + "/data_test/hist-MiniNTuple.root"
dst_link = inputpath + "data_test/hist-MiniNTuple.root"
#print ori_link, dst_link
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
#for ttbar, also need to link the MCs.
if "syst_tt_" in t:
##copy zjets as well
helpers.checkpath(inputpath + "zjets_test")
ori_link = CONF.inputpath + ops.inputdir + "/zjets_test/hist-MiniNTuple.root"
dst_link = inputpath + "zjets_test/hist-MiniNTuple.root"
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
##copy SM_hh as well
helpers.checkpath(inputpath + "signal_SM_hh")
ori_link = CONF.inputpath + ops.inputdir + "/signal_SM_hh/hist-MiniNTuple.root"
dst_link = inputpath + "signal_SM_hh/hist-MiniNTuple.root"
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
##copy other MC signals
sigMClist = ["signal_G_hh_c10_M"]
if (ops.Xhh):
sigMClist = [
"signal_G_hh_c10_M", "signal_G_hh_c20_M", "signal_X_hh_M"
]
for sigMC in sigMClist:
for i, mass in enumerate(CONF.mass_lst):
if mass == 2750 and sigMC == "signal_G_hh_c20_M": ##no 2750 c20 sample
continue
#print "creating links of signal samples", "signal_G_hh_c10_M" + str(mass)
#this is a really bad practice and temp fix now! need to watch this very carfully...
ori_link = CONF.inputpath + ops.inputdir + "/" + sigMC + str(
mass) + "/hist-MiniNTuple.root"
#ori_link = inputpath.replace("TEST", "DS1_cb") + "signal_G_hh_c10_M" + str(mass) + "/hist-MiniNTuple.root"
dst_link = inputpath + sigMC + str(
mass) + "/hist-MiniNTuple.root"
helpers.checkpath(inputpath + sigMC + str(mass))
#print ori_link, dst_link
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
for i, mass in enumerate([3500, 4000, 4500, 5000, 6000]):
if sigMC != "signal_G_hh_c10_M": ##no 2750 c20 sample
continue
ori_link = CONF.inputpath + ops.inputdir + "/" + sigMC + str(
mass) + "/hist-MiniNTuple.root"
dst_link = inputpath + sigMC + str(
mass) + "/hist-MiniNTuple.root"
helpers.checkpath(inputpath + sigMC + str(mass))
if os.path.islink(dst_link):
os.unlink(dst_link)
os.symlink(ori_link, dst_link)
#start running programs
#print (inputpath)
#os.system("rm " + inputpath + "sum_" + t + ".root")
os.system("rm -r " + inputpath + "Limitinput")
# print "done clearing!"
# ###this is correcting the 3b/4b normalization to 2b. Should only be applied when ttbar stats makes no sense!
# if "syst_tt_" in t or "JET_JER" in t or "JET_JMR" in t: ##only for ttbar variations for now
# Tophack(inputpath=inputpath)
# #Tophack(inputpath=inputpath)
#os.system("python get_count.py --dosyst " + " --inputdir " + t)
##ttbar has weird smoothing behaviour, use ttbar + qcd for final distribution now
os.system("python dump_hists.py " + " --inputdir " + t +
(" --dosyst" if "syst_tt_" in t else ""))
def analysis_pipeline(config):
#setup the directories
motherdir = config["motherdir"] #the one with TinyTree
reweight = config["reweight"] #this is the reweight method
iter_re = config["iter_re"]
reweightplotdir = config["reweightplotdir"]
outputdir = ops.inputdir + "_" + reweight + "_" + str(
iter_re) #the output from Plot TinyTree, input for analysis code
print "the directory is: ", outputdir, " parent dir is: ", motherdir, " reweight: ", reweight, " iteration: ", iter_re
##reweight
#print "python PlotTinyTree.py --inputdir " + motherdir + " --outputdir " + outputdir + " --reweight " + reweight + " --iter " + str(iter_re)
os.system("python PlotTinyTree.py --inputdir " + motherdir +
" --outputdir " + outputdir + " --reweight " + reweight +
" --iter " + str(iter_re)) #+ " --debug")
# if (iter_re == iter_total - 1): ## reweight the dijet MC for the last iteration
# os.system("python PlotTinyTree.py --inputdir " + motherdir + " --outputdir " + outputdir + " --reweight " + reweight + " --iter " + str(iter_re) + " --dijet")
##fit and produce plot
os.system("python get_count.py --full --inputdir " + outputdir)
os.system("python plot.py --inputdir " + outputdir)
os.system("python reweight.py --inputdir " + outputdir + " --iter " +
str(iter_re + 1) + " --var " +
reweight) ##+1 because it is really for the next iteration
if ops.publish:
##for publication purpose
homepath = "/afs/cern.ch/user/b/btong/"
workpath = CONF.outputpath + outputdir
print "Publish!"
helpers.checkpath(homepath + "/www/share/hh4b/reweight/" + outputdir)
helpers.checkpath(homepath + "/www/share/hh4b/plot/" + outputdir)
helpers.checkpath(homepath + "/www/share/hh4b/express/" + outputdir)
##list of plots
if CONF.fullstudy:
plt_lst = ["mHH_l_1",\
"leadHCand_Pt_m_1", "leadHCand_Eta", "leadHCand_Phi", "leadHCand_Mass", "leadHCand_Mass_s", "leadHCand_trk_dr",\
"sublHCand_Pt_m_1", "sublHCand_Eta", "sublHCand_Phi", "sublHCand_Mass", "sublHCand_Mass_s", "sublHCand_trk_dr",\
"leadHCand_trk0_Pt", "leadHCand_trk1_Pt", "sublHCand_trk0_Pt", "sublHCand_trk1_Pt"]
else:
plt_lst = ["mHH_l_1", \
"leadHCand_Pt_m_1",\
"sublHCand_Pt_m_1",\
"leadHCand_trk0_Pt", "leadHCand_trk1_Pt", "sublHCand_trk0_Pt", "sublHCand_trk1_Pt"]
#"hCandDr", "hCandDeta", "hCandDphi",\
##clean up the current plots
pubDirs = ["reweight", "express", "plot"]
for pubdir in pubDirs:
for pic in glob.glob(homepath + "/www/share/hh4b/" + pubdir + "/" +
outputdir + "/*"):
os.remove(pic)
##add description file
descript = open(
homepath + "/www/share/hh4b/" + pubdir + "/" + outputdir +
"/shortdescription.txt", "w")
descript.write(" reweight: " + reweight + " iteration: " +
str(iter_re))
descript.write(" time: " +
time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime()))
descript.close()
##copy
for plot in plt_lst:
for pic in glob.glob(workpath + "/Plot_r" + str(iter_re + 1) +
"/" + reweightplotdir + "/*" + plot + ".png"):
os.system("cp " + pic + " " + homepath +
"/www/share/hh4b/reweight/" + outputdir + "/.")
for pic in glob.glob(workpath + "/Plot" + "/Sideband/*" + plot +
".png"):
os.system("cp " + pic + " " + homepath +
"/www/share/hh4b/plot/" + outputdir + "/.")
if "mHH_l_1" in pic:
os.system("cp " + pic + " " + homepath +
"/www/share/hh4b/express/" + outputdir + "/.")
for pic in glob.glob(workpath + "/Plot" + "/Control/*" + plot +
".png"):
#print pic
os.system("cp " + pic + " " + homepath +
"/www/share/hh4b/plot/" + outputdir + "/.")
if "mHH_l_1" in pic:
os.system("cp " + pic + " " + homepath +
"/www/share/hh4b/express/" + outputdir + "/.")
#print "cp " + pic + " " + homepath + "/www/share/hh4b/express/" + outputdir +"/."
##publish
os.chdir(homepath + "/www/share/")
os.system("python createHtmlOverview.py")
os.chdir(CONF.currpath)
print "Done!"
def main():
global ops
ops = options()
inputpath = CONF.inputpath + ops.inputdir + "/"
global outputpath
outputpath = CONF.outputpath + ops.outputdir + "/tmvaplot/"
helpers.checkpath(outputpath)
#start analysis on TinyNtuple
mass = 1500
fSignal = TFile( inputpath + "signal_G_hh_c10_M" + str(mass) + "/" + "hist-MiniNTuple.root", "read" )
fBackground = TFile( inputpath + "data_test/" + "hist-MiniNTuple.root", "read" )
# Get the signal and background trees for training
signal = fSignal.Get( "TinyTree" )
background = fBackground.Get( "TinyTree" )
# Set output paraemters and TMVA methods
outfname = "TMVA_" + ops.sel + ".root"
methods = DEFAULT_METHODS
verbose = False
# Print methods
mlist = methods.replace(' ',',').split(',')
print "=== TMVAClassification: use method(s)..."
for m in mlist:
if m.strip() != '':
print "=== - <%s>" % m.strip()
# Import TMVA classes from ROOT
from ROOT import TMVA
# Output file
outputFile = TFile( outputpath + outfname, 'RECREATE' )
# Create instance of TMVA factory (see TMVA/macros/TMVAClassification.C for more factory options)
# All TMVA output can be suppressed by removing the "!" (not) in
# front of the "Silent" argument in the option string
factory = TMVA.Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" )
# Set verbosity
factory.SetVerbose( verbose )
# If you wish to modify default settings
# (please check "src/Config.h" to see all available global options)
# gConfig().GetVariablePlotting()).fTimesRMS = 8.0
# gConfig().GetIONames().fWeightFileDir = outputpath + "weights"
# Define the input variables that shall be used for the classifier training
# note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
# [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory.AddVariable( "mHH", "mHH", "GeV", 'F' )
#factory.AddVariable( "j0_nb + j1_nb", "Nb", "Nb", 'I' )
factory.AddVariable( "j0_pt", "j0_pt", "GeV", 'F' )
#factory.AddVariable( "j0_eta", "j0_eta", "rad", 'F' )
#factory.AddVariable( "j0_phi", "j0_phi", "rad", 'F' )
factory.AddVariable( "j0_m", "j0_m", "GeV", 'F' )
factory.AddVariable( "j1_pt", "j1_pt", "GeV", 'F' )
#factory.AddVariable( "j1_eta", "j1_eta", "rad", 'F' )
#factory.AddVariable( "j1_phi", "j1_phi", "rad", 'F' )
factory.AddVariable( "j1_m", "j1_m", "GeV", 'F' )
factory.AddVariable( "j0_trk0_pt", "j0_trk0_pt", "GeV", 'F' )
#factory.AddVariable( "j0_trk0_eta", "j0_trk0_eta", "rad", 'F' )
#factory.AddVariable( "j0_trk0_phi", "j0_trk0_phi", "rad", 'F' )
#factory.AddVariable( "j0_trk0_m", "j0_trk0_m", "GeV", 'F' )
#factory.AddVariable( "j0_trk0_Mv2", "j0_trk0_Mv2", "MV2", 'F' )
factory.AddVariable( "j0_trk1_pt", "j0_trk1_pt", "GeV", 'F' )
#factory.AddVariable( "j0_trk1_eta", "j0_trk1_eta", "rad", 'F' )
#factory.AddVariable( "j0_trk1_phi", "j0_trk1_phi", "rad", 'F' )
#factory.AddVariable( "j0_trk1_m", "j0_trk1_m", "GeV", 'F' )
#factory.AddVariable( "j0_trk1_Mv2", "j0_trk1_Mv2", "MV2", 'F' )
factory.AddVariable( "j1_trk0_pt", "j1_trk0_pt", "GeV", 'F' )
#factory.AddVariable( "j1_trk0_eta", "j1_trk0_eta", "rad", 'F' )
#factory.AddVariable( "j1_trk0_phi", "j1_trk0_phi", "rad", 'F' )
#factory.AddVariable( "j1_trk0_m", "j1_trk0_m", "GeV", 'F' )
#factory.AddVariable( "j1_trk0_Mv2", "j1_trk0_Mv2", "MV2", 'F' )
factory.AddVariable( "j1_trk1_pt", "j1_trk1_pt", "GeV", 'F' )
#factory.AddVariable( "j1_trk1_eta", "j1_trk1_eta", "rad", 'F' )
#factory.AddVariable( "j1_trk1_phi", "j1_trk1_phi", "rad", 'F' )
#factory.AddVariable( "j1_trk1_m", "j1_trk1_m", "GeV", 'F' )
#factory.AddVariable( "j1_trk1_Mv2", "j1_trk1_Mv2", "MV2", 'F' )
#factory.AddVariable( "myvar1 := var1+var2", 'F' )
#factory.AddVariable( "myvar2 := var1-var2", "Expression 2", "", 'F' )
#factory.AddVariable( "var3", "Variable 3", "units", 'F' )
#factory.AddVariable( "var4", "Variable 4", "units", 'F' )
# You can add so-called "Spectator variables", which are not used in the MVA training,
# but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
# input variables, the response values of all trained MVAs, and the spectator variables
#factory.AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' )
#factory.AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' )
# Read input data
#if gSystem.AccessPathName( infname ) != 0: gSystem.Exec( "wget http://root.cern.ch/files/" + infname )
#input = TFile.Open( infname )
# Get the signal and background trees for training
#signal = input.Get( treeNameSig )
#background = input.Get( treeNameBkg )
# Global event weights (see below for setting event-wise weights)
signalWeight = 1.0
backgroundWeight = 1.0
# ====== register trees ====================================================
#
# the following method is the prefered one:
# you can add an arbitrary number of signal or background trees
factory.AddSignalTree ( signal, signalWeight )
factory.AddBackgroundTree( background, backgroundWeight )
# To give different trees for training and testing, do as follows:
# factory.AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" )
# factory.AddSignalTree( signalTestTree, signalTestWeight, "Test" )
# Use the following code instead of the above two or four lines to add signal and background
# training and test events "by hand"
# NOTE that in this case one should not give expressions (such as "var1+var2") in the input
# variable definition, but simply compute the expression before adding the event
#
# # --- begin ----------------------------------------------------------
#
# ... *** please lookup code in TMVA/macros/TMVAClassification.C ***
#
# # --- end ------------------------------------------------------------
#
# ====== end of register trees ==============================================
# Set individual event weights (the variables must exist in the original TTree)
# for signal : factory.SetSignalWeightExpression ("weight1*weight2");
# for background: factory.SetBackgroundWeightExpression("weight1*weight2");
factory.SetSignalWeightExpression ("weight");
factory.SetBackgroundWeightExpression( "weight" )
# Apply additional cuts on the signal and background sample.
# example for cut: mycut = TCut( "abs(var1)<0.5 && abs(var2-0.5)<1" )
mycutSig = TCut( Sigcut_dic[ops.sel] )
mycutBkg = TCut( Bkgcut_dic[ops.sel] ) #TCut( "Rhh < 63 && (j0_nb +j1_nb == 0)" )
# Here, the relevant variables are copied over in new, slim trees that are
# used for TMVA training and testing
# "SplitMode=Random" means that the input events are randomly shuffled before
# splitting them into training and test samples
factory.PrepareTrainingAndTestTree( mycutSig, mycutBkg,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" )
# --------------------------------------------------------------------------------------------------
# ---- Book MVA methods
#
# please lookup the various method configuration options in the corresponding cxx files, eg:
# src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
# it is possible to preset ranges in the option string in which the cut optimisation should be done:
# "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
# Cut optimisation
if "Cuts" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart" )
if "CutsD" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" )
if "CutsPCA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" )
if "CutsGA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95" )
if "CutsSA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" )
# Likelihood ("naive Bayes estimator")
if "Likelihood" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" )
# Decorrelated likelihood
if "LikelihoodD" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" )
# PCA-transformed likelihood
if "LikelihoodPCA" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" )
# Use a kernel density estimator to approximate the PDFs
if "LikelihoodKDE" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" )
# Use a variable-dependent mix of splines and kernel density estimator
if "LikelihoodMIX" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" )
# Test the multi-dimensional probability density estimator
# here are the options strings for the MinMax and RMS methods, respectively:
# "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
# "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if "PDERS" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" )
if "PDERSD" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" )
if "PDERSPCA" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" )
# Multi-dimensional likelihood estimator using self-adapting phase-space binning
if "PDEFoam" in mlist:
factory.BookMethod( TMVA.Types.kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" )
if "PDEFoamBoost" in mlist:
factory.BookMethod( TMVA.Types.kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" )
# K-Nearest Neighbour classifier (KNN)
if "KNN" in mlist:
factory.BookMethod( TMVA.Types.kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" )
# H-Matrix (chi2-squared) method
if "HMatrix" in mlist:
factory.BookMethod( TMVA.Types.kHMatrix, "HMatrix", "!H:!V" )
# Linear discriminant (same as Fisher discriminant)
if "LD" in mlist:
factory.BookMethod( TMVA.Types.kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" )
# Fisher discriminant (same as LD)
if "Fisher" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" )
# Fisher with Gauss-transformed input variables
if "FisherG" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "FisherG", "H:!V:VarTransform=Gauss" )
# Composite classifier: ensemble (tree) of boosted Fisher classifiers
if "BoostedFisher" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2" )
# Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if "FDA_MC" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if "FDA_GA" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if "FDA_SA" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if "FDA_MT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if "FDA_GAMT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if "FDA_MCMT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
# TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if "MLP" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" )
if "MLPBFGS" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" )
if "MLPBNN" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ) # BFGS training with bayesian regulators
# CF(Clermont-Ferrand)ANN
if "CFMlpANN" in mlist:
factory.BookMethod( TMVA.Types.kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ) # n_cycles:#nodes:#nodes:...
# Tmlp(Root)ANN
if "TMlpANN" in mlist:
factory.BookMethod( TMVA.Types.kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ) # n_cycles:#nodes:#nodes:...
# Support Vector Machine
if "SVM" in mlist:
factory.BookMethod( TMVA.Types.kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" )
# Boosted Decision Trees
if "BDTG" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" )
if "BDT" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" )
if "BDTB" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" )
if "BDTD" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" )
# RuleFit -- TMVA implementation of Friedman's method
if "RuleFit" in mlist:
factory.BookMethod( TMVA.Types.kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" )
# --------------------------------------------------------------------------------------------------
# ---- Now you can tell the factory to train, test, and evaluate the MVAs.
# Train MVAs
factory.TrainAllMethods()
# Test MVAs
factory.TestAllMethods()
# Evaluate MVAs
factory.EvaluateAllMethods()
# Save the output.
outputFile.Close()
fBackground.Close()
fSiganl.Close()
print "=== wrote root file %s\n" % outfname
print "=== TMVAClassification is done!\n"
def main():
print "Start TinyTree--->Plots!"
start_time = time.time()
global DEBUG
DEBUG = False
global ops
ops = options()
global inputpath
inputpath = CONF.inputpath + ops.inputdir + "/"
#for reweight options
global turnon_reweight #reweight or not
turnon_reweight = False
if ops.reweight is not None:
turnon_reweight = True
#set the output directory of all the hist-files
global outputpath
outputpath = CONF.outputpath + ops.outputdir + ("_" + ops.dosyst if (ops.dosyst is not None) else "") + "/"
helpers.checkpath(outputpath)
##setup control region size, and sideband region size
global Syst_cut
##36-60 is not bad; but 4b CR is off
CR_size = float(ops.CR) #this needs to be fixed; so good so far
SB_size = float(ops.SB) #56 is the new default; should be between 48-58 due to stats
CR_X = 124. ##center for control region
CR_Y = 115. ##center for control region
SB_X = 124. + float(ops.SBshift) ##center for sideband region; 12 is also ok
SB_Y = 115. + float(ops.SBshift) ##center for sideband region; 12 is also ok
Syst_cut = {
"SR" : "event.Xhh < 1.6", # #GetXhh(), #"event.Xhh < 1.6", #
"CR" : GetRhh(RhhCenterX=CR_X, RhhCenterY=CR_Y, RhhCut=CR_size), #"event.Rhh < %s" % str(CR_size) ,
"SB" : GetRhh(RhhCenterX=SB_X, RhhCenterY=SB_Y, RhhCut=SB_size), #"event.Rhh < %s" % str(SB_size) ,
"CR_High" : GetRhh(RhhCenterX=CR_X+3, RhhCenterY=CR_Y+3, RhhCut=CR_size),
"CR_Low" : GetRhh(RhhCenterX=CR_X-3, RhhCenterY=CR_Y-3, RhhCut=CR_size),
"CR_Small" : "event.Xhh > 2.0 and event.Rhh < %s" % str(CR_size) ,
"SB_High" : GetRhh(RhhCenterX=SB_X+3, RhhCenterY=SB_Y+3, RhhCut=SB_size),
"SB_Low" : GetRhh(RhhCenterX=SB_X-3, RhhCenterY=SB_Y-3, RhhCut=SB_size),
"SB_Large" : GetRhh(RhhCenterX=SB_X, RhhCenterY=SB_Y, RhhCut=SB_size + 3), #"event.Rhh < %s" % str(SB_size + 5) ,
"SB_Small" : GetRhh(RhhCenterX=SB_X, RhhCenterY=SB_Y, RhhCut=SB_size - 3), #"event.Rhh < %s" % str(SB_size - 5) ,
"ZZ" : GetXhh(XhhCenterX=103., XhhCenterY=96., XhhCut=1.6), #"event.Xzz < 1.6" , ##use to be 2.1
"TT" : GetXhh(XhhCenterX=164., XhhCenterY=155., XhhCut=1.6) #"event.Xzz < 1.6" , ##use to be 2.1
}
global SR_cut
SR_cut = Syst_cut["SR"]
global CR_cut
CR_cut = "not " + Syst_cut["SR"] + " and " + Syst_cut["CR"]
global SB_cut
SB_cut = "not " + Syst_cut["CR"] + " and " + Syst_cut["SB"]
if ops.dosyst is not None:
if "CR" in ops.dosyst:
CR_cut = "not " + Syst_cut["SR"] + " and " + Syst_cut[ops.dosyst]
SB_cut = "not " + Syst_cut[ops.dosyst] + " and " + Syst_cut["SB"] ##fix this
if "Small" in ops.dosyst: #sepecial treatment for this asshole
SB_cut = ("event.Rhh > %s " % (str(CR_size))) + " and " + Syst_cut["SB"]
elif "SB" in ops.dosyst:
SB_cut = "not " + Syst_cut["CR"] + " and " + Syst_cut[ops.dosyst]
elif "ZZ" in ops.dosyst or "TT" in ops.dosyst:
SR_cut = "not " + Syst_cut["SR"] + " and " + Syst_cut[ops.dosyst]
CR_cut = "not " + Syst_cut["SR"] + " and not " + Syst_cut[ops.dosyst] + " and " + Syst_cut["CR"]
SB_cut = "not " + Syst_cut["CR"] + " and not " + Syst_cut[ops.dosyst] + " and " + Syst_cut["SB"]
##for testing
if (DEBUG):
analysis(pack_input("zjets_test"))
print("--- %s seconds ---" % (time.time() - start_time))
return
##real job; full chain 2 mins...just data is 50 seconds
nsplit = CONF.splits
split_list = ["data_test", "ttbar_comb_test"] #, "signal_QCD"] #if not turnon_reweight else ["data_test"] #["data_test", "ttbar_comb_test", "signal_QCD"]
#split_list = ["signal_QCD"]
if turnon_reweight and ops.dosyst is None:
split_list = ["data_test"]
if (ops.dijet): ##only do dijet in this case, always
split_list = ["signal_QCD"]
#split_list = []
inputtasks = []
for split_file in split_list:
for i in range(nsplit):
inputtasks.append(pack_input(split_file, inputsplit=i))
##for other MCs
##for reweighting condition; copy zjet and ttbar
if not turnon_reweight or ops.dosyst is not None :
if (not ops.dijet):
inputtasks.append(pack_input("zjets_test"))
inputtasks.append(pack_input("signal_SM_hh"))
else:##if reweight or do syst
linklist = ["zjets_test", "ttbar_comb_test", "signal_SM_hh"] ##don't reweight ttbar and zjets
for target in linklist:
helpers.checkpath(outputpath + target)
ori_link = inputpath.replace(ops.inputdir, "Moriond") + target + "/hist-MiniNTuple.root"
dst_link = outputpath + target + "/hist-MiniNTuple.root"
try:
os.remove(dst_link)
except OSError:
pass
if os.path.islink(dst_link):
os.unlink(dst_link)
print ori_link, dst_link
os.symlink(ori_link, dst_link)
##for signal samples; only need to process once
sigMClist = ["signal_G_hh_c10_M"]
if (ops.Xhh):
sigMClist = ["signal_G_hh_c10_M", "signal_G_hh_c20_M", "signal_X_hh_M"]
#for i, mass in enumerate([3500, 4000, 4500, 5000, 6000]):
for i, mass in enumerate(CONF.mass_lst):
if (ops.dijet): ##don't do anything for the dijet case
continue
#do not reweight signal samples; create links to the original files instead
if not turnon_reweight or ops.dosyst is not None :
for sigMC in sigMClist:
if mass == 2750 and sigMC == "signal_G_hh_c20_M": ##no c20 2750 sample
continue
inputtasks.append(pack_input(sigMC + str(mass)))
else:#if reweight, creat the folders and the links to the files
for sigMC in sigMClist:
if mass == 2750 and sigMC == "signal_G_hh_c20_M": ##no c20 2750 sample
continue
print "creating links of signal samples", sigMC + str(mass)
helpers.checkpath(outputpath + sigMC + str(mass))
#this is a really bad practice and temp fix now! need to watch this very carfully...
