file_names = [
#
# CvsL
#
('CvsL_76_17Jan/ROCs/5565121efc_ROCs.root', '7.6 Optimization'),
('test/ROCs.root', 'separate testing'),
#
# CvsB
#
# ('CvsB_76_18Jan/ROCs/82d2a6148a_ROCs.root', '7.5 Optimization'),
# ('CvsB_76_18Jan/ROCs/ff481cb37f_ROCs.root', '7.6 Optimization'),
]
output = 'test/test.png'
if args.input:
jconf = prettyjson.loads(open(args.input[-1]).read())
file_names = [tuple(i) for i in jconf['file_names']]
output = jconf['output']
graph_path = jconf['graph_path']
#dump configuration in json for bookkeeping
jconf = {
'file_names' : file_names,
'output' : output,
'graph_path' : graph_path,
}
jout = output.split('.')[0]
with open('%s.json' % jout, 'w') as out:
out.write(prettyjson.dumps(jconf))
def processNtuple(infile_name, outfile_name, variables, sample,
flav_weight=False, pteta_weight=False, cat_weight=False,
tag=''):
log.debug("processing %s --> %s" % (infile_name, outfile_name))
type_dict = {
'i' : int,
'l' : long,
'f' : float
}
fname_regex = re.compile('[a-zA-Z_0-9\/]*\/?[a-zA-Z_0-9]+_(?P<category>[a-zA-Z]+)_(?P<flavor>[A-Z]+)\.root')
match = fname_regex.match(infile_name)
if not match:
raise ValueError("Could not match the regex to the file %s" % infile_name)
flavor = match.group('flavor')
full_category = match.group('category')
weight_tfile = None
flav_dir = None
tfile_category = ''
if pteta_weight or flav_weight or cat_weight:
weight_tfile = io.root_open('data/%s_weights.root' % sample)
flav_dir = weight_tfile.Get(flavor)
categories = [i.name for i in flav_dir.keys()]
#match existing categories to this one, which might be a subset of general category stored in the root file
tfile_category = [i for i in categories if i in full_category][0]
weights = None
if pteta_weight:
weights = flav_dir.Get('%s/kin' % tfile_category)
flavor_weight = 1.
if flav_weight:
flavor_weight = prettyjson.loads(
weight_tfile.flavour_weights.String().Data()
)[flavor]
#put bias weights
category_weights = None
if cat_weight:
category_weights = flav_dir.Get('%s/bias' % tfile_category)
with io.root_open(outfile_name, 'recreate') as outfile:
outtree = Tree('tree', title='c-tagging training tree')
branches_def = dict((name, info['type']) for name, info in variables.iteritems())
if pteta_weight:
branches_def['kinematic_weight'] = 'F'
branches_def['total_weight'] = 'F'
if flav_weight:
branches_def['flavour_weight'] = 'F'
branches_def['total_weight'] = 'F'
if cat_weight:
branches_def['slcategory_weight'] = 'F'
branches_def['total_weight'] = 'F'
outtree.create_branches(
branches_def
)
with io.root_open(infile_name) as infile:
intree = infile.Get(full_category)
for e_idx, entry in enumerate(intree):
if e_idx % 1000 == 0:
log.debug("processing entry: %i" % e_idx)
for name, info in variables.iteritems():
value = info['default']
try:
if 'var' in info and hasattr(entry, info['var']):
var = getattr(entry, info['var'])
vtype = type_dict[info['type'].lower()]
if 'idx' in info:
if var.size() > info['idx']:
value = vtype(var[info['idx']])
else:
value = vtype(var)
elif 'fcn' in info:
vtype = type_dict[info['type'].lower()]
fcn = globals()[info['fcn']]
value = vtype(fcn(entry, *info['args']))
except:
set_trace()
# else:
# set_trace()
# raise RuntimeError("something went wrong processing variable %s" % name)
#if value is nan, then set to default (maybe better if you skip the whole jet)
value = info['default'] if math.isnan(value) else value
setattr(outtree, name, value)
total_weight = 1.
