def read(scan, param, files, chop, remove_near_min, rezero,
remove_delta=None, improve=False, remove_dups=True):
# print files
goodfiles = [f for f in files if plot.TFileIsGood(f)]
limit = plot.MakeTChain(goodfiles, 'limit')
graph = plot.TGraphFromTree(
limit, param, '2*%s' % DELTANLL, 'quantileExpected > -1.5')
# print 'INPUT'
# graph.Print()
graph.SetName(scan)
graph.Sort()
if remove_dups:
plot.RemoveGraphXDuplicates(graph)
if remove_delta is not None:
plot.RemoveSmallDelta(graph, remove_delta)
plot.RemoveGraphYAbove(graph, chop)
plot.ReZeroTGraph(graph, rezero)
if remove_near_min is not None:
plot.RemoveNearMin(graph, remove_near_min)
if improve:
global NAMECOUNTER
spline = ROOT.TSpline3("spline3", graph)
func = ROOT.TF1('splinefn' + str(NAMECOUNTER), partial(Eval, spline),
graph.GetX()[0], graph.GetX()[graph.GetN() - 1], 1)
func.SetNpx(NPX)
NAMECOUNTER += 1
plot.ImproveMinimum(graph, func, True)
# graph.Print()
if FILTER is not None:
plot.FilterGraph(graph, FILTER)
if REMOVE_X_RANGES is not None:
for remove_x in REMOVE_X_RANGES:
plot.RemoveInXRange(graph, remove_x[0], remove_x[1])
return graph
def read(scan,
param,
files,
chop,
remove_near_min,
rezero,
remove_delta=None,
improve=False):
# print files
goodfiles = [f for f in files if plot.TFileIsGood(f)]
limit = plot.MakeTChain(goodfiles, 'limit')
# require quantileExpected > -0.5 to avoid the final point which is always committed twice
# (even if the fit fails)
graph = plot.TGraphFromTree(limit, param, '2*deltaNLL',
'quantileExpected > -0.5')
graph.SetName(scan)
graph.Sort()
plot.RemoveGraphXDuplicates(graph)
if remove_delta is not None: plot.RemoveSmallDelta(graph, remove_delta)
plot.RemoveGraphYAbove(graph, chop)
plot.ReZeroTGraph(graph, rezero)
if remove_near_min is not None: plot.RemoveNearMin(graph, remove_near_min)
if improve:
global NAMECOUNTER
spline = ROOT.TSpline3("spline3", graph)
func = ROOT.TF1('splinefn' + str(NAMECOUNTER), partial(Eval, spline),
graph.GetX()[0],
graph.GetX()[graph.GetN() - 1], 1)
NAMECOUNTER += 1
plot.ImproveMinimum(graph, func, True)
# graph.Print()
return graph
def read(scan, param, files, ycut):
goodfiles = [f for f in files if plot.TFileIsGood(f)]
limit = plot.MakeTChain(goodfiles, 'limit')
graph = plot.TGraphFromTree(limit, param, '2*deltaNLL', 'quantileExpected > -1.5')
graph.SetName(scan)
graph.Sort()
plot.RemoveGraphXDuplicates(graph)
plot.RemoveGraphYAbove(graph, ycut)
# graph.Print()
return graph
def run_method(self):
limit_sets = defaultdict(list)
for filename in self.args.input:
if not plot.TFileIsGood(filename):
print '>> File %s is corrupt or incomplete, skipping' % filename
if self.args.use_dirs is False:
limit_sets['default'].append(filename)
else:
label = 'default'
dirs = filename.split('/')
# The last dir could be the mass, if so we ignore it and check the next
if len(dirs) > 1:
if not isfloat(dirs[-2]):
label = dirs[-2]
elif len(dirs) > 2:
label = dirs[-3]
limit_sets[label].append(filename)
# print limit_sets
for label, filenames in limit_sets.iteritems():
js_out = {}
for filename in filenames:
file = ROOT.TFile(filename)
tree = file.Get('limit')
for evt in tree:
mh = str(evt.mh)
if mh not in js_out:
js_out[mh] = {}
if evt.quantileExpected == -1:
js_out[mh]['obs'] = evt.limit
elif abs(evt.quantileExpected - 0.5) < 1E-4:
js_out[mh]["exp0"] = evt.limit
elif abs(evt.quantileExpected - 0.025) < 1E-4:
js_out[mh]["exp-2"] = evt.limit
elif abs(evt.quantileExpected - 0.160) < 1E-4:
js_out[mh]["exp-1"] = evt.limit
elif abs(evt.quantileExpected - 0.840) < 1E-4:
js_out[mh]["exp+1"] = evt.limit
