class DataAnalyzer(object):
"""
Collects common functionality that is used when analysing data in the MadMiner file.
Parameters
----------
filename : str
Path to MadMiner file (for instance the output of `madminer.delphes.DelphesProcessor.save()`).
disable_morphing : bool, optional
If True, the morphing setup is not loaded from the file. Default value: False.
include_nuisance_parameters : bool, optional
If True, nuisance parameters are taken into account. Default value: True.
"""
def __init__(self,
filename,
disable_morphing=False,
include_nuisance_parameters=True):
# Save setup
self.include_nuisance_parameters = include_nuisance_parameters
self.madminer_filename = filename
# Load data
logger.info("Loading data from %s", filename)
(
self.parameters,
self.benchmarks,
self.benchmark_is_nuisance,
self.morphing_components,
self.morphing_matrix,
self.observables,
self.n_samples,
_,
self.reference_benchmark,
self.nuisance_parameters,
self.n_events_generated_per_benchmark,
self.n_events_backgrounds,
) = load_madminer_settings(
filename, include_nuisance_benchmarks=include_nuisance_parameters)
self.n_parameters = len(self.parameters)
self.n_benchmarks = len(self.benchmarks)
self.n_benchmarks_phys = np.sum(
np.logical_not(self.benchmark_is_nuisance))
self.n_observables = 0 if self.observables is None else len(
self.observables)
self.n_nuisance_parameters = 0
if self.nuisance_parameters is not None and include_nuisance_parameters:
self.n_nuisance_parameters = len(self.nuisance_parameters)
else:
self.nuisance_parameters = None
# Morphing
self.morpher = None
if self.morphing_matrix is not None and self.morphing_components is not None and not disable_morphing:
self.morpher = PhysicsMorpher(self.parameters)
self.morpher.set_components(self.morphing_components)
self.morpher.set_basis(self.benchmarks,
morphing_matrix=self.morphing_matrix)
# Nuisance morphing
self.nuisance_morpher = None
if self.nuisance_parameters is not None:
self.nuisance_morpher = NuisanceMorpher(
self.nuisance_parameters, list(self.benchmarks.keys()),
self.reference_benchmark)
else:
self.include_nuisance_parameters = False
# Check event numbers
self._check_n_events()
self._report_setup()
def event_loader(
self,
start=0,
end=None,
batch_size=100000,
include_nuisance_parameters=None,
generated_close_to=None,
return_sampling_ids=False,
):
"""
Yields batches of events in the MadMiner file.
Parameters
----------
start : int, optional
First event index to load
end : int or None, optional
Last event index to load
batch_size : int, optional
Batch size
include_nuisance_parameters : bool, optional
Whether nuisance parameter benchmarks are included in the returned data
generated_close_to : None or ndarray, optional
If None, this function yields all events. Otherwise, it just yields just the events that were generated
at the closest benchmark point to a given parameter point.
return_sampling_ids : bool, optional
If True, the iterator returns the sampling IDs in additioin to observables and weights.
Yields
------
observations : ndarray
Event data
weights : ndarray
Event weights
sampling_ids : int
Sampling IDs (benchmark used for sampling for signal events, -1 for background events). Only returned if
return_sampling_ids = True was set.
"""
if include_nuisance_parameters is None:
include_nuisance_parameters = self.include_nuisance_parameters
sampling_benchmark = self._find_closest_benchmark(generated_close_to)
logger.debug("Sampling benchmark closest to %s: %s",
generated_close_to, sampling_benchmark)
if sampling_benchmark is None:
sampling_factors = self._calculate_sampling_factors()
else:
sampling_factors = np.ones(self.n_benchmarks_phys + 1)
logger.debug("Sampling factors: %s", sampling_factors)
for data in madminer_event_loader(
self.madminer_filename,
start,
end,
batch_size,
include_nuisance_parameters,
benchmark_is_nuisance=self.benchmark_is_nuisance,
sampling_benchmark=sampling_benchmark,
sampling_factors=sampling_factors,
return_sampling_ids=return_sampling_ids,
):
yield data
def weighted_events(
self,
theta=None,
nu=None,
start_event=None,
end_event=None,
derivative=False,
generated_close_to=None,
n_draws=None,
):
"""
Returns all events together with the benchmark weights (if theta is None) or weights for a given theta.
Parameters
----------
theta : None or ndarray or str, optional
If None, the function returns all benchmark weights. If str, the function returns the weights for a given
benchmark name. If ndarray, it uses morphing to calculate the weights for this value of theta. Default
value: None.
nu : None or ndarray, optional
If None, the nuisance parameters are set to their nominal values. Otherwise, and if theta is an ndarray,
sets the values of the nuisance parameters.
start_event : int
Index (in the MadMiner file) of the first event to consider.
end_event : int
Index (in the MadMiner file) of the last unweighted event to consider.
derivative : bool, optional
If True and if theta is not None, the derivative of the weights with respect to theta are returned. Default
value: False.
generated_close_to : None or int, optional
Only returns benchmarks generated from this benchmark (and background events). Default value: None.
n_draws : None or int, optional
If not None, returns only this number of events, drawn randomly.
Returns
-------
x : ndarray
Observables with shape `(n_unweighted_samples, n_observables)`.
weights : ndarray
If theta is None and derivative is False, benchmark weights with shape
`(n_unweighted_samples, n_benchmarks)` in pb. If theta is not None and derivative is True, the gradient of
the weight for the given parameter with respect to theta with shape `(n_unweighted_samples, n_gradients)`
in pb. Otherwise, weights for the given parameter theta with shape `(n_unweighted_samples,)` in pb.
"""
x, weights_benchmarks = next(
self.event_loader(batch_size=None,
start=start_event,
end=end_event,
generated_close_to=generated_close_to))
# Pick events randomly
n_events = len(x)
if n_draws is not None and n_draws < n_events:
idx = np.random.choice(n_events, n_draws, replace=False)
x = x[idx]
weights_benchmarks = weights_benchmarks[idx]
elif n_draws is not None:
logger.warning("Requested %s events, but only %s available",
n_draws, n_events)
# Process and return appropriate weights
if theta is None:
return x, weights_benchmarks
elif isinstance(theta, six.string_types):
i_benchmark = list(self.benchmarks.keys()).index(theta)
return x, weights_benchmarks[:, i_benchmark]
elif derivative:
dtheta_matrix = self._get_dtheta_benchmark_matrix(theta)
gradients_theta = mdot(
dtheta_matrix, weights_benchmarks) # (n_gradients, n_samples)
gradients_theta = gradients_theta.T
return x, gradients_theta
else:
# TODO: nuisance params
if nu is not None:
raise NotImplementedError
theta_matrix = self._get_theta_benchmark_matrix(theta)
weights_theta = mdot(theta_matrix, weights_benchmarks)
return x, weights_theta
def xsecs(
self,
thetas=None,
nus=None,
events="all",
test_split=0.2,
include_nuisance_benchmarks=True,
batch_size=100000,
generated_close_to=None,
):
"""
Returns the total cross sections for benchmarks or parameter points.
Parameters
----------
thetas : None or list of (ndarray or str), optional
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing). Default value: None.
nus : None or list of (None or ndarray), optional
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
include_nuisance_benchmarks : bool, optional
Whether to include nuisance benchmarks if thetas is None. Default value: True.
test_split : float, optional
Fraction of events reserved for testing. Default value: 0.2.
events : {"train", "test", "all"}, optional
Which events to use. Default: "all".
batch_size : int, optional
Size of the batches of events that are loaded into memory at the same time. Default value: 100000.
generated_close_to : None or ndarray, optional
If not None, only events originally generated from the closest benchmark to this parameter point will be
used. Default value : None.
Returns
-------
xsecs : ndarray
Calculated cross sections in pb.
xsec_uncertainties : ndarray
Cross-section uncertainties in pb. Basically calculated as sum(weights**2)**0.5.
"""
logger.debug("Calculating cross sections for thetas = %s and nus = %s",
thetas, nus)
# Inputs
if thetas is not None:
include_nuisance_benchmarks = True
if thetas is not None:
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Which events to use
if events == "all":
start_event, end_event = None, None
correction_factor = 1.0
elif events == "train":
start_event, end_event, correction_factor = self._train_test_split(
True, test_split)
elif events == "test":
start_event, end_event, correction_factor = self._train_test_split(
False, test_split)
else:
raise ValueError(
"Events has to be either 'all', 'train', or 'test', but got {}!"
.format(events))
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
# Loop over events
xsecs = 0.0
xsec_uncertainties = 0.0
n_events = 0
for i_batch, (_, benchmark_weights) in enumerate(
self.event_loader(
start=start_event,
end=end_event,
include_nuisance_parameters=include_nuisance_benchmarks,
batch_size=batch_size,
generated_close_to=generated_close_to,
)):
n_batch, _ = benchmark_weights.shape
n_events += n_batch
# Benchmark xsecs
if thetas is None:
xsecs += np.sum(benchmark_weights, axis=0)
xsec_uncertainties += np.sum(benchmark_weights *
benchmark_weights,
axis=0)
# xsecs at given parameters(theta, nu)
else:
# Weights at nominal nuisance params (nu=0)
weights_nom = mdot(
theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
weights_sq_nom = mdot(theta_matrices, benchmark_weights *
benchmark_weights) # same
# Effect of nuisance parameters
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
weights = nuisance_factors * weights_nom
weights_sq = nuisance_factors * weights_sq_nom
# Sum up
xsecs += np.sum(weights, axis=1)
xsec_uncertainties += np.sum(weights_sq, axis=1)
if n_events == 0:
raise RuntimeError(
"Did not find events with test_split = %s and generated_close_to = %s",
test_split, generated_close_to)
xsec_uncertainties = np.maximum(xsec_uncertainties, 0.0)**0.5
# Correct for not using all events
xsecs *= correction_factor
xsec_uncertainties *= correction_factor
logger.debug("xsecs and uncertainties [pb]:")
for this_xsec, this_uncertainty in zip(xsecs, xsec_uncertainties):
logger.debug(" (%4f +/- %4f) pb (%4f %%)", this_xsec,
this_uncertainty, 100 * this_uncertainty / this_xsec)
return xsecs, xsec_uncertainties
def xsec_gradients(
self,
thetas,
nus=None,
events="all",
test_split=0.2,
gradients="all",
batch_size=100000,
generated_close_to=None,
):
"""
Returns the gradient of total cross sections with respect to parameters.
Parameters
----------
thetas : list of (ndarray or str), optional
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing). Default value: None.
nus : None or list of (None or ndarray), optional
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
test_split : float, optional
Fraction of events reserved for testing. Default value: 0.2.
events : {"train", "test", "all"}, optional
Which events to use. Default: "all".
gradients : {"all", "theta", "nu"}, optional
Which gradients to calculate. Default value: "all".
batch_size : int, optional
Size of the batches of events that are loaded into memory at the same time. Default value: 100000.
generated_close_to : None or ndarray, optional
If not None, only events originally generated from the closest benchmark to this parameter point will be
used. Default value : None.
Returns
-------
xsecs_gradients : ndarray
Calculated cross section gradients in pb with shape (n_gradients,).
"""
logger.debug(
"Calculating cross section gradients for thetas = %s and nus = %s",
thetas, nus)
# Inputs
include_nuisance_benchmarks = nus is not None or gradients in [
"all", "nu"
]
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
if gradients not in ["all", "theta", "nu"]:
raise RuntimeError(
"Gradients has to be 'all', 'theta', or 'nu', but got {}".
format(gradients))
# Which events to use
if events == "all":
start_event, end_event = None, None
correction_factor = 1.0
elif events == "train":
start_event, end_event, correction_factor = self._train_test_split(
True, test_split)
elif events == "test":
start_event, end_event, correction_factor = self._train_test_split(
False, test_split)
else:
raise ValueError(
"Events has to be either 'all', 'train', or 'test', but got {}!"
.format(events))
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
theta_matrices = np.asarray([
self._get_theta_benchmark_matrix(theta) for theta in thetas
]) # shape (n_thetas, n_benchmarks)
theta_gradient_matrices = np.asarray([
self._get_dtheta_benchmark_matrix(theta) for theta in thetas
]) # shape (n_thetas, n_gradients, n_benchmarks)
# Loop over events
xsec_gradients = 0.0
for i_batch, (_, benchmark_weights) in enumerate(
self.event_loader(
start=start_event,
end=end_event,
include_nuisance_parameters=include_nuisance_benchmarks,
batch_size=batch_size,
generated_close_to=generated_close_to,
)):
n_batch, _ = benchmark_weights.shape
logger.debug("Batch %s with %s events", i_batch + 1, n_batch)
if gradients in ["all", "theta"]:
nom_gradients = mdot(
theta_gradient_matrices, benchmark_weights
) # Shape (n_thetas, n_phys_gradients, n_batch)
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights) # Shape (n_thetas, n_batch)
try:
dweight_dtheta = nuisance_factors[:, np.
newaxis, :] * nom_gradients
except TypeError:
dweight_dtheta = nom_gradients
if gradients in ["all", "nu"]:
weights_nom = mdot(
theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
nuisance_factor_gradients = np.asarray([
self.nuisance_morpher.calculate_nuisance_factor_gradients(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_nuisance_gradients, n_batch)
dweight_dnu = nuisance_factor_gradients * weights_nom[:, np.
newaxis, :]
if gradients == "all":
dweight_dall = np.concatenate((dweight_dtheta, dweight_dnu), 1)
elif gradients == "theta":
dweight_dall = dweight_dtheta
elif gradients == "nu":
dweight_dall = dweight_dnu
xsec_gradients += np.sum(dweight_dall, axis=2)
# Correct for not using all events
xsec_gradients *= correction_factor
return xsec_gradients
def _check_n_events(self):
if self.n_events_generated_per_benchmark is None:
return
n_events_check = sum(self.n_events_generated_per_benchmark)
if self.n_events_backgrounds is not None:
n_events_check += self.n_events_backgrounds
if self.n_samples != n_events_check:
logger.warning(
"Inconsistent event numbers in HDF5 file! Please recalculate them by calling "
"combine_and_shuffle(recalculate_header=True).")
def _report_setup(self):
logger.info("Found %s parameters", self.n_parameters)
for key, values in six.iteritems(self.parameters):
logger.debug(
" %s (LHA: %s %s, maximal power in squared ME: %s, range: %s)",
key,
values[0],
values[1],
values[2],
values[3],
)
if self.nuisance_parameters is not None:
logger.info("Found %s nuisance parameters",
self.n_nuisance_parameters)
for key, values in six.iteritems(self.nuisance_parameters):
logger.debug(" %s (%s)", key, values)
else:
logger.info("Did not find nuisance parameters")
self.include_nuisance_parameters = False
logger.info("Found %s benchmarks, of which %s physical",
self.n_benchmarks, self.n_benchmarks_phys)
for (key, values), is_nuisance in zip(six.iteritems(self.benchmarks),
self.benchmark_is_nuisance):
if is_nuisance:
logger.debug(" %s: systematics", key)
else:
logger.debug(" %s: %s", key, format_benchmark(values))
logger.info("Found %s observables", self.n_observables)
if self.observables is not None:
for i, obs in enumerate(self.observables):
logger.debug(" %2.2s %s", i, obs)
logger.info("Found %s events", self.n_samples)
if self.n_events_generated_per_benchmark is not None:
for events, name in zip(self.n_events_generated_per_benchmark,
six.iterkeys(self.benchmarks)):
if events > 0:
logger.info(" %s signal events sampled from benchmark %s",
events, name)
if self.n_events_backgrounds is not None and self.n_events_backgrounds > 0:
logger.info(" %s background events",
self.n_events_backgrounds)
else:
logger.debug(" Did not find sample summary information")
if self.morpher is not None:
logger.info("Found morphing setup with %s components",
len(self.morphing_components))
else:
logger.info("Did not find morphing setup.")
if self.nuisance_morpher is not None:
logger.info("Found nuisance morphing setup")
else:
logger.info("Did not find nuisance morphing setup")
def _calculate_nuisance_factors(self, nus, benchmark_weights):
if self._any_nontrivial_nus(nus):
return np.asarray([
self.nuisance_morpher.calculate_nuisance_factors(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_batch)
else:
return 1.0
@staticmethod
def _any_nontrivial_nus(nus):
if nus is None:
return False
for nu in nus:
if nu is not None:
return True
return False
def _weights(self, thetas, nus, benchmark_weights, theta_matrices=None):
"""
Turns benchmark weights into weights for given parameter points (theta, nu).
