def getit(s):
s.z = {}
for year in 2015, 2016:
if year == 2015:
fn = suppl[s.name+'_2015'][0]
else:
fn = '/uscms_data/d2/tucker/crab_dirs/MiniTreeV16/%s.root' % s.name
f = ROOT.TFile.Open(fn)
t = f.Get('mfvMiniTree/t')
hr = draw_hist_register(t, True)
h,n = hr.draw('svdist', 'nvtx>=2', binning='400,0,4', get_n=True, goff=True)
assert h.GetXaxis().GetBinLowEdge(1) == 0.
assert h.GetXaxis().GetBinLowEdge(5) == 0.04
assert h.GetXaxis().GetBinLowEdge(8) == 0.07
N = norm_from_file(f)
n = h.Integral(1,10000)
b1 = h.Integral(1,4)
b2 = h.Integral(5,7)
b3 = h.Integral(8,10000)
#print s.name, N, n, b1, b2, b3
s.z[year] = (N,n,b1,b2,b3)
N15, n15 = s.z[2015][:2]
N16, n16 = s.z[2016][:2]
s.ratio = [x * N16/N15 for x in clopper_pearson_poisson_means(n15, n16)]
s.ratio[1] = s.ratio[0] - s.ratio[1]
s.ratio[2] = s.ratio[2] - s.ratio[0]
s.ratio = tuple(s.ratio)
print s.name.ljust(30), '%.4f - %.4f + %.4f' % s.ratio
def analyze(plots=False):
if plots:
set_style()
ps = plot_saver(plot_dir('pdfweights', temp=True), size=(600, 600))
fields = ('nominal', 'plus', 'minus', 'pdfunc', 'rel', 'relavg', 'n16',
'n84', 'ctl', 'ctlrel', 'ctlrelmd')
fmt = '%-45s' + ' %10s' * len(fields)
print fmt % (('sname', ) + fields)
ss = samples()
for s in ss:
f = ROOT.TFile.Open(s.fn)
s.norm = norm_from_file(f)
s.w = ac.int_lumi_2018 * 1e-3 / s.norm
t = f.Get('mfvMiniTree/t')
hr = draw_hist_register(t, True, True)
if plots:
for i in xrange(48, 148):
h = hr.draw('weights[%i]' % i, 'nvtx>=2', binning='100,0,2')
ps.save(str(i))
cut = '(nvtx>=2)' # '(nvtx>=2 && (gen_x[0]**2 + gen_y[0]**2)**0.5<0.08 && (gen_x[1]**2+gen_y[1]**2)**0.5 < 0.08)'
h = hr.draw('weight', cut, binning='1,0,1')
s.nominal, _ = tuple(s.w * x for x in get_integral(h))
s.pdfunc, s.family = [], []
for i in xrange(
46, 148
): # JMTBAD indices into misc_weights are fragile, need to put the pdf weights/info somewhere else than weights
h = hr.draw('weight',
'%s*misc_weights[%i]' % (cut, i),
binning='1,0,1')
v = tuple(s.w * x for x in get_integral(h))[0]
(s.pdfunc if i < 48 else s.family).append(v)
s.plus, s.minus = s.pdfunc
s.pdfunc = abs(s.plus - s.minus) / 2
s.plus = abs(s.plus - s.nominal)
s.minus = abs(s.nominal - s.minus)
s.rel = s.pdfunc / s.nominal
s.family.sort()
s.n16, s.n84 = s.family[16], s.family[83]
s.ctl = (s.n84 - s.n16) / 2
s.avg = avg(s.family)
s.rms = rms(s.family)
s.mdn = (s.family[49] + s.family[50]) / 2
s.md = (s.n84 + s.n16) / 2
s.relavg = s.pdfunc / s.avg
s.ctlrel = s.ctl / s.nominal
s.ctlrelmd = s.ctl / s.md
print fmt.replace('%10s', '%10.4f') % (
(s.name, ) + tuple(getattr(s, fi) for fi in fields))
to_pickle(ss, 'pdfuncerts.gzpickle')
def getit(fn, ntk):
f = ROOT.TFile(fn)
den = norm_from_file(f)
assert 3 <= ntk <= 5
t = f.Get('mfvMiniTree%s/t' % ('Ntk%i' % ntk if ntk < 5 else ''))
if not t:
return None
n1v = t.Draw('dist0', 'nvtx==1', 'goff')