elif abs(evt.quantileExpected - 0.975) < 1E-4:
js_out[mh]["exp+2"] = evt.limit
# print js_out
jsondata = json.dumps(js_out,
sort_keys=True,
indent=2,
separators=(',', ': '))
# print jsondata
if self.args.output is not None:
outname = self.args.output.replace(
'.json', '_%s.json' %
label) if self.args.use_dirs else self.args.output
with open(outname, 'w') as out_file:
print '>> Writing output %s from files:' % outname
pprint.pprint(filenames, indent=2)
out_file.write(jsondata)
def read(scan, param_x, param_y, file):
# print files
goodfiles = [f for f in [file] if plot.TFileIsGood(f)]
limit = plot.MakeTChain(goodfiles, 'limit')
graph = plot.TGraph2DFromTree(limit, param_x, param_y, '2*deltaNLL', 'quantileExpected > -0.5 && deltaNLL > 0')
best = plot.TGraphFromTree(limit, param_x, param_y, 'quantileExpected > -0.5 && deltaNLL == 0')
plot.RemoveGraphXDuplicates(best)
assert(best.GetN() == 1)
graph.SetName(scan)
best.SetName(scan+'_best')
# graph.Print()
return (graph, best)
def read(scan, param, other_param, files, remove_dups=True):
# print files
goodfiles = [f for f in files if plot.TFileIsGood(f)]
limit = plot.MakeTChain(goodfiles, 'limit')
graph = plot.TGraphFromTree(limit, param, other_param,
'quantileExpected > -0.5')
# print 'INPUT'
# graph.Print()
graph.SetName(scan)
graph.Sort()
if remove_dups:
plot.RemoveGraphXDuplicates(graph)
# graph.Print()
return graph
def ReadScanFromTFiles(self,
filenames,
param_name,
tree_selection='quantileExpected > -1.5'):
# TODO: should report bad files here
goodfiles = [f for f in filenames if plotting.TFileIsGood(f)]
if len(goodfiles) == 0:
raise RuntimeError('[ReadScanFromTFiles] no valid TFiles')
limit = plotting.MakeTChain(goodfiles, 'limit')
graph = plotting.TGraphFromTree(limit, param_name, '2*deltaNLL',
tree_selection)
# graph.SetName(label)
graph.Sort()
if self.verbosity >= 2:
print '[ReadScanFromTFiles] Produced TGraph:'
graph.Print()
return graph
def run_method(self):
limit_sets = defaultdict(list)
for filename in self.args.input:
if not plot.TFileIsGood(filename):
print '>> File %s is corrupt or incomplete, skipping' % filename
continue
if not self.args.use_dirs:
if 'default' not in limit_sets:
limit_sets['default'] = ([], [])
limit_sets['default'][0].append(filename)
else:
label = 'default'
dirs = filename.split('/')
# The last dir could be the mass, if so we ignore it and check the next
if len(dirs) > 1:
if not isfloat(dirs[-2]):
label = dirs[-2]
elif len(dirs) > 2:
label = dirs[-3]
if label not in limit_sets:
limit_sets[label] = ([], [])
limit_sets[label][0].append(filename)
for label, (filenames, toyfiles) in limit_sets.iteritems():
js_out = {}
for filename in filenames:
file = ROOT.TFile(filename)
tree = file.Get('limit')
adding_cat_branch = False
branches = []
for branch in tree.GetListOfBranches():
# Current logic says any branch after quantileExpected is a special
# GOF branch labelled according to category
if adding_cat_branch:
branches.append(branch.GetName())
if branch.GetName() == 'quantileExpected':
adding_cat_branch = True
# print branches
for evt in tree:
mh = str(evt.mh)
if mh not in js_out:
js_out[mh] = {}
if evt.quantileExpected != -1:
continue
if branches:
for branch in branches:
if branch not in js_out[mh]:
js_out[mh][branch] = {}
js_out[mh][branch]['toy'] = []
if evt.iToy <= 0:
js_out[mh][branch]['obs'] = [
getattr(evt, branch)
]
else:
js_out[mh][branch]['toy'].append(
getattr(evt, branch))
else:
if 'toy' not in js_out[mh]:
js_out[mh]['toy'] = []
if evt.iToy <= 0:
js_out[mh]['obs'] = [evt.limit]
else:
