return output def postprocess(self, accumulator): return accumulator if __name__ == '__main__': from Tools.config_helpers import redirector_ucsd from Tools.nano_mapping import make_fileset from processors.default_accumulators import desired_output year = 2018 fileset = make_fileset(['Data'], year, redirector=redirector_ucsd, small=False) exe_args = { 'workers': 8, 'function_args': { 'flatten': False }, "schema": NanoAODSchema, "skipbadfiles": True, } exe = processor.futures_executor output = processor.run_uproot_job( fileset, "Events",
for sample in fileset: meta[sample] = meta_output[sample] good_files = [] skipped_files = [] for rootfile in fileset[sample]: if meta_output[rootfile]: good_files.append(rootfile) else: skipped_files.append(rootfile) meta[sample]['good_files'] = good_files meta[sample]['n_good'] = len(good_files) meta[sample]['bad_files'] = skipped_files meta[sample]['n_bad'] = len(skipped_files) meta[sample]['xsec'] = samples[sample]['xsec'] return meta if __name__ == '__main__': from Tools.config_helpers import redirector_ucsd, redirector_fnal from Tools.nano_mapping import make_fileset, nano_mapping fileset = make_fileset(['QCD'], redirector=redirector_ucsd, small=False) meta = get_sample_meta(fileset) import pandas as pd df = pd.DataFrame(meta) print(df.transpose())
import uproot from Tools.helpers import get_samples from Tools.config_helpers import redirector_ucsd, redirector_fnal from Tools.nano_mapping import make_fileset, nano_mapping samples = get_samples() fileset = make_fileset(['QCD'], samples, redirector=redirector_ucsd, small=False, year='UL2018') good = [] bad = [] for sample in list(fileset.keys()): for f_in in fileset[sample]: print(f_in) try: tree = uproot.open(f_in)["Events"] good.append(f_in) except OSError: print("XRootD Error") bad.append(f_in)
import uproot from Tools.helpers import get_samples from Tools.config_helpers import redirector_ucsd, redirector_fnal from Tools.nano_mapping import make_fileset, nano_mapping samples = get_samples(f_in='samples_QCD.yaml') fileset = make_fileset(['QCD'], samples, redirector=redirector_ucsd, small=False) print(fileset) <<<<<<< HEAD good = [] bad = [] #breakpoint() for n in range(len(list(fileset.keys()))): for f_in in fileset[list(fileset.keys())[n]]: ======= fileset = make_fileset(['TTW'], samples, redirector=redirector_ucsd, small=False) good = [] bad = [] for sample in list(fileset.keys()): for f_in in fileset[sample]: >>>>>>> 6987d93c61482b8369a70afe8a3071d806185974 print (f_in) try: tree = uproot.open(f_in)["Events"] good.append(f_in)
# load the config and the cache cfg = loadConfig() cacheName = 'nano_analysis' cache = dir_archive(os.path.join(os.path.expandvars(cfg['caches']['base']), cacheName), serialized=True) histograms = sorted(list(desired_output.keys())) year = 2018 samples = get_samples() fileset = make_fileset(['QCD'], samples, redirector=redirector_ucsd, small=True) meta = get_sample_meta(fileset, samples) add_processes_to_output(fileset, desired_output) desired_output.update({ "single_mu_fakeable": hist.Hist("Counts", dataset_axis, pt_axis, eta_axis), "single_mu": hist.Hist("Counts", dataset_axis, pt_axis, eta_axis) }) exe_args = { 'workers': 16,
import uproot from Tools.helpers import get_samples from Tools.config_helpers import redirector_ucsd, redirector_fnal from Tools.nano_mapping import make_fileset, nano_mapping samples = get_samples() fileset = make_fileset(['top'], samples, redirector=redirector_ucsd, small=False) good = [] bad = [] for f_in in fileset[list(fileset.keys())[0]]: print(f_in) try: tree = uproot.open(f_in)["Events"] good.append(f_in) except OSError: print("XRootD Error") bad.append(f_in)
# load the config and the cache cfg = loadConfig() cacheName = 'charge_flip_calc' cache = dir_archive(os.path.join(os.path.expandvars(cfg['caches']['base']), cacheName), serialized=True) histograms = sorted(list(desired_output.keys())) year = 2018 samples = get_samples() fileset = make_fileset(['TTW', 'TTZ'], samples, redirector=redirector_ucsd, small=True) add_processes_to_output(fileset, desired_output) if local: exe_args = { 'workers': 16, 'function_args': { 'flatten': False }, "schema": NanoAODSchema, } exe = processor.futures_executor
local = True # load the config and the cache cfg = loadConfig() cacheName = 'charge_flip_check' cache = dir_archive(os.path.join(os.path.expandvars(cfg['caches']['base']), cacheName), serialized=True) histograms = sorted(list(desired_output.keys())) year = 2018 samples = get_samples(2018) #fileset = make_fileset(['TTW', 'TTZ'], samples, redirector=redirector_ucsd, small=True, n_max=5) # small, max 5 files per sample #fileset = make_fileset(['DY'], samples, redirector=redirector_ucsd, small=True, n_max=10) fileset = make_fileset(['top', 'DY',], redirector=redirector_ucsd, small=False) add_processes_to_output(fileset, desired_output) #meta = get_sample_meta(fileset, samples) if local: exe_args = { 'workers': 16, 'function_args': {'flatten': False}, 'schema': NanoAODSchema, 'skipbadfiles': True, } exe = processor.futures_executor
cfg = loadConfig() cacheName = 'nano_analysis' cache = dir_archive(os.path.join(os.path.expandvars(cfg['caches']['base']), cacheName), serialized=True) histograms = sorted(list(desired_output.keys())) year = 2018 samples = get_samples() #fileset = make_fileset(['TTW', 'TTZ'], samples, redirector=redirector_ucsd, small=True, n_max=5) # small, max 5 files per sample #fileset = make_fileset(['DY'], samples, redirector=redirector_ucsd, small=True, n_max=10) fileset = make_fileset(['top', 'DY', 'TTZ'], samples, redirector=redirector_fnal, small=True) add_processes_to_output(fileset, desired_output) pt_axis_coarse = hist.Bin("pt", r"$p_{T}$ (GeV)", [15, 40, 60, 80, 100, 200, 300]) eta_axis_coarse = hist.Bin("eta", r"$\eta$", [0, 0.8, 1.479, 2.5]) desired_output.update({ "gen_matched_electron": hist.Hist("Counts", dataset_axis, pt_axis_coarse, eta_axis_coarse), "flipped_electron": hist.Hist("Counts", dataset_axis, pt_axis_coarse, eta_axis_coarse), })