n2v = t.Draw('dist0', 'nvtx>=2', 'goff')
return den, n1v, n2v
def getit(fn, ntk):
f = ROOT.TFile(fn)
den = norm_from_file(f)
assert 3 <= ntk <= 5
t = f.Get('mfvMiniTree%s/t' % ('Ntk%i' % ntk if ntk < 5 else ''))
if not t:
return None
n1v = t.Draw('dist0', 'nvtx==1', 'goff')
n2v = t.Draw('dist0', 'nvtx>=2', 'goff')
return den, n1v, n2v
def crab_hadd(working_dir,
new_name=None,
new_dir=None,
raise_on_empty=False,
chunk_size=900,
pattern=None,
lpc_shortcut=False,
range_filter=None):
working_dir, new_name, new_dir = crab_hadd_args(working_dir, new_name,
new_dir)
expected, files = crab_hadd_files(working_dir,
lpc_shortcut,
range_filter=range_filter)
result = HaddBatchResult('crab', working_dir, new_name, new_dir, expected,
files)
print '%s: expecting %i files if all jobs succeeded' % (working_dir,
expected)
if pattern:
if '/' not in pattern:
pattern = '*/' + pattern
files = fnmatch.filter(files, pattern)
automatic_splitting = False
pprinted = False
jobs = []
for f in files:
jobnum = f.split('_')[-1].split('.root')[0]
if crab_global_options.support_automatic_splitting and '-' in jobnum:
automatic_splitting = True
if not pprinted:
pprint(files)
pprinted = True
it, jobnum = jobnum.split('-')
it, jobnum = int(it), int(jobnum)
assert it >= 1 # probe jobs "0-*" should not show up
jobnum = it * 10000 + jobnum
else:
jobnum = int(jobnum)
jobs.append(jobnum)
jobs.sort()
expected = range(1, expected + 1)
if jobs != expected:
print '\033[36;7m %i files found %s not what expected \033[m' % (
len(jobs), crabify_list(jobs))
missing = sorted(set(expected) - set(jobs))
print '\033[36;7m %i missing: %r \033[m' % (len(missing), ' '.join(
str(j) for j in missing))
l = len(files)
if l == 0:
result.success = False
msg = 'crab_hadd: no files found in %s' % working_dir
if raise_on_empty:
raise CRABToolsException(msg)
else:
print '\033[36;7m', msg, '\033[m'
elif l == 1:
print working_dir, ': just one file found, copying'
cmd = 'xrdcp -s %s %s' % (files[0], new_name)
result.success = os.system(cmd) == 0
if result.success and not new_name.startswith('root://'):
os.chmod(new_name, 0644)
else:
result.success = hadd(new_name, files)
if automatic_splitting:
n = norm_from_file(new_name)
sn, s = fn_to_sample(Samples, new_name)
if not s:
print colors.yellow(
"\tnorm_from_file returns %r, couldn't get sample %s" %
(n, sn))
else:
no1, no2 = s.datasets['main'].nevents_orig, s.datasets[
'miniaod'].nevents_orig
if n == no1 or n == no2:
print '\tnorm_from_file returns nevents_orig = %i' % n
else:
print colors.yellow(
'\tnorm_from_file returns %r while %s.nevents_orig is %i (main) %i (miniaod'
% (n, sn, no1, no2))
return result
def cutplayMangle(filename):
debug = False
file = ROOT.TFile.Open(filename)
if not file.IsOpen():
raise RuntimeError('could not open %s' % filename)
norm = norm_from_file(filename)
x = file.Get('SimpleTriggerEfficiency/triggers_pass_num')