js_out[mh]['toy'].append(evt.limit)
for mh in js_out:
if all([entry in js_out[mh] for entry in ['toy', 'obs']]):
js_out[mh]["p"] = float(
len([
toy for toy in js_out[mh]['toy']
if toy >= js_out[mh]['obs'][0]
])) / len(js_out[mh]['toy'])
else:
for branch in js_out[mh]:
js_out[mh][branch]["p"] = float(
len([
toy for toy in js_out[mh][branch]['toy']
if toy >= js_out[mh][branch]['obs'][0]
])) / len(js_out[mh][branch]['toy'])
# print js_out
jsondata = json.dumps(js_out,
sort_keys=True,
indent=2,
separators=(',', ': '))
# print jsondata
if self.args.output is not None:
outname = self.args.output.replace(
'.json', '_%s.json' %
label) if self.args.use_dirs else self.args.output
with open(outname, 'w') as out_file:
print '>> Writing output %s from files:' % outname
pprint.pprint(filenames, indent=2)
out_file.write(jsondata)
def run_method(self):
limit_sets = defaultdict(list)
for filename in self.args.input:
if not plot.TFileIsGood(filename):
print '>> File %s is corrupt or incomplete, skipping' % filename
continue
if self.args.use_dirs is False:
limit_sets['default'].append(filename)
else:
label = 'default'
dirs = filename.split('/')
# The last dir could be the mass, if so we ignore it and check the next
if len(dirs) > 1:
if not isfloat(dirs[-2]):
label = dirs[-2]
elif len(dirs) > 2:
label = dirs[-3]
limit_sets[label].append(filename)
# print limit_sets
for label, filenames in limit_sets.iteritems():
js_out = {}
for filename in filenames:
if plot.TFileIsGood(filename):
file = ROOT.TFile(filename)
tree = file.Get('limit')
for evt in tree:
mh = str(evt.mh)
if mh not in js_out:
js_out[mh] = {}
if self.args.toys:
js_out[mh]['toys'] = {}
for limit in [
'obs', 'exp0', 'exp-2', 'exp-1',
'exp+1', 'exp+2'
]:
js_out[mh]['toys'][limit] = []
if self.args.toys:
if evt.iToy > 0:
if evt.quantileExpected == -1:
js_out[mh]['toys']['obs'].append(evt.limit)
elif abs(evt.quantileExpected - 0.5) < 1E-4:
js_out[mh]['toys']["exp0"].append(
evt.limit)
elif abs(evt.quantileExpected - 0.025) < 1E-4:
js_out[mh]['toys']["exp-2"].append(
evt.limit)
elif abs(evt.quantileExpected - 0.160) < 1E-4:
js_out[mh]['toys']["exp-1"].append(
evt.limit)
elif abs(evt.quantileExpected - 0.840) < 1E-4:
js_out[mh]['toys']["exp+1"].append(
evt.limit)
elif abs(evt.quantileExpected - 0.975) < 1E-4:
js_out[mh]['toys']["exp+2"].append(
evt.limit)
elif evt.iToy == 0:
if evt.quantileExpected == -1:
js_out[mh]['obs'].append(evt.limit)
else:
if evt.quantileExpected == -1:
js_out[mh]['obs'] = evt.limit
if self.args.limit_err:
js_out[mh]['obs_err'] = evt.limitErr
elif abs(evt.quantileExpected - 0.5) < 1E-4:
js_out[mh]["exp0"] = evt.limit
if self.args.limit_err:
js_out[mh]['exp0_err'] = evt.limitErr
elif abs(evt.quantileExpected - 0.025) < 1E-4:
js_out[mh]["exp-2"] = evt.limit
if self.args.limit_err:
js_out[mh]['exp-2_err'] = evt.limitErr
elif abs(evt.quantileExpected - 0.160) < 1E-4:
js_out[mh]["exp-1"] = evt.limit
if self.args.limit_err:
js_out[mh]['exp-1_err'] = evt.limitErr
elif abs(evt.quantileExpected - 0.840) < 1E-4:
js_out[mh]["exp+1"] = evt.limit
if self.args.limit_err:
js_out[mh]['exp+1_err'] = evt.limitErr
elif abs(evt.quantileExpected - 0.975) < 1E-4:
js_out[mh]["exp+2"] = evt.limit
if self.args.limit_err:
js_out[mh]['exp+2_err'] = evt.limitErr
if self.args.toys:
for mh in js_out.keys():
print "Expected bands will be taken from toys"
print mh
limits = sorted(js_out[mh]['toys']['obs'])
#if mh == '160.0' or mh == '90.0' :
# limits = [x for x in limits if x > 0.1]
quantiles = array('d', [0.025, 0.160, 0.5, 0.840, 0.975])
res = array('d', [0., 0., 0., 0., 0.])
