def main():
ds_helper = DatasetHelper()
json_fpath = os.path.join(GIT_REPO_DIR,
'GenReader/data/JSON/datasets.json')
ds_helper.load(json_fpath)
if args.list:
print "---Available Samples---"
for name in sorted(ds_helper.list()):
print "{name}".format(name=name)
return
if len(args.datasets) == 0:
print "No datasets specified, exiting..."
return
for name in args.datasets:
if not ds_helper.exists(name):
print "Unknown dataset: {name}".format(name)
continue
ds_helper.dump(name)
if args.nfiles:
lst = ds_helper.getFiles(name)
max_idx = len(lst) if args.nfiles < 0 else min(
args.nfiles, len(lst))
for idx, fn in enumerate(lst):
if idx >= args.nfiles and args.nfiles > 0:
break
print "[{0}/{1}] {fpath}".format(idx + 1, max_idx, fpath=fn)
def main():
if args.list:
ds_helper = DatasetHelper()
json_fpath = os.path.join(GIT_REPO_DIR,
'GenReader/data/JSON/datasets.json')
ds_helper.load(json_fpath)
print "---Available Samples---"
for sample_name in sorted(ds_helper.list()):
print "{name}".format(name=sample_name)
return
if len(args.datasets) == 0:
print "No samples specified, exiting..."
return
lst = args.datasets
if args.test and len(lst) > 1:
print "WARNING: Only running over the first sample when in 'test' mode"
lst = [lst[0]]
max_events = args.nevents
norm_type = 1
intg_lumi = 1.0
#base_cmd = ["cmsRun","EFTGenReader_cfg.py"]
base_cmd = ["cmsRun", "EFTSelectionAnalyzer_cfg.py"]
width = 1
if len(lst) >= 10:
width = 2
for idx, ds_name in enumerate(lst):
print "\nProcessing dataset {0}... [{1:0>{w}}/{2}]".format(ds_name,
idx + 1,
len(lst),
w=width)
full_cmd = [x for x in base_cmd]
full_cmd.append("maxEvents={}".format(max_events))
full_cmd.append("normType={}".format(norm_type))
full_cmd.append("intgLumi={}".format(intg_lumi))
full_cmd.append("fnSuffix={}".format(args.out_suffix))
if args.test:
full_cmd.append("test=True")
# Add kinematic cut options
if args.minptj:
full_cmd.append("minPtJet={}".format(args.minptj))
if args.minptl:
full_cmd.append("minPtLep={}".format(args.minptl))
if args.maxetaj:
full_cmd.append("maxEtaJet={}".format(args.maxetaj))
if args.maxetal:
full_cmd.append("maxEtaLep={}".format(args.maxetal))
full_cmd.append("dataset={}".format(ds_name))
print "Full Command: {}".format(" ".join(full_cmd))
subprocess.check_call(full_cmd)
VarParsing.VarParsing.multiplicity.singleton,
VarParsing.VarParsing.varType.float,
"max eta cut for genleptons (-1 means no cut)")
# Get and parse the command line arguments
options.parseArguments()
nd_redirect = "root://ndcms.crc.nd.edu/"
fnal_redirect = "root://cmsxrootd.fnal.gov/"
global_redirect = "root://cms-xrd-global.cern.ch/"
cmssw_base_dir = os.environ['CMSSW_BASE']
dataset_fpath = os.path.join(
cmssw_base_dir, "src/EFTGenReader/GenReader/data/JSON/datasets.json")
ds_helper = DatasetHelper()
ds_helper.load(dataset_fpath)
ds_helper.root_redirect = nd_redirect
from Configuration.StandardSequences.Eras import eras
process = cms.Process("Demo", eras.Run2_2017)
process.load('FWCore.MessageService.MessageLogger_cfi')
process.maxEvents = cms.untracked.PSet(
input=cms.untracked.int32(options.maxEvents) # number of events
)
process.MessageLogger.cerr.FwkReport.reportEvery = 500
ds_name = options.dataset
"gsiftp://T3_US_NotreDame" + output_path,
"srm://T3_US_NotreDame" + output_path,
], )
processing = Category(
name='processing',
#mode='fixed',
cores=1,
memory=1200,
#disk=1000
#disk=2900
disk=6000)
wf = []
ds_helper = DatasetHelper()
ds_helper.load(os.path.join(GIT_REPO_DIR, "GenReader/data/JSON/datasets.json"))
width = 1
samples = [
#'central_tZq',
#'central_tZq_new_pmx_v2',
#'central_ttH',
#'central_ttW',
#'central_ttZ',
#'tllq4fMatchedNoSchanW_fromMAOD_nJetMax1',
#'tllq4fMatchedNoSchanW_fromGEN_nJetMax1',
#'tllq4fMatchedNoSchanW_fromGEN_nJetMax2',
#'tllq4fMatchedNoSchanW_fromGEN_nJetMax2doublecheck',
#'tllq4fMatchedNoSchanW_fromMAOD_nJetMax2',
#'tllq4fMatchedNoHiggs_fromMAOD',
"root://deepthought.crc.nd.edu/" +
output_path, # Note the extra slash after the hostname!
"gsiftp://T3_US_NotreDame" + output_path,
"srm://T3_US_NotreDame" + output_path,
"file:///hadoop" + output_path,
])
processing = Category(name='processing',
cores=1,
memory=1200,
disk=1000,
mode='fixed')
wf = []
ds_helper = DatasetHelper()
ds_helper.load(os.path.join(GIT_REPO_DIR, "GenReader/data/JSON/datasets.json"))
width = 1
samples = ['central_tZq']
print "Generating workflows:"
for idx, sample_name in enumerate(samples):
if not ds_helper.exists(sample_name):
print "[{0:0>{w}}/{1:0>{w}}] Skipping unknown sample: {sample}".format(
idx + 1, len(samples), sample=sample_name, w=width)
continue
if not ds_helper.getData(sample_name, 'on_das'):
print "[{0:0>{w}}/{1:0>{w}}] Skipping non-DAS sample: {sample}".format(
idx + 1, len(samples), sample=sample_name, w=width)
continue