cutscans = {}
nm1 = None
# Extract from the big list of bins the numbers separately for each
# cut.
for i in xrange(1, x.GetNbinsX() + 1):
label = x.GetXaxis().GetBinLabel(i)
if label == 'nm1':
nm1 = x.GetBinContent(i), x.GetBinError(i)
continue
try:
cut, cut_val = label.split('X')
except ValueError:
print 'warning: could not parse label %s' % label
continue
if not cutscans.has_key(cut):
cutscans[cut] = []
cutscans[cut].append((cut_val, x.GetBinContent(i)))
h_intot = file.Get('SimpleTriggerEfficiency/triggers_pass_den')
ntot = h_intot.GetBinContent(1), h_intot.GetBinError(1)
file.Close()
output_fn = filename.replace('.root', '_mangled.root')
output_file = ROOT.TFile(output_fn, 'RECREATE')
sample_name = os.path.basename(filename).replace('.root', '')
try:
sample = getattr(Samples, sample_name)
except AttributeError:
sample = None
h_ntot = ROOT.TH1F('ntot', '', 1, 0, 1)
scale = ntot[0] / norm if sample is not None else 1.
h_ntot.SetBinContent(1, ntot[0] / scale)
h_ntot.SetBinError(1, ntot[1] / scale)
if nm1 is not None:
h_nm1 = ROOT.TH1F('nm1', '', 1, 0, 1)
h_nm1.SetBinContent(1, nm1[0])
h_nm1.SetBinError(1, nm1[1])
else:
raise ValueError('did not find nm1 value in input')
output_hists = []
for cut_name, scan in cutscans.iteritems():
if debug:
print 'cut: %s' % cut_name
hmin = depize(scan[0][0])
hminplus1 = depize(scan[1][0])
binwidth = hminplus1 - hmin
hmaxminus1 = depize(scan[-1][0])
hmax = hmaxminus1 + binwidth
if debug:
print 'hmin: ', hmin, ' hminplus1: ', hminplus1, ' binwidth: ', binwidth, ' hmaxminus1: ', hmaxminus1, ' hmax: ', hmax
hist = ROOT.TH1F(cut_name, '', len(scan), hmin, hmax)
output_hists.append(hist)
for cut_bin_name, nevents in scan:
bin = hist.FindBin(depize(cut_bin_name) + 0.00001)
bin_edge = hist.GetBinLowEdge(bin)
if debug:
print 'cut bin name: %s ibin: %i bin_edge: %s number of events: %f' % (
cut_bin_name, bin, bin_edge, nevents)
hist.SetBinContent(bin, nevents)
output_file.Write()
output_file.Close()
def effs(fn):
global tot_sum, tot_var
f = ROOT.TFile(fn)
def get_n(dir_name):
h = f.Get('%s/h_npv' % dir_name)
return h.Integral(0,1000000) if integral else h.GetEntries()
den = norm_from_file(fn)
sname = os.path.basename(fn).replace('.root','')
sample = getattr(Samples, sname, None)
if sample:
weight = sample.xsec * int_lumi / den
weighted = True
else:
weight = 1.
