def dump_event_info(tree, cut, is_reco=False):
print 40 * "-"
print "cut =", cut
print "event numbers:"
elist = TEventList('elist', 'elist')
tree.Draw('>>elist', cut)
for i in xrange(0, elist.GetN()):
tree.GetEntry(elist.GetEntry(i))
if is_reco:
event_number = tree.event_number
weight = tree.event_weight
lep_pt = tree.lep_pt
lep_eta = tree.lep_eta
else:
event_number = tree.eventNumber
weight = tree.mcEventWeight
lep_pt = tree.lepton_pt
lep_eta = tree.lepton_eta
n_lep = tree.n_leptons
print " event_number={}, met={:.2f}, meff={:.2f}, lep:".format(
event_number, tree.met, tree.meff),
for i, lpt in enumerate(lep_pt):
print "(pt={:.2f}, eta={:.2f}),".format(lpt, lep_eta[i]),
print
# reset default
is_reco = False
def makeList(sample):
f1 = TFile.Open(indir+"signal.root")
t1 = f1.Get("Nominal")
t1.Draw(">>elist","mchannelnumber == "+sample)
elist = TEventList()
elist = ROOT.gDirectory.Get("elist")
ef = TFile(outdir+"elist.root","recreate")
elist.Write()
return True
def buildArraysFromROOT(tree, allowedFeatures, cut, skipEvents, maxEvents,
name):
dataContainer = {}
featureNames = []
eventCounter = -1
gROOT.Reset()
# Get branch names
for item in tree.GetListOfBranches():
featureName = item.GetName()
if featureName in allowedFeatures:
featureNames.append(featureName)
dataContainer[featureName] = []
# Build the event list
tcut = TCut(cut)
tree.Draw(">>eventList", tcut)
eventList = TEventList()
eventList = gDirectory.Get("eventList")
nSelectedEvents = eventList.GetN()
# Event loop
for i in range(0, nSelectedEvents):
if (i < skipEvents):
continue
if (i % 100 == 0):
sys.stdout.write("Reading %s: %d%% \r" %
(tree.GetName(), 100 * i /
(maxEvents + skipEvents)))
sys.stdout.flush()
if i >= (maxEvents + skipEvents):
break
selectedEvNum = eventList.GetEntry(i)
tree.GetEntry(selectedEvNum)
for feature in featureNames:
dataContainer[feature].append(tree.__getattr__(feature))
sys.stdout.write("\n")
# Make the numpy arrays
outputArray = np.array([])
for feature in allowedFeatures:
column = dataContainer[feature]
feature_vector = np.asarray(column)
feature_vector = feature_vector.reshape(feature_vector.size, 1)
if outputArray.shape[0] == 0:
outputArray = feature_vector
else:
outputArray = np.concatenate((outputArray, feature_vector), axis=1)
imp = Imputer(missing_values=-999, strategy='mean', axis=0)
imp.fit(outputArray)
outputArray = imp.transform(outputArray)
print name
print "Events: ", outputArray.shape[0]
print "Features: ", outputArray.shape[1]
return outputArray
# Set up the axes for plotting
figROC, axsROC = plt.subplots(2,3)
axesROC = axsROC.ravel()
figRecErr, axsRecErr = plt.subplots(2,3)
axesRecErr = axsRecErr.ravel()
# MAIN LOOP OVER SIGNAL SAMPLES
axesCounter = 0
for cut in cutList:
# Selections and numbers of events
cutSignal = cut
tcut = TCut(cutSignal)
tree.Draw(">>eventList",tcut)
eventList = TEventList()
eventList = gDirectory.Get("eventList")
nSignalEvents = eventList.GetN()/2
nBackgroundEvents = nSignalEvents
print "====================================="
print "Selection: ",cutSignal, "with ",nSignalEvents," signal events and ",nBackgroundEvents," background events"
# Build data arrays
X_train_bg = X_train_bg_all[0:nBackgroundEvents,:]
X_test_bg = X_test_bg_all[0:nBackgroundEvents,:]
X_test_sig = buildArraysFromROOT(tree,susyFeaturesNtup,cutSignal,nSignalEvents,nSignalEvents,"TESTING SAMPLE (signal)")
X_test_sig = min_max_scaler.transform(X_test_sig)
# Set target equal to input - auto-encoder
Y_train = X_train_bg
print " l_eq_subsam {}".format(l_eq_subsam[s])
print " ngenev {}".format(ngenev)
ns += 1
# set min lum eq
min_lum_eq = 999999.
for s, sname in enumerate(snames):
if (l_eq_subsam[s] < min_lum_eq): min_lum_eq = l_eq_subsam[s]
print "min_lum_eq {}".format(min_lum_eq)
config["isMixed"] = True #debug
config["lumiFb"] = min_lum_eq
json_str = json.dumps(config)
els = [TEventList("el" + sname, "el" + sname) for sname in snames]
n_ev_base = 0
t_sm = 1.
for s, sname in enumerate(snames):
if (s == len(snames) - 1): t_sm = times_sm #debug
n_ev_sfrac = n_ev_subsam[s] * (min_lum_eq / l_eq_subsam[s]) * t_sm
print "# {} events to use: {} ".format(sname, n_ev_sfrac)
print tchain.Draw(
">>el{}".format(sname),
"(Entry$ > {}) && ( Entry$ <= {} ) {}".format(n_ev_base,
n_ev_base + n_ev_sfrac,
extra_cut))
n_ev_base += n_ev_subsam[s]
el = TEventList("el", "el")
for list_to_add in els:
el.Add(list_to_add)