#ori_link = inputpath.replace("F_c10", "f_fin") + "signal_G_hh_c10_M" + str(mass) + "/hist-MiniNTuple.root"
ori_link = inputpath.replace(ops.inputdir, "Moriond") + sigMC + str(mass) + "/hist-MiniNTuple.root"
dst_link = outputpath + sigMC + str(mass) + "/hist-MiniNTuple.root"
#print ori_link, dst_link
if os.path.islink(dst_link):
os.unlink(dst_link)
print ori_link, dst_link
os.symlink(ori_link, dst_link)
#return
##if reweight, reweight everything
##for debug parallel
#analysis(pack_input("ttbar_comb_test"))
if ops.debug:
analysis(inputtasks[0])
return
else:
##parallel compute!
print " START: Running %s jobs on %s cores" % (len(inputtasks), mp.cpu_count()-1)
npool = min(len(inputtasks), mp.cpu_count()-1) ##because herophysics sucks
pool = mp.Pool(npool)
pool.map(analysis, inputtasks)
##all the other extra set of MCs
for split_file in split_list:
targetpath = outputpath + split_file + "/"
targetfiles = []
for i in range(nsplit):
targetfiles += glob.glob(targetpath + ("hist-MiniNTuple_%s"% str(i)) + ".root")
haddcommand = ["hadd", "-f", targetpath + "hist-MiniNTuple" + ".root"]
haddcommand += targetfiles
#print haddcommand
subprocess.call(haddcommand)
#clean up the sub process outputs
for i in range(nsplit):
hrmcommand = ["rm"]
hrmcommand += glob.glob(targetpath + ("hist-MiniNTuple_%s"% str(i)) + ".root")
subprocess.call(hrmcommand)
#analysis(pack_input("signal_BQCD_200")) #2 mins! 4 mins with expanded...
#analysis("signal_QCD") #2 mins! 10 mins...
print("--- %s seconds ---" % (time.time() - start_time))
print "Finish!"
##consistency check
#f = ROOT.TFile(outputpath + "ttbar_comb_test" + "/hist-MiniNTuple.root", "read")
f = ROOT.TFile(outputpath + "signal_G_hh_c10_M1000" + "/hist-MiniNTuple.root", "read")
print f.Get("FourTag_Signal/mHH_l").GetEntries()
f.Close()
def main():
start_time = time.time()
ops = options()
global blinded
blinded = True
global iter_reweight
iter_reweight = int(ops.iter)
#setup basics
inputdir = ops.inputdir
inputroot = ops.inputroot
inputpath = CONF.inputpath + inputdir + "/"
rootinputpath = inputpath + inputroot + "_"
print "input root file is: ", rootinputpath
global StatusLabel
StatusLabel = "Internal" ##StatusLabel = "Preliminary"
global reweightfolder
reweightfolder = inputpath + "Reweight/"
helpers.checkpath(reweightfolder)
global outputroot
outputroot = ROOT.TFile(reweightfolder + "reweights.root", "recreate")
# plot in the control region #
# outputFolder = inputpath + inputroot + "Plot/" + "Sideband"
# plotRegion(rootinputpath, inputdir, cut="FourTag" + "_" + "Sideband" + "_" + "mHH_l", xTitle="m_{2J} [GeV]")
# plotRegion(rootinputpath, inputdir, cut="FourTag" + "_" + "Sideband" + "_" + "mHH_l", xTitle="m_{2J} [GeV]", Logy=1)
##comp_lst are the distributios we want to look like
##cut_lst are the disbrituions we are changing
##this is the default
if "j0pT" in ops.var:
region_lst = ["Sideband"]
cut_lst = ["TwoTag_split", "ThreeTag", "FourTag"]
#this is the one tag rewieght
if "bkg" in ops.var:
region_lst = ["Incl"]
cut_lst = [
"NoTag_2Trk_split_lead", "NoTag_2Trk_split_subl",
"NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead",
"NoTag_4Trk_subl"
]
comp_lst = [
"OneTag_subl", "OneTag_lead", "OneTag_subl", "OneTag_lead",
"TwoTag_subl", "TwoTag_lead"
]
comp_region_lst = ["Incl"]
##this is to the sidebands rewieght
if "bkgsb" in ops.var:
region_lst = ["Sideband"]
comp_region_lst = ["Sideband"]
cut_lst = [
"NoTag_2Trk_split_lead", "NoTag_2Trk_split_subl",
"NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead",
"NoTag_4Trk_subl"
]
comp_lst = [
"TwoTag_split", "TwoTag_split", "ThreeTag", "ThreeTag", "FourTag",
"FourTag"
]
##this is the detailed trk reweight
# region_lst = ["Incl"]
# cut_lst = ["NoTag_2Trk_split_lead_lead", "NoTag_2Trk_split_subl_lead", "NoTag_2Trk_split_lead_subl", "NoTag_2Trk_split_subl_subl", "NoTag_3Trk_lead", "NoTag_3Trk_subl", "NoTag_4Trk_lead", "NoTag_4Trk_subl"]
# comp_lst = ["OneTag_subl_lead", "OneTag_lead_subl", "OneTag_subl_subl", "OneTag_lead_lead", "OneTag_subl", "OneTag_lead", "TwoTag_subl", "TwoTag_lead"]
# comp_region_lst = ["Incl"]
#create master list
inputtasks = []
#fill the task list
for i, region in enumerate(region_lst):
if inputroot == "sum":
inputroot = ""
outputFolder = inputpath + inputroot + "Plot_r" + str(
iter_reweight) + "/" + region
helpers.checkpath(outputFolder)
for j, cut in enumerate(cut_lst):
config = {}
config["root"] = rootinputpath
config["inputdir"] = inputdir
config["outputdir"] = outputFolder
config["cut"] = cut + "_" + region + "_"
try:
config["compcut"] = comp_lst[j] + "_" + comp_region_lst[
i] + "_" ##change this to be flexiable to regions
except NameError:
config["compcut"] = "" ##by default this is disabled
inputtasks.append(config)
#parallel compute!