weighted = False
if sigreg:
namenumall = 'mfvEventHistosSigReg'
namenumvtx = 'mfvVertexHistosSigReg/h_nsv'
elif nvtx == 1:
namenumall = 'mfvEventHistosOnlyOneVtx'
namenumvtx = 'mfvVertexHistosOnlyOneVtx/h_nsv'
elif presel:
namenumall = 'mfvEventHistosPreSel'
namenumvtx = None
elif nocuts:
namenumall = 'mfvEventHistosNoCuts'
namenumvtx = None
else:
namenumall = 'mfvEventHistosFullSel'
namenumvtx = None
namenumall = ntk + namenumall
if namenumvtx:
namenumvtx = ntk + namenumvtx
numall = get_n(namenumall)
if namenumvtx is not None:
h = f.Get(namenumvtx)
numvtx = h.Integral(h.FindBin(nvtx), 1000000)
else:
numvtx = -1
tot_sum += numall * weight
tot_var += numall * weight**2
if csv:
print '%s,%e,%f,%f,%f,%f,%f' % (sname, weight, den, numall, float(numall)/den, numall*weight, numall**0.5 * weight)
else:
print '%s (w = %.3e): # ev: %10.1f pass evt+vtx: %5.1f -> %5.3e pass vtx only: %5.1f -> %5.3e' % (sname.ljust(30), weight, den, numall, float(numall)/den, numvtx, float(numvtx)/den)
if weighted:
print ' weighted to %.1f/pb: %5.2f +/- %5.2f' % (int_lumi, numall*weight, numall**0.5 * weight)
else:
print ' number of events: %5.2f +/- %5.2f' % (numall*weight, numall**0.5 * weight)
if cuts:
nm1s_name = 'h_nm1_%s' % sname
h_nm1_abs = ROOT.TH1F(nm1s_name + '_abs', ';cut;abs. eff. w/o cut', len(cuts)+1, 0, len(cuts)+1)
h_nm1_rel = ROOT.TH1F(nm1s_name + '_rel', ';cut;n-1 eff.', len(cuts), 0, len(cuts))
for icut, cut in enumerate(cuts):
h_nm1_abs.GetXaxis().SetBinLabel(icut+1, cut)
h_nm1_rel.GetXaxis().SetBinLabel(icut+1, cut)
nm1 = get_n('evtHst%sVNo%s' % (nvtx, cut))
nm1_abs = float(nm1)/den
nm1_rel = float(numall)/nm1 if nm1 > 0 else -1
h_nm1_abs.SetBinContent(icut+1, nm1_abs)
h_nm1_rel.SetBinContent(icut+1, nm1_rel)
print ' remove %s cut: %5i -> %5.3e (n-1: %5.3e)' % (cut.ljust(max_cut_name_len), nm1, nm1_abs, nm1_rel)
h_nm1_abs.GetXaxis().SetBinLabel(len(cuts)+1, 'all')
h_nm1_abs.SetBinContent(len(cuts)+1, float(numall)/den)
def draw(h):
if not plots:
return
h.SetStats(0)
h.GetYaxis().SetRangeUser(0,1.05)
h.SetMarkerSize(2)
h.Draw('hist text')
ps.save(h.GetName())
draw(h_nm1_abs)
draw(h_nm1_rel)
def analyze(plots=False):
if plots:
set_style()
ps = plot_saver(plot_dir('scaleweights', temp=True), size=(600, 600))
fields = ('nominal', 'n16', 'n84', 'ctl', 'ctlrel', 'ctlrelmd')
fmt = '%-45s' + ' %10s' * len(fields)
print fmt % (('sname', ) + fields)
ss = samples()
for s in ss:
f = ROOT.TFile.Open(s.fn)
s.norm = norm_from_file(f)
s.w = ac.int_lumi_2018 * 1e-3 / s.norm
t = f.Get('mfvMiniTree/t')
hr = draw_hist_register(t, True, True)
weight_str_list = [
"ren_weight_up", "ren_weight_dn", "fac_weight_up", "fac_weight_dn",
"ren_weight_up*fac_weight_up", "ren_weight_dn*fac_weight_dn"
]
cut = '(nvtx>=2)' # '(nvtx>=2 && (gen_x[0]**2 + gen_y[0]**2)**0.5<0.08 && (gen_x[1]**2+gen_y[1]**2)**0.5 < 0.08)'
h = hr.draw('weight', cut, binning='1,0,1')
s.nominal, _ = tuple(s.w * x for x in get_integral(h))
s.scaleunc, s.family = [], []
for weight_str in weight_str_list:
# because I didn't pick better names...
if "ren" in weight_str and "fac" in weight_str:
weight_name_for_norm = "sum_weight_ren_fac"
elif "ren" in weight_str:
weight_name_for_norm = "sum_weight_ren"
elif "fac" in weight_str:
weight_name_for_norm = "sum_weight_fac"
if "_up" in weight_str:
weight_name_for_norm += "_up"
elif "_dn" in weight_str:
weight_name_for_norm += "_dn"
s.norm = norm_from_file_weight(f, weight_name=weight_name_for_norm)
s.w = ac.int_lumi_2018 * 1e-3 / s.norm
h = hr.draw('weight', '%s*%s' % (cut, weight_str), binning='1,0,1')
v = tuple(s.w * x for x in get_integral(h))[0]
#print '%s*%s, weight*nvtx==2 = %s' % (cut,weight_str,v)
s.family.append(v)
if len(weight_str_list) == 6:
s.family.sort()
s.n16, s.n84 = s.family[1], s.family[4] # since total is 6
s.ctl = max(abs(s.family[0] - s.nominal),
abs(s.family[5] -
s.nominal)) # i.e. maximum deviation ==> envelope
#s.ctl = (s.n84 - s.n16)/2
s.avg = avg(s.family)
s.rms = rms(s.family)
s.mdn = (s.family[2] + s.family[3]) / 2
s.md = (s.n84 + s.n16) / 2
#s.relavg = s.scaleunc / s.avg
if s.nominal == 0:
print "s.nominal is 0!!!!!!!!!!!!"
s.nominal = 0.00001
if s.md == 0:
print "s.md is 0!!!!!!!!!!!!"
s.md = 0.00001
s.ctlrel = s.ctl / s.nominal
s.ctlrelmd = s.ctl / s.md
print fmt.replace('%10s', '%10.4f') % (
(s.name, ) + tuple(getattr(s, fi) for fi in fields))
else:
print "invalid weight_str_list!!!!!!!!!!!!!!!!!"
to_pickle(ss, 'ren_fac.gzpickle')
def effs(fn):
global tot_sum, tot_var
f = ROOT.TFile(fn)
def get_n(dir_name):
h = f.Get('%s/h_npv' % dir_name)
return h.Integral(0, 1000000) if integral else h.GetEntries()
den = norm_from_file(fn)
sname = os.path.basename(fn).replace('.root', '')
sample = getattr(Samples, sname, None)
if sample:
weight = sample.xsec * int_lumi / den
weighted = True
else:
weight = 1.
weighted = False
if sigreg:
namenumall = 'mfvEventHistosSigReg'
namenumvtx = 'mfvVertexHistosSigReg/h_nsv'
elif nvtx == 1:
namenumall = 'mfvEventHistosOnlyOneVtx'
namenumvtx = 'mfvVertexHistosOnlyOneVtx/h_nsv'
elif presel:
namenumall = 'mfvEventHistosPreSel'
namenumvtx = None
elif nocuts:
namenumall = 'mfvEventHistosNoCuts'
namenumvtx = None
else:
namenumall = 'mfvEventHistosFullSel'
namenumvtx = None
namenumall = ntk + namenumall
if namenumvtx:
namenumvtx = ntk + namenumvtx
numall = get_n(namenumall)
if namenumvtx is not None:
h = f.Get(namenumvtx)
numvtx = h.Integral(h.FindBin(nvtx), 1000000)
else:
numvtx = -1
tot_sum += numall * weight
tot_var += numall * weight**2
if csv:
print '%s,%e,%f,%f,%f,%f,%f' % (sname, weight, den, numall,
float(numall) / den, numall * weight,
numall**0.5 * weight)
else:
print '%s (w = %.3e): # ev: %10.1f pass evt+vtx: %5.1f -> %5.3e pass vtx only: %5.1f -> %5.3e' % (
sname.ljust(30), weight, den, numall, float(numall) / den, numvtx,