if pteta_weight:
bin_idx = weights.FindFixBin(entry.jetPt, abs(entry.jetEta))
outtree.kinematic_weight = weights[bin_idx].value
total_weight *= weights[bin_idx].value
if flav_weight:
outtree.flavour_weight = flavor_weight
total_weight *= flavor_weight
if cat_weight:
bin_idx = category_weights.FindFixBin(entry.jetPt, abs(entry.jetEta))
outtree.slcategory_weight = category_weights[bin_idx].value
total_weight *= category_weights[bin_idx].value
if 'total_weight' in branches_def:
outtree.total_weight = total_weight
#set_trace()
outtree.Fill()
log.info("processing done [%s]" % tag)
def processNtuple(infile_name, outfile_name, sample,
flav_weight=False, pteta_weight=False, cat_weight=False,
tag=''):
log.debug("processing %s --> %s" % (infile_name, outfile_name))
fname_regex = re.compile('[a-zA-Z_0-9\/]*\/?[a-zA-Z_0-9]+_(?P<category>[a-zA-Z]+)_(?P<flavor>[A-Z]+)\.root')
match = fname_regex.match(infile_name)
if not match:
raise ValueError("Could not match the regex to the file %s" % infile_name)
flavor = match.group('flavor')
full_category = match.group('category')
weight_tfile = None
flav_dir = None
tfile_category = ''
if pteta_weight or flav_weight or cat_weight:
weight_tfile = io.root_open('../data_trees/%s_weights.root' % sample)
flav_dir = weight_tfile.Get(flavor)
categories = [i.name for i in flav_dir.keys()]
#match existing categories to this one, which might be a subset of general category stored in the root file
tfile_category = [i for i in categories if i in full_category][0]
weights = None
if pteta_weight:
weights = flav_dir.Get('%s/kin' % tfile_category)
flavor_weight = 1.
if flav_weight:
flavor_weight = prettyjson.loads(
weight_tfile.flavour_weights.String().Data()
)[flavor]
#put bias weights
category_weights = None
if cat_weight:
category_weights = flav_dir.Get('%s/bias' % tfile_category)
print "Starting to process %s" %infile_name
# make copy of input ntuple to be safe and work with that
print "copying %s to %s" %(infile_name, outfile_name)
shutil.copy2("%s" %(infile_name), "%s"%(outfile_name))
# retrieve the ntuple of interest
inFile = TFile.Open( "%s" %(outfile_name), "update" ) # this now uses the copied file in outDirName
inTreeName = "ttree"
myTree = inFile.Get( inTreeName )
#create new branches
weight_etaPt = array( "f", [ 0. ] )
weight_category = array( "f", [ 0. ] )
weight_flavour = array( "f", [ 0. ] )
weight = array( "f", [ 0. ] )
b_weight_etaPt = myTree.Branch( "weight_etaPt", weight_etaPt, 'weight_etaPt/F' )
b_weight_category = myTree.Branch( "weight_category", weight_category, 'weight_category/F' )
b_weight_flavour = myTree.Branch( "weight_flavour", weight_flavour, 'weight_flavour/F' )
b_weight = myTree.Branch( "weight", weight, 'weight/F' )
# connect branches needed for weight calculation
Jet_pt = array( "f", [ 0. ] )
Jet_eta = array( "f", [ 0. ] )
myTree.SetBranchAddress( 'Jet_pt', Jet_pt )
myTree.SetBranchAddress( 'Jet_eta', Jet_eta )
### actual loop ###
entries = myTree.GetEntriesFast()
print "%s: Starting event loop" %(multiprocessing.current_process().name)
startTime = time.time()
for ientry in xrange(entries):
# get the next tree in the chain and verify
myTree.GetEntry(ientry)
# timing
reportEveryNevents = 50000
if (ientry%reportEveryNevents==0):
if (ientry != 0):
print "%s: Progress: %3.1f%%" %(multiprocessing.current_process().name, float(ientry)/(entries)*100)
endTime = time.time()
deltaTime = endTime - startTime
rate = float(reportEveryNevents)/deltaTime
print "%s: current rate: %5.2f Hz" %(multiprocessing.current_process().name, rate)
startTime = time.time()
# obtain the different weights
weight[0] = 1.
