def __init__(
self,
model,
sample_list=None,
total_samples=10,
log_evidence=0.0,
number_live_points=5,
time: Optional[float] = None,
):
self.model = model
if sample_list is None:
sample_list = [
Sample(
log_likelihood=log_likelihood,
log_prior=0.0,
weight=0.0
)
for log_likelihood
in self.log_likelihood_list
]
super().__init__(
model=model,
sample_list=sample_list,
time=time
)
self._total_samples = total_samples
self._log_evidence = log_evidence
self._number_live_points = number_live_points
def samples(self):
if self._samples is not None:
return self._samples
return [
Sample(log_likelihood=log_likelihood, log_prior=0.0, weight=0.0)
for log_likelihood in self.log_likelihood_list
]
def make_sample():
return Sample(
log_likelihood=1.0,
log_prior=1.0,
weight=0.5,
centre=1.0,
intensity=2.0,
sigma=3.0
)
def samples_with_log_likelihood_list(
log_likelihood_list
):
return [
Sample(
log_likelihood=log_likelihood,
log_prior=0,
weight=0
)
for log_likelihood
in log_likelihood_list
]
def default_sample_list(self):
if self._log_likelihood_list is not None:
log_likelihood_list = self._log_likelihood_list
else:
log_likelihood_list = range(3)
return [
Sample(
log_likelihood=log_likelihood,
log_prior=0.0,
weight=0.0
)
for log_likelihood
in log_likelihood_list
]
def __init__(
self,
max_log_likelihood_instance=None,
log_likelihoods=None,
gaussian_tuples=None,
):
if log_likelihoods is None:
log_likelihoods = [1.0, 2.0, 3.0]
super().__init__(model=None,
samples=[
Sample(log_likelihood=log_likelihood,
log_prior=0.0,
weights=0.0)
for log_likelihood in log_likelihoods
])
self._max_log_likelihood_instance = max_log_likelihood_instance
self.gaussian_tuples = gaussian_tuples
def samples_with_log_likelihoods(log_likelihoods):
return [
Sample(log_likelihood=log_likelihood, log_prior=0, weights=0)
for log_likelihood in log_likelihoods
]