Parameters
----------
thetas : list of (ndarray or str)
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing).
nus : None or list of (None or ndarray)
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
Returns
-------
weights : ndarray
Calculated weights in pb.
"""
n_events, _ = benchmark_weights.shape
# Inputs
include_nuisance_benchmarks = nus is not None
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
if theta_matrices is None:
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
# Weights at nominal nuisance params (nu=0)
weights_nom = mdot(theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
# Effect of nuisance parameters
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
weights = nuisance_factors * weights_nom
return weights
def _weight_gradients(self,
thetas,
nus,
benchmark_weights,
gradients="all",
theta_matrices=None,
theta_gradient_matrices=None):
"""
Turns benchmark weights into weights for given parameter points (theta, nu).
Parameters
----------
thetas : list of (ndarray or str)
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing).
nus : None or list of (None or ndarray)
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
gradients : {"all", "theta", "nu"}, optional
Which gradients to calculate. Default value: "all".
Returns
-------
gradients : ndarray
Calculated gradients in pb.
"""
n_events, _ = benchmark_weights.shape
# Inputs
if gradients == "all" and self.n_nuisance_parameters == 0:
gradients = "theta"
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
if theta_matrices is None:
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
if theta_gradient_matrices is None:
theta_gradient_matrices = [
self._get_dtheta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
theta_gradient_matrices = np.asarray(
theta_gradient_matrices
) # Shape (n_thetas, n_gradients, n_benchmarks)
# Calculate theta gradient
if gradients in ["all", "theta"]:
nom_gradients = mdot(
theta_gradient_matrices,
benchmark_weights) # (n_thetas, n_phys_gradients, n_batch)
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
try:
dweight_dtheta = nuisance_factors[:, np.
newaxis, :] * nom_gradients
except TypeError:
dweight_dtheta = nom_gradients
else:
dweight_dtheta = None
# Calculate nu gradient
if gradients in ["all", "nu"]:
weights_nom = mdot(theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
nuisance_factor_gradients = np.asarray([
self.nuisance_morpher.calculate_nuisance_factor_gradients(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_nuisance_gradients, n_batch)
dweight_dnu = nuisance_factor_gradients * weights_nom[:, np.
newaxis, :]
else:
dweight_dnu = None
if gradients == "theta":
return dweight_dtheta
elif gradients == "nu":
return dweight_dnu
return np.concatenate((dweight_dtheta, dweight_dnu), 1)
def _train_test_split(self, train, test_split):
"""
Returns the start and end event for train samples (train = True) or test samples (train = False).
Parameters
----------
train : bool
True if training data is generated, False if test data is generated.
test_split : float
Fraction of events reserved for testing.
Returns
-------
start_event : int
Index (in the MadMiner file) of the first event to consider.
end_event : int
Index (in the MadMiner file) of the last unweighted event to consider.
correction_factor : float
Factor with which the weights and cross sections will have to be multiplied to make up for the missing
events.
"""
if train:
start_event = 0
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
end_event = None
correction_factor = 1.0
else:
end_event = int(round((1.0 - test_split) * self.n_samples, 0))
correction_factor = 1.0 / (1.0 - test_split)
if end_event < 0 or end_event > self.n_samples:
raise ValueError(
"Irregular train / test split: sample {} / {}",
end_event, self.n_samples)
else:
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
start_event = 0
correction_factor = 1.0
else:
start_event = int(round(
(1.0 - test_split) * self.n_samples, 0)) + 1
correction_factor = 1.0 / test_split
if start_event < 0 or start_event > self.n_samples:
raise ValueError(
"Irregular train / test split: sample {} / {}",
start_event, self.n_samples)
end_event = None
return start_event, end_event, correction_factor
def _get_theta_value(self, theta):
if isinstance(theta, six.string_types):
benchmark = self.benchmarks[theta]
theta_value = np.array([benchmark[key] for key in benchmark])
elif isinstance(theta, int):
benchmark = self.benchmarks[list(self.benchmarks.keys())[theta]]
theta_value = np.array([benchmark[key] for key in benchmark])
else:
theta_value = np.asarray(theta)
return theta_value
def _get_nu_value(self, nu):
if nu is None:
nu_value = np.zeros(self.n_nuisance_parameters)
else:
nu_value = np.asarray(nu)
return nu_value
def _get_theta_benchmark_matrix(self, theta, zero_pad=True):
"""Calculates vector A such that dsigma(theta) = A * dsigma_benchmarks"""
if zero_pad:
unpadded_theta_matrix = self._get_theta_benchmark_matrix(
theta, zero_pad=False)
theta_matrix = np.zeros(self.n_benchmarks)
theta_matrix[:unpadded_theta_matrix.
shape[0]] = unpadded_theta_matrix
elif isinstance(theta, six.string_types):
i_benchmark = list(self.benchmarks).index(theta)
theta_matrix = self._get_theta_benchmark_matrix(i_benchmark)
elif isinstance(theta, int):
n_benchmarks = len(self.benchmarks)
theta_matrix = np.zeros(n_benchmarks)
theta_matrix[theta] = 1.0
else:
theta_matrix = self.morpher.calculate_morphing_weights(theta)
return theta_matrix
def _get_dtheta_benchmark_matrix(self, theta, zero_pad=True):
"""Calculates matrix A_ij such that d dsigma(theta) / d theta_i = A_ij * dsigma (benchmark j)"""
if self.morpher is None:
raise RuntimeError("Cannot calculate score without morphing")
if zero_pad:
unpadded_theta_matrix = self._get_dtheta_benchmark_matrix(
theta, zero_pad=False)
dtheta_matrix = np.zeros(
(unpadded_theta_matrix.shape[0], self.n_benchmarks))
dtheta_matrix[:, :unpadded_theta_matrix.
shape[1]] = unpadded_theta_matrix
elif isinstance(theta, six.string_types):
benchmark = self.benchmarks[theta]
benchmark = np.array(
[value for _, value in six.iteritems(benchmark)])
dtheta_matrix = self._get_dtheta_benchmark_matrix(benchmark)
elif isinstance(theta, int):
benchmark = self.benchmarks[list(self.benchmarks.keys())[theta]]
benchmark = np.array(
[value for _, value in six.iteritems(benchmark)])
dtheta_matrix = self._get_dtheta_benchmark_matrix(benchmark)
else:
dtheta_matrix = self.morpher.calculate_morphing_weight_gradient(
theta) # Shape (n_parameters, n_benchmarks_phys)
return dtheta_matrix
def _calculate_sampling_factors(self):
events = np.asarray(self.n_events_generated_per_benchmark,
dtype=np.float)
logger.debug("Events per benchmark: %s", events)
factors = events / np.sum(events)
factors = np.hstack((factors, 1.0)) # background events
return factors
def _find_closest_benchmark(self, theta):
if theta is None:
return None
benchmarks = self._benchmark_array()
distances = [
np.linalg.norm(benchmark - theta) for benchmark in benchmarks
]
logger.debug("Distances from %s: %s", theta, distances)
# Don't use benchmarks where we don't actually have events
if self.n_events_generated_per_benchmark is not None:
logger.debug("n_events_generated_per_benchmark: %s",
self.n_events_generated_per_benchmark)
distances = distances + 1.0e9 * (
self.n_events_generated_per_benchmark == 0).astype(np.float)
closest_idx = np.argmin(distances)
return closest_idx
def _benchmark_array(self):
benchmarks_array = []
for benchmark in six.itervalues(self.benchmarks):
benchmarks_array.append(list(six.itervalues(benchmark)))
return np.asarray(benchmarks_array)
class MadMiner:
"""
The central class to manage parameter spaces, benchmarks, and the generation of events through MadGraph and
Pythia.
An instance of this class is the starting point of most MadMiner applications. It is typically used in four steps:
* Defining the parameter space through `MadMiner.add_parameter`
* Defining the benchmarks, i.e. the points at which the squared matrix elements will be evaluated in MadGraph, with
`MadMiner.add_benchmark()` or, if operator morphing is used, with `MadMiner.set_benchmarks_from_morphing()`
* Saving this setup with `MadMiner.save()` (it can be loaded in a new instance with `MadMiner.load()`)
* Running MadGraph and Pythia with the appropriate settings with `MadMiner.run()` or `MadMiner.run_multiple()` (the
latter allows the user to combine runs from multiple run cards and sampling points)
Please see the tutorial for a hands-on introduction to its methods.
"""
def __init__(self):
self.parameters = OrderedDict()
self.benchmarks = OrderedDict()
self.default_benchmark = None
self.morpher = None
self.export_morphing = False
self.systematics = OrderedDict()
self.finite_difference_benchmarks = OrderedDict()
self.finite_difference_epsilon = 0.0
def _reset_systematics(self):
self.systematics = OrderedDict()
def _reset_benchmarks(self):
self.benchmarks = OrderedDict()
self.default_benchmark = None
def _reset_morpher(self):
self.morpher = None
self.export_morphing = False
def add_parameter(
self,
lha_block,
lha_id,
parameter_name=None,
param_card_transform=None,
morphing_max_power=2,
parameter_range=(0.0, 1.0),
):
"""
Adds an individual parameter.
Parameters
----------
lha_block : str
The name of the LHA block as used in the param_card. Case-sensitive.
lha_id : int
The LHA id as used in the param_card.
parameter_name : str or None
An internal name for the parameter. If None, a the default 'benchmark_i' is used.
morphing_max_power : int
The maximal power with which this parameter contributes to the
squared matrix element of the process of interest. Typically at tree level,
this maximal number is 2 for parameters that affect one vertex (e.g. only production
or only decay of a particle), and 4 for parameters that affect two vertices (e.g.
production and decay). Default value: 2.
param_card_transform : None or str
Represents a one-parameter function mapping the parameter
(`"theta"`) to the value that should be written in the parameter cards. This
str is parsed by Python's `eval()` function, and `"theta"` is parsed as the
parameter value. Default value: None.
parameter_range : tuple of float
The range of parameter values of primary interest. Only affects the
basis optimization. Default value: (0., 1.).
Returns
-------
None
"""
# Default names
if parameter_name is None:
parameter_name = f"parameter_{len(self.parameters)}"
if param_card_transform is None:
param_card_transform = "_"
# Check and sanitize input
assert isinstance(lha_block,
str), f"LHA block is not a string: {lha_block}"
assert isinstance(lha_id, int), f"LHA id is not an integer: {lha_id}"
assert isinstance(
parameter_name,
str), f"Parameter name is not a string: {parameter_name}"
assert isinstance(
morphing_max_power,
int), f"Morphing max power is not an integer: {morphing_max_power}"
parameter_name = parameter_name.replace(" ", "_")
parameter_name = parameter_name.replace("-", "_")
assert parameter_name not in self.parameters, f"Parameter already exists: {parameter_name}"
parameter = AnalysisParameter(
parameter_name,
lha_block,
lha_id,
morphing_max_power,
parameter_range,
param_card_transform,
)
# Add parameter
logger.info("Adding parameter: %s", parameter)
self.parameters[parameter_name] = parameter
# The morphing information is not accurate anymore
logger.warning("Resetting benchmarks and morphing")
self._reset_benchmarks()
self._reset_morpher()
def set_parameters(self, parameters: Union[Dict[str, AnalysisParameter],
List[tuple]]):
"""
Manually sets all parameters, overwriting previously added parameters.
Parameters
----------
parameters : dict or list
If parameters is an dict, the keys should be str and give the parameter names, and the values are
AnalysisParameter model instances. If parameters is a list, the items should be tuples of the
form (LHA_block, LHA_ID).
Returns
-------
None
"""
self.parameters = OrderedDict()
if isinstance(parameters, dict):
for param in parameters.values():
self.add_parameter(
lha_block=param.lha_block,
lha_id=param.lha_id,
parameter_name=param.name,
morphing_max_power=param.max_power,
parameter_range=param.val_range,
)
elif isinstance(parameters, list):
for values in parameters:
self.add_parameter(values[0], values[1])
else:
raise RuntimeError(f"Invalid set of parameters: {parameters}")
# The morphing information is not accurate anymore
logger.warning("Resetting benchmarks and morphing")
self._reset_benchmarks()
self._reset_morpher()
def add_benchmark(self,
parameter_values: Dict[str, float],
benchmark_name: str = None,
verbose: float = True):
"""
Manually adds an individual benchmark, that is, a parameter point that will be evaluated by MadGraph.
Parameters
----------
parameter_values : dict
The keys of this dict should be the parameter names and the values the corresponding parameter values.
benchmark_name : str or None, optional
Name of benchmark. If None, a default name is used. Default value: None.
verbose : bool, optional
If True, prints output about each benchmark. Default value: True.
Returns
-------
None
Raises
------
RuntimeError
If a benchmark with the same name already exists, if parameter_values is not a dict, or if a key of
parameter_values does not correspond to a defined parameter.
"""
# Default names
if benchmark_name is None:
benchmark_name = f"benchmark_{len(self.benchmarks)}"
# Check input
if not isinstance(parameter_values, dict):
raise RuntimeError(
f"Parameter values are not a dict: {parameter_values}")
for p_name in parameter_values.keys():
if p_name not in self.parameters.keys():
raise RuntimeError(f"Unknown parameter: {p_name}")
if benchmark_name in self.benchmarks.keys():
raise RuntimeError(f"Benchmark {benchmark_name} exists already")
# Add benchmark
self.benchmarks[benchmark_name] = Benchmark(
name=benchmark_name,
values=parameter_values,
)
# If first benchmark, this will be the default for sampling
if len(self.benchmarks) == 1:
self.default_benchmark = benchmark_name
if verbose:
logger.info("Added benchmark %s", self.benchmarks[benchmark_name])
else:
logger.debug("Added benchmark %s", self.benchmarks[benchmark_name])
def set_benchmarks(self,
benchmarks: Union[Dict[str, dict], List[dict]],
verbose: bool = True):
"""
Manually sets all benchmarks, that is, parameter points that will be evaluated by MadGraph. Calling this
function overwrites all previously defined benchmarks.
