def _analyse_delphes_sample(
self,
delete_delphes_files,
delphes_file,
generator_truth,
is_background,
k_factor,
lhe_file,
lhe_file_for_weights,
parse_lhe_events_as_xml,
reference_benchmark,
sampling_benchmark,
weight_labels,
sample_syst_names,
):
# Relevant systematics
systematics_used = OrderedDict()
if sample_syst_names is None:
sample_syst_names = []
for key in sample_syst_names:
systematics_used[key] = self.systematics[key]
if len(systematics_used) > 0 and lhe_file_for_weights is None:
raise NotImplementedError(
"Systematic uncertainties are currently only supported when the weights"
" are extracted from the LHE file (instead of the HepMC / Delphes ROOT"
" file). Please use the keyword lhe_filename when calling add_sample()."
)
# Read systematics setup from LHE file
logger.debug("Extracting nuisance parameter definitions from LHE file")
systematics_dict = extract_nuisance_parameters_from_lhe_file(
lhe_file, systematics_used)
logger.debug("systematics_dict: %s", systematics_dict)
# systematics_dict has structure
# {systematics_name : {nuisance_parameter_name : ((benchmark0, weight0), (benchmark1, weight1), processing)}}
# Store nuisance parameters
for systematics_name, nuisance_info in six.iteritems(systematics_dict):
for nuisance_parameter_name, ((benchmark0, weight0), (benchmark1,
weight1),
_) in six.iteritems(nuisance_info):
if (self.nuisance_parameters is not None
and nuisance_parameter_name in self.nuisance_parameters
and (systematics_name, benchmark0, benchmark1) !=
self.nuisance_parameters[nuisance_parameter_name]):
raise RuntimeError(
"Inconsistent information for same nuisance parameter {}. Old: {}. New: {}."
.format(
nuisance_parameter_name,
self.nuisance_parameters[nuisance_parameter_name],
(systematics_name, benchmark0, benchmark1),
))
self.nuisance_parameters[nuisance_parameter_name] = (
systematics_name, benchmark0, benchmark1)
# Calculate observables and weights in Delphes ROOT file
this_observations, this_weights, cut_filter = parse_delphes_root_file(
delphes_file,
self.observables,
self.observables_required,
self.observables_defaults,
self.cuts,
self.cuts_default_pass,
weight_labels,
use_generator_truth=generator_truth,
delete_delphes_sample_file=delete_delphes_files,
acceptance_eta_max_a=self.acceptance_eta_max_a,
acceptance_eta_max_e=self.acceptance_eta_max_e,
acceptance_eta_max_mu=self.acceptance_eta_max_mu,
acceptance_eta_max_j=self.acceptance_eta_max_j,
acceptance_pt_min_a=self.acceptance_pt_min_a,
acceptance_pt_min_e=self.acceptance_pt_min_e,
acceptance_pt_min_mu=self.acceptance_pt_min_mu,
acceptance_pt_min_j=self.acceptance_pt_min_j,
)
# No events found?
if this_observations is None:
logger.warning(
"No remaining events in this Delphes file, skipping it")
return None, None, None
if this_weights is not None:
logger.debug("Found weights %s in Delphes file",
list(this_weights.keys()))
else:
logger.debug("Did not extract weights from Delphes file")
# Sanity checks
n_events = self._check_sample_observations(this_observations)
# Find weights in LHE file
if lhe_file_for_weights is not None:
logger.debug("Extracting weights from LHE file")
_, this_weights = parse_lhe_file(
filename=lhe_file_for_weights,
sampling_benchmark=sampling_benchmark,
benchmark_names=self.benchmark_names_phys,
observables=OrderedDict(),
parse_events_as_xml=parse_lhe_events_as_xml,
systematics_dict=systematics_dict,
is_background=is_background,
)
logger.debug("Found weights %s in LHE file",
list(this_weights.keys()))
# Apply cuts
logger.debug("Applying Delphes-based cuts to LHE weights")
for key, weights in six.iteritems(this_weights):
this_weights[key] = weights[cut_filter]
if this_weights is None:
raise RuntimeError(
"Could not extract weights from Delphes ROOT file or LHE file."
)
# Sanity checks
n_events = self._check_sample_weights(n_events, this_weights)
# k factors
if k_factor is not None:
for key in this_weights:
this_weights[key] = k_factor * this_weights[key]
# Background scenario: we only have one set of weights, but these should be true for all benchmarks
if is_background:
logger.debug("Sample is background")
benchmarks_weight = list(six.itervalues(this_weights))[0]
for benchmark_name in self.benchmark_names_phys:
this_weights[benchmark_name] = benchmarks_weight
# Rescale nuisance parameters to reference benchmark
reference_weights = this_weights[reference_benchmark]
sampling_weights = this_weights[sampling_benchmark]
for key in this_weights:
if key not in self.benchmark_names_phys: # Only rescale nuisance benchmarks
this_weights[
key] = reference_weights / sampling_weights * this_weights[
key]
return this_observations, this_weights, n_events
def _analyse_delphes_sample(
self,
delete_delphes_files,
delphes_file,
generator_truth,
is_background,
k_factor,
lhe_file,
lhe_file_for_weights,
parse_lhe_events_as_xml,
reference_benchmark,
sampling_benchmark,
weight_labels,
):
# Read systematics setup from LHE file
logger.debug("Extracting nuisance parameter definitions from LHE file")
nuisance_parameters = extract_nuisance_parameters_from_lhe_file(lhe_file, self.systematics)
logger.debug("Found %s nuisance parameters with matching benchmarks:", len(nuisance_parameters))
for key, value in six.iteritems(nuisance_parameters):
logger.debug(" %s: %s", key, value)
# Compare to existing data
if self.nuisance_parameters is None:
self.nuisance_parameters = nuisance_parameters
else:
if dict(self.nuisance_parameters) != dict(nuisance_parameters):
raise RuntimeError(
"Different LHE files have different definitions of nuisance parameters / benchmarks!\n"
"Previous: {}\nNew:{}".format(self.nuisance_parameters, nuisance_parameters)
)
# Calculate observables and weights in Delphes ROOT file
this_observations, this_weights, cut_filter = parse_delphes_root_file(
delphes_file,
self.observables,
self.observables_required,
self.observables_defaults,
self.cuts,
self.cuts_default_pass,
weight_labels,
use_generator_truth=generator_truth,
delete_delphes_sample_file=delete_delphes_files,
acceptance_eta_max_a=self.acceptance_eta_max_a,
acceptance_eta_max_e=self.acceptance_eta_max_e,
acceptance_eta_max_mu=self.acceptance_eta_max_mu,
acceptance_eta_max_j=self.acceptance_eta_max_j,
acceptance_pt_min_a=self.acceptance_pt_min_a,
acceptance_pt_min_e=self.acceptance_pt_min_e,
acceptance_pt_min_mu=self.acceptance_pt_min_mu,
acceptance_pt_min_j=self.acceptance_pt_min_j,
)
# No events found?
if this_observations is None:
logger.debug("No observations in this Delphes file, skipping it")
return None, None, None
if this_weights is not None:
logger.debug("Found weights %s in Delphes file", list(this_weights.keys()))
else:
logger.debug("Did not extract weights from Delphes file")
# Sanity checks
n_events = self._check_sample_observations(this_observations)
# Find weights in LHE file
if lhe_file_for_weights is not None:
logger.debug("Extracting weights from LHE file")
_, this_weights = parse_lhe_file(
filename=lhe_file_for_weights,
sampling_benchmark=sampling_benchmark,
observables=OrderedDict(),
parse_events_as_xml=parse_lhe_events_as_xml,
)
logger.debug("Found weights %s in LHE file", list(this_weights.keys()))
# Apply cuts
logger.debug("Applying Delphes-based cuts to LHE weights")
for key, weights in six.iteritems(this_weights):
this_weights[key] = weights[cut_filter]
if this_weights is None:
raise RuntimeError("Could not extract weights from Delphes ROOT file or LHE file.")