float(numvtx) / den)
if weighted:
print ' weighted to %.1f/pb: %5.2f +/- %5.2f' % (
int_lumi, numall * weight, numall**0.5 * weight)
else:
print ' number of events: %5.2f +/- %5.2f' % (
numall * weight, numall**0.5 * weight)
if cuts:
nm1s_name = 'h_nm1_%s' % sname
h_nm1_abs = ROOT.TH1F(nm1s_name + '_abs', ';cut;abs. eff. w/o cut',
len(cuts) + 1, 0,
len(cuts) + 1)
h_nm1_rel = ROOT.TH1F(nm1s_name + '_rel', ';cut;n-1 eff.',
len(cuts), 0, len(cuts))
for icut, cut in enumerate(cuts):
h_nm1_abs.GetXaxis().SetBinLabel(icut + 1, cut)
h_nm1_rel.GetXaxis().SetBinLabel(icut + 1, cut)
nm1 = get_n('%sevtHst%sVNo%s' % (ntk, nvtx, cut))
nm1_abs = float(nm1) / den
nm1_rel = float(numall) / nm1 if nm1 > 0 else -1
h_nm1_abs.SetBinContent(icut + 1, nm1_abs)
h_nm1_rel.SetBinContent(icut + 1, nm1_rel)
print ' remove %s cut: %5i -> %5.3e (n-1: %5.3e)' % (
cut.ljust(max_cut_name_len), nm1, nm1_abs, nm1_rel)
print ' weighted to %.1f/pb: %5.2f +/- %5.2f' % (
int_lumi, nm1 * weight, abs(nm1)**0.5 * weight)
h_nm1_abs.GetXaxis().SetBinLabel(len(cuts) + 1, 'all')
h_nm1_abs.SetBinContent(len(cuts) + 1, float(numall) / den)
def draw(h):
if not plots:
return
h.SetStats(0)
h.GetYaxis().SetRangeUser(0, 1.05)
h.SetMarkerSize(2)
h.Draw('hist text')
ps.save(h.GetName())
draw(h_nm1_abs)
draw(h_nm1_rel)
def analyze(plots=False):
if plots:
set_style()
ps = plot_saver(plot_dir('scaleweights', temp=True), size=(600, 600))
fields = ('nominal', 'n16', 'n84', 'ctl', 'ctlrel', 'ctlrelmd')
fmt = '%-45s' + ' %10s' * len(fields)
print fmt % (('sname', ) + fields)
ss = samples()
for s in ss:
f = ROOT.TFile.Open(s.fn)
s.norm = norm_from_file(f)
s.w = ac.int_lumi_2018 * 1e-3 / s.norm
t = f.Get('mfvMiniTree/t')
hr = draw_hist_register(t, True, True)
myrange = (14, 46) # decorrelated variations - recommended!
#myrange = (6,10) # simple 2x up/down
if plots:
for i in xrange(*myrange):
h = hr.draw('weights[%i]' % i, 'nvtx>=2', binning='100,0,2')
ps.save(str(i))
cut = '(nvtx>=2)' # '(nvtx>=2 && (gen_x[0]**2 + gen_y[0]**2)**0.5<0.08 && (gen_x[1]**2+gen_y[1]**2)**0.5 < 0.08)'
h = hr.draw('weight', cut, binning='1,0,1')
s.nominal, _ = tuple(s.w * x for x in get_integral(h))
s.scaleunc, s.family = [], []
for i in xrange(
*myrange
): # JMTBAD indices into misc_weights are fragile, need to put the pdf weights/info somewhere else than weights
h = hr.draw('weight',
'%s*misc_weights[%i]' % (cut, i),
binning='1,0,1')
v = tuple(s.w * x for x in get_integral(h))[0]
s.family.append(v)
if myrange == (14, 46):
s.family.sort()
s.n16, s.n84 = s.family[5], s.family[27] # since total is 32
s.ctl = (s.n84 - s.n16) / 2
s.avg = avg(s.family)
s.rms = rms(s.family)
s.mdn = (s.family[15] + s.family[16]) / 2
s.md = (s.n84 + s.n16) / 2
#s.relavg = s.scaleunc / s.avg
if s.nominal == 0:
print "s.nominal is 0!!!!!!!!!!!!"