Parameters
----------
benchmarks : dict or list
Specifies all benchmarks. If None, all benchmarks are reset. If dict, the keys are the benchmark names and
the values the Benchmark instances. If list, the entries are dicts {parameter_name:value}
(and the benchmark names are chosen automatically). Default value: None.
verbose : bool, optional
If True, prints output about each benchmark. Default value: True.
Returns
-------
None
"""
self.benchmarks = OrderedDict()
self.default_benchmark = None
if isinstance(benchmarks, dict):
for name, values in benchmarks.items():
self.add_benchmark(values, name, verbose=verbose)
elif isinstance(benchmarks, list):
for values in benchmarks:
self.add_benchmark(values)
else:
raise RuntimeError(f"Invalid set of benchmarks: {benchmarks}")
# After manually adding benchmarks, the morphing information is not accurate anymore
if self.morpher is not None:
logger.warning("Reset morphing")
self.morpher = None
self.export_morphing = False
def set_morphing(
self,
max_overall_power=4,
n_bases=1,
include_existing_benchmarks=True,
n_trials=100,
n_test_thetas=100,
):
"""
Sets up the morphing environment.
Sets benchmarks, i.e. parameter points that will be evaluated by MadGraph, for a morphing algorithm, and
calculates all information required for morphing. Morphing is a technique that allows MadMax to infer the full
probability distribution `p(x_i | theta)` for each simulated event `x_i` and any `theta`, not just the
benchmarks.
The morphing basis is optimized with respect to the expected mean squared morphing weights over the parameter
region of interest. If keep_existing_benchmarks=True, benchmarks defined previously will be incorporated in the
morphing basis and only the remaining basis points will be optimized.
Note that any subsequent call to `set_benchmarks` or `add_benchmark` will overwrite the morphing setup. The
correct order is therefore to manually define benchmarks first, using `set_benchmarks` or `add_benchmark`, and
then to create the morphing setup and complete the basis by calling
`set_benchmarks_from_morphing(keep_existing_benchmarks=True)`.
Parameters
----------
max_overall_power : int, optional
The maximal sum of powers of all parameters contributing to the squared matrix element.
Typically, if parameters can affect the couplings at n vertices, this number is 2n. Default value: 4.
n_bases : int, optional
The number of morphing bases generated. If n_bases > 1, multiple bases are combined, and the
weights for each basis are reduced by a factor 1 / n_bases. Currently only the default choice of 1 is
fully implemented. Do not use any other value for now. Default value: 1.
include_existing_benchmarks : bool, optional
If True, the previously defined benchmarks are included in the morphing basis. In that case, the number of
free parameters in the optimization routine is reduced. If False, the existing benchmarks will still be
simulated, but are not part of the morphing routine. Default value: True.
n_trials : int, optional
Number of random basis configurations tested in the optimization procedure. A larger number will increase
the run time of the optimization, but lead to better results. Default value: 100.
n_test_thetas : int, optional
Number of random parameter points used to evaluate the expected mean squared morphing weights. A larger
number will increase the run time of the optimization, but lead to better results. Default value: 100.
Returns
-------
None
"""
logger.info("Optimizing basis for morphing")
morpher = PhysicsMorpher(parameters_from_madminer=self.parameters)
morpher.find_components(max_overall_power)
if include_existing_benchmarks:
n_predefined_benchmarks = len(self.benchmarks)
basis = morpher.optimize_basis(
n_bases=n_bases,
benchmarks_from_madminer=self.benchmarks,
n_trials=n_trials,
n_test_thetas=n_test_thetas,
)
else:
n_predefined_benchmarks = 0
basis = morpher.optimize_basis(
n_bases=n_bases,
benchmarks_from_madminer=None,
n_trials=n_trials,
n_test_thetas=n_test_thetas,
)
basis.update(self.benchmarks)
self.set_benchmarks(basis, verbose=False)
self.morpher = morpher
self.export_morphing = True
logger.info(
"Set up morphing with %s parameters, %s morphing components, %s predefined basis points, and %s "
"new basis points",
morpher.n_parameters,
morpher.n_components,
n_predefined_benchmarks,
morpher.n_components - n_predefined_benchmarks,
)
def finite_differences(self, epsilon=0.01):
"""
Adds benchmarks so that the score can be computed from finite differences
Don't add any more benchmarks or parameters after calling this!
"""
logger.info("Adding finite-differences benchmarks with epsilon = %s",
epsilon)
self.finite_difference_epsilon = epsilon
# Copy is necessary to avoid endless loop :/
for b_name, benchmark in self.benchmarks.copy().items():
fd_keys = {}
for param_name, param_value in benchmark.values.items():
fd_key = f"{b_name}_plus_{param_name}"
fd_obj = benchmark.copy()
fd_obj.values[param_name] += epsilon
self.add_benchmark(fd_obj, fd_key)
fd_keys[param_name] = fd_key
self.finite_difference_benchmarks[b_name].shift_names = fd_keys
def add_systematics(
self,
effect,
systematic_name=None,
norm_variation=1.1,
scale="mu",
scale_variations=(0.5, 1.0, 2.0),
pdf_variation="CT10",
):
"""
Parameters
----------
effect : {"norm", "scale", "pdf"}
Type of the nuisance parameter. If "norm", it will affect the overall normalization of one or multiple
samples in the process. If "scale", the nuisance parameter effect will be determined by varying
factorization or regularization scales (depending on scale_variation and scales). If "pdf", the effect
of the nuisance parameters will be determined by varying the PDF used.
systematic_name : None or str, optional
scale : {"mu", "mur", "muf"}, optional
If type is "scale", this sets whether only the regularization scale ("mur"), only the factorization scale
("muf"), or both simultaneously ("mu") are varied. Default value: "mu".
norm_variation : float, optional
If type is "norm", this sets the relative effect of the nuisance parameter on the cross section at the
"plus 1 sigma" variation. 1.1 corresponds to a 10% increase, 0.9 to a 10% decrease relative to the nominal
cross section. Default value: 1.1.
scale_variations : tuple of float, optional
If type is "scale", this sets how the regularization and / or factorization scales are varied. A tuple
like (0.5, 1.0, 2.0) specifies the factors with which they are varied. Default value: (0.5, 1.0, 2.0).
pdf_variation : str, optional
If type is "pdf", defines the PDF set for the variation. The option is passed along to the `--pdf` option
of MadGraph's systematics module. See https://cp3.irmp.ucl.ac.be/projects/madgraph/wiki/Systematics for a
list. The option "CT10" would, as an example, run over all the eigenvectors of the CTEQ10 set.
Default value: "CT10".
Returns
-------
None
"""
assert scale in ["mu", "mur", "muf"]
# Default name
if systematic_name is None:
i = 0
while f"{effect}_{i}" in list(self.systematics.keys()):
i += 1
systematic_name = f"{type}_{i}"
systematic_name = systematic_name.replace(" ", "_")
systematic_name = systematic_name.replace("-", "_")
scale = SystematicScale.from_str(scale)
effect = SystematicType.from_str(effect)
if effect is SystematicType.PDF:
self.systematics[systematic_name] = Systematic(
systematic_name,
SystematicType.PDF,
pdf_variation,
)
elif effect is SystematicType.SCALE:
scale_variation_string = ",".join(
(str(factor) for factor in scale_variations))
self.systematics[systematic_name] = Systematic(
systematic_name,
SystematicType.SCALE,
scale_variation_string,
scale,
)
elif effect is SystematicType.NORM:
self.systematics[systematic_name] = Systematic(
systematic_name,
SystematicType.NORM,
norm_variation,
)
def load(self, filename, disable_morphing=False):
"""
Loads MadMiner setup from a file. All parameters, benchmarks, and morphing settings are overwritten.
See `save` for more details.
Parameters
----------
filename : str
Path to the MadMiner file.
disable_morphing : bool, optional
If True, the morphing setup is not loaded from the file. Default value: False.
Returns
-------
None
"""
# Load data
(
self.parameters,
self.benchmarks,
_,
morphing_components,
morphing_matrix,
_,
_,
self.systematics,
_,
_,
_,
_,
self.finite_difference_benchmarks,
self.finite_difference_epsilon,
) = load_madminer_settings(filename, include_nuisance_benchmarks=False)
logger.info("Found %s parameters:", len(self.parameters))
for param in self.parameters.values():
logger.info(" %s", param)
logger.info("Found %s benchmarks:", len(self.benchmarks))
for benchmark in self.benchmarks.values():
logger.info(" %s", benchmark)
if self.default_benchmark is None:
self.default_benchmark = benchmark.name
# Morphing
self.morpher = None
self.export_morphing = False
if morphing_matrix is not None and morphing_components is not None and not disable_morphing:
self.morpher = PhysicsMorpher(self.parameters)
self.morpher.set_components(morphing_components)
self.morpher.set_basis(self.benchmarks,
morphing_matrix=morphing_matrix)
self.export_morphing = True
logger.info("Found morphing setup with %s components",
len(morphing_components))
else:
logger.info("Did not find morphing setup.")
# Systematics setup
if len(self.systematics) == 0:
logger.info("Did not find systematics setup.")
else:
logger.info("Found systematics setup with %s groups",
len(self.systematics))
for name, systematic in self.systematics.items():
logger.debug(" %s: %s", name, systematic)
def save(self, filename):
"""
Saves MadMiner setup into a file.
The file format follows the HDF5 standard. The saved information includes:
* the parameter definitions,
* the benchmark points,
* the systematics setup (if defined), and
* the morphing setup (if defined).
This file is an important input to later stages in the analysis chain, including the processing of generated
events, extraction of training samples, and calculation of Fisher information matrices. In these downstream
tasks, additional information will be written to the MadMiner file, including the observations and event
weights.
Parameters
----------
filename : str
Path to the MadMiner file.
Returns
-------
None
"""
Path(filename) \
.parent \
.mkdir(parents=True, exist_ok=True)
if self.morpher is not None:
logger.info("Saving setup (including morphing) to %s", filename)
save_madminer_settings(
file_name=filename,
file_override=True,
parameters=self.parameters,
benchmarks=self.benchmarks,
morphing_components=self.morpher.components,
morphing_matrix=self.morpher.morphing_matrix,
systematics=self.systematics,
finite_differences=self.finite_difference_benchmarks,
finite_differences_epsilon=self.finite_difference_epsilon,
)
else:
logger.info("Saving setup (without morphing) to %s", filename)
save_madminer_settings(
file_name=filename,
file_override=True,
parameters=self.parameters,
benchmarks=self.benchmarks,
systematics=self.systematics,
finite_differences=self.finite_difference_benchmarks,
finite_differences_epsilon=self.finite_difference_epsilon,
)
def _export_cards(
self,
param_card_template_file,
mg_process_directory,
sample_benchmark=None,
param_card_filename=None,
reweight_card_filename=None,
include_param_card=True,
benchmarks=None,
):
"""
Writes out a param_card and reweight_card for MadGraph. Instead of this low-level function, it is recommended to
use `run` or `run_multiple`.
Parameters
----------
param_card_template_file : str
Path to a param_card.dat of the used model.
mg_process_directory : str
Path to the directory of the MG process.
sample_benchmark : str or None, optional
Name of the benchmark used for sampling. If None, the very first defined benchmark is used. Default value:
None.
param_card_filename : str or None, optional
Output filename for the generated param card. If None, a default filename in the MG process folder is used.
Default value: None.
reweight_card_filename : str or None, optional
str or None. Output filename for the generated reweight card. If None, a default filename in the MG process
folder is used. Default value: None.
include_param_card : bool, optional
If False, no param card is exported, only a reweight card
benchmarks : None or OrderedDict, optional
If None, uses all benchmarks. Otherwise uses these benchmarks.
Returns
-------
None
"""
if param_card_filename is None or reweight_card_filename is None:
logger.info("Creating param and reweight cards in %s",
mg_process_directory)
else:
logger.info("Creating param and reweight cards in %s, %s",
param_card_filename, reweight_card_filename)
if benchmarks is None:
benchmarks = self.benchmarks
# Check status
assert self.default_benchmark is not None
assert len(self.benchmarks) > 0
# Default benchmark
if sample_benchmark is None:
sample_benchmark = self.default_benchmark
# Export param card
if include_param_card:
export_param_card(
benchmark=benchmarks[sample_benchmark],
parameters=self.parameters,
param_card_template_file=param_card_template_file,
mg_process_directory=mg_process_directory,
param_card_filename=param_card_filename,
)
# Export reweight card
export_reweight_card(
sample_benchmark=sample_benchmark,
benchmarks=benchmarks,
parameters=self.parameters,
mg_process_directory=mg_process_directory,
reweight_card_filename=reweight_card_filename,
)
def run(
self,
mg_directory,
proc_card_file,
param_card_template_file,
run_card_file=None,
mg_process_directory=None,
pythia8_card_file=None,
configuration_file=None,
sample_benchmark=None,
is_background=False,
only_prepare_script=False,
ufo_model_directory=None,
log_directory=None,
temp_directory=None,
initial_command=None,
systematics=None,
order="LO",
python_executable=None,
):
"""
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for one combination of cards.
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for multiple combinations of run_cards or importance samplings (`sample_benchmarks`).
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Parameters
----------
mg_directory : str
Path to the MadGraph 5 base directory.
proc_card_file : str
Path to the process card that tells MadGraph how to generate the process.
param_card_template_file : str
Path to a param card that will be used as template to create the
appropriate param cards for these runs.
run_card_file : str
Paths to the MadGraph run card. If None, the default run_card is used.
mg_process_directory : str or None, optional
Path to the MG process directory. If None, MadMiner uses ./MG_process. Default value: None.
pythia8_card_file : str or None, optional
Path to the MadGraph Pythia8 card. If None, the card present in the process folder is used.
Default value: None.
configuration_file : str, optional
Path to the MadGraph me5_configuration card. If None, the card present in the process folder
is used. Default value: None.
sample_benchmark : list of str or None, optional
Lists the names of benchmarks that should be used to sample events. A different sampling does not change
the expected differential cross sections, but will change which regions of phase space have many events
(small variance) or few events (high variance). If None, the benchmark added first is used. Default value:
None.
is_background : bool, optional
Should be True for background processes, i.e. process in which the differential cross section does not
depend on the parameters (i.e. is the same for all benchmarks). In this case, no reweighting is run, which
can substantially speed up the event generation. Default value: False.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
ufo_model_directory : str or None, optional
Path to an UFO model directory that should be used, but is not yet installed in mg_directory/models. The
model will be copied to the MadGraph model directory before the process directory is generated. (Default
value = None.
