def test_rochester():
rochester_data = lookup_tools.txt_converters.convert_rochester_file('tests/samples/RoccoR2018.txt.gz',loaduncs=True)
rochester = lookup_tools.rochester_lookup.rochester_lookup(rochester_data)
# to test 1-to-1 agreement with official Rochester requires loading C++ files
# instead, preload the correct scales in the sample directory
# the script tests/samples/rochester/build_rochester.py produces these
official_data_k = np.load('tests/samples/nano_dimuon_rochester.npy')
official_data_err = np.load('tests/samples/nano_dimuon_rochester_err.npy')
official_mc_k = np.load('tests/samples/nano_dy_rochester.npy')
official_mc_err = np.load('tests/samples/nano_dy_rochester_err.npy')
mc_rand = np.load('tests/samples/nano_dy_rochester_rand.npy')
# test against nanoaod
events = NanoEvents.from_file(os.path.abspath('tests/samples/nano_dimuon.root'))
data_k = rochester.kScaleDT(events.Muon.charge, events.Muon.pt, events.Muon.eta, events.Muon.phi)
assert(all(np.isclose(data_k.flatten(), official_data_k)))
data_err = rochester.kScaleDTerror(events.Muon.charge, events.Muon.pt, events.Muon.eta, events.Muon.phi)
data_err = np.array(data_err.flatten(), dtype=float)
assert(all(np.isclose(data_err, official_data_err, atol=1e-8)))
# test against mc
events = NanoEvents.from_file(os.path.abspath('tests/samples/nano_dy.root'))
hasgen = ~np.isnan(events.Muon.matched_gen.pt.fillna(np.nan))
mc_rand = JaggedArray.fromoffsets(hasgen.offsets, mc_rand)
mc_kspread = rochester.kSpreadMC(events.Muon.charge[hasgen], events.Muon.pt[hasgen], events.Muon.eta[hasgen], events.Muon.phi[hasgen],
events.Muon.matched_gen.pt[hasgen])
mc_ksmear = rochester.kSmearMC(events.Muon.charge[~hasgen], events.Muon.pt[~hasgen], events.Muon.eta[~hasgen], events.Muon.phi[~hasgen],
events.Muon.nTrackerLayers[~hasgen], mc_rand[~hasgen])
mc_k = np.ones_like(events.Muon.pt.flatten())
mc_k[hasgen.flatten()] = mc_kspread.flatten()
mc_k[~hasgen.flatten()] = mc_ksmear.flatten()
assert(all(np.isclose(mc_k, official_mc_k)))
mc_errspread = rochester.kSpreadMCerror(events.Muon.charge[hasgen], events.Muon.pt[hasgen], events.Muon.eta[hasgen], events.Muon.phi[hasgen],
events.Muon.matched_gen.pt[hasgen])
mc_errsmear = rochester.kSmearMCerror(events.Muon.charge[~hasgen], events.Muon.pt[~hasgen], events.Muon.eta[~hasgen], events.Muon.phi[~hasgen],
events.Muon.nTrackerLayers[~hasgen], mc_rand[~hasgen])
mc_err = np.ones_like(events.Muon.pt.flatten())
mc_err[hasgen.flatten()] = mc_errspread.flatten()
mc_err[~hasgen.flatten()] = mc_errsmear.flatten()
assert(all(np.isclose(mc_err, official_mc_err, atol=1e-8)))
def test_read_nanomc():
events = NanoEvents.from_file(os.path.abspath('tests/samples/nano_dy.root'))
# test after views first
genroundtrips(events.GenPart[events.GenPart.eta > 0])
genroundtrips(events[(events.Electron.eta > 0).any()].GenPart)
genroundtrips(events.GenPart)
# sane gen matching (note for electrons gen match may be photon(22))
assert ((abs(events.Electron.matched_gen.pdgId) == 11) | (events.Electron.matched_gen.pdgId == 22)).all().all()
assert (abs(events.Muon.matched_gen.pdgId) == 13).all().all()
genroundtrips(events.Electron.matched_gen)
crossref(events[events.Jet.counts > 2])
crossref(events)
assert events.Photon.isTight.any().tolist()[:9] == [False, True, True, True, False, False, False, False, False]
