def get_hf_frac(name, cut):
logging.info("Getting fractions for %s" % name)
basepath = get_paths(dataset="latest")
samp = Sample.fromFile("/".join([basepath["mc"]["mu"]["nominal"]["iso"], name]))
hi = samp.drawHistogram("wjets_flavour_classification0", str(cut), plot_range=[8, 0, 8], dtype="I")
out = dict()
for sc, fr in zip(flavour_scenarios[0], list(hi.y())):
out[sc] = fr
return out
def compare_plot(plot_def):
"""
Draws a comparison plot based on a plot definition dictionary, which has the following arguments:
*mandatory*
var: a string with the TTree branch name / TFormula expression to plot
plot_range: the plot range definition for Sample.drawHistogram
items: a list of tuples, containing the plots to be drawn in the following format
[
(name_of_plot, pathname_of_file, filename, cut_object, weight_object)
]
*optional*
lumi: the luminosity to normalize to in /pb
merge_cmds: a merge command for the merge_hists method, which merges the histograms
according to the names in the items list
hist_callback: a method that is called on each of the histograms after merging,
having the form:
def f(hist_name, hist):
dostuff
return hist
x_label: a string the the label for the x axis
*returns*
a tuple (canvas, final_histogram_dict)
"""
proc_cuts = plot_def['items']
var = plot_def.get('var')
plot_range = plot_def.get('range')
lumi = plot_def.get('lumi', 20000)
merge_cmds = plot_def.get('merge_cmds', None)
hist_callback = plot_def.get('hist_callback', None)
x_label = plot_def.get('xlab', 'xlab')
hists = {}
for name, path, fname, cut, weight in proc_cuts:
fname = join(path, fname)
sample = Sample.fromFile(fname)
hists[name] = sample.drawHistogram(var, str(cut), weight=str(weight), plot_range=plot_range)
hists[name].SetName(name)
hists[name] = copy.deepcopy(hists[name])
hists[name].Scale(sample.lumiScaleFactor(lumi))
if merge_cmds:
hists_merged = merge_hists(hists, merge_cmds)
hists = hists_merged
if hist_callback:
for hn, h in hists.items():
hists[hn] = hist_callback(hn, h)
canv = plot_hists_dict(hists, x_label=x_label)
return canv, hists
parser.add_argument(
"--indir", type=str, required=False, default=(os.environ["STPOL_DIR"] + "/step3_latest"),
help="the input directory"
)
args = parser.parse_args()
lumi=19700
for proc in ['ele', 'mu']:
physics_processes = PhysicsProcess.get_proc_dict(lepton_channel=proc)
merge_cmds = PhysicsProcess.get_merge_dict(physics_processes)
flist = get_file_list({'signal': merge_cmds['tchan']}, args.indir + "/%s/mc/iso/nominal/Jul15/" % proc)
samples={}
for f in flist:
samples[f] = Sample.fromFile(f)
yld = 0;
for k,v in samples.items():
yld+=v.getEntries(cut[proc])*v.lumiScaleFactor(lumi)
found = False
for b in range(100):
bc=b*1./100
mvayld = 0
mcut = Cuts.met
if proc == 'mu':
mcut = Cuts.mt_mu
for k,v in samples.items():
mvayld+=v.getEntries(str(cutlist['2j1t']*cutlist['presel_'+proc]*mcut*Cut('mva_BDT>'+str(bc))))*v.lumiScaleFactor(lumi)
if not found and mvayld < yld:
found = True
break
"wjets": "W",
}
pretty_names_weights = {
"unw": "unweighted",
"nom": "nominal",
"bc_up": "SF_{bc} up",
"bc_down": "SF_{bc} down",
"l_up": "SF_{l} up",
"l_down": "SF_{l} down",
}
recreate = True
if recreate:
for sn in sampnames:
sample = Sample.fromFile(path + "/" + sn + ".root")
for wn, w in weights:
hi = sample.drawHistogram(var, str(cut), weight=w, plot_range=plot_range)
hi.Scale(sample.lumiScaleFactor(lumi))
hists[wn][sample.name] = hi
merged = dict()
for wn, w in weights:
merged[wn] = merge_hists(hists[wn], merge_cmds)
hc = HistCollection(merged[wn], name="bweight_%s" % wn)
hc.save(".")
colls = dict()
for wn, w in weights:
flist = get_file_list(
merge_cmds,
args.indir + "/%s/mc/%s/nominal/Jul15/" % (lepton_channel,isoreg)
)
for iso in ['iso', 'antiiso']:
for ds in ['Jul15', 'Aug1']:
flist += get_file_list(
merge_cmds,
args.indir + "/%s/data/%s/%s/" % (lepton_channel, iso, ds)
)
if len(flist)==0:
raise Exception("Couldn't open any files. Are you sure that %s exists and contains root files?" % args.indir)
samples={}
for f in flist:
samples[f] = Sample.fromFile(f, tree_name=tree)
samples_syst = {}
for name, syst in systs.items():
samples_syst[name] = {}
for s in list(syst):
samples_syst[name][s] = {}
for f in change_syst(flist, s):
samples_syst[name][s][f] = Sample.fromFile(f, tree_name=tree)
for plotname in args.plots:
plot_def = plot_defs[plotname]
canv, merged_hists, htot_mc, htot_data = data_mc_plot(samples, plot_def, plotname, lepton_channel, lumi, weight, physics_processes, use_antiiso)
canv = plot_hists_dict(hc.hists, do_chi2=False, do_ks=True, x_label=varname, legend_pos="top-left")
hc.hists.values()[0].SetTitle("shape variation")
canv.SaveAs(out_name + ".png")
hc.save(out_name)
return hc, canv
if __name__=="__main__":
ROOT.TH1F.AddDirectory(False)
import logging
#rootpy.log.basic_config_colorized()
logging.basicConfig(level=logging.WARNING)
logger = rootpy.log["/systematics"]
data_repro = "Jul15"
path = get_paths()[data_repro]["mc"]["mu"]["nominal"]["iso"]
logger.info("Input path %s" % path)
samples = [
Sample.fromFile(f) for f in
filter(lambda x: re.match(".*/W[1-4]Jets.*", x), glob.glob(path + "/*.root"))
]
logger.info("samples %s" % samples)
cut = Cuts.final(2,1)
recreate = True
r1 = shape_variation("cos_theta", [10, -1, 1], "cos #theta", recreate, "variations_cos_theta")
r2 = shape_variation("abs(eta_lj)", [10, 2.5, 4.5], "|#eta|_{j'}", recreate, "variations_abs_eta_lj")
# for i in range(1, data_post.nbins()+1):
# data_post.SetBinError(i, pe_post.GetBinError(i))
# Get the true distribution at generator level,
# requiring the presence of a lepton with the
# correct gen flavour
htrue = None
datadir = "data/37acf5_343e0a9_Aug22"
def gen_hist(sample):
hi = sample.drawHistogram("true_cos_theta", str(Cuts.true_lepton(lep)), binning=list(binning))
hi.Scale(s.lumiScaleFactor(lumi))
return hi
for fn in ["T_t_ToLeptons", "Tbar_t_ToLeptons"]:
#s = Sample.fromFile("data/Step3_Jul26/%s/mc/iso/nominal/Jul15/%s.root" % (lep, fn))
s = Sample.fromFile("data/37acf5_343e0a9_Aug22/%s.root" % (fn))
hi = gen_hist(s)
if htrue:
htrue += hi
else:
htrue = hi
htrue.SetTitle("generated (POWHEG)")
#Scale to the final fit
htrue.Scale(fitpars[lep])
hcomphep = None
for fn in ["TToBENu_t-channel", "TToBMuNu_t-channel", "TToBTauNu_t-channel"]:
s = Sample.fromFile(datadir + "/{0}/{1}.root".format(lep, fn))
hi = gen_hist(s)
if hcomphep:
hcomphep += hi
def __init__(self, saver, *args, **kwargs):
super(SampleNode, self).__init__(*args, **kwargs)
self.sample = Sample.fromFile(self.name)
self.saver = saver
proc = args.channel
# Which luminosity we use
lumi = lumis[args.lumitag]['iso'][proc]
flist = []
for i in ['sig','bg']:
for j in ['train','eval']:
flist += mvaFileList[i][j]
logger.debug('Used file list: %s',str(flist))
# Read in the samples
samples = {}
for f in flist:
samples[f] = Sample.fromFile(args.indir+'/%s/%s.root' % (proc,f), tree_name='Events_MVA')
# Set the weight expression
weightString = str(Weights.total(proc) *
Weights.wjets_madgraph_shape_weight() *
Weights.wjets_madgraph_flat_weight())