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
temp_directory : str or None, optional
Path to a temporary directory. If None, a system default is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
Default value: None.
systematics : None or list of str, optional
If list of str, defines which systematics are used for this run.
order : 'LO' or 'NLO', optional
Differentiates between LO and NLO order runs. Minor changes to writing, reading and naming cards.
Default value: 'LO'
python_executable : None or str, optional
Provides a path to the Python executable that should be used to call MadMiner. Default: None.
Returns
-------
None
"""
if sample_benchmark is None:
sample_benchmark = self.default_benchmark
self.run_multiple(
mg_directory=mg_directory,
proc_card_file=proc_card_file,
param_card_template_file=param_card_template_file,
run_card_files=[run_card_file],
mg_process_directory=mg_process_directory,
pythia8_card_file=pythia8_card_file,
configuration_file=configuration_file,
sample_benchmarks=[sample_benchmark],
is_background=is_background,
only_prepare_script=only_prepare_script,
ufo_model_directory=ufo_model_directory,
log_directory=log_directory,
temp_directory=temp_directory,
initial_command=initial_command,
systematics=systematics,
order=order,
python_executable=python_executable,
)
def run_multiple(
self,
mg_directory,
proc_card_file,
param_card_template_file,
run_card_files,
mg_process_directory=None,
pythia8_card_file=None,
configuration_file=None,
sample_benchmarks=None,
is_background=False,
only_prepare_script=False,
ufo_model_directory=None,
log_directory=None,
temp_directory=None,
initial_command=None,
systematics=None,
order="LO",
python_executable=None,
):
"""
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for multiple combinations of run_cards or importance samplings (`sample_benchmarks`).
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Parameters
----------
mg_directory : str
Path to the MadGraph 5 base directory.
proc_card_file : str
Path to the process card that tells MadGraph how to generate the process.
param_card_template_file : str
Path to a param card that will be used as template to create the appropriate param cards for these runs.
run_card_files : list of str
Paths to the MadGraph run card.
mg_process_directory : str or None, optional
Path to the MG process directory. If None, MadMiner uses ./MG_process. Default value: None.
pythia8_card_file : str, optional
Path to the MadGraph Pythia8 card. If None, the card present in the process folder
is used. Default value: None.
configuration_file : str, optional
Path to the MadGraph me5_configuration card. If None, the card present in the process folder
is used. Default value: None.
sample_benchmarks : list of str or None, optional
Lists the names of benchmarks that should be used to sample events. A different sampling does not change
the expected differential cross sections, but will change which regions of phase space have many events
(small variance) or few events (high variance). If None, a run is started for each of the benchmarks, which
should map out all regions of phase space well. Default value: None.
is_background : bool, optional
Should be True for background processes, i.e. process in which the differential cross section does not
depend on the parameters (i.e. is the same for all benchmarks). In this case, no reweighting is run, which
can substantially speed up the event generation. Default value: False.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
ufo_model_directory : str or None, optional
Path to an UFO model directory that should be used, but is not yet installed in mg_directory/models. The
model will be copied to the MadGraph model directory before the process directory is generated. (Default
value = None)
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
temp_directory : str or None, optional
Path to a temporary directory. If None, a system default is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
If not specified and `python2_override` is True, it adds the user-installed Python2 binaries to the PATH.
Default value: None.
systematics : None or list of str, optional
If list of str, defines which systematics are used for these runs.
order : 'LO' or 'NLO', optional
Differentiates between LO and NLO order runs. Minor changes to writing, reading and naming cards.
Default value: 'LO'
python_executable : None or str, optional
Provides a path to the Python executable that should be used to call MadMiner. Default: None.
Returns
-------
None
"""
# Defaults
if mg_process_directory is None:
mg_process_directory = "./MG_process"
if temp_directory is None:
temp_directory = tempfile.gettempdir()
if log_directory is None:
log_directory = "./logs"
if sample_benchmarks is None:
sample_benchmarks = [
benchmark for benchmark in self.benchmarks.keys()
]
# This snippet is useful when using virtual envs.
# (Derives from a Python2 - Python3 issue).
# Ref: https://github.com/madminer-tool/madminer/issues/422
if python_executable and initial_command is None:
logger.info(f"Adding {python_executable} bin folder to PATH")
binary_path = os.popen(
f"command -v {python_executable}").read().strip()
binary_folder = Path(binary_path).parent
initial_command = f"export PATH={binary_folder}:$PATH"
logger.info(f"Using Python executable {binary_path}")
# Generate process folder
log_file_generate = f"{log_directory}/generate.log"
generate_mg_process(
mg_directory,
temp_directory,
proc_card_file,
mg_process_directory,
ufo_model_directory=ufo_model_directory,
initial_command=initial_command,
log_file=log_file_generate,
python_executable=python_executable,
)
# Make MadMiner folders
Path(mg_process_directory, "madminer", "cards").mkdir(parents=True,
exist_ok=True)
Path(mg_process_directory, "madminer", "scripts").mkdir(parents=True,
exist_ok=True)
# Systematics
if systematics is None:
systematics_used = self.systematics
else:
systematics_used = OrderedDict()
for key in systematics:
systematics_used[key] = self.systematics[key]
# Loop over settings
i = 0
mg_scripts = []
for run_card_file in run_card_files:
for sample_benchmark in sample_benchmarks:
# Files
script_file = f"madminer/scripts/run_{i}.sh"
log_file_run = f"run_{i}.log"
mg_commands_filename = f"madminer/cards/mg_commands_{i}.dat"
param_card_file = f"madminer/cards/param_card_{i}.dat"
reweight_card_file = f"madminer/cards/reweight_card_{i}.dat"
new_pythia8_card_file = None
if pythia8_card_file is not None:
new_pythia8_card_file = f"madminer/cards/pythia8_card_{i}.dat"
new_run_card_file = None
if run_card_file is not None:
new_run_card_file = f"madminer/cards/run_card_{i}.dat"
new_configuration_file = None
if configuration_file is not None:
new_configuration_file = f"madminer/cards/me5_configuration_{i}.txt"
logger.info("Run %s", i)
logger.info(" Sampling from benchmark: %s", sample_benchmark)
logger.info(" Original run card: %s", run_card_file)
logger.info(" Original Pythia8 card: %s", pythia8_card_file)
logger.info(" Original config card: %s",
configuration_file)
logger.info(" Copied run card: %s", new_run_card_file)
logger.info(" Copied Pythia8 card: %s",
new_pythia8_card_file)
logger.info(" Copied config card: %s",
new_configuration_file)
logger.info(" Param card: %s", param_card_file)
logger.info(" Reweight card: %s",
reweight_card_file)
logger.info(" Log file: %s", log_file_run)
# Check input
if run_card_file is None and any(
syst.type in
{SystematicType.PDF, SystematicType.SCALE}
for syst in systematics_used.values()):
logger.warning(
"Warning: No run card given, but PDF or scale variation set up. The correct systematics"
" settings are not set automatically. Make sure to set them correctly!"
)
# Create param and reweight cards
self._export_cards(
param_card_template_file,
mg_process_directory,
sample_benchmark=sample_benchmark,
param_card_filename=
f"{mg_process_directory}/{param_card_file}",
reweight_card_filename=
f"{mg_process_directory}/{reweight_card_file}",
)
# Create run card
if run_card_file is not None:
export_run_card(
template_filename=run_card_file,
run_card_filename=
f"{mg_process_directory}/{new_run_card_file}",
systematics=systematics_used,
order=order,
)
# Copy Pythia card
if pythia8_card_file is not None:
copy_file(
pythia8_card_file,
f"{mg_process_directory}/{new_pythia8_card_file}")
# Copy Configuration card
if configuration_file is not None:
copy_file(
configuration_file,
f"{mg_process_directory}/{new_configuration_file}")
# Run MG and Pythia
if only_prepare_script:
mg_script = setup_mg_with_scripts(
mg_process_directory,
proc_card_filename_from_mgprocdir=mg_commands_filename,
run_card_file_from_mgprocdir=new_run_card_file,
param_card_file_from_mgprocdir=param_card_file,
reweight_card_file_from_mgprocdir=reweight_card_file,
pythia8_card_file_from_mgprocdir=new_pythia8_card_file,
configuration_file_from_mgprocdir=
new_configuration_file,
is_background=is_background,
script_file_from_mgprocdir=script_file,
initial_command=initial_command,
log_dir=log_directory,
log_file_from_logdir=log_file_run,
python_executable=python_executable,
order=order,
)
mg_scripts.append(mg_script)
else:
run_mg(
mg_directory,
mg_process_directory,
f"{mg_process_directory}/{mg_commands_filename}",
f"{mg_process_directory}/{new_run_card_file}",
f"{mg_process_directory}/{param_card_file}",
f"{mg_process_directory}/{reweight_card_file}",
None if new_pythia8_card_file is None else
f"{mg_process_directory}/{new_pythia8_card_file}",
None if new_configuration_file is None else
f"{mg_process_directory}/{new_configuration_file}",
is_background=is_background,
initial_command=initial_command,
log_file=f"{log_directory}/{log_file_run}",
python_executable=python_executable,
order=order,
)
i += 1
n_runs_total = i
# Master shell script
if only_prepare_script:
master_script_filename = f"{mg_process_directory}/madminer/run.sh"
create_master_script(
log_directory,
master_script_filename,
mg_directory,
mg_process_directory,
mg_scripts,
)
logger.info(
"To generate events, please run:\n\n %s [MG_directory] [MG_process_directory] [log_dir]\n\n",
master_script_filename,
)
else:
expected_event_files = [
f"{mg_process_directory}/Events/run_{(i+1):02d}"
for i in range(n_runs_total)
]
expected_event_files = "\n".join(expected_event_files)
logger.info(
"Finished running MadGraph! Please check that events were successfully generated in the following "
"folders:\n\n%s\n\n",
expected_event_files,
)
def reweight_existing_sample(
self,
mg_process_directory,
run_name,
param_card_template_file,
sample_benchmark,
reweight_benchmarks=None,
only_prepare_script=False,
log_directory=None,
initial_command=None,
):
"""
High-level function that adds the weights required for MadMiner to an existing sample.
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Currently does not support adding systematics.
Parameters
----------
mg_process_directory : str
Path to the MG process directory. If None, MadMiner uses ./MG_process.
run_name : str
Run name.
param_card_template_file : str
Path to a param card that will be used as template to create the appropriate param cards for these runs.
sample_benchmark : str
The name of the benchmark used to generate this sample.
reweight_benchmarks : list of str or None
Lists the names of benchmarks to which the sample should be reweighted. If None, all benchmarks (except
sample_benchmarks) are used.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
Default value: None.
Returns
-------
None
"""
# TODO: check that we don't reweight to benchmarks that already have weights in the LHE file
# TODO: add systematics
# Defaults
if log_directory is None:
log_directory = "./logs"
# Make MadMiner folders
Path(mg_process_directory, "madminer", "cards").mkdir(parents=True,
exist_ok=True)
Path(mg_process_directory, "madminer", "scripts").mkdir(parents=True,
exist_ok=True)
# Files
script_file = "madminer/scripts/run_reweight.sh"
log_file_run = "reweight.log"
reweight_card_file = "/madminer/cards/reweight_card_reweight.dat"
# Missing benchmarks
missing_benchmarks = OrderedDict()
for benchmark_name in reweight_benchmarks:
missing_benchmarks[benchmark_name] = self.benchmarks[
benchmark_name]
# Inform user
logger.info("Reweighting setup")
logger.info(" Originally sampled from benchmark: %s",
sample_benchmark)
logger.info(" Now reweighting to benchmarks: %s",
reweight_benchmarks)
logger.info(" Reweight card: %s",
reweight_card_file)
logger.info(" Log file: %s", log_file_run)
# Create param and reweight cards
self._export_cards(
param_card_template_file,
mg_process_directory,
sample_benchmark=sample_benchmark,
reweight_card_filename=
f"{mg_process_directory}/{reweight_card_file}",
include_param_card=False,
benchmarks=missing_benchmarks,
)
# Run reweighting
if only_prepare_script:
call_instruction = setup_mg_reweighting_with_scripts(
mg_process_directory,
run_name=run_name,
reweight_card_file_from_mgprocdir=reweight_card_file,
script_file_from_mgprocdir=script_file,
initial_command=initial_command,
log_dir=log_directory,
log_file_from_logdir=log_file_run,
)
logger.info("To generate events, please run:\n\n %s \n\n",
call_instruction)
else:
run_mg_reweighting(
mg_process_directory,
run_name=run_name,
reweight_card_file=
f"{mg_process_directory}/{reweight_card_file}",
initial_command=initial_command,
log_file=f"{log_directory}/{log_file_run}",
)
logger.info(
"Finished running reweighting! Please check that events were successfully reweighted in the following "
"folder:\n\n %s/Events/%s \n\n",
mg_process_directory,
run_name,
)
class MadMiner:
"""
The central class to manage parameter spaces, benchmarks, and the generation of events through MadGraph and
Pythia.
An instance of this class is the starting point of most MadMiner applications. It is typically used in four steps:
* Defining the parameter space through `MadMiner.add_parameter`
* Defining the benchmarks, i.e. the points at which the squared matrix elements will be evaluated in MadGraph, with
`MadMiner.add_benchmark()` or, if operator morphing is used, with `MadMiner.set_benchmarks_from_morphing()`
* Saving this setup with `MadMiner.save()` (it can be loaded in a new instance with `MadMiner.load()`)
* Running MadGraph and Pythia with the appropriate settings with `MadMiner.run()` or `MadMiner.run_multiple()` (the
latter allows the user to combine runs from multiple run cards and sampling points)
Please see the tutorial for a hands-on introduction to its methods.
"""
def __init__(self):
self.parameters = OrderedDict()
self.benchmarks = OrderedDict()
self.default_benchmark = None
self.morpher = None
self.export_morphing = False
self.systematics = OrderedDict()
def add_parameter(
self,
lha_block,
lha_id,
parameter_name=None,
param_card_transform=None,
morphing_max_power=2,
parameter_range=(0.0, 1.0),
):
"""
Adds an individual parameter.
Parameters
----------
lha_block : str
The name of the LHA block as used in the param_card. Case-sensitive.
lha_id : int
The LHA id as used in the param_card.
parameter_name : str or None
An internal name for the parameter. If None, a the default 'benchmark_i' is used.
morphing_max_power : int or tuple of int
The maximal power with which this parameter contributes to the
squared matrix element of the process of interest. If a tuple is given, gives this
maximal power for each of several operator configurations. Typically at tree level,
this maximal number is 2 for parameters that affect one vertex (e.g. only production
or only decay of a particle), and 4 for parameters that affect two vertices (e.g.
production and decay). Default value: 2.
param_card_transform : None or str
Represents a one-parameter function mapping the parameter
(`"theta"`) to the value that should be written in the parameter cards. This
str is parsed by Python's `eval()` function, and `"theta"` is parsed as the
parameter value. Default value: None.
parameter_range : tuple of float
The range of parameter values of primary interest. Only affects the
basis optimization. Default value: (0., 1.).