return np.savez(npz_file, np.array(event_list), np.array(genmet_list))
if __name__ == '__main__':
parser = OptionParser()
parser.add_option('-d', '--dataset', help='dataset', dest='dataset')
(options, args) = parser.parse_args()
dataset = options.dataset
#fname = '/cms/scratch/matteoc/CMSSW_10_2_22/src/PhysicsTools/NanoMET/test/'+options.dataset+'.root'
fname = 'root://cms-xrdr.private.lo:2094//xrd/store/user/' + os.environ[
'USER'] + '/' + dataset + '.root'
print('Opening file:', fname)
events = NanoEvents.from_file(fname)
n_events = events.JetPFCands.pt.shape[0]
print('Total events:', n_events)
for i in range(n_events):
future_savez(i)
'''
with concurrent.futures.ProcessPoolExecutor(max_workers=1) as executor:
futures = set()
futures.update(executor.submit(future_savez, i) for i in range(n_events))
try:
total = len(futures)
processed = 0
while len(futures) > 0:
finished = set(job for job in futures if job.done())
for job in finished:
def _work_function(item, processor_instance, flatten=False, savemetrics=False,
mmap=False, nano=False, cachestrategy=None, skipbadfiles=False,
retries=0, xrootdtimeout=None):
if processor_instance == 'heavy':
item, processor_instance = item
if not isinstance(processor_instance, ProcessorABC):
processor_instance = cloudpickle.loads(lz4f.decompress(processor_instance))
if mmap:
localsource = {}
else:
opts = dict(uproot.FileSource.defaults)
opts.update({'parallel': None})
def localsource(path):
return uproot.FileSource(path, **opts)
import warnings
out = processor_instance.accumulator.identity()
retry_count = 0
while retry_count <= retries:
try:
from uproot.source.xrootd import XRootDSource
xrootdsource = XRootDSource.defaults
xrootdsource['timeout'] = xrootdtimeout
file = uproot.open(item.filename, localsource=localsource, xrootdsource=xrootdsource)
if nano:
cache = None
if cachestrategy == 'dask-worker':
from dask.distributed import get_worker
cache = get_worker().data
df = NanoEvents.from_file(
file=file,
treename=item.treename,
entrystart=item.index * item.chunksize,
entrystop=(item.index + 1) * item.chunksize,
metadata={'dataset': item.dataset},
cache=cache,
)
else:
tree = file[item.treename]
df = LazyDataFrame(tree, item.chunksize, item.index, flatten=flatten)
df['dataset'] = item.dataset
tic = time.time()
out = processor_instance.process(df)
toc = time.time()
metrics = dict_accumulator()
if savemetrics:
if isinstance(file.source, uproot.source.xrootd.XRootDSource):
metrics['bytesread'] = value_accumulator(int, file.source.bytesread)
metrics['dataservers'] = set_accumulator({file.source._source.get_property('DataServer')})
metrics['columns'] = set_accumulator(df.materialized)
metrics['entries'] = value_accumulator(int, df.size)
metrics['processtime'] = value_accumulator(float, toc - tic)
wrapped_out = dict_accumulator({'out': out, 'metrics': metrics})
file.source.close()
break
# catch xrootd errors and optionally skip
# or retry to read the file
except OSError as e:
if not skipbadfiles:
raise e
else:
w_str = 'Bad file source %s.' % item.filename
if retries:
w_str += ' Attempt %d of %d.' % (retry_count + 1, retries + 1)
if retry_count + 1 < retries:
w_str += ' Will retry.'
else:
w_str += ' Skipping.'
else:
w_str += ' Skipping.'
