def generