def test_lazy_dataframe_getattr():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath('tests/samples/nano_dy.root'))['Events']
entrystart = 0
entrystop = 100
df = LazyDataFrame(tree, entrystart, entrystop, preload_items=['nMuon'])
assert (len(df) == 1)
pt = df.Muon_pt
assert (len(df) == 2)
assert ('Muon_pt' in df.materialized)
assert ('Muon_eta' in df.available)
assert (df.size == tree.num_entries)
with pytest.raises(AttributeError):
x = df.notthere
import copy
df2 = copy.copy(df)
pt = df2.Muon_pt
with pytest.raises(AttributeError):
df2.notthere
def test_lazy_dataframe_getattr():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath("tests/samples/nano_dy.root"))["Events"]
entrystart = 0
entrystop = 100
df = LazyDataFrame(tree, entrystart, entrystop, preload_items=["nMuon"])
assert len(df) == 1
df.Muon_pt
assert len(df) == 2
assert "Muon_pt" in df.materialized
assert "Muon_eta" in df.available
assert df.size == tree.num_entries
with pytest.raises(AttributeError):
df.notthere
import copy
df2 = copy.copy(df)
df2.Muon_pt
with pytest.raises(AttributeError):
df2.notthere
def test_lazy_dataframe():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath('tests/samples/nano_dy.root'))['Events']
chunksize = 20
index = 0
df = LazyDataFrame(tree, chunksize, index, preload_items=['nMuon'])
assert (len(df) == 1)
pt = df['Muon_pt']
df['Muon_pt_up'] = pt * 1.05
assert (len(df) == 3)
assert ('Muon_pt' in df.materialized)
assert (b'Muon_eta' in df.available)
assert (df.size == tree.numentries)
try:
x = df['notthere']
except KeyError:
pass
def test_lazy_dataframe_getattr():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath('tests/samples/nano_dy.root'))['Events']
chunksize = 20
index = 0
df = LazyDataFrame(tree, chunksize, index, preload_items=['nMuon'])
assert (len(df) == 1)
pt = df.Muon_pt
assert (len(df) == 2)
assert ('Muon_pt' in df.materialized)
assert (b'Muon_eta' in df.available)
assert (df.size == tree.numentries)
with pytest.raises(AttributeError):
x = df.notthere
def test_lazy_dataframe():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath("tests/samples/nano_dy.root"))["Events"]
entrystart = 0
entrystop = 100
df = LazyDataFrame(tree, entrystart, entrystop, preload_items=["nMuon"])
assert len(df) == 1
pt = df["Muon_pt"]
assert len(df) == 2
df["Muon_pt_up"] = pt * 1.05
assert len(df) == 3
assert "Muon_pt" in df.materialized
assert "Muon_eta" in df.available
assert df.size == tree.num_entries
with pytest.raises(KeyError):
df["notthere"]
def test_lazy_dataframe():
import uproot
from coffea.processor import LazyDataFrame
tree = uproot.open(osp.abspath('tests/samples/nano_dy.root'))['Events']
entrystart = 0
entrystop = 100
df = LazyDataFrame(tree, entrystart, entrystop, preload_items=['nMuon'])
assert (len(df) == 1)
pt = df['Muon_pt']
assert (len(df) == 2)
df['Muon_pt_up'] = pt * 1.05
assert (len(df) == 3)
assert ('Muon_pt' in df.materialized)
assert ('Muon_eta' in df.available)
assert (df.size == tree.num_entries)
with pytest.raises(KeyError):
x = df['notthere']
def _work_function_nanoaod(item, flatten=False, savemetrics=False, mmap=False, **_):
dataset, fn, treename, chunksize, index, processor_instance = item
if mmap:
localsource = {}
else:
opts = dict(uproot.FileSource.defaults)
opts.update({'parallel': None})
def localsource(path):
return uproot.FileSource(path, **opts)
file = uproot.open(fn, localsource=localsource)
tree = file[treename]
df = LazyDataFrame(tree, chunksize, index, flatten=flatten)
for name in file['Runs'].keys():
name = name.decode('utf-8')
if index==0:
df[name] = file['Runs'][name].array()
else:
df[name] = 0 * file['Runs'][name].array()
df['dataset'] = 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()
return wrapped_out
from awkward import JaggedArray
import numpy as np
from bucoffea.helpers import object_overlap
from bucoffea.helpers.paths import bucoffea_path
from bucoffea.helpers.gen import find_first_parent
from coffea.processor import LazyDataFrame
import uproot
fn = 'root://cmsxrootd.fnal.gov/eos/cms/store/group/phys_exotica/monojet/aalbert/nanopost/16Jul19/DYJetsToLL_M-50_HT-400to600_TuneCP5_13TeV-madgraphMLM-pythia8/DYJetsToLL_M-50_HT-400to600-MLM_2017/190717_212115/0000/tree_6.root'
file = uproot.open(fn)
tree = file['Events']
df = LazyDataFrame(tree, flatten=True)
ak4 = JaggedCandidateArray.candidatesfromcounts(
df['nJet'],
pt=df['Jet_pt'],
eta=df['Jet_eta'],
phi=df['Jet_phi'],
mass=df['Jet_mass'],
)
muons = JaggedCandidateArray.candidatesfromcounts(
df['nMuon'],
pt=df['Muon_pt'],
eta=df['Muon_eta'],
phi=df['Muon_phi'],
mass=0 * df['Muon_pt'],
)