s.nominal = 0.00001
if s.md == 0:
print "s.md is 0!!!!!!!!!!!!"
s.md = 0.00001
s.ctlrel = s.ctl / s.nominal
s.ctlrelmd = s.ctl / s.md
print fmt.replace('%10s', '%10.4f') % (
(s.name, ) + tuple(getattr(s, fi) for fi in fields))
elif myrange == (6, 10):
s.family.sort()
s.n16, s.n84 = s.family[1], s.family[2] # since total is 4
s.ctl = (s.n84 - s.n16) / 2
s.avg = avg(s.family)
s.rms = rms(s.family)
s.mdn = (s.family[1] + s.family[2]) / 2
s.md = (s.n84 + s.n16) / 2
s.ctlrel = s.ctl / s.nominal
s.ctlrelmd = s.ctl / s.md
print fmt.replace('%10s', '%10.4f') % (
(s.name, ) + tuple(getattr(s, fi) for fi in fields))
print "avg %10.4f, rms %10.4f, rel %10.4f" % (s.avg, s.rms,
s.rms / s.avg)
else:
print "invalid range!!!!!!!!!!!!!!!!!"
to_pickle(ss, 'alphaS_parton_shower_uncerts.gzpickle')
def cutplayMangle(filename):
debug = False
file = ROOT.TFile.Open(filename)
if not file.IsOpen():
raise RuntimeError('could not open %s' % filename)
norm = norm_from_file(filename)
x = file.Get('SimpleTriggerEfficiency/triggers_pass_num')
cutscans = {}
nm1 = None
# Extract from the big list of bins the numbers separately for each
# cut.
for i in xrange(1, x.GetNbinsX()+1):
label = x.GetXaxis().GetBinLabel(i)
if label == 'nm1':
nm1 = x.GetBinContent(i), x.GetBinError(i)
continue
try:
cut, cut_val = label.split('X')
except ValueError:
print 'warning: could not parse label %s' % label
continue
if not cutscans.has_key(cut):
cutscans[cut] = []
cutscans[cut].append((cut_val, x.GetBinContent(i)))
h_intot = file.Get('SimpleTriggerEfficiency/triggers_pass_den')
ntot = h_intot.GetBinContent(1), h_intot.GetBinError(1)
file.Close()
output_fn = filename.replace('.root', '_mangled.root')
output_file = ROOT.TFile(output_fn, 'RECREATE')
sample_name = os.path.basename(filename).replace('.root', '')
try:
sample = getattr(Samples, sample_name)
except AttributeError:
sample = None
h_ntot = ROOT.TH1F('ntot', '', 1, 0, 1)
scale = ntot[0] / norm if sample is not None else 1.