# Which file do we use to write our TMVA trainings
ext=''
if len(rVar):
ext='_sans'
for v in rVar:
ext+='_'+v
if len(cVar):
ext='_with'
def get_samples(path, channel, systematic):
samples2 = None
if systematic in ["EnDown", "EnUp", "ResDown", "ResUp", "UnclusteredEnDown", "UnclusteredEnUp"]:
datadir = "/".join((path, channel, "mc", "iso", systematic, "Jul15"))
elif systematic != "nominal":
#datadir2 = "/".join((path, channel, "mc_syst", "iso", "SYST", "Jul15"))
#datadir = "/".join((path, channel, "mc", "iso", "nominal", "Jul15"))
datadir = "/".join(("/hdfs/local/stpol/step3/Sep4_syst_a554579", channel, "mc", "iso", "nominal", "Jul15"))
datadir2 = "/".join(("/home/andres/single_top/stpol/Sep4_syst_a554579/", channel, "mc_syst", "iso", "SYST", "Jul15"))
datadir3 = "/".join(("/home/andres/single_top/stpol/Sep4_syst_a554579/", channel, "mc_syst", "iso", "SYST", "Sep4"))
#print "dd2", datadir2
#print "dd3", datadir3
samples2 = Sample.fromDirectory(datadir2, out_type="dict")
#print "samp2", samples2
#datadir3 = "/".join(("/hdfs/local/stpol/step3/Sep1_wjets_fsim", channel, "mc_syst", "nominal", "wjets_fsim"))
samples2.update(Sample.fromDirectory(datadir3, out_type="dict"))
#print "samp3", samples2
else:
#datadir = "/".join((path, channel, "mc", "iso", systematic, "Jul15"))
datadir = "/".join(("/hdfs/local/stpol/step3/Sep4_syst_a554579", channel, "mc", "iso", systematic, "Jul15"))
datadir2 = "/".join(("/home/andres/single_top/stpol/Sep4_syst_a554579/", channel, "mc_syst", "iso", "SYST", "Jul15"))
datadir3 = "/".join(("/home/andres/single_top/stpol/Sep4_syst_a554579/", channel, "mc_syst", "iso", "SYST", "Sep4"))
#datadir2 = "/".join((path, channel, "mc_syst", "iso", "SYST", "Jul15"))
samples2 = Sample.fromDirectory(datadir2, out_type="dict")
samples2.update(Sample.fromDirectory(datadir3, out_type="dict"))
samples = Sample.fromDirectory(datadir, out_type="dict")
datadir_data = "/".join((path, channel, "data", "iso", "Jul15"))
datadir_data_Aug1 = "/".join((path, channel, "data", "iso", "Aug1"))
samples.update(Sample.fromDirectory(datadir_data, out_type="dict"))
samples.update(Sample.fromDirectory(datadir_data_Aug1, out_type="dict"))
if samples2 is not None:
samples.update(samples2)
if channel == "mu":
samples["SingleMu1_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleMu1.root")))
samples["SingleMu2_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleMu2.root")))
samples["SingleMu3_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleMu3.root")))
samples["SingleMu_miss_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleMu_miss.root")))
elif channel == "ele":
samples["SingleEle1_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleEle1.root")))
samples["SingleEle2_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleEle2.root")))
samples["SingleEle_miss_aiso"] = Sample.fromFile("/".join((path, channel, "data", "antiiso", "Jul15", "SingleEle_miss.root")))
return samples
def load_nominal_mc_samples(path, channel, iso):
datadir = "/".join((path, channel, "mc", iso, "nominal", "Jul15"))
samples = Sample.fromDirectory(datadir, out_type="dict")
return samples