if pteta_weight:
bin_idx = weights.FindFixBin(Jet_pt[0], abs(Jet_eta[0]))
weight_etaPt[0] = weights[bin_idx].value
weight[0] *= weights[bin_idx].value
if flav_weight:
weight_flavour[0] = flavor_weight
weight[0] *= flavor_weight
if cat_weight:
bin_idx = category_weights.FindFixBin(Jet_pt[0], abs(Jet_eta[0]))
weight_category[0] = category_weights[bin_idx].value
weight[0] *= category_weights[bin_idx].value
# and fill the branches
b_weight_etaPt.Fill()
b_weight_category.Fill()
b_weight_flavour.Fill()
b_weight.Fill()
inFile.Write()
inFile.Close()
print "%s: Total time: %5.2f s" %(multiprocessing.current_process().name, time.clock())
from argparse import ArgumentParser
import rootpy.io as io
from rootpy.plotting import Hist2D
import prettyjson
import glob
import re
import rootpy
from pdb import set_trace
import copy
import binning
import ROOT
log = rootpy.log["/compute_weights"]
log.setLevel(rootpy.log.INFO)
qcd_yields = prettyjson.loads(open('data/qcd_yields.json' ).read())
ttj_yields = prettyjson.loads(open('data/ttjets_yields.json').read())
biased_qcd = copy.deepcopy(qcd_yields)
cat_weight = copy.deepcopy(qcd_yields)
bin_weight = copy.deepcopy(qcd_yields)
flavours = qcd_yields.keys()
categories = qcd_yields[flavours[0]].keys()
bins = qcd_yields[flavours[0]][categories[0]].keys()
total_yield = sum( k for i in qcd_yields.itervalues() for j in i.itervalues() for k in j.itervalues() ) #sum( k for k in j.itervalues() for j in i.itervalues() for i in qcd_yields.itervalues() )
flav_weights = {}
from argparse import ArgumentParser
import rootpy.io as io
from rootpy.plotting import Hist2D
import prettyjson
import glob
import re
import rootpy
from pdb import set_trace
import copy
import binning
import ROOT
log = rootpy.log["/compute_weights"]
log.setLevel(rootpy.log.INFO)
qcd_yields = prettyjson.loads(open('../data_trees/qcd_yields.json' ).read())
ttj_yields = prettyjson.loads(open('../data_trees/ttjets_yields.json').read())
biased_qcd = copy.deepcopy(qcd_yields)
cat_weight = copy.deepcopy(qcd_yields)
bin_weight = copy.deepcopy(qcd_yields)
flavours = qcd_yields.keys()
categories = qcd_yields[flavours[0]].keys()
bins = qcd_yields[flavours[0]][categories[0]].keys()
total_yield = sum( k for i in qcd_yields.itervalues() for j in i.itervalues() for k in j.itervalues() ) #sum( k for k in j.itervalues() for j in i.itervalues() for i in qcd_yields.itervalues() )
flav_weights = {}
def processNtuple(infile_name,
outfile_name,
variables,
sample,
flav_weight=False,
pteta_weight=False,
cat_weight=False,
tag=''):
log.debug("processing %s --> %s" % (infile_name, outfile_name))
type_dict = {'i': int, 'l': long, 'f': float}
fname_regex = re.compile(
'[a-zA-Z_0-9\/]*\/?[a-zA-Z_0-9]+_(?P<category>[a-zA-Z]+)_(?P<flavor>[A-Z]+)\.root'
)
match = fname_regex.match(infile_name)
if not match:
raise ValueError("Could not match the regex to the file %s" %
infile_name)
flavor = match.group('flavor')
full_category = match.group('category')
weight_tfile = None
flav_dir = None
tfile_category = ''
if pteta_weight or flav_weight or cat_weight:
weight_tfile = io.root_open('data/%s_weights.root' % sample)
flav_dir = weight_tfile.Get(flavor)
categories = [i.name for i in flav_dir.keys()]
#match existing categories to this one, which might be a subset of general category stored in the root file
tfile_category = [i for i in categories if i in full_category][0]
weights = None
if pteta_weight:
weights = flav_dir.Get('%s/kin' % tfile_category)
flavor_weight = 1.
if flav_weight:
flavor_weight = prettyjson.loads(
weight_tfile.flavour_weights.String().Data())[flavor]
#put bias weights
category_weights = None
if cat_weight:
category_weights = flav_dir.Get('%s/bias' % tfile_category)
with io.root_open(outfile_name, 'recreate') as outfile:
outtree = Tree('tree', title='c-tagging training tree')
branches_def = dict(
(name, info['type']) for name, info in variables.iteritems())
if pteta_weight:
branches_def['kinematic_weight'] = 'F'
branches_def['total_weight'] = 'F'
if flav_weight:
branches_def['flavour_weight'] = 'F'
branches_def['total_weight'] = 'F'
if cat_weight:
branches_def['slcategory_weight'] = 'F'
branches_def['total_weight'] = 'F'
outtree.create_branches(branches_def)
with io.root_open(infile_name) as infile:
intree = infile.Get(full_category)
for e_idx, entry in enumerate(intree):
if e_idx % 1000 == 0:
log.debug("processing entry: %i" % e_idx)
for name, info in variables.iteritems():
value = info['default']
try:
if 'var' in info and hasattr(entry, info['var']):
var = getattr(entry, info['var'])
vtype = type_dict[info['type'].lower()]
if 'idx' in info:
if var.size() > info['idx']:
value = vtype(var[info['idx']])
else:
value = vtype(var)
elif 'fcn' in info:
vtype = type_dict[info['type'].lower()]
fcn = globals()[info['fcn']]
value = vtype(fcn(entry, *info['args']))
except:
set_trace()
# else:
# set_trace()
# raise RuntimeError("something went wrong processing variable %s" % name)
#if value is nan, then set to default (maybe better if you skip the whole jet)
value = info['default'] if math.isnan(value) else value
setattr(outtree, name, value)
total_weight = 1.
if pteta_weight:
bin_idx = weights.FindFixBin(entry.jetPt,
abs(entry.jetEta))
outtree.kinematic_weight = weights[bin_idx].value
total_weight *= weights[bin_idx].value
if flav_weight:
outtree.flavour_weight = flavor_weight
total_weight *= flavor_weight
if cat_weight:
bin_idx = category_weights.FindFixBin(
entry.jetPt, abs(entry.jetEta))
outtree.slcategory_weight = category_weights[bin_idx].value
total_weight *= category_weights[bin_idx].value
if 'total_weight' in branches_def:
outtree.total_weight = total_weight
#set_trace()
outtree.Fill()
log.info("processing done [%s]" % tag)
file_names = [
#
# CvsL
#
('CvsL_76_17Jan/ROCs/5565121efc_ROCs.root', '7.6 Optimization'),
('test/ROCs.root', 'separate testing'),
#
# CvsB
#
# ('CvsB_76_18Jan/ROCs/82d2a6148a_ROCs.root', '7.5 Optimization'),
# ('CvsB_76_18Jan/ROCs/ff481cb37f_ROCs.root', '7.6 Optimization'),
]
output = 'test/test.png'
if args.input:
jconf = prettyjson.loads(open(args.input[-1]).read())
file_names = [tuple(i) for i in jconf['file_names']]
output = jconf['output']
graph_path = jconf['graph_path']
#dump configuration in json for bookkeeping
jconf = {
'file_names': file_names,
'output': output,
'graph_path': graph_path,
}
jout = output.split('.')[0]
with open('%s.json' % jout, 'w') as out:
out.write(prettyjson.dumps(jconf))