Returns
-------
None
"""
# Default names
if parameter_name is None:
parameter_name = "parameter_" + str(len(self.parameters))
# Check and sanitize input
assert isinstance(
parameter_name,
six.string_types), "Parameter name is not a string: {}".format(
parameter_name)
assert isinstance(
lha_block,
six.string_types), "LHA block is not a string: {}".format(
lha_block)
assert isinstance(lha_id,
int), "LHA id is not an integer: {}".format(lha_id)
parameter_name = parameter_name.replace(" ", "_")
parameter_name = parameter_name.replace("-", "_")
assert parameter_name not in self.parameters, "Parameter name exists already: {}".format(
parameter_name)
if isinstance(morphing_max_power, int):
morphing_max_power = (morphing_max_power, )
# Add parameter
self.parameters[parameter_name] = (lha_block, lha_id,
morphing_max_power, parameter_range,
param_card_transform)
# After manually adding parameters, the morphing information is not accurate anymore
self.morpher = None
logger.info(
"Added parameter %s (LHA: %s %s, maximal power in squared ME: %s, range: %s)",
parameter_name,
lha_block,
lha_id,
morphing_max_power,
parameter_range,
)
# Reset benchmarks
if len(self.benchmarks) > 0:
logger.warning("Resetting benchmarks and morphing")
self.benchmarks = OrderedDict()
self.default_benchmark = None
self.morpher = None
self.export_morphing = False
def set_parameters(self, parameters=None):
"""
Manually sets all parameters, overwriting previously added parameters.
Parameters
----------
parameters : dict or list or None, optional
If parameters is None, resets parameters. If parameters is an dict, the keys should be str and give the
parameter names, and the values are tuples of the form (LHA_block, LHA_ID, morphing_max_power, param_min,
param_max) or of the form (LHA_block, LHA_ID). If parameters is a list, the items should be tuples of the
form (LHA_block, LHA_ID). Default value: None.
Returns
-------
None
"""
if parameters is None:
parameters = OrderedDict()
self.parameters = OrderedDict()
if isinstance(parameters, dict):
for key, values in six.iteritems(parameters):
if len(values) == 5:
self.add_parameter(
lha_block=values[0],
lha_id=values[1],
parameter_name=key,
parameter_range=[values[3], values[4]],
morphing_max_power=values[2],
)
elif len(values) == 2:
self.add_parameter(lha_block=values[0],
lha_id=values[1],
parameter_name=key)
else:
raise ValueError(
"Parameter properties has unexpected length: {0}".
format(values))
else:
for values in parameters:
assert len(
values
) == 2, "Parameter list entry does not have length 2: {0}".format(
values)
self.add_parameter(values[0], values[1])
# After manually adding parameters, the morphing information is not accurate anymore
if len(self.benchmarks) > 0:
logger.warning("Resetting benchmarks and morphing")
self.benchmarks = OrderedDict()
self.default_benchmark = None
self.morpher = None
self.export_morphing = False
def add_benchmark(self,
parameter_values,
benchmark_name=None,
verbose=True):
"""
Manually adds an individual benchmark, that is, a parameter point that will be evaluated by MadGraph.
If this command is called before
Parameters
----------
parameter_values : dict
The keys of this dict should be the parameter names and the values the corresponding parameter values.
benchmark_name : str or None, optional
Name of benchmark. If None, a default name is used. Default value: None.
verbose : bool, optional
If True, prints output about each benchmark. Default value: True.
Returns
-------
None
Raises
------
RuntimeError
If a benchmark with the same name already exists, if parameter_values is not a dict, or if a key of
parameter_values does not correspond to a defined parameter.
"""
# Default names
if benchmark_name is None:
benchmark_name = "benchmark_" + str(len(self.benchmarks))
# Check input
if not isinstance(parameter_values, dict):
raise RuntimeError(
"Parameter values are not a dict: {}".format(parameter_values))
for key, value in six.iteritems(parameter_values):
if key not in self.parameters:
raise RuntimeError("Unknown parameter: {0}".format(key))
if benchmark_name in self.benchmarks:
raise RuntimeError(
"Benchmark name {} exists already".format(benchmark_name))
# Add benchmark
self.benchmarks[benchmark_name] = parameter_values
# If first benchmark, this will be the default for sampling
if len(self.benchmarks) == 1:
self.default_benchmark = benchmark_name
if verbose:
logger.info("Added benchmark %s: %s)", benchmark_name,
format_benchmark(parameter_values))
else:
logger.debug("Added benchmark %s: %s)", benchmark_name,
format_benchmark(parameter_values))
def set_benchmarks(self, benchmarks=None, verbose=True):
"""
Manually sets all benchmarks, that is, parameter points that will be evaluated by MadGraph. Calling this
function overwrites all previously defined benchmarks.
Parameters
----------
benchmarks : dict or list or None, optional
Specifies all benchmarks. If None, all benchmarks are reset. If dict, the keys are the benchmark names and
the values are dicts of the form {parameter_name:value}. If list, the entries are dicts
{parameter_name:value} (and the benchmark names are chosen automatically). Default value: None.
verbose : bool, optional
If True, prints output about each benchmark. Default value: True.
Returns
-------
None
"""
if benchmarks is None:
benchmarks = OrderedDict()
self.benchmarks = OrderedDict()
self.default_benchmark = None
if isinstance(benchmarks, dict):
for name, values in six.iteritems(benchmarks):
self.add_benchmark(values, name, verbose=verbose)
else:
for values in benchmarks:
self.add_benchmark(values)
# After manually adding benchmarks, the morphing information is not accurate anymore
if self.morpher is not None:
logger.warning("Reset morphing")
self.morpher = None
self.export_morphing = False
def set_morphing(self,
max_overall_power=4,
n_bases=1,
include_existing_benchmarks=True,
n_trials=100,
n_test_thetas=100):
"""
Sets up the morphing environment.
Sets benchmarks, i.e. parameter points that will be evaluated by MadGraph, for a morphing algorithm, and
calculates all information required for morphing. Morphing is a technique that allows MadMax to infer the full
probability distribution `p(x_i | theta)` for each simulated event `x_i` and any `theta`, not just the
benchmarks.
The morphing basis is optimized with respect to the expected mean squared morphing weights over the parameter
region of interest. If keep_existing_benchmarks=True, benchmarks defined previously will be incorporated in the
morphing basis and only the remaining basis points will be optimized.
Note that any subsequent call to `set_benchmarks` or `add_benchmark` will overwrite the morphing setup. The
correct order is therefore to manually define benchmarks first, using `set_benchmarks` or `add_benchmark`, and
then to create the morphing setup and complete the basis by calling
`set_benchmarks_from_morphing(keep_existing_benchmarks=True)`.
Parameters
----------
max_overall_power : int or tuple of int, optional
The maximal sum of powers of all parameters contributing to the squared matrix element. If a tuple is given,
gives the maximal sum of powers for each of several operator configurations (see `add_parameter`).
Typically, if parameters can affect the couplings at n vertices, this number is 2n. Default value: 4.
n_bases : int, optional
The number of morphing bases generated. If n_bases > 1, multiple bases are combined, and the
weights for each basis are reduced by a factor 1 / n_bases. Currently only the default choice of 1 is
fully implemented. Do not use any other value for now. Default value: 1.
include_existing_benchmarks : bool, optional
If True, the previously defined benchmarks are included in the morphing basis. In that case, the number of
free parameters in the optimization routine is reduced. If False, the existing benchmarks will still be
simulated, but are not part of the morphing routine. Default value: True.
n_trials : int, optional
Number of random basis configurations tested in the optimization procedure. A larger number will increase
the run time of the optimization, but lead to better results. Default value: 100.
n_test_thetas : int, optional
Number of random parameter points used to evaluate the expected mean squared morphing weights. A larger
number will increase the run time of the optimization, but lead to better results. Default value: 100.
Returns
-------
None
"""
logger.info("Optimizing basis for morphing")
if isinstance(max_overall_power, int):
max_overall_power = (max_overall_power, )
morpher = PhysicsMorpher(parameters_from_madminer=self.parameters)
morpher.find_components(max_overall_power)
if include_existing_benchmarks:
n_predefined_benchmarks = len(self.benchmarks)
basis = morpher.optimize_basis(
n_bases=n_bases,
fixed_benchmarks_from_madminer=self.benchmarks,
n_trials=n_trials,
n_test_thetas=n_test_thetas,
)
else:
n_predefined_benchmarks = 0
basis = morpher.optimize_basis(n_bases=n_bases,
fixed_benchmarks_from_madminer=None,
n_trials=n_trials,
n_test_thetas=n_test_thetas)
basis.update(self.benchmarks)
self.set_benchmarks(basis, verbose=False)
self.morpher = morpher
self.export_morphing = True
logger.info(
"Set up morphing with %s parameters, %s morphing components, %s predefined basis points, and %s "
"new basis points",
morpher.n_parameters,
morpher.n_components,
n_predefined_benchmarks,
morpher.n_components - n_predefined_benchmarks,
)
def reset_systematics(self):
self.systematics = OrderedDict()
def add_systematics(
self,
effect,
systematic_name=None,
norm_variation=1.1,
scale="mu",
scale_variations=(0.5, 1.0, 2.0),
pdf_variation="CT10",
):
"""
Parameters
----------
effect : {"norm", "scale", "pdf"}
Type of the nuisance parameter. If "norm", it will affect the overall normalization of one or multiple
samples in the process. If "scale", the nuisance parameter effect will be determined by varying
factorization or regularization scales (depending on scale_variation and scales). If "pdf", the effect
of the nuisance parameters will be determined by varying the PDF used.
systematic_name : None or str, optional
scale : {"mu", "mur", "muf"}, optional
If type is "scale", this sets whether only the regularization scale ("mur"), only the factorization scale
("muf"), or both simulatenously ("mu") are varied. Default value:
"mu".
norm_variation : float, optional
If type is "norm", this sets the relative effect of the nuisance parameter on the cross section at the
"plus 1 sigma" variation. 1.1 corresponds to a 10% increase, 0.9 to a 10% decrease relative to the nominal
cross section. Default value: 1.1.
scale_variations : tuple of float, optional
If type is "scale", this sets how the regularization and / or factorization scales are varied. A tuple
like (0.5,1.,2.) specifies the factors with which they are varied. Default value: (0.5,1.,2.0).
pdf_variation : str, optional
If type is "pdf", defines the PDF set for the variation. The option is passed along to the `--pdf` option
of MadGraph's systematics module. See https://cp3.irmp.ucl.ac.be/projects/madgraph/wiki/Systematics for a
list. The option "CT10" would, as an example, run over all the eigenvectors of the CTEQ10 set. Default
value: "CT10".
Returns
-------
None
"""
# Default name
if systematic_name is None:
i = 0
while "{}_{}".format(effect,
i) in list(six.iterkeys(self.systematics)):
i += 1
systematic_name = "{}_{}".format(type, i)
systematic_name = systematic_name.replace(" ", "_")
systematic_name = systematic_name.replace("-", "_")
if effect == "pdf":
self.systematics[systematic_name] = ("pdf", pdf_variation)
elif effect == "scale":
scale_variation_string = ",".join(
[str(factor) for factor in scale_variations])
assert scale in ["mu", "mur", "muf"]
self.systematics[systematic_name] = ("scale", scale,
scale_variation_string)
elif effect == "norm":
self.systematics[systematic_name] = ("norm", norm_variation)
else:
raise ValueError(
"Unknown systematic type {}, has to be one of 'norm', 'scale', or 'pdf'!"
.format(type))
def load(self, filename, disable_morphing=False):
"""
Loads MadMiner setup from a file. All parameters, benchmarks, and morphing settings are overwritten. See `save`
for more details.
Parameters
----------
filename : str
Path to the MadMiner file.
disable_morphing : bool, optional
If True, the morphing setup is not loaded from the file. Default value: False.
Returns
-------
None
"""
# Load data
(
self.parameters,
self.benchmarks,
_,
morphing_components,
morphing_matrix,
_,
_,
self.systematics,
_,
_,
_,
_,
) = load_madminer_settings(filename, include_nuisance_benchmarks=False)
logger.info("Found %s parameters:", len(self.parameters))
for key, values in six.iteritems(self.parameters):
logger.info(
" %s (LHA: %s %s, maximal power in squared ME: %s, range: %s)",
key,
values[0],
values[1],
values[2],
values[3],
)
logger.info("Found %s benchmarks:", len(self.benchmarks))
for key, values in six.iteritems(self.benchmarks):
logger.info(" %s: %s", key, format_benchmark(values))
if self.default_benchmark is None:
self.default_benchmark = key
# Morphing
self.morpher = None
self.export_morphing = False
if morphing_matrix is not None and morphing_components is not None and not disable_morphing:
self.morpher = PhysicsMorpher(self.parameters)
self.morpher.set_components(morphing_components)
self.morpher.set_basis(self.benchmarks,
morphing_matrix=morphing_matrix)
self.export_morphing = True
logger.info("Found morphing setup with %s components",
len(morphing_components))
else:
logger.info("Did not find morphing setup.")
# Systematics setup
if len(self.systematics) == 0:
logger.info("Did not find systematics setup.")
else:
logger.info(
"Found systematics setup with %s nuisance parameter groups",
len(self.systematics))
for key, value in six.iteritems(self.systematics):
logger.debug(" %s: %s", key,
" / ".join(str(x) for x in value))
def save(self, filename):
"""
Saves MadMiner setup into a file.
The file format follows the HDF5 standard. The saved information includes:
* the parameter definitions,
* the benchmark points,
* the systematics setup (if defined), and
* the morphing setup (if defined).
This file is an important input to later stages in the analysis chain, including the processing of generated
events, extraction of training samples, and calculation of Fisher information matrices. In these downstream
tasks, additional information will be written to the MadMiner file, including the observations and event
weights.
Parameters
----------
filename : str
Path to the MadMiner file.
Returns
-------
None
"""
create_missing_folders([os.path.dirname(filename)])
if self.morpher is not None:
logger.info("Saving setup (including morphing) to %s", filename)
save_madminer_settings(
filename=filename,
parameters=self.parameters,
benchmarks=self.benchmarks,
morphing_components=self.morpher.components,
morphing_matrix=self.morpher.morphing_matrix,
systematics=self.systematics,
overwrite_existing_files=True,
)
else:
logger.info("Saving setup (without morphing) to %s", filename)
save_madminer_settings(
filename=filename,
parameters=self.parameters,
benchmarks=self.benchmarks,
systematics=self.systematics,
overwrite_existing_files=True,
)
def _export_cards(
self,
param_card_template_file,
mg_process_directory,
sample_benchmark=None,
param_card_filename=None,
reweight_card_filename=None,
include_param_card=True,
benchmarks=None,
):
"""
Writes out a param_card and reweight_card for MadGraph. Instead of this low-level function, it is recommended to
use `run` or `run_multiple`.
Parameters
----------
param_card_template_file : str
Path to a param_card.dat of the used model.
mg_process_directory : str
Path to the directory of the MG process.
sample_benchmark : str or None, optional
Name of the benchmark used for sampling. If None, the very first defined benchmark is used. Default value:
None.
param_card_filename : str or None, optional
Output filename for the generated param card. If None, a default filename in the MG process folder is used.