empty = array('i', [0])
ROOT.TMath.Quantiles(len(limits), len(quantiles),
array('d', limits), res, quantiles,
True, empty, 1)
print res
js_out[mh]['exp-2'] = res[0]
js_out[mh]['exp-1'] = res[1]
js_out[mh]['exp0'] = res[2]
js_out[mh]['exp+1'] = res[3]
js_out[mh]['exp+2'] = res[4]
# print js_out
jsondata = json.dumps(js_out,
sort_keys=True,
indent=2,
separators=(',', ': '))
# print jsondata
if self.args.output is not None:
outname = self.args.output.replace(
'.json', '_%s.json' %
label) if self.args.use_dirs else self.args.output
with open(outname, 'w') as out_file:
print '>> Writing output %s from files:' % outname
pprint.pprint(filenames, indent=2)
out_file.write(jsondata)
def run_method(self):
ROOT.PyConfig.IgnoreCommandLineOptions = True
ROOT.gROOT.SetBatch(ROOT.kTRUE)
# Open the json config file
with open(self.args.config) as json_file:
cfg = json.load(json_file)
# Set all the parameter values locally using defaults if necessary
grids = cfg['grids']
POIs = cfg['POIs']
opts = cfg['opts']
toys_per_cycle = cfg['toys_per_cycle']
zipname = cfg.get('zipfile', None)
contours = cfg.get('contours',
['obs', 'exp-2', 'exp-1', 'exp0', 'exp+1', 'exp+2'])
min_toys = cfg.get('min_toys', 500)
max_toys = cfg.get('max_toys', 5000)
signif = cfg.get('signif', 3.0)
cl = cfg.get('CL', 0.95)
verbose = cfg.get('verbose', False)
make_plots = cfg.get('make_plots', False)
# Write CLs values into the output even if current toys do not pass validation
incomplete = cfg.get('output_incomplete', False)
outfile = cfg.get('output', 'hybrid_grid.root')
# NB: blacklisting not yet implemented for this method
# Have to merge some arguments from both the command line and the "opts" in the json file
to_freeze = []
to_set = []
set_opt, opts = self.extract_arg('--setPhysicsModelParameters', opts)
if set_opt is not None: to_set.append(set_opt)
freeze_opt, opts = self.extract_arg('--freezeNuisances', opts)
if freeze_opt is not None: to_freeze.append(freeze_opt)
if hasattr(self.args, 'setPhysicsModelParameters'
) and self.args.setPhysicsModelParameters is not None:
to_set.append(self.args.setPhysicsModelParameters)
if hasattr(
self.args,
'freezeNuisances') and self.args.freezeNuisances is not None:
to_freeze.append(self.args.freezeNuisances)
points = []
blacklisted_points = []
for igrid in grids:
assert (len(igrid) == 3)
if igrid[2] == '':
points.extend(
itertools.product(utils.split_vals(igrid[0]),
utils.split_vals(igrid[1])))
else:
blacklisted_points.extend(
itertools.product(utils.split_vals(igrid[0]),
utils.split_vals(igrid[1]),
utils.split_vals(igrid[2])))
# This dictionary will keep track of the combine output files for each model point
file_dict = {}
for p in points:
file_dict[p] = {}
# The regex we will use to identify output files and extract POI values
rgx = re.compile(
'higgsCombine\.%s\.(?P<p1>.*)\.%s\.(?P<p2>.*)\.HybridNew\.mH.*\.(?P<toy>.*)\.root'
% (POIs[0], POIs[1]))
# Can optionally copy output root files into a zip archive
# If the user has specified a zipfile we will first
# look for output files in this archive before scanning the
# current directory
if zipname:
# Open the zip file in append mode, this should also
# create it if it doesn't exist
zipf = zipfile.ZipFile(zipname, 'a')
for f in zipf.namelist():
matches = rgx.search(f)
p = (matches.group('p1'), matches.group('p2'))
seed = int(matches.group('toy'))
if p in file_dict:
if seed not in file_dict[p]:
# For each model point have a dictionary keyed on the seed number
# with a value pointing to the file in the archive in the format
# ROOT expects: "zipfile.zip#higgsCombine.blah.root"
file_dict[p][seed] = zipname + '#' + f
# Now look for files in the local directory
for f in glob.glob('higgsCombine.%s.*.%s.*.HybridNew.mH*.root' %
(POIs[0], POIs[1])):
matches = rgx.search(f)
p = (matches.group('p1'), matches.group('p2'))
seed = int(matches.group('toy'))
if p in file_dict:
# Don't add this file to the list if its seed number is already
# a value in the dict.
if seed not in file_dict[p]:
# If we're using the zipfile we'll add this now and
# then delete it from the local directory
# But: only in the file is good, we don't want to pollute the zip
# file with incomplete or failed jobs
if zipname and plot.TFileIsGood(f):
zipf.write(f) # assume this throws if it fails
print 'Adding %s to %s' % (f, zipname)
file_dict[p][seed] = zipname + '#' + f
os.remove(f)
else: # otherwise just add the file to the dict in the normal way
file_dict[p][seed] = f
if zipname:
zipf.close()
# These lists will keep track of the CLs values which we will use
# to create the output TGraph2Ds
output_x = []
output_y = []
output_data = {}
output_ntoys = []
output_clserr = {}
output_signif = {}
# One list of Z-values per contour
for contour in contours:
output_data[contour] = []
output_clserr[contour] = []
output_signif[contour] = []
# Also keep track of the number of model points which have met the
# CLs criteria
total_points = 0
complete_points = 0
for key, val in file_dict.iteritems():
total_points += 1
name = '%s.%s.%s.%s' % (POIs[0], key[0], POIs[1], key[1])
files = [x for x in val.values() if plot.TFileIsGood(x)]
# Merge the HypoTestResult objects from each file into one
res = self.GetCombinedHypoTest(files)
# Do the validation of this model point
#
ok, point_res = self.ValidateHypoTest(
res,
min_toys=min_toys,
max_toys=max_toys,
contours=contours,
signif=signif,
cl=cl,
output=self.args.output,
verbose=verbose) if res is not None else (False, {
"ntoys": 0
})
print '>> Point %s [%i toys, %s]' % (
name, point_res['ntoys'], 'DONE' if ok else 'INCOMPLETE')
if ok:
complete_points += 1
# Make plots of the test statistic distributions if requested
if res is not None and make_plots:
self.PlotTestStat(res,
'plot_' + name,
opts=cfg['plot_settings'],
poi_vals=(float(key[0]), float(key[1])))
# Add the resulting CLs values to the output arrays. Normally just
# for the model points that passed the validation criteria, but if "output_incomplete"
# has been set to true then we'll write all model points where at least one HypoTestResult
# is present
if res is not None and (ok or incomplete) and self.args.output:
output_x.append(float(key[0]))
output_y.append(float(key[1]))
output_ntoys.append(point_res['ntoys'])
for contour in contours:
output_data[contour].append(point_res[contour][0])
output_clserr[contour].append(point_res[contour][1])
output_signif[contour].append(point_res[contour][2])
# Do the job cycle generation if requested
if not ok and self.args.cycles > 0:
print '>>> Going to generate %i job(s) for point %s' % (
self.args.cycles, key)
# Figure out the next seed numbers we need to run by finding the maximum seed number
# so far
done_cycles = val.keys()
new_idx = max(done_cycles) + 1 if len(done_cycles) > 0 else 1
new_cycles = range(new_idx, new_idx + self.args.cycles)
print '>>> Done cycles: ' + ','.join(
str(x) for x in done_cycles)
print '>>> New cycles: ' + ','.join(str(x) for x in new_cycles)
# Build to combine command. Here we'll take responsibility for setting the name and the
# model parameters, making sure the latter are frozen
set_arg = ','.join(
['%s=%s,%s=%s' %
(POIs[0], key[0], POIs[1], key[1])] + to_set)
freeze_arg = ','.join(['%s,%s' % (POIs[0], POIs[1])] +
to_freeze)
point_args = '-n .%s --setPhysicsModelParameters %s --freezeNuisances %s' % (
name, set_arg, freeze_arg)
# Build a command for each job cycle setting the number of toys and random seed and passing through any other
# user options from the config file or the command line
for idx in new_cycles:
cmd = ' '.join([
'combine -M HybridNew', opts, point_args,
'-T %i' % toys_per_cycle,
'-s %i' % idx
] + self.passthru)
self.job_queue.append(cmd)
print ">> %i/%i points have completed and require no further toys" % (
complete_points, total_points)
self.flush_queue()
# Create and write output CLs TGraph2Ds here
# TODO: add graphs with the CLs errors, the numbers of toys and whether or not the point passes
if self.args.output:
fout = ROOT.TFile(outfile, 'RECREATE')
for c in contours:
graph = ROOT.TGraph2D(len(output_data[c]),
array('d',
output_x), array('d', output_y),
array('d', output_data[c]))
graph.SetName(c)
fout.WriteTObject(graph, c)
# Also write a Graph with the CLsErr
graph = ROOT.TGraph2D(len(output_clserr[c]),
array('d', output_x),
array('d', output_y),
array('d', output_clserr[c]))
graph.SetName('clsErr_' + c)
fout.WriteTObject(graph, 'clsErr_' + c)
# And a Graph with the significance
graph = ROOT.TGraph2D(len(output_signif[c]),
array('d', output_x),
array('d', output_y),
array('d', output_signif[c]))
graph.SetName('signif_' + c)
fout.WriteTObject(graph, 'signif_' + c)
graph = ROOT.TGraph2D(len(output_ntoys), array('d', output_x),
array('d', output_y),
array('d', output_ntoys))
graph.SetName('ntoys' + c)
fout.WriteTObject(graph, 'ntoys')
fout.Close()
def run_method(self):
ROOT.PyConfig.IgnoreCommandLineOptions = True
ROOT.gROOT.SetBatch(ROOT.kTRUE)
# Open the json config file
with open(self.args.config) as json_file:
cfg = json.load(json_file)
# Set all the parameter values locally using defaults if necessary
grids = cfg['grids']