import os import copy sys.path.append(os.environ["STPOL_DIR"]) import plots import plots.common from plots.common.odict import OrderedDict as dict from plots.common.sample import Sample from plots.common.cuts import Cuts, Cut from plots.common.utils import merge_cmds, merge_hists, get_hist_int_err lumi_total = 12210 sample_dir = "data/out_step3_05_30_08_20" samples = [] samples.append(Sample.fromFile(sample_dir + "/TTJets_MassiveBinDECAY.root")) samples.append(Sample.fromFile(sample_dir + "/TTJets_FullLept.root")) samples.append(Sample.fromFile(sample_dir + "/TTJets_SemiLept.root")) samples.append(Sample.fromFile(sample_dir + "/T_t.root")) samples.append(Sample.fromFile(sample_dir + "/Tbar_t.root")) samples.append(Sample.fromFile(sample_dir + "/T_t_ToLeptons.root")) samples.append(Sample.fromFile(sample_dir + "/Tbar_t_ToLeptons.root")) samples.append(Sample.fromFile(sample_dir + "/QCDMu.root")) samples.append(Sample.fromFile(sample_dir + "/WJets_inclusive.root")) samples.append(Sample.fromFile(sample_dir + "/W1Jets_exclusive.root")) samples.append(Sample.fromFile(sample_dir + "/W2Jets_exclusive.root")) samples.append(Sample.fromFile(sample_dir + "/W3Jets_exclusive.root")) samples.append(Sample.fromFile(sample_dir + "/W4Jets_exclusive.root")) def mc_amount(cut, weight, lumi=12210, ref=None):
from plots.common.sample import Sample
from plots.common.cuts import Cuts
import sys
if __name__=="__main__":
for fi in sys.argv[1:]:
print fi
samp = Sample.fromFile(fi)
print "Lumi scale factor: ", samp.lumiScaleFactor(20000)
for lep in ["mu", "ele"]:
if "/%s/"%lep not in fi:
continue
print lep
cut = None
for cutname, _cut in [
("hlt", Cuts.hlt(lep)),
("lep", Cuts.single_lepton(lep)),
("2J", Cuts.n_jets(2)),
("1T", Cuts.n_tags(1)),
("MET/MtW", Cuts.metmt(lep)),
("rms", Cuts.rms_lj),
("Mtop", Cuts.top_mass_sig),
("etalj", Cuts.eta_lj)
]:
if not cut:
cut = _cut
else:
cut *= _cut
try:
hi = samp.drawHistogram("eta_lj", str(cut), binning=[50, -5, 5])
description='Caches entries.'
)
parser.add_argument('outfile', action='store',
help="The output file name."
)
parser.add_argument('cut', action='store',
help="The cut string."
)
parser.add_argument('infiles', nargs='+',
help="The input file names"
)
args = parser.parse_args()
of = ROOT.TFile(args.outfile, "RECREATE")
for inf in args.infiles:
samp = Sample.fromFile(inf)
samp_path = samp.getPath(escape=True)
print samp_path
cache = samp.cacheEntries(samp_path, args.cut)
print "Cached %d entries for sample %s" % (cache.GetN(), samp.tfile.GetPath())
of.cd()
cache = cache.Clone()
cache.SetDirectory(of)
cache.Write()
samp.tfile.Close()
#of.Write()
of.Close()
from plots.common.sample import Sample
from plots.common.cuts import Cuts
import sys
if __name__=="__main__":
if len(sys.argv)!=2:
print "Usage: %s /path/to/mu/iso/nominal/T_t_ToLeptons.root" % sys.argv[1]
sys.exit(0)
s = Sample.fromFile(sys.argv[1])
cut = Cuts.final(2,1)
nentries = s.tree.Draw("cos_theta", str(cut))
print "Nentries=",nentries
physics_processes = PhysicsProcess.get_proc_dict(lepton_channel=proc)
merge_cmds = PhysicsProcess.get_merge_dict(physics_processes)
flist = get_file_list(
merge_cmds,
step3 + "/%s/mc/iso/nominal/Jul15/" % proc
)
flist += get_file_list(
{'QCD': merge_cmds['data']},
step3 + "/%s/data/antiiso/Jul15/" % proc
)
# Read in the file list from the output directory
samples = {}
for f in flist:
samples[f] = Sample.fromFile(f, tree_name="Events_MVAwQCD")
# To compute accurate weight we need to load from the tree also the weights in question
weightString = str(Weights.total(proc) *
Weights.wjets_madgraph_shape_weight() *
Weights.wjets_madgraph_flat_weight())
# Temporary patch until proper step3 is available
#weightString = "1.0"
t={}
f={}
w={}
for key in flist:
w[key]=1.