Default value: None.
reweight_card_filename : str or None, optional
str or None. Output filename for the generated reweight card. If None, a default filename in the MG process
folder is used. Default value: None.
include_param_card : bool, optional
If False, no param card is exported, only a reweight card
benchmarks : None or OrderedDict, optional
If None, uses all benchmarks. Otherwise uses these benchmarks.
Returns
-------
None
"""
if param_card_filename is None or reweight_card_filename is None:
logger.info("Creating param and reweight cards in %s",
mg_process_directory)
else:
logger.info("Creating param and reweight cards in %s, %s",
param_card_filename, reweight_card_filename)
if benchmarks is None:
benchmarks = self.benchmarks
# Check status
assert self.default_benchmark is not None
assert len(self.benchmarks) > 0
# Default benchmark
if sample_benchmark is None:
sample_benchmark = self.default_benchmark
# Export param card
if include_param_card:
export_param_card(
benchmark=benchmarks[sample_benchmark],
parameters=self.parameters,
param_card_template_file=param_card_template_file,
mg_process_directory=mg_process_directory,
param_card_filename=param_card_filename,
)
# Export reweight card
export_reweight_card(
sample_benchmark=sample_benchmark,
benchmarks=benchmarks,
parameters=self.parameters,
mg_process_directory=mg_process_directory,
reweight_card_filename=reweight_card_filename,
)
def run(
self,
mg_directory,
proc_card_file,
param_card_template_file,
run_card_file=None,
mg_process_directory=None,
pythia8_card_file=None,
configuration_file=None,
sample_benchmark=None,
is_background=False,
only_prepare_script=False,
ufo_model_directory=None,
log_directory=None,
temp_directory=None,
initial_command=None,
python2_override=False,
systematics=None,
):
"""
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for one combination of cards.
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for multiple combinations of run_cards or importance samplings (`sample_benchmarks`).
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Parameters
----------
mg_directory : str
Path to the MadGraph 5 base directory.
proc_card_file : str
Path to the process card that tells MadGraph how to generate the process.
param_card_template_file : str
Path to a param card that will be used as template to create the
appropriate param cards for these runs.
run_card_file : str
Paths to the MadGraph run card. If None, the default run_card is used.
mg_process_directory : str or None, optional
Path to the MG process directory. If None, MadMiner uses ./MG_process. Default value: None.
pythia8_card_file : str or None, optional
Path to the MadGraph Pythia8 card. If None, the card present in the process folder is used.
Default value: None.
configuration_file : str, optional
Path to the MadGraph me5_configuration card. If None, the card present in the process folder
is used. Default value: None.
sample_benchmark : list of str or None, optional
Lists the names of benchmarks that should be used to sample events. A different sampling does not change
the expected differential cross sections, but will change which regions of phase space have many events
(small variance) or few events (high variance). If None, the benchmark added first is used. Default value:
None.
is_background : bool, optional
Should be True for background processes, i.e. process in which the differential cross section does not
depend on the parameters (i.e. is the same for all benchmarks). In this case, no reweighting is run, which
can substantially speed up the event generation. Default value: False.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
ufo_model_directory : str or None, optional
Path to an UFO model directory that should be used, but is not yet installed in mg_directory/models. The
model will be copied to the MadGraph model directory before the process directory is generated. (Default
value = None.
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
temp_directory : str or None, optional
Path to a temporary directory. If None, a system default is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
Default value: None.
python2_override : bool, optional
If True, MadMiner explicitly calls "python2" instead of relying on the system Python version to be
Python 2.6 or Python 2.7. If you use systematics, make sure that the python interface of LHAPDF was compiled
with the Python version you are using. Default: False.
systematics : None or list of str, optional
If list of str, defines which systematics are used for this run.
Returns
-------
None
"""
if sample_benchmark is None:
sample_benchmark = self.default_benchmark
self.run_multiple(
mg_directory=mg_directory,
proc_card_file=proc_card_file,
param_card_template_file=param_card_template_file,
run_card_files=[run_card_file],
mg_process_directory=mg_process_directory,
pythia8_card_file=pythia8_card_file,
configuration_file=configuration_file,
sample_benchmarks=[sample_benchmark],
is_background=is_background,
only_prepare_script=only_prepare_script,
ufo_model_directory=ufo_model_directory,
log_directory=log_directory,
temp_directory=temp_directory,
initial_command=initial_command,
python2_override=python2_override,
systematics=systematics,
)
def run_multiple(
self,
mg_directory,
proc_card_file,
param_card_template_file,
run_card_files,
mg_process_directory=None,
pythia8_card_file=None,
configuration_file=None,
sample_benchmarks=None,
is_background=False,
only_prepare_script=False,
ufo_model_directory=None,
log_directory=None,
temp_directory=None,
initial_command=None,
python2_override=False,
systematics=None,
):
"""
High-level function that creates the the MadGraph process, all required cards, and prepares or runs the event
generation for multiple combinations of run_cards or importance samplings (`sample_benchmarks`).
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Parameters
----------
mg_directory : str
Path to the MadGraph 5 base directory.
proc_card_file : str
Path to the process card that tells MadGraph how to generate the process.
param_card_template_file : str
Path to a param card that will be used as template to create the appropriate param cards for these runs.
run_card_files : list of str
Paths to the MadGraph run card.
mg_process_directory : str or None, optional
Path to the MG process directory. If None, MadMiner uses ./MG_process. Default value: None.
pythia8_card_file : str, optional
Path to the MadGraph Pythia8 card. If None, the card present in the process folder
is used. Default value: None.
configuration_file : str, optional
Path to the MadGraph me5_configuration card. If None, the card present in the process folder
is used. Default value: None.
sample_benchmarks : list of str or None, optional
Lists the names of benchmarks that should be used to sample events. A different sampling does not change
the expected differential cross sections, but will change which regions of phase space have many events
(small variance) or few events (high variance). If None, a run is started for each of the benchmarks, which
should map out all regions of phase space well. Default value: None.
is_background : bool, optional
Should be True for background processes, i.e. process in which the differential cross section does not
depend on the parameters (i.e. is the same for all benchmarks). In this case, no reweighting is run, which
can substantially speed up the event generation. Default value: False.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
ufo_model_directory : str or None, optional
Path to an UFO model directory that should be used, but is not yet installed in mg_directory/models. The
model will be copied to the MadGraph model directory before the process directory is generated. (Default
value = None)
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
temp_directory : str or None, optional
Path to a temporary directory. If None, a system default is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
If not specified and `python2_override` is True, it adds the user-installed Python2 binaries to the PATH.
Default value: None.
python2_override : bool, optional
If True, MadMiner explicitly calls "python2" instead of relying on the system Python version to be
Python 2.6 or Python 2.7. If you use systematics, make sure that the python interface of LHAPDF was compiled
with the Python version you are using. Default: False.
systematics : None or list of str, optional
If list of str, defines which systematics are used for these runs.
Returns
-------
None
"""
# Defaults
if mg_process_directory is None:
mg_process_directory = "./MG_process"
if temp_directory is None:
temp_directory = tempfile.gettempdir()
if log_directory is None:
log_directory = "./logs"
if sample_benchmarks is None:
sample_benchmarks = [benchmark for benchmark in self.benchmarks]
# Gives 'python2_override' full power if 'initial_command' is empty.
# (Reference: https://github.com/diana-hep/madminer/issues/422)
if python2_override and initial_command is None:
logger.info("Adding Python2.7 bin folder to PATH")
binary_path = os.popen("command -v python2.7").read().strip()
binary_folder = os.path.dirname(os.path.realpath(binary_path))
initial_command = "export PATH={}:$PATH".format(binary_folder)
# Generate process folder
log_file_generate = log_directory + "/generate.log"
generate_mg_process(
mg_directory,
temp_directory,
proc_card_file,
mg_process_directory,
ufo_model_directory=ufo_model_directory,
initial_command=initial_command,
log_file=log_file_generate,
explicit_python_call=python2_override,
)
# Make MadMiner folders
create_missing_folders([
mg_process_directory + "/madminer",
mg_process_directory + "/madminer/cards",
mg_process_directory + "/madminer/scripts",
])
# Systematics
if systematics is None:
systematics_used = self.systematics
else:
systematics_used = OrderedDict()
for key in systematics:
systematics_used[key] = self.systematics[key]
# Loop over settings
i = 0
mg_scripts = []
for run_card_file in run_card_files:
for sample_benchmark in sample_benchmarks:
# Files
script_file = "madminer/scripts/run_{}.sh".format(i)
log_file_run = "run_{}.log".format(i)
mg_commands_filename = "madminer/cards/mg_commands_{}.dat".format(
i)
param_card_file = "madminer/cards/param_card_{}.dat".format(i)
reweight_card_file = "madminer/cards/reweight_card_{}.dat".format(
i)
new_pythia8_card_file = None
if pythia8_card_file is not None:
new_pythia8_card_file = "madminer/cards/pythia8_card_{}.dat".format(
i)
new_run_card_file = None
if run_card_file is not None:
new_run_card_file = "madminer/cards/run_card_{}.dat".format(
i)
new_configuration_file = None
if configuration_file is not None:
new_configuration_file = "madminer/cards/me5_configuration_{}.txt".format(
i)
logger.info("Run %s", i)
logger.info(" Sampling from benchmark: %s", sample_benchmark)
logger.info(" Original run card: %s", run_card_file)
logger.info(" Original Pythia8 card: %s", pythia8_card_file)
logger.info(" Original config card: %s",
configuration_file)
logger.info(" Copied run card: %s", new_run_card_file)
logger.info(" Copied Pythia8 card: %s",
new_pythia8_card_file)
logger.info(" Copied config card: %s",
new_configuration_file)
logger.info(" Param card: %s", param_card_file)
logger.info(" Reweight card: %s",
reweight_card_file)
logger.info(" Log file: %s", log_file_run)
# Check input
if run_card_file is None and self._check_pdf_or_scale_variation(
systematics_used):
logger.warning(
"Warning: No run card given, but PDF or scale variation set up. The correct systematics"
" settings are not set automatically. Make sure to set them correctly!"
)
# Create param and reweight cards
self._export_cards(
param_card_template_file,
mg_process_directory,
sample_benchmark=sample_benchmark,
param_card_filename=mg_process_directory + "/" +
param_card_file,
reweight_card_filename=mg_process_directory + "/" +
reweight_card_file,
)
# Create run card
if run_card_file is not None:
export_run_card(
template_filename=run_card_file,
run_card_filename=mg_process_directory + "/" +
new_run_card_file,
systematics=systematics_used,
)
# Copy Pythia card
if pythia8_card_file is not None:
copy_file(
pythia8_card_file,
mg_process_directory + "/" + new_pythia8_card_file)
# Copy Configuration card
if configuration_file is not None:
copy_file(
configuration_file,
mg_process_directory + "/" + new_configuration_file)
# Run MG and Pythia
if only_prepare_script:
mg_script = setup_mg_with_scripts(
mg_process_directory,
proc_card_filename_from_mgprocdir=mg_commands_filename,
run_card_file_from_mgprocdir=new_run_card_file,
param_card_file_from_mgprocdir=param_card_file,
reweight_card_file_from_mgprocdir=reweight_card_file,
pythia8_card_file_from_mgprocdir=new_pythia8_card_file,
configuration_file_from_mgprocdir=
new_configuration_file,
is_background=is_background,
script_file_from_mgprocdir=script_file,
initial_command=initial_command,
log_dir=log_directory,
log_file_from_logdir=log_file_run,
explicit_python_call=python2_override,
)
mg_scripts.append(mg_script)
else:
run_mg(
mg_directory,
mg_process_directory,
mg_process_directory + "/" + mg_commands_filename,
mg_process_directory + "/" + new_run_card_file,
mg_process_directory + "/" + param_card_file,
mg_process_directory + "/" + reweight_card_file,
None if new_pythia8_card_file is None else
mg_process_directory + "/" + new_pythia8_card_file,
None if new_configuration_file is None else
mg_process_directory + "/" + new_configuration_file,
is_background=is_background,
initial_command=initial_command,
log_file=log_directory + "/" + log_file_run,
explicit_python_call=python2_override,
)
i += 1
n_runs_total = i
# Master shell script
if only_prepare_script:
master_script_filename = "{}/madminer/run.sh".format(
mg_process_directory)
create_master_script(log_directory, master_script_filename,
mg_directory, mg_process_directory,
mg_scripts)
logger.info(
"To generate events, please run:\n\n %s [MG_directory] [MG_process_directory] [log_dir]\n\n",
master_script_filename,
)
else:
expected_event_files = [
mg_process_directory + "/Events/run_{:02d}".format(i + 1)
for i in range(n_runs_total)
]
expected_event_files = "\n".join(expected_event_files)
logger.info(
"Finished running MadGraph! Please check that events were succesfully generated in the following "
"folders:\n\n%s\n\n",
expected_event_files,
)
def reweight_existing_sample(
self,
mg_process_directory,
run_name,
param_card_template_file,
sample_benchmark,
reweight_benchmarks=None,
only_prepare_script=False,
log_directory=None,
temp_directory=None,
initial_command=None,
):
"""
High-level function that adds the weights required for MadMiner to an existing sample.
If `only_prepare_scripts=True`, the event generation is not run
directly, but a bash script is created in `<process_folder>/madminer/run.sh` that will start the event
generation with the correct settings.
Currently does not support adding systematics.
Parameters
----------
mg_process_directory : str
Path to the MG process directory. If None, MadMiner uses ./MG_process.
run_name : str
Run name.
param_card_template_file : str
Path to a param card that will be used as template to create the appropriate param cards for these runs.
sample_benchmark : str
The name of the benchmark used to generate this sample.
reweight_benchmarks : list of str or None
Lists the names of benchmarks to which the sample should be reweighted. If None, all benchmarks (except
sample_benchmarks) are used.
only_prepare_script : bool, optional
If True, the event generation is not started, but instead a run.sh script is created in the process
directory. Default value: False.
log_directory : str or None, optional
Directory for log files with the MadGraph output. If None, ./logs is used. Default value: None.
initial_command : str or None, optional
Initial shell commands that have to be executed before MG is run (e.g. to load a virtual environment).
Default value: None.