grids_to_remove = cfg.get('grids_to_remove', None)
POIs = cfg['POIs']
opts = cfg['opts']
toys_per_cycle = cfg['toys_per_cycle']
zipname = cfg.get('zipfile', None)
statfile = cfg.get('statusfile', None)
contours = cfg.get('contours',
['obs', 'exp-2', 'exp-1', 'exp0', 'exp+1', 'exp+2'])
min_toys = cfg.get('min_toys', 500)
max_toys = cfg.get('max_toys', 5000)
signif = cfg.get('signif', 3.0)
cl = cfg.get('CL', 0.95)
verbose = cfg.get('verbose', False)
make_plots = cfg.get('make_plots', False)
# Write CLs values into the output even if current toys do not pass validation
incomplete = cfg.get('output_incomplete', False)
outfile = cfg.get('output', 'hybrid_grid.root')
from_asymptotic_settings = cfg.get('from_asymptotic_settings', dict())
# NB: blacklisting not yet implemented for this method
# Have to merge some arguments from both the command line and the "opts" in the json file
to_freeze = []
to_set = []
set_opt, opts = self.extract_arg('--setPhysicsModelParameters', opts)
if set_opt is not None: to_set.append(set_opt)
freeze_opt, opts = self.extract_arg('--freezeNuisances', opts)
if freeze_opt is not None: to_freeze.append(freeze_opt)
if hasattr(self.args, 'setPhysicsModelParameters'
) and self.args.setPhysicsModelParameters is not None:
to_set.append(self.args.setPhysicsModelParameters)
if hasattr(
self.args,
'freezeNuisances') and self.args.freezeNuisances is not None:
to_freeze.append(self.args.freezeNuisances)
points = []
blacklisted_points = []
# For the automatic grid for the "from_asymptotic option" we should fix the format specifier for
# the grid points, as the numerical precision of a given point may change once the grid spacing is
# modified. By default we let split_vals do it's thing however
fmt_spec = None
# In this mode we're doing a classic limit search vs MH instead of a 2D grid.
# Most of the same code can be used however. First we'll use the json file containing the
# asymptotic limits to create a new grid from scratch.
if self.args.from_asymptotic is not None:
grids = []
bound_vals = None
bound_pars = []
fmt_spec = '%.5g'
with open(self.args.from_asymptotic) as limit_json:
limits = json.load(limit_json)
for m in limits.keys():
limit_vals = [x for x in limits[m].values()]
max_limit = max(limit_vals)
min_limit = min(limit_vals)
# print (min_limit, max_limit)
width = max_limit - min_limit
max_limit += width * 0.3
min_limit = max(0.0, min_limit - width * 0.3)
nsteps = from_asymptotic_settings.get('points', 100)
step_width = (max_limit - min_limit) / nsteps
grids.append(
[m, '%g:%g|%g' % (min_limit, max_limit, step_width), ''])
boundlist_file = from_asymptotic_settings.get('boundlist', '')
if boundlist_file:
with open(boundlist_file) as json_file:
bnd = json.load(json_file)
bound_pars = list(bnd.keys())
print 'Found bounds for parameters %s' % ','.join(
bound_pars)
bound_vals = {}
for par in bound_pars:
bound_vals[par] = list()
for mass, bounds in bnd[par].iteritems():
bound_vals[par].append(
(float(mass), bounds[0], bounds[1]))
bound_vals[par].sort(key=lambda x: x[0])
# print (min_limit, max_limit)
# sys.exit(0)
for igrid in grids:
assert (len(igrid) == 3)
if igrid[2] == '':
points.extend(
itertools.product(
utils.split_vals(igrid[0], fmt_spec=fmt_spec),
utils.split_vals(igrid[1], fmt_spec=fmt_spec)))
else:
blacklisted_points.extend(
itertools.product(utils.split_vals(igrid[0]),
utils.split_vals(igrid[1]),
utils.split_vals(igrid[2])))
#In between cycles of toys we may find there's something wrong with some of the points in the grid and therefore want to remove them:
points_to_remove = []
if grids_to_remove is not None:
for igrid in grids_to_remove:
assert (len(igrid) == 2)
points_to_remove.extend(
itertools.product(utils.split_vals(igrid[0]),
utils.split_vals(igrid[1])))
for p in points_to_remove:
points.remove(p)
# This dictionary will keep track of the combine output files for each model point
file_dict = {}
for p in points:
file_dict[p] = {}
# The regex we will use to identify output files and extract POI values
rgx = re.compile(
'higgsCombine\.%s\.(?P<p1>.*)\.%s\.(?P<p2>.*)\.HybridNew\.mH.*\.(?P<toy>.*)\.root'
% (POIs[0], POIs[1]))
stats = {}
if statfile and os.path.isfile(statfile):
with open(statfile) as stat_json:
stats = json.load(stat_json)
# Can optionally copy output root files into a zip archive
# If the user has specified a zipfile we will first
# look for output files in this archive before scanning the
# current directory
if zipname:
# Open the zip file in append mode, this should also
# create it if it doesn't exist
zipf = zipfile.ZipFile(zipname, 'a')
for f in zipf.namelist():
matches = rgx.search(f)
p = (matches.group('p1'), matches.group('p2'))
seed = int(matches.group('toy'))
if p in file_dict:
if seed not in file_dict[p]:
# For each model point have a dictionary keyed on the seed number
# with a value pointing to the file in the archive in the format
# ROOT expects: "zipfile.zip#higgsCombine.blah.root"
file_dict[p][seed] = zipname + '#' + f
# Now look for files in the local directory
for f in glob.glob('higgsCombine.%s.*.%s.*.HybridNew.mH*.root' %
(POIs[0], POIs[1])):
matches = rgx.search(f)
p = (matches.group('p1'), matches.group('p2'))
seed = int(matches.group('toy'))
if p in file_dict:
# Don't add this file to the list if its seed number is already
# a value in the dict.
if seed not in file_dict[p]:
# If we're using the zipfile we'll add this now and
# then delete it from the local directory
# But: only in the file is good, we don't want to pollute the zip
# file with incomplete or failed jobs
if zipname and plot.TFileIsGood(f):
zipf.write(f) # assume this throws if it fails
print 'Adding %s to %s' % (f, zipname)
file_dict[p][seed] = zipname + '#' + f
os.remove(f)
else: # otherwise just add the file to the dict in the normal way
file_dict[p][seed] = f
if zipname:
zipf.close()
# These lists will keep track of the CLs values which we will use
# to create the output TGraph2Ds
output_x = []
output_y = []
output_data = {}
output_ntoys = []
output_clserr = {}
output_signif = {}
# One list of Z-values per contour
for contour in contours:
output_data[contour] = []
output_clserr[contour] = []
output_signif[contour] = []
# Also keep track of the number of model points which have met the
# CLs criteria
total_points = 0
complete_points = 0
for key, val in file_dict.iteritems():
status_changed = True
total_points += 1
status_key = ':'.join(key)
name = '%s.%s.%s.%s' % (POIs[0], key[0], POIs[1], key[1])
# First check if we use the status json
all_files = val.values()
status_files = []
files = []
if status_key in stats:
status_files = stats[status_key]['files']
if set(all_files) == set(status_files):
print 'For point %s, no files have been updated' % name
status_changed = False
files = all_files
else:
files = [x for x in val.values() if plot.TFileIsGood(x)]
if set(files) == set(
status_files) and len(files) < len(all_files):
print 'For point %s, new files exist but they are not declared good' % name
status_changed = False
else:
files = [x for x in val.values() if plot.TFileIsGood(x)]
# Merge the HypoTestResult objects from each file into one
res = None
precomputed = None
if status_key in stats and not status_changed and stats[
status_key]["ntoys"] > 0:
precomputed = stats[status_key]
else:
res = self.GetCombinedHypoTest(files)
# Do the validation of this model point
#
ok, point_res = self.ValidateHypoTest(res,
min_toys=min_toys,
max_toys=max_toys,
contours=contours,
signif=signif,
cl=cl,
output=self.args.output,
verbose=verbose,
precomputed=precomputed)
print '>> Point %s [%i toys, %s]' % (
name, point_res['ntoys'], 'DONE' if ok else 'INCOMPLETE')
stats[status_key] = {'files': files, 'ntoys': point_res['ntoys']}
for cont in contours:
if cont in point_res:
stats[status_key][cont] = point_res[cont]
if ok:
complete_points += 1
# Make plots of the test statistic distributions if requested
if res is not None and make_plots:
self.PlotTestStat(res,
'plot_' + name,
opts=cfg['plot_settings'],
poi_vals=(float(key[0]), float(key[1])),
point_info=point_res)
# Add the resulting CLs values to the output arrays. Normally just
# for the model points that passed the validation criteria, but if "output_incomplete"
# has been set to true then we'll write all model points where at least one HypoTestResult
# is present
if (res is not None or precomputed
is not None) and (ok or incomplete) and self.args.output:
output_x.append(float(key[0]))
output_y.append(float(key[1]))
output_ntoys.append(point_res['ntoys'])
for contour in contours:
output_data[contour].append(point_res[contour][0])
output_clserr[contour].append(point_res[contour][1])
output_signif[contour].append(point_res[contour][2])
# Do the job cycle generation if requested
if not ok and self.args.cycles > 0:
print '>>> Going to generate %i job(s) for point %s' % (
self.args.cycles, key)
# Figure out the next seed numbers we need to run by finding the maximum seed number
# so far
done_cycles = val.keys()
new_idx = max(done_cycles) + 1 if len(done_cycles) > 0 else 1
new_cycles = range(new_idx, new_idx + self.args.cycles)