t[key]=samples[key].getTree()
from plots.common.sample import Sample
from plots.common.sample_style import ColorStyleGen
from plots.common.hist_plots import plot_hists
from plots.common.cuts import Cuts, Weights
from plots.common.legend import legend
from plots.common.tdrstyle import tdrstyle
if __name__=="__main__":
samp = Sample.fromFile("~/Documents/stpol/data/out_step3_joosep_11_07_19_44/mu/iso/nominal/W4Jets_exclusive.root")
samp.tree.AddFriend("trees/WJets_weights", samp.file_name)
tdrstyle()
cut = str(Cuts.final(2,0)*Cuts.Wflavour("W_heavy"))
mean_weight = samp.drawHistogram(str(Weights.wjets_madgraph_weight("nominal")), cut, weight="1.0", plot_range=[200, 0, 2]).hist.GetMean()
print "mean weight=%.2f" % mean_weight
hi0 = samp.drawHistogram("cos_theta", cut, weight="1.0", plot_range=[20, -1, 1]).hist
hi0.Scale(samp.lumiScaleFactor(20000))
hi1 = samp.drawHistogram("cos_theta", cut, weight=str(Weights.wjets_madgraph_weight("nominal")), plot_range=[20, -1, 1]).hist
hi1.Scale(samp.lumiScaleFactor(20000))
hi2 = samp.drawHistogram("cos_theta", cut, weight=str(Weights.wjets_madgraph_weight("wjets_up")), plot_range=[20, -1, 1]).hist
hi2.Scale(samp.lumiScaleFactor(20000))
hi3 = samp.drawHistogram("cos_theta", cut, weight=str(Weights.wjets_madgraph_weight("wjets_down")), plot_range=[20, -1, 1]).hist
hi3.Scale(samp.lumiScaleFactor(20000))
hists = [hi0, hi1, hi2, hi3]
#for h in hists:
# h.Scale(1.0/h.Integral())
hi0.SetTitle("unweighted")
hi1.SetTitle("weighted")
hi2.SetTitle("weighted wjets_up")
import os
import copy
sys.path.append(os.environ["STPOL_DIR"])
import plots
import plots.common
from plots.common.odict import OrderedDict as dict
from plots.common.sample import Sample
from plots.common.cuts import Cuts, Cut
from plots.common.utils import merge_cmds, merge_hists, get_hist_int_err
lumi_total=12210
sample_dir = "data/out_step3_05_30_08_20"
samples = []
samples.append(Sample.fromFile(sample_dir + "/TTJets_MassiveBinDECAY.root"))
samples.append(Sample.fromFile(sample_dir + "/TTJets_FullLept.root"))
samples.append(Sample.fromFile(sample_dir + "/TTJets_SemiLept.root"))
samples.append(Sample.fromFile(sample_dir + "/T_t.root"))
samples.append(Sample.fromFile(sample_dir + "/Tbar_t.root"))
samples.append(Sample.fromFile(sample_dir + "/T_t_ToLeptons.root"))
samples.append(Sample.fromFile(sample_dir + "/Tbar_t_ToLeptons.root"))
samples.append(Sample.fromFile(sample_dir + "/QCDMu.root"))
samples.append(Sample.fromFile(sample_dir + "/WJets_inclusive.root"))
samples.append(Sample.fromFile(sample_dir + "/W1Jets_exclusive.root"))
samples.append(Sample.fromFile(sample_dir + "/W2Jets_exclusive.root"))
samples.append(Sample.fromFile(sample_dir + "/W3Jets_exclusive.root"))
samples.append(Sample.fromFile(sample_dir + "/W4Jets_exclusive.root"))
def mc_amount(cut, weight, lumi=12210, ref=None):
histsD = dict()
if __name__=="__main__":
#import plots.common.tdrstyle as tdrstyle
#tdrstyle.tdrstyle()
datadirs = dict()
#This symlink is present in the repo for *.hep.kbfi.ee, if running on other machines, you must make it yourself by doing
#ln -s /path/to/step3/out $STPOL_DIR/step3_latest
#isolated files are by default in $STPOL_DIR/step3_latest/mu/iso/nominal/*.root
datadirs["iso"] = "/".join((os.environ["STPOL_DIR"], "step3_latest", "mu" ,"iso", "nominal"))
#Use the anti-isolated data for QCD $STPOL_DIR/step3_latest/mu/antiiso/nominal/SingleMu.root
datadirs["antiiso"] = "/".join((os.environ["STPOL_DIR"], "step3_latest", "mu" ,"antiiso", "nominal"))
#Load all the samples in the isolated directory
samples = Sample.fromDirectory(datadirs["iso"], out_type="dict")
samples["SingleMu_aiso"] = Sample.fromFile(datadirs["antiiso"] + "/SingleMu.root")
hists_mc = dict()
hist_data = None
#Define the variable, cut, weight and lumi
var = "cos_theta"
cut_name = "2j1t"
cut_str = str(Cuts.n_jets(2)*Cuts.n_tags(1)*Cuts.lepton_veto*Cuts.one_muon*Cuts.mt_mu*Cuts.top_mass_sig*Cuts.eta_lj)
weight_str = "1.0"
lumi = 20000 #FIXME: take from the step2 output filelists/step2/latest/iso/nominal/luminosity.txt
#nbins, min, max
plot_range= [20, -1, 1]