Returns
-------
None
"""
# TODO: check that we don't reweight to benchmarks that already have weights in the LHE file
# TODO: add systematics
# Defaults
if log_directory is None:
log_directory = "./logs"
# Make MadMiner folders
create_missing_folders([
mg_process_directory + "/madminer",
mg_process_directory + "/madminer/cards",
mg_process_directory + "/madminer/scripts",
])
# Files
script_file = "madminer/scripts/run_reweight.sh"
log_file_run = "reweight.log"
reweight_card_file = "/madminer/cards/reweight_card_reweight.dat"
# Missing benchmarks
missing_benchmarks = OrderedDict()
for benchmark in reweight_benchmarks:
missing_benchmarks[benchmark] = self.benchmarks[benchmark]
# Inform user
logger.info("Reweighting setup")
logger.info(" Originally sampled from benchmark: %s",
sample_benchmark)
logger.info(" Now reweighting to benchmarks: %s",
reweight_benchmarks)
logger.info(" Reweight card: %s",
reweight_card_file)
logger.info(" Log file: %s", log_file_run)
# Create param and reweight cards
self._export_cards(
param_card_template_file,
mg_process_directory,
sample_benchmark=sample_benchmark,
reweight_card_filename=mg_process_directory + "/" +
reweight_card_file,
include_param_card=False,
benchmarks=missing_benchmarks,
)
# Run reweighting
if only_prepare_script:
call_instruction = setup_mg_reweighting_with_scripts(
mg_process_directory,
run_name=run_name,
reweight_card_file_from_mgprocdir=reweight_card_file,
script_file_from_mgprocdir=script_file,
initial_command=initial_command,
log_dir=log_directory,
log_file_from_logdir=log_file_run,
)
logger.info("To generate events, please run:\n\n %s \n\n",
call_instruction)
else:
run_mg_reweighting(
mg_process_directory,
run_name=run_name,
reweight_card_file=mg_process_directory + "/" +
reweight_card_file,
initial_command=initial_command,
log_file=log_directory + "/" + log_file_run,
)
logger.info(
"Finished running reweighting! Please check that events were succesfully reweighted in the following "
"folder:\n\n %s/Events/%s \n\n",
mg_process_directory,
run_name,
)
def _check_pdf_or_scale_variation(self, systematics):
for value in six.itervalues(systematics):
if value[0] in ["pdf", "scale"]:
return True
return False
class DataAnalyzer:
"""
Collects common functionality that is used when analysing data in the MadMiner file.
Parameters
----------
filename : str
Path to MadMiner file (for instance the output of `madminer.delphes.DelphesProcessor.save()`).
disable_morphing : bool, optional
If True, the morphing setup is not loaded from the file. Default value: False.
include_nuisance_parameters : bool, optional
If True, nuisance parameters are taken into account. Default value: True.
"""
def __init__(self,
filename,
disable_morphing=False,
include_nuisance_parameters=True):
# Save setup
self.include_nuisance_parameters = include_nuisance_parameters
self.madminer_filename = filename
# Load data
logger.info("Loading data from %s", filename)
(
self.parameters,
self.benchmarks,
self.benchmark_nuisance_flags,
self.morphing_components,
self.morphing_matrix,
self.observables,
self.n_samples,
self.systematics,
self.reference_benchmark,
self.nuisance_parameters,
self.n_events_generated_per_benchmark,
self.n_events_backgrounds,
self.finite_difference_benchmarks,
self.finite_difference_epsilon,
) = load_madminer_settings(
filename, include_nuisance_benchmarks=include_nuisance_parameters)
self.n_observables = len(self.observables)
self.n_parameters = len(self.parameters)
self.n_benchmarks = len(self.benchmarks)
self.n_benchmarks_phys = np.sum(
np.logical_not(self.benchmark_nuisance_flags))
self.n_nuisance_parameters = len(self.nuisance_parameters)
# Morphing
self.morpher = None
if self.morphing_matrix is not None and self.morphing_components is not None and not disable_morphing:
self.morpher = PhysicsMorpher(self.parameters)
self.morpher.set_components(self.morphing_components)
self.morpher.set_basis(self.benchmarks,
morphing_matrix=self.morphing_matrix)
# Nuisance morphing
self.nuisance_morpher = None
if self.n_nuisance_parameters > 0:
self.nuisance_morpher = NuisanceMorpher(
self.nuisance_parameters,
self.benchmarks.keys(),
self.reference_benchmark,
)
# Check event numbers
self._check_n_events()
self._report_setup()
def event_loader(
self,
start=0,
end=None,
batch_size=100000,
include_nuisance_parameters=None,
generated_close_to=None,
return_sampling_ids=False,
):
"""
Yields batches of events in the MadMiner file.
Parameters
----------
start : int, optional
First event index to load
end : int or None, optional
Last event index to load
batch_size : int, optional
Batch size
include_nuisance_parameters : bool, optional
Whether nuisance parameter benchmarks are included in the returned data
generated_close_to : None or ndarray, optional
If None, this function yields all events. Otherwise, it just yields just the events that were generated
at the closest benchmark point to a given parameter point.
return_sampling_ids : bool, optional
If True, the iterator returns the sampling IDs in addition to observables and weights.
Yields
------
observations : ndarray
Event data
weights : ndarray
Event weights
sampling_ids : int
Sampling IDs (benchmark used for sampling for signal events, -1 for background events). Only returned if
return_sampling_ids = True was set.
"""
if include_nuisance_parameters is None:
include_nuisance_parameters = self.include_nuisance_parameters
sampling_benchmark = self._find_closest_benchmark(generated_close_to)
logger.debug(
f"Sampling benchmark closest to {generated_close_to}: {sampling_benchmark}"
)
if sampling_benchmark is None:
sampling_factors = self._calculate_sampling_factors()
else:
sampling_factors = np.ones(self.n_benchmarks_phys + 1)
for data in load_events(
file_name=self.madminer_filename,
start_index=start,
final_index=end,
batch_size=batch_size,
benchmark_nuisance_flags=self.benchmark_nuisance_flags,
sampling_benchmark=sampling_benchmark,
sampling_factors=sampling_factors,
include_nuisance_params=include_nuisance_parameters,
include_sampling_ids=return_sampling_ids,
):
yield data
def weighted_events(
self,
theta=None,
nu=None,
start_event=None,
end_event=None,
derivative=False,
generated_close_to=None,
n_draws=None,
):
"""
Returns all events together with the benchmark weights (if theta is None) or weights for a given theta.
Parameters
----------
theta : None or ndarray or str, optional
If None, the function returns all benchmark weights. If str, the function returns the weights for a given
benchmark name. If ndarray, it uses morphing to calculate the weights for this value of theta. Default
value: None.
nu : None or ndarray, optional
If None, the nuisance parameters are set to their nominal values. Otherwise, and if theta is an ndarray,
sets the values of the nuisance parameters.
start_event : int
Index (in the MadMiner file) of the first event to consider.
end_event : int
Index (in the MadMiner file) of the last unweighted event to consider.
derivative : bool, optional
If True and if theta is not None, the derivative of the weights with respect to theta are returned. Default
value: False.
generated_close_to : None or int, optional
Only returns benchmarks generated from this benchmark (and background events). Default value: None.
n_draws : None or int, optional
If not None, returns only this number of events, drawn randomly.
Returns
-------
x : ndarray
Observables with shape `(n_unweighted_samples, n_observables)`.
weights : ndarray
If theta is None and derivative is False, benchmark weights with shape
`(n_unweighted_samples, n_benchmarks)` in pb. If theta is not None and derivative is True, the gradient of
the weight for the given parameter with respect to theta with shape `(n_unweighted_samples, n_gradients)`
in pb. Otherwise, weights for the given parameter theta with shape `(n_unweighted_samples,)` in pb.
"""
x, weights_benchmarks = next(
self.event_loader(
start=start_event,
end=end_event,
batch_size=None,
generated_close_to=generated_close_to,
))
# Pick events randomly
n_events = len(x)
if n_draws is not None and n_draws < n_events:
idx = np.random.choice(n_events, n_draws, replace=False)
x = x[idx]
weights_benchmarks = weights_benchmarks[idx]
elif n_draws is not None:
logger.warning(
f"Requested {n_draws} events, but only {n_events} available")
# Process and return appropriate weights
if theta is None:
return x, weights_benchmarks
elif isinstance(theta, str):
i_benchmark = list(self.benchmarks.keys()).index(theta)
return x, weights_benchmarks[:, i_benchmark]
elif derivative:
dtheta_matrix = self._get_dtheta_benchmark_matrix(theta)
gradients_theta = mdot(
dtheta_matrix, weights_benchmarks) # (n_gradients, n_samples)
gradients_theta = gradients_theta.T
return x, gradients_theta
else:
# TODO: nuisance params
if nu is not None:
raise NotImplementedError()
theta_matrix = self._get_theta_benchmark_matrix(theta)
weights_theta = mdot(theta_matrix, weights_benchmarks)
return x, weights_theta
def xsecs(
self,
thetas=None,
nus=None,
partition="all",
test_split=0.2,
validation_split=0.2,
include_nuisance_benchmarks=True,
batch_size=100000,
generated_close_to=None,
):
"""
Returns the total cross sections for benchmarks or parameter points.
Parameters
----------
thetas : None or list of (ndarray or str), optional
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing). Default value: None.
nus : None or list of (None or ndarray), optional
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
partition : {"train", "test", "validation", "all"}, optional
Which event partition to use. Default: "all".
test_split : float, optional
Fraction of events reserved for testing. Default value: 0.2.
validation_split : float, optional
Fraction of weighted events reserved for validation. Default value: 0.2.
include_nuisance_benchmarks : bool, optional
Whether to include nuisance benchmarks if thetas is None. Default value: True.
batch_size : int, optional
Size of the batches of events that are loaded into memory at the same time. Default value: 100000.
generated_close_to : None or ndarray, optional
If not None, only events originally generated from the closest benchmark to this parameter point will be
used. Default value : None.
Returns
-------
xsecs : ndarray
Calculated cross sections in pb.
xsec_uncertainties : ndarray
Cross-section uncertainties in pb. Basically calculated as sum(weights**2)**0.5.
"""
logger.debug("Calculating cross sections for thetas = %s and nus = %s",
thetas, nus)
# Inputs
if thetas is not None:
include_nuisance_benchmarks = True
if thetas is not None:
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Which events to use
if partition == "all":
start_event, end_event = None, None
correction_factor = 1.0
elif partition in ["train", "validation", "test"]:
start_event, end_event, correction_factor = self._train_validation_test_split(
partition, test_split, validation_split)
else:
raise ValueError(f"Invalid partition type: {partition}")
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
if thetas is None:
theta_matrices = np.identity(self.n_benchmarks)
else:
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
# Loop over events
xsecs = 0.0
xsec_uncertainties = 0.0
n_events = 0
for i_batch, (_, benchmark_weights) in enumerate(
self.event_loader(
start=start_event,
end=end_event,
include_nuisance_parameters=include_nuisance_benchmarks,
batch_size=batch_size,
generated_close_to=generated_close_to,
)):
n_batch, _ = benchmark_weights.shape
n_events += n_batch
# Benchmark xsecs
if thetas is None:
xsecs += np.sum(benchmark_weights, axis=0)
xsec_uncertainties += np.sum(benchmark_weights *
benchmark_weights,
axis=0)
# xsecs at given parameters(theta, nu)
else:
# Weights at nominal nuisance params (nu=0)
weights_nom = mdot(
theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
weights_sq_nom = mdot(theta_matrices, benchmark_weights *
benchmark_weights) # same
# Effect of nuisance parameters
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
weights = nuisance_factors * weights_nom
weights_sq = nuisance_factors * weights_sq_nom
# Sum up
xsecs += np.sum(weights, axis=1)
xsec_uncertainties += np.sum(weights_sq, axis=1)
if n_events == 0:
raise RuntimeError(
f"Did not find events with test_split = {test_split} "
f"and generated_close_to = {generated_close_to}")
xsec_uncertainties = np.maximum(xsec_uncertainties, 0.0)**0.5
# Correct for not using all events
xsecs *= correction_factor
xsec_uncertainties *= correction_factor
logger.debug("xsecs and uncertainties [pb]:")
for this_xsec, this_uncertainty in zip(xsecs, xsec_uncertainties):
logger.debug(" (%4f +/- %4f) pb (%4f %%)", this_xsec,
this_uncertainty, 100 * this_uncertainty / this_xsec)
return xsecs, xsec_uncertainties
def xsec_gradients(
self,
thetas,
nus=None,
partition="all",
test_split=0.2,
validation_split=0.2,
gradients="all",
batch_size=100000,
generated_close_to=None,
):
"""
Returns the gradient of total cross sections with respect to parameters.
Parameters
----------
thetas : list of (ndarray or str), optional
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing). Default value: None.
nus : None or list of (None or ndarray), optional
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
partition : {"train", "test", "validation", "all"}, optional
Which events to use. Default: "all".
test_split : float, optional
Fraction of events reserved for testing. Default value: 0.2.
validation_split : float, optional
Fraction of weighted events reserved for validation. Default value: 0.2.
gradients : {"all", "theta", "nu"}, optional
Which gradients to calculate. Default value: "all".
batch_size : int, optional
Size of the batches of events that are loaded into memory at the same time. Default value: 100000.
generated_close_to : None or ndarray, optional
If not None, only events originally generated from the closest benchmark to this parameter point will be
used. Default value : None.
Returns
-------
xsecs_gradients : ndarray
Calculated cross section gradients in pb with shape (n_gradients,).