print " Running %s jobs on %s cores" % (len(inputtasks),
mp.cpu_count() - 1)
npool = min(len(inputtasks), mp.cpu_count() - 1)
pool = mp.Pool(npool)
pool.map(dumpRegion, inputtasks)
##for debug
# for task in inputtasks:
# dumpRegion(task)
# dumpRegion(inputtasks[0])
outputroot.Close()
print("--- %s seconds ---" % (time.time() - start_time))
def get_oxsty_mAP_score_from_res(hs, res, SV, oxsty_qres_dpath,
compute_ap_exe, oxford_gt_dir):
# find oxford ground truth directory
cwd = os.getcwd()
# build groundtruth query
qcx = res.qcx
qnx = hs.tables.cx2_nx[qcx]
cx2_oxnum = hs.tables.prop_dict['oxnum']
qoxnum = cx2_oxnum[qcx]
qname = hs.tables.nx2_name[qnx]
# build ranked list
cx2_score = res.cx2_score_V if SV else res.cx2_score
top_cx = cx2_score.argsort()[::-1]
top_gx = hs.tables.cx2_gx[top_cx]
top_gname = hs.tables.gx2_gname[top_gx]
# build mAP args
if qoxnum == '':
print("HACK: Adding a dummy qoxynum")
qoxnum = '1'
ground_truth_query = qname+'_'+qoxnum
# build ranked list of gnames (remove duplicates)
seen = set([])
ranked_list = []
for gname in iter(top_gname):
gname_ = gname.replace('.jpg','')
if not gname_ in seen:
seen.add(gname_)
ranked_list.append(gname_)
ranked_list2 = [gname.replace('.jpg','') for gname in top_gname]
# Write the ranked list of images names
cx_aug = 'qcx_'+str(qcx)
ranked_list_fname = 'ranked_list_' + cx_aug + ground_truth_query + '.txt'
ranked_list_fpath = join(oxsty_qres_dpath, ranked_list_fname)
helpers.write_to(ranked_list_fpath, '\n'.join(ranked_list))
# execute external mAP code:
# ./compute_ap [GROUND_TRUTH] [RANKED_LIST]
os.chdir(oxford_gt_dir)
def filename(path):
return os.path.split(path)[1]
if OXSTY_VERBOSE:
printable_cmd = ' '.join((filename(compute_ap_exe),
ground_truth_query,
filename(ranked_list_fpath)))
print('Executing: %r' % printable_cmd)
else:
helpers.print_('.')
args = (compute_ap_exe, ground_truth_query, ranked_list_fpath)
cmdstr = ' '.join(args)
try:
proc_out = run_process(args)
out = proc_out.out
except OSError as ex:
out = -1
if OXSTY_VERBOSE:
print(repr(ex))
if repr(ex) == "OSError(12, 'Cannot allocate memory')":
args_hash = helpers.hashstr(args)
proc_err_fname = 'proc_err'+args_hash
proc_err_cmd = proc_err_fname+'.cmd'
proc_err_out = proc_err_fname+'.out'
helpers.write_to(proc_err_cmd, repr(args))
if helpers.checkpath(proc_err_out):
out = helpers.read_from(proc_err_out)
mAP = float(out.strip())
os.chdir(cwd)
return mAP
def plot_RSG_syst_detail(masterdic, cut):
canv = ROOT.TCanvas(cut + "_" + "RSG" + "_" + "syst_detail", "Sytematics", 800, 800)
xleg, yleg = 0.52, 0.7
legend = ROOT.TLegend(xleg, yleg, xleg+0.3, yleg+0.2)
# setup basic plot parameters
# load input MC file
mass_lst = [1000, 1100, 1200, 1300, 1400, 1500, 1600, 1800, 2000, 2250, 2500, 2750, 3000]
eff_lst = []
graph_lst = []
maxbincontent = 100.0
minbincontent = -0.001
lowmass = 950
highmass = 3150
#create bsyst list
bsyst_lst = []
for i in bsyst:
if "up" in i:
bsyst_lst.append(i.replace("up", ""))
#now loop
draw_counter = 0
for i, syst in enumerate(bsyst_lst):
eff_lst.append( ROOT.TH1F(syst, "%s; Mass, GeV; Systematic Percentage Diff" %syst, int((highmass-lowmass)/100), lowmass, highmass) )
maxsyst = 0.0
for mass in mass_lst:
temp_col_dic = find_syst(masterdic, cut, syst, "RSG1_" + str(mass))
syst_eff = add_syst(temp_col_dic) #this is a tuple!