# Sanity checks
n_events = self._check_sample_weights(n_events, this_weights)
# k factors
if k_factor is not None:
for key in this_weights:
this_weights[key] = k_factor * this_weights[key]
# Background scenario: we only have one set of weights, but these should be true for all benchmarks
if is_background:
logger.debug("Sample is background")
benchmarks_weight = list(six.itervalues(this_weights))[0]
for benchmark_name in self.benchmark_names_phys:
this_weights[benchmark_name] = benchmarks_weight
# Rescale nuisance parameters to reference benchmark
reference_weights = this_weights[reference_benchmark]
sampling_weights = this_weights[sampling_benchmark]
for key in this_weights:
if key not in self.benchmark_names_phys: # Only rescale nuisance benchmarks
this_weights[key] = reference_weights / sampling_weights * this_weights[key]
return this_observations, this_weights, n_events
def analyse_delphes_samples(
self, generator_truth=False, delete_delphes_files=False, reference_benchmark=None, parse_lhe_events_as_xml=True
):
"""
Main function that parses the Delphes samples (ROOT files), checks acceptance and cuts, and extracts
the observables and weights.
Parameters
----------
generator_truth : bool, optional
If True, the generator truth information (as given out by Pythia) will be parsed. Detector resolution or
efficiency effects will not be taken into account.
delete_delphes_files : bool, optional
If True, the Delphes ROOT files will be deleted after extracting the information from them. Default value:
False.
reference_benchmark : str or None, optional
The weights at the nuisance benchmarks will be rescaled to some reference theta benchmark:
`dsigma(x|theta_sampling(x),nu) -> dsigma(x|theta_ref,nu) = dsigma(x|theta_sampling(x),nu)
* dsigma(x|theta_ref,0) / dsigma(x|theta_sampling(x),0)`. This sets the name of the reference benchmark.
If None, the first one will be used. Default value: None.
parse_lhe_events_as_xml : bool, optional
Decides whether the LHE events are parsed with an XML parser (more robust, but slower) or a text parser
(less robust, faster). Default value: True.
Returns
-------
None
"""
# Input
if reference_benchmark is None:
reference_benchmark = self.benchmark_names_phys[0]
self.reference_benchmark = reference_benchmark
# Reset observations
self.observations = None
self.weights = None
self.nuisance_parameters = None
for (
delphes_file,
weight_labels,
is_background,
sampling_benchmark,
lhe_file,
lhe_file_for_weights,
k_factor,
) in zip(
self.delphes_sample_filenames,
self.hepmc_sample_weight_labels,
self.hepmc_is_backgrounds,
self.hepmc_sampled_from_benchmark,
self.lhe_sample_filenames,
self.lhe_sample_filenames_for_weights,
self.sample_k_factors,
):
logger.info("Analysing Delphes sample %s", delphes_file)
# Read systematics setup from LHE file
logger.debug("Extracting nuisance parameter definitions from LHE file")
nuisance_parameters = extract_nuisance_parameters_from_lhe_file(lhe_file, self.systematics)
logger.debug("Found %s nuisance parameters with matching benchmarks:", len(nuisance_parameters))
for key, value in six.iteritems(nuisance_parameters):
logger.debug(" %s: %s", key, value)
# Compare to existing data
if self.nuisance_parameters is None:
self.nuisance_parameters = nuisance_parameters
else:
if dict(self.nuisance_parameters) != dict(nuisance_parameters):
raise RuntimeError(
"Different LHE files have different definitions of nuisance parameters / benchmarks!\n"
"Previous: {}\nNew:{}".format(self.nuisance_parameters, nuisance_parameters)
)
# Calculate observables and weights in Delphes ROOT file
this_observations, this_weights, cut_filter = parse_delphes_root_file(
delphes_file,
self.observables,
self.observables_required,
self.observables_defaults,
self.cuts,
self.cuts_default_pass,
weight_labels,
use_generator_truth=generator_truth,
delete_delphes_sample_file=delete_delphes_files,
acceptance_eta_max_a=self.acceptance_eta_max_a,
acceptance_eta_max_e=self.acceptance_eta_max_e,
acceptance_eta_max_mu=self.acceptance_eta_max_mu,
acceptance_eta_max_j=self.acceptance_eta_max_j,
acceptance_pt_min_a=self.acceptance_pt_min_a,
acceptance_pt_min_e=self.acceptance_pt_min_e,
acceptance_pt_min_mu=self.acceptance_pt_min_mu,
acceptance_pt_min_j=self.acceptance_pt_min_j,
)