"""
logger.debug(
f"Calculating cross section gradients for thetas = {thetas} and nus = {nus}"
)
# Inputs
include_nuisance_benchmarks = nus is not None or gradients in [
"all", "nu"
]
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
if gradients not in ["all", "theta", "nu"]:
raise RuntimeError(f"Invalid gradients type: {gradients}")
# Which events to use
if partition == "all":
start_event, end_event = None, None
correction_factor = 1.0
elif partition in ["train", "validation", "test"]:
start_event, end_event, correction_factor = self._train_validation_test_split(
partition, test_split, validation_split)
else:
raise ValueError(f"Invalid partition type: {partition}")
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
theta_matrices = np.asarray([
self._get_theta_benchmark_matrix(theta) for theta in thetas
]) # shape (n_thetas, n_benchmarks)
theta_gradient_matrices = np.asarray([
self._get_dtheta_benchmark_matrix(theta) for theta in thetas
]) # shape (n_thetas, n_gradients, n_benchmarks)
# Loop over events
xsec_gradients = 0.0
for i_batch, (_, benchmark_weights) in enumerate(
self.event_loader(
start=start_event,
end=end_event,
include_nuisance_parameters=include_nuisance_benchmarks,
batch_size=batch_size,
generated_close_to=generated_close_to,
)):
n_batch, _ = benchmark_weights.shape
logger.debug(f"Batch {i_batch+1} with {n_batch} events")
if gradients in ["all", "theta"]:
nom_gradients = mdot(
theta_gradient_matrices, benchmark_weights
) # Shape (n_thetas, n_phys_gradients, n_batch)
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights) # Shape (n_thetas, n_batch)
try:
dweight_dtheta = nuisance_factors[:, np.
newaxis, :] * nom_gradients
except TypeError:
dweight_dtheta = nom_gradients
if gradients in ["all", "nu"]:
weights_nom = mdot(
theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
nuisance_factor_gradients = np.asarray([
self.nuisance_morpher.calculate_nuisance_factor_gradients(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_nuisance_gradients, n_batch)
dweight_dnu = nuisance_factor_gradients * weights_nom[:, np.
newaxis, :]
if gradients == "all":
dweight_dall = np.concatenate((dweight_dtheta, dweight_dnu), 1)
elif gradients == "theta":
dweight_dall = dweight_dtheta
elif gradients == "nu":
dweight_dall = dweight_dnu
xsec_gradients += np.sum(dweight_dall, axis=2)
# Correct for not using all events
xsec_gradients *= correction_factor
return xsec_gradients
def _check_n_events(self):
n_events_check = \
sum(self.n_events_generated_per_benchmark) \
+ self.n_events_backgrounds
if self.n_samples != n_events_check:
logger.warning(
"Inconsistent event numbers in HDF5 file! Please recalculate them by calling "
"combine_and_shuffle(recalculate_header=True).")
def _report_setup(self):
logger.info(f"Found {self.n_parameters} parameters")
for i, param in enumerate(self.parameters.values()):
logger.info(" %s: %s", i, param)
if self.n_nuisance_parameters > 0:
logger.info(
f"Found {self.n_nuisance_parameters} nuisance parameters")
for i, param in enumerate(self.nuisance_parameters.values()):
logger.info(" %s: %s", i, param)
else:
logger.info("Did not find nuisance parameters")
logger.info(f"Found {self.n_benchmarks} benchmarks")
for benchmark in self.benchmarks.values():
if benchmark.is_nuisance:
logger.debug(" %s: systematics", benchmark.name)
else:
logger.debug(" %s", benchmark)
logger.info(f"Found {self.n_observables} observables")
for i, obs in enumerate(self.observables):
logger.debug(" %2.2s %s", i, obs)
logger.info(f"Found {self.n_samples} events")
if len(self.n_events_generated_per_benchmark) > 0:
for events, name in zip(self.n_events_generated_per_benchmark,
self.benchmarks.keys()):
logger.info(" %s signal events sampled from benchmark %s",
events, name)
if self.n_events_backgrounds is not None and self.n_events_backgrounds > 0:
logger.info(" %s background events",
self.n_events_backgrounds)
else:
logger.debug(" Did not find sample summary information")
if self.morpher is not None:
logger.info("Found morphing setup with %s components",
len(self.morphing_components))
else:
logger.info("Did not find morphing setup.")
if self.nuisance_morpher is not None:
logger.info("Found nuisance morphing setup")
else:
logger.info("Did not find nuisance morphing setup")
def _calculate_nuisance_factors(self, nus, benchmark_weights):
if self._any_nontrivial_nus(nus):
return np.asarray([
self.nuisance_morpher.calculate_nuisance_factors(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_batch)
else:
return 1.0
def _finite_differences_theta_gradient_matrices(self):
""" Constructs the matrix that translates benchmark weights to the gradient of the weight evaluated at the benchmarks """
assert self.finite_difference_benchmarks is not None
assert self.finite_difference_epsilon is not None
matrix = np.zeros(
(self.n_benchmarks, self.n_parameters,
self.n_benchmarks)) # (n_thetas, n_gradients, n_benchmarks)
benchmark_names = list(self.benchmarks.keys())
# We'll generally try to find the tuples p, i, j, k such that
# matrix[i, p, j] = - 1 / eps and matrix[i, p, i] = 1 / eps
for i, b_name in enumerate(self.benchmarks.keys()):
# For the FD-shifted benchmarks, we assume that the gradients are
# the same as at the original point, and will just copy the matrix later
copy_to = []
if b_name not in self.finite_difference_benchmarks.keys():
continue
for p, p_name in enumerate(self.parameters.keys()):
shifted_benchmark_dict = self.finite_difference_benchmarks[
b_name].shift_names
shifted_benchmark_name = shifted_benchmark_dict[p_name]
j = benchmark_names.index(shifted_benchmark_name)
copy_to.append(j)
matrix[i, p, j] = +1.0 / self.finite_difference_epsilon
matrix[i, p, i] = -1.0 / self.finite_difference_epsilon
for j in copy_to:
matrix[j, :, :] = matrix[i, :, :]
return matrix
@staticmethod
def _any_nontrivial_nus(nus):
if nus is None:
return False
for nu in nus:
if nu is not None:
return True
return False
def _derivative_mode(self):
if self.morpher is not None:
mode = "morphing"
elif self.finite_difference_benchmarks is not None:
mode = "fd"
else:
raise RuntimeError(
"Cannot compute xsec gradients when neither morphing nor finite differences are correctly set up!"
)
return mode
def _weights(self, thetas, nus, benchmark_weights, theta_matrices=None):
"""
Turns benchmark weights into weights for given parameter points (theta, nu).
Parameters
----------
thetas : list of (ndarray or str)
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing).
nus : None or list of (None or ndarray)
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
Returns
-------
weights : ndarray
Calculated weights in pb.
"""
n_events, _ = benchmark_weights.shape
# Inputs
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
if theta_matrices is None:
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
# Weights at nominal nuisance params (nu=0)
weights_nom = mdot(theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
# Effect of nuisance parameters
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
weights = nuisance_factors * weights_nom
return weights
def _weight_gradients(self,
thetas,
nus,
benchmark_weights,
gradients="all",
theta_matrices=None,
theta_gradient_matrices=None):
"""
Turns benchmark weights into weights for given parameter points (theta, nu).
Parameters
----------
thetas : list of (ndarray or str)
If None, the function returns all benchmark cross sections. Otherwise, it returns the cross sections for a
series of parameter points that are either given by their benchmark name (as a str), their benchmark index
(as an int), or their parameter value (as an ndarray, using morphing).
nus : None or list of (None or ndarray)
If None, the nuisance parameters are set to their nominal values (0), i.e. no systematics are taken into
account. Otherwise, the list has to have the same number of elements as thetas, and each entry can specify
nuisance parameters at nominal value (None) or a value of the nuisance parameters (ndarray).
gradients : {"all", "theta", "nu"}, optional
Which gradients to calculate. Default value: "all".
Returns
-------
gradients : ndarray
Calculated gradients in pb.
"""
n_events, _ = benchmark_weights.shape
# Inputs
if gradients == "all" and self.n_nuisance_parameters == 0:
gradients = "theta"
if nus is None:
nus = [None for _ in thetas]
assert len(nus) == len(
thetas), "Numbers of thetas and nus don't match!"
# Theta matrices (translation of benchmarks to theta, at nominal nuisance params)
if theta_matrices is None:
theta_matrices = [
self._get_theta_benchmark_matrix(theta) for theta in thetas
]
if theta_gradient_matrices is None:
theta_gradient_matrices = [
self._get_dtheta_benchmark_matrix(theta) for theta in thetas
]
theta_matrices = np.asarray(
theta_matrices) # Shape (n_thetas, n_benchmarks)
theta_gradient_matrices = np.asarray(
theta_gradient_matrices
) # Shape (n_thetas, n_gradients, n_benchmarks)
# Calculate theta gradient
if gradients in ["all", "theta"]:
nom_gradients = mdot(
theta_gradient_matrices,
benchmark_weights) # (n_thetas, n_phys_gradients, n_batch)
nuisance_factors = self._calculate_nuisance_factors(
nus, benchmark_weights)
try:
dweight_dtheta = nuisance_factors[:, np.
newaxis, :] * nom_gradients
except TypeError:
dweight_dtheta = nom_gradients
else:
dweight_dtheta = None
# Calculate nu gradient
if gradients in ["all", "nu"]:
weights_nom = mdot(theta_matrices,
benchmark_weights) # Shape (n_thetas, n_batch)
nuisance_factor_gradients = np.asarray([
self.nuisance_morpher.calculate_nuisance_factor_gradients(
nu, benchmark_weights) for nu in nus
]) # Shape (n_thetas, n_nuisance_gradients, n_batch)
dweight_dnu = nuisance_factor_gradients * weights_nom[:, np.
newaxis, :]
else:
dweight_dnu = None
if gradients == "theta":
return dweight_dtheta
elif gradients == "nu":
return dweight_dnu
return np.concatenate((dweight_dtheta, dweight_dnu), 1)
def _train_test_split(self, train, test_split):
"""
Returns the start and end event for train samples (train = True) or test samples (train = False).
Parameters
----------
train : bool
True if training data is generated, False if test data is generated.
test_split : float
Fraction of events reserved for testing.
Returns
-------
start_event : int
Index (in the MadMiner file) of the first event to consider.
end_event : int
Index (in the MadMiner file) of the last unweighted event to consider.
correction_factor : float
Factor with which the weights and cross sections will have to be multiplied to make up for the missing
events.
"""
if train:
start_event = 0
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
end_event = None
correction_factor = 1.0
else:
end_event = int(round((1.0 - test_split) * self.n_samples, 0))
correction_factor = 1.0 / (1.0 - test_split)
if end_event < 0 or end_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {end_event} / {self.n_samples}"
)
else:
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
start_event = 0
correction_factor = 1.0
else:
start_event = int(round(
(1.0 - test_split) * self.n_samples, 0)) + 1
correction_factor = 1.0 / test_split
if start_event < 0 or start_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {start_event} / {self.n_samples}"
)
end_event = None
return start_event, end_event, correction_factor
def _train_validation_test_split(self, partition, test_split,
validation_split):
"""
Returns the start and end event for train samples (train = True) or test samples (train = False).
Parameters
----------
partition : ["train", "validation", "test"]
test_split : float
Fraction of events reserved for testing.
validation_split : float
Fraction of events reserved for testing.
Returns
-------
start_event : int
Index (in the MadMiner file) of the first event to consider.
end_event : int
Index (in the MadMiner file) of the last unweighted event to consider.
correction_factor : float
Factor with which the weights and cross sections will have to be multiplied to make up for the missing
events.
"""
if test_split is None or test_split < 0.0:
test_split = 0.0
if validation_split is None or validation_split < 0.0:
validation_split = 0.0
assert test_split + validation_split <= 1.0
train_split = 1.0 - test_split - validation_split
if partition == "train":
start_event = 0
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
end_event = None
correction_factor = 1.0
else:
end_event = int(round(train_split * self.n_samples, 0))
correction_factor = 1.0 / train_split
if end_event < 0 or end_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {end_event} / {self.n_samples}"
)
elif partition == "validation":
if validation_split is None or validation_split <= 0.0 or validation_split >= 1.0:
start_event = 0
end_event = None
correction_factor = 1.0
else:
start_event = int(round(train_split * self.n_samples, 0)) + 1
end_event = int(round((1.0 - test_split) * self.n_samples, 0))
correction_factor = 1.0 / validation_split
if start_event < 0 or start_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {start_event} / {self.n_samples}"
)
if end_event < 0 or end_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {end_event} / {self.n_samples}"
)
elif partition == "test":
end_event = None
if test_split is None or test_split <= 0.0 or test_split >= 1.0:
start_event = 0
correction_factor = 1.0
else:
start_event = int(round(
(1.0 - test_split) * self.n_samples, 0)) + 1
correction_factor = 1.0 / test_split
if start_event < 0 or start_event > self.n_samples:
raise ValueError(
f"Irregular split: sample {start_event} / {self.n_samples}"
)
else:
raise RuntimeError(f"Unknown partition {partition}")
return start_event, end_event, correction_factor
def _get_theta_value(self, theta):
if isinstance(theta, str):
benchmark = self.benchmarks[theta]
theta_value = np.array([val for val in benchmark.values.values()])
elif isinstance(theta, int):
benchmark = self.benchmarks[list(self.benchmarks.keys())[theta]]
theta_value = np.array([val for val in benchmark.values.values()])
else:
theta_value = np.asarray(theta)
return theta_value
def _get_nu_value(self, nu):
if nu is None:
nu_value = np.zeros(self.n_nuisance_parameters)
else:
nu_value = np.asarray(nu)
return nu_value
def _get_theta_benchmark_matrix(self, theta, zero_pad=True):
"""Calculates vector A such that dsigma(theta) = A * dsigma_benchmarks"""
if zero_pad:
unpadded_theta_matrix = self._get_theta_benchmark_matrix(
theta, zero_pad=False)
theta_matrix = np.zeros(self.n_benchmarks)
theta_matrix[:unpadded_theta_matrix.
shape[0]] = unpadded_theta_matrix
elif isinstance(theta, str):
i_benchmark = list(self.benchmarks).index(theta)
theta_matrix = self._get_theta_benchmark_matrix(i_benchmark)
elif isinstance(theta, int):
n_benchmarks = len(self.benchmarks)
theta_matrix = np.zeros(n_benchmarks)
theta_matrix[theta] = 1.0
else:
theta_matrix = self.morpher.calculate_morphing_weights(theta)
return theta_matrix
def _get_dtheta_benchmark_matrix(self, theta, zero_pad=True):
"""Calculates matrix A_ij such that d dsigma(theta) / d theta_i = A_ij * dsigma (benchmark j)"""
mode = self._derivative_mode()
if zero_pad:
unpadded_theta_matrix = self._get_dtheta_benchmark_matrix(
theta, zero_pad=False)
dtheta_matrix = np.zeros(
(unpadded_theta_matrix.shape[0], self.n_benchmarks))
dtheta_matrix[:, :unpadded_theta_matrix.
shape[1]] = unpadded_theta_matrix
elif isinstance(theta, str) and mode == "morphing":
benchmark = self.benchmarks[theta]
benchmark = np.array([val for val in benchmark.values.values()])
dtheta_matrix = self._get_dtheta_benchmark_matrix(benchmark)
elif isinstance(theta, int) and mode == "morphing":
benchmark = self.benchmarks[list(self.benchmarks.keys())[theta]]
benchmark = np.array([val for val in benchmark.values.values()])
dtheta_matrix = self._get_dtheta_benchmark_matrix(benchmark)
elif isinstance(theta, str):
benchmark_id = list(self.benchmarks.keys()).index(theta)
dtheta_matrix = self._get_dtheta_benchmark_matrix(benchmark_id)
elif isinstance(theta, int): # finite differences
# TODO: avoid constructing the full matrix every time
dtheta_matrix = self._finite_differences_theta_gradient_matrices(
)[theta]
else:
if mode == "fd":
raise RuntimeError(
"Cannot calculate score for arbitrary parameter points without morphing setup"
)
# Shape (n_parameters, n_benchmarks_phys)
dtheta_matrix = self.morpher.calculate_morphing_weight_gradient(
theta)
return dtheta_matrix
def _calculate_sampling_factors(self):
events = np.asarray(self.n_events_generated_per_benchmark,
dtype=np.float64)
logger.debug(f"Events per benchmark: {events}")
factors = events / np.sum(events)
factors = np.hstack((factors, 1.0)) # background events
return factors
def _find_closest_benchmark(self, theta):
if theta is None:
return None
benchmarks = self._benchmark_array()[:self.n_benchmarks_phys]
distances = [
np.linalg.norm(benchmark - theta) for benchmark in benchmarks
]
# Don't use benchmarks where we don't actually have events
if len(self.n_events_generated_per_benchmark) > 0:
distances = distances + 1.0e9 * (
self.n_events_generated_per_benchmark == 0).astype(np.float64)
closest_idx = np.argmin(distances)
return closest_idx
def _benchmark_array(self):
return np.asarray([
list(benchmark.values.values())
for benchmark in self.benchmarks.values()
])