h_ntot.SetBinContent(1, ntot[0] / scale)
h_ntot.SetBinError (1, ntot[1] / scale)
if nm1 is not None:
h_nm1 = ROOT.TH1F('nm1', '', 1, 0, 1)
h_nm1.SetBinContent(1, nm1[0])
h_nm1.SetBinError(1, nm1[1])
else:
raise ValueError('did not find nm1 value in input')
output_hists = []
for cut_name, scan in cutscans.iteritems():
if debug:
print 'cut: %s' % cut_name
hmin = depize(scan[0][0])
hminplus1 = depize(scan[1][0])
binwidth = hminplus1 - hmin
hmaxminus1 = depize(scan[-1][0])
hmax = hmaxminus1 + binwidth
if debug:
print 'hmin: ', hmin, ' hminplus1: ', hminplus1, ' binwidth: ', binwidth, ' hmaxminus1: ', hmaxminus1, ' hmax: ', hmax
hist = ROOT.TH1F(cut_name, '', len(scan), hmin, hmax)
output_hists.append(hist)
for cut_bin_name, nevents in scan:
bin = hist.FindBin(depize(cut_bin_name) + 0.00001)
bin_edge = hist.GetBinLowEdge(bin)
if debug:
print 'cut bin name: %s ibin: %i bin_edge: %s number of events: %f' % (cut_bin_name, bin, bin_edge, nevents)
hist.SetBinContent(bin, nevents)
output_file.Write()
output_file.Close()
import sys, glob, os
from JMTucker.Tools.Sample import norm_from_file
from JMTucker.Tools import Samples, colors
path = sys.argv[1]
dataset = sys.argv[2]
target = float(sys.argv[3]) if len(sys.argv) > 3 else 0.5
for fn in glob.glob(os.path.join(path, '*.root')):
sname = os.path.basename(fn).replace('.root', '')
s = getattr(Samples, sname)
s.set_curr_dataset(dataset)
n = norm_from_file(fn)
frac = n/s.nevents_orig
delta = abs(frac - target)/target
if delta > 0.01:
color = colors.red
elif delta > 1e-3:
color = colors.yellow
else:
color = colors.green
print color('%-50s %15i %15i %e' % (fn, s.nevents_orig, n, frac))
def crab_hadd(working_dir, new_name=None, new_dir=None, raise_on_empty=False, chunk_size=900, pattern=None, lpc_shortcut=False, range_filter=None):
working_dir, new_name, new_dir = crab_hadd_args(working_dir, new_name, new_dir)
expected, files = crab_hadd_files(working_dir, lpc_shortcut, range_filter=range_filter)
print '%s: expecting %i files if all jobs succeeded' % (working_dir, expected)
if pattern:
if '/' not in pattern:
pattern = '*/' + pattern
files = fnmatch.filter(files, pattern)
automatic_splitting = False
pprinted = False
jobs = []
for f in files:
jobnum = f.split('_')[-1].split('.root')[0]
if crab_global_options.support_automatic_splitting and '-' in jobnum:
automatic_splitting = True
if not pprinted:
pprint(files)
pprinted = True
it, jobnum = jobnum.split('-')
it, jobnum = int(it), int(jobnum)
assert it >= 1 # probe jobs "0-*" should not show up
jobnum = it*10000 + jobnum
else:
jobnum = int(jobnum)
jobs.append(jobnum)
jobs.sort()
expected = range(1, expected+1)
if jobs != expected:
print '\033[36;7m %i files found %s not what expected \033[m' % (len(jobs), crabify_list(jobs))
missing = sorted(set(expected) - set(jobs))
print '\033[36;7m %i missing: %r \033[m' % (len(missing), ' '.join(str(j) for j in missing))
l = len(files)
if l == 0:
msg = 'crab_hadd: no files found in %s' % working_dir
if raise_on_empty:
raise CRABToolsException(msg)
else:
print '\033[36;7m', msg, '\033[m'
elif l == 1:
print working_dir, ': just one file found, copying'
cmd = 'xrdcp -s %s %s' % (files[0], new_name)
os.system(cmd)
os.chmod(new_name, 0644)
else:
hadd(new_name, files)
if automatic_splitting:
n = norm_from_file(new_name)
sn, s = fn_to_sample(Samples, new_name)
if not s:
print colors.yellow("\tnorm_from_file returns %r, couldn't get sample %s" % (n, sn))
else:
no1, no2 = s.datasets['main'].nevents_orig, s.datasets['miniaod'].nevents_orig
if n == no1 or n == no2:
print '\tnorm_from_file returns nevents_orig = %i' % n
else:
print colors.yellow('\tnorm_from_file returns %r while %s.nevents_orig is %i (main) %i (miniaod' % (n, sn, no1, no2))
return new_name