warnings.warn(w_str)
metrics = dict_accumulator()
if savemetrics:
metrics['bytesread'] = value_accumulator(int, 0)
metrics['dataservers'] = set_accumulator({})
metrics['columns'] = set_accumulator({})
metrics['entries'] = value_accumulator(int, 0)
metrics['processtime'] = value_accumulator(float, 0)
wrapped_out = dict_accumulator({'out': out, 'metrics': metrics})
except Exception as e:
if retries == retry_count:
raise e
w_str = 'Attempt %d of %d. Will retry.' % (retry_count + 1, retries + 1)
warnings.warn(w_str)
retry_count += 1
return wrapped_out
def test_read_nanodata():
events = NanoEvents.from_file(os.path.abspath('tests/samples/nano_dimuon.root'))
crossref(events)
crossref(events[events.Jet.counts > 2])
from coffea.nanoaod import NanoEvents
from hbbprocessor import HbbProcessor
from ddt_processor import DDTProcessor
from zqq_processor import ZQQProcessor
from coffea.nanoaod.methods import Candidate
events = NanoEvents.from_file(
#'root://cmseos.fnal.gov//store/user/jkrupa/nanopost_process/24Jul20/ZJetsToQQ_HT-800toInf_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8/nano_mc_2017_9ZJetsToQQ_HT-800toInf_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/group/lpcbacon/jkrupa/nanopost_process/6Aug20//WJetsToQQ_HT-800toInf_qc19_3j_TuneCP5_13TeV-madgraphMLM-pythia8/nano_mc_2017_9WJetsToQQ_HT-800toInf_qc19_3j_TuneCP5_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20/QCD_HT700to1000_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8/nano_mc_2017_9QCD_HT700to1000_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8.root',
'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20/QCD_HT700to1000_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8/nano_mc_2017_9QCD_HT700to1000_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20/ST_tW_top_5f_inclusiveDecays_TuneCP5_PSweights_13TeV-powheg-pythia8/nano_mc_2017_15ST_tW_top_5f_inclusiveDecays_TuneCP5_PSweights_13TeV-powheg-pythia8.root',
#'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20/TTToSemiLeptonic_TuneCP5_13TeV-powheg-pythia8/nano_mc_2017_1119TTToSemiLeptonic_TuneCP5_13TeV-powheg-pythia8.root',
#'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20_v2/SingleMuon_pancakes-02-withPF_Run2017D-09Aug2019_UL2017-v1/nano_data_2017_8SingleMuon_pancakes-02-withPF_Run2017D-09Aug2019_UL2017-v1.root',
#'root://cmseos.fnal.gov//store/group/lpcbacon/jkrupa/nanopost_process/6Aug20/TTToHadronic_TuneCP5_13TeV-powheg-pythia8/nano_mc_2017_99TTToHadronic_TuneCP5_13TeV-powheg-pythia8.root',
#'root://cmseos.fnal.gov//store/user/lpcbacon/jkrupa/nanopost_process/6Aug20/WJetsToLNu_TuneCP5_13TeV-madgraphMLM-pythia8/nano_mc_2017_1WJetsToLNu_TuneCP5_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/user/jkrupa/nanopost_process/27Jul20_v3/ZJetsToQQ_HT400to600_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8/nano_mc_2017_9ZJetsToQQ_HT400to600_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/user/jkrupa/nanopost_process/27Jul20_v3/ZJetsToQQ_HT400to600_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8/nano_mc_2017_98ZJetsToQQ_HT400to600_qc19_4j_TuneCP5_13TeV-madgraphMLM-pythia8.root',
#'root://cmseos.fnal.gov//store/user/jkrupa/nanopost_process/22Jul20_v2/QCD_HT2000toInf_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8/nano_mc_2017_9_Skim.root',
#entrystop=100000,
#metadata={'dataset': 'WJetsToQQ_HT-800toInf_qc19_3j_TuneCP5_13TeV-madgraphMLM-pythia8'},#,QCD_HT2000toInf_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8-test'},
#metadata={'dataset': 'QCD_HT2000toInf_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8-test'},
#metadata={'dataset':'WJetsToQQ_HT-800toInf_qc19_3j_TuneCP5_13TeV-madgraphMLM-pythia8'},#TTToSemiLeptonic_TuneCP5_13TeV-powheg-pythia8'},
metadata={'dataset': 'QCD_HT700to1000_TuneCP5_PSWeights_13TeV-madgraphMLM-pythia8'},
#metadata={'dataset': 'WJetsToLNu_TuneCP5_13TeV-madgraphMLM-pythia8'},
#methods={"FatJetPFCands": Candidate}
)
#p = HbbProcessor(year='2017')
p = ZQQProcessor(year='2017')
#p = DDTProcessor(year='2017')
out = p.process(events)
print(out)
# import uproot
batch = False
plt.style.use(hep.style.ROOT)
fname = "test.root"
fname = sys.argv[1]
if fname.startswith('/store/'):
print("Attempting to read over XRootD...")
fname = "root://xrootd-cms.infn.it//" + fname
outdir = "pkls"
os.system("mkdir -p " + outdir)
events = Events.from_file(fname)
alljets = events.Jet
def maskDC(jets):
dflt = (jets.btagDeepB < 0) | (jets.btagDeepC < 0) | (
jets.btagDeepB > 1
) | (jets.btagDeepC > 1) | (jets.btagDeepB + jets.btagDeepC > 1) | (
1 - jets.btagDeepB <= 0) | (jets.btagDeepC + jets.btagDeepB <= 0) | (
np.isnan(jets.btagDeepB)) | (np.isnan(jets.btagDeepC))
return dflt
def maskDJ(jets):
dflt = (jets.btagDeepFlavB < 0) | (jets.btagDeepFlavC < 0) | (
jets.btagDeepFlavB >= 1) | (jets.btagDeepFlavC >= 1) | (