print '>>> Done cycles: ' + ','.join(
str(x) for x in done_cycles)
print '>>> New cycles: ' + ','.join(str(x) for x in new_cycles)
# Build to combine command. Here we'll take responsibility for setting the name and the
# model parameters, making sure the latter are frozen
set_arg = ','.join(
['%s=%s,%s=%s' %
(POIs[0], key[0], POIs[1], key[1])] + to_set)
freeze_arg = ','.join(['%s,%s' % (POIs[0], POIs[1])] +
to_freeze)
point_args = '-n .%s --setPhysicsModelParameters %s --freezeNuisances %s' % (
name, set_arg, freeze_arg)
if self.args.from_asymptotic:
mval = key[0]
command = []
for par in bound_pars:
# The (mass, None, None) is just a trick to make bisect_left do the comparison
# with the list of tuples in bound_var[par]. The +1E-5 is to avoid float rounding
# issues
lower_bound = bisect.bisect_left(
bound_vals[par], (float(mval) + 1E-5, None, None))
# If lower_bound == 0 this means we are at or below the lowest mass point,
# in which case we should increase by one to take the bounds from this lowest
# point
if lower_bound == 0:
lower_bound += 1
command.append(
'%s=%g,%g' %
(par, bound_vals[par][lower_bound - 1][1],
bound_vals[par][lower_bound - 1][2]))
if len(command) > 0:
point_args += (' --setPhysicsModelParameterRanges %s' %
(':'.join(command)))
# print per_mass_point_args
point_args += ' --singlePoint %s' % key[1]
point_args += ' -m %s' % mval
# Build a command for each job cycle setting the number of toys and random seed and passing through any other
# user options from the config file or the command line
for idx in new_cycles:
cmd = ' '.join([
'combine -M HybridNew', opts, point_args,
'-T %i' % toys_per_cycle,
'-s %i' % idx
] + self.passthru)
self.job_queue.append(cmd)
print ">> %i/%i points have completed and require no further toys" % (
complete_points, total_points)
self.flush_queue()
# Create and write output CLs TGraph2Ds here
# TODO: add graphs with the CLs errors, the numbers of toys and whether or not the point passes
if self.args.output and not self.args.from_asymptotic:
fout = ROOT.TFile(outfile, 'RECREATE')
for c in contours:
graph = ROOT.TGraph2D(len(output_data[c]),
array('d',
output_x), array('d', output_y),
array('d', output_data[c]))
graph.SetName(c)
fout.WriteTObject(graph, c)
# Also write a Graph with the CLsErr
graph = ROOT.TGraph2D(len(output_clserr[c]),
array('d', output_x),
array('d', output_y),
array('d', output_clserr[c]))
graph.SetName('clsErr_' + c)
fout.WriteTObject(graph, 'clsErr_' + c)
# And a Graph with the significance
graph = ROOT.TGraph2D(len(output_signif[c]),
array('d', output_x),
array('d', output_y),
array('d', output_signif[c]))
graph.SetName('signif_' + c)
fout.WriteTObject(graph, 'signif_' + c)
graph = ROOT.TGraph2D(len(output_ntoys), array('d', output_x),
array('d', output_y),
array('d', output_ntoys))
graph.SetName('ntoys' + c)
fout.WriteTObject(graph, 'ntoys')
fout.Close()
if self.args.output and self.args.from_asymptotic:
# Need to collect all the files for each mass point and hadd them:
files_by_mass = {}
for key, val in file_dict.iteritems():
if key[0] not in files_by_mass:
files_by_mass[key[0]] = list()
files_by_mass[key[0]].extend(val.values())
for m, files in files_by_mass.iteritems():
gridfile = 'higgsCombine.gridfile.%s.%s.%s.root' % (POIs[0], m,
POIs[1])
self.job_queue.append('hadd -f %s %s' %
(gridfile, ' '.join(files)))
for exp in ['', '0.025', '0.160', '0.500', '0.840', '0.975']:
self.job_queue.append(' '.join([
'combine -M HybridNew --rAbsAcc 0', opts,
'--grid %s' % gridfile,
'-n .final.%s.%s.%s' % (POIs[0], m, POIs[1]),
'-m %s' % (m), ('--expectedFromGrid %s' %
exp) if exp else '--noUpdateGrid'
] + self.passthru))
self.flush_queue()
if statfile:
with open(statfile, 'w') as stat_out:
stat_json = json.dumps(stats,
sort_keys=True,
indent=2,
separators=(',', ': '))
stat_out.write(stat_json)