# No events found?
if this_observations is None:
logger.debug("No observations in this Delphes file, skipping it")
continue
if this_weights is not None:
logger.debug("Found weights %s in Delphes file", list(this_weights.keys()))
else:
logger.debug("Did not extract weights from Delphes file")
# Check number of events in observables
n_events = None
for key, obs in six.iteritems(this_observations):
this_n_events = len(obs)
if n_events is None:
n_events = this_n_events
logger.debug("Found %s events", n_events)
if this_n_events != n_events:
raise RuntimeError(
"Mismatching number of events in Delphes observations for {}: {} vs {}".format(
key, n_events, this_n_events
)
)
# Find weights in LHE file
if lhe_file_for_weights is not None:
logger.debug("Extracting weights from LHE file")
_, this_weights = parse_lhe_file(
filename=lhe_file_for_weights,
sampling_benchmark=sampling_benchmark,
observables=OrderedDict(),
parse_events_as_xml=parse_lhe_events_as_xml,
)
logger.debug("Found weights %s in LHE file", list(this_weights.keys()))
# Apply cuts
logger.debug("Applying Delphes-based cuts to LHE weights")
for key, weights in six.iteritems(this_weights):
this_weights[key] = weights[cut_filter]
if this_weights is None:
raise RuntimeError("Could not extract weights from Delphes ROOT file or LHE file.")
# Check number of events in weights
for key, weights in six.iteritems(this_weights):
this_n_events = len(weights)
if n_events is None:
n_events = this_n_events
logger.debug("Found %s events", n_events)
if this_n_events != n_events:
raise RuntimeError(
"Mismatching number of events in weights {}: {} vs {}".format(key, n_events, this_n_events)
)
# k factors
if k_factor is not None:
for key in this_weights:
this_weights[key] = k_factor * this_weights[key]
# Background scenario: we only have one set of weights, but these should be true for all benchmarks
if is_background:
logger.debug("Sample is background")
benchmarks_weight = list(six.itervalues(this_weights))[0]
for benchmark_name in self.benchmark_names_phys:
this_weights[benchmark_name] = benchmarks_weight
# Rescale nuisance parameters to reference benchmark
reference_weights = this_weights[reference_benchmark]
sampling_weights = this_weights[sampling_benchmark]
for key in this_weights:
if key not in self.benchmark_names_phys: # Only rescale nuisance benchmarks
this_weights[key] = reference_weights / sampling_weights * this_weights[key]
# First results
if self.observations is None and self.weights is None:
self.observations = this_observations
self.weights = this_weights
continue
# Following results: check consistency with previous results
if len(self.weights) != len(this_weights):
raise ValueError(
"Number of weights in different files incompatible: {} vs {}".format(
len(self.weights), len(this_weights)
)
)
if len(self.observations) != len(this_observations):
raise ValueError(
"Number of observations in different Delphes files incompatible: {} vs {}".format(
len(self.observations), len(this_observations)
)
)
# Merge results with previous
for key in self.weights:
assert key in this_weights, "Weight label {} not found in sample!".format(key)
self.weights[key] = np.hstack([self.weights[key], this_weights[key]])
for key in self.observations:
assert key in this_observations, "Observable {} not found in Delphes sample!".format(key)
self.observations[key] = np.hstack([self.observations[key], this_observations[key]])