# if (syst_eff[0] * 100 < 3): #if the systematic contribution is less than 3 percent
# continue
eff_lst[i].SetBinContent(eff_lst[i].GetXaxis().FindBin(mass), syst_eff[0] * 100)
eff_lst[i].SetBinError(eff_lst[i].GetXaxis().FindBin(mass), 0)
#print syst, syst_eff[0]
maxbincontent = max(maxbincontent, syst_eff[0] * 100)
maxsyst = max(maxsyst, syst_eff[0] * 100)
#print maxsyst, i
#start the canvas
canv.cd()
#convert it to a graph
if maxsyst < 3: #don't draw everything
print syst
continue
graph_lst.append(helpers.TH1toTAsym(eff_lst[i]))
graph_lst[-1].SetLineColor(CONF.clr_lst[draw_counter])
graph_lst[-1].SetMarkerStyle(20 + draw_counter)
graph_lst[-1].SetMarkerColor(CONF.clr_lst[draw_counter])
graph_lst[-1].SetMarkerSize(1)
graph_lst[-1].SetMaximum(maxbincontent * 1.5)
graph_lst[-1].SetMinimum(minbincontent)
legend.AddEntry(graph_lst[-1], syst.replace("_", " "), "apl")
if draw_counter==0:
graph_lst[-1].Draw("APC")
draw_counter += 1
else:
graph_lst[-1].Draw("PC")
draw_counter += 1
legend.SetBorderSize(0)
legend.SetMargin(0.3)
legend.SetTextSize(0.04)
legend.Draw()
# draw reference lines
# draw watermarks
xatlas, yatlas = 0.35, 0.87
atlas = ROOT.TLatex(xatlas, yatlas, "ATLAS Internal")
hh4b = ROOT.TLatex(xatlas, yatlas-0.06, "RSG c=1.0")
lumi = ROOT.TLatex(xatlas, yatlas-0.12, "MC #sqrt{s} = 13 TeV")
watermarks = [atlas, hh4b, lumi]
for wm in watermarks:
wm.SetTextAlign(22)
wm.SetTextSize(0.04)
wm.SetTextFont(42)
wm.SetNDC()
wm.Draw()
# finish up
helpers.checkpath(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/")
canv.SaveAs(CONF.inputpath + ops.inputdir + "/" + "Plot/Syst/" + canv.GetName() + ".pdf")
canv.Close()
def write_reweight(fname="TEST",
reweight_dic={},
region_dic=[("2bs", "TwoTag_split_Sideband"),
("3b", "ThreeTag_Sideband"),
("4b", "FourTag_Sideband")],
split=False,
cond=False):
'''write reweight output '''
motherfolder = "Moriond"
helpers.checkpath("script")
#building the inputdictionary
#creat an empty dictionary
#ready to dump file
f = open("script/" + fname + ".txt", "w")
#make sure over write everytime!
f.truncate()
f.write("#reweighting script for hh4b analysis \n")
#iteration; Ntrk; parameter; inputfolder; parameterfile
for i in range(iteration):
f.write("#iteration:" + str(i) + "\n")
#space is very important!!!!
for region, region_fname in region_dic:
for var, var_fname in reweight_dic.iteritems():
if split: #this is to reweight leading pT and trk pT seperately
if "j0_" in var and i % 2 == 1: #for even skip j0_pt
continue
elif "j0_" not in var and i % 2 != 1: #for odd, skip other
continue
# if "j0_pt" in var and i%4 > 1: #for even skip j0_pt
# continue
# elif "j0_pt" not in var and i%4 <= 1: #for odd, skip other
# continue
##notice this onlyputs condition on subl, lead reweighting; reweight lead's subl and subl's lead
#print region_fname, var_fname, ("lead_subl" in region_fname), ("lead" in var_fname)
if (("lead_lead" in region_fname)
or ("lead_subl" in region_fname)):
if "lead" in var_fname:
continue
elif (("subl_lead" in region_fname)
or ("subl_subl" in region_fname)):
if "subl" in var_fname:
continue
elif "lead" in region_fname:
if "lead" in var_fname:
continue
elif "subl" in region_fname:
if "subl" in var_fname:
continue
templine = ""
templine += str(i) + " " #iteration
templine += region + " " #Ntrk
templine += "event." + var + " " #parameter
templine += motherfolder + (
"_" + fname + "_" + str(i - 1)
if i != 0 else "") + " " #look for the original iteration
templine += "r" + str(
i
) + "_" + region_fname + "_" + var_fname + ".txt" + " " #parameterfile;
##add in condition; be very careful, this means the TinyNtuple has to be produced with the correct b-tagging MV2Cut
##also the definition of condition needs to agree with the PlotTinyTree region condition!!! STUPID but be very careful!!!
if cond:
if "2Trk_split_lead_Incl" in region_fname:
templine += "((event.j0_nb==1)and(event.j1_nb==0))" + " " #condition
if "2Trk_split_subl_Incl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==1))" + " " #condition
# if "2Trk_split_lead_lead_Incl" in region_fname:
# templine += "((event.j0_nb==1)and(event.j1_nb==0)and(event.j0_trk0_Mv2>0.6455))" + " " #condition
# if "2Trk_split_subl_lead_Incl" in region_fname:
# templine += "((event.j0_nb==0)and(event.j1_nb==1)and(event.j1_trk0_Mv2>0.6455))" + " " #condition
# if "2Trk_split_lead_subl_Incl" in region_fname:
# templine += "((event.j0_nb==1)and(event.j1_nb==0)and(event.j0_trk0_Mv2<0.6455))" + " " #condition
# if "2Trk_split_subl_subl_Incl" in region_fname:
# templine += "((event.j0_nb==0)and(event.j1_nb==1)and(event.j1_trk0_Mv2<0.6455))" + " " #condition
if "3Trk_lead" in region_fname:
templine += "((event.j0_nb==2)and(event.j1_nb==0))" + " " #condition
if "3Trk_subl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==2))" + " " #condition
if "4Trk_lead" in region_fname:
templine += "((event.j0_nb==2)and(event.j1_nb==0))" + " " #condition
if "4Trk_subl" in region_fname:
templine += "((event.j0_nb==0)and(event.j1_nb==2))" + " " #condition
templine += "\n"
print templine
f.write(templine)
#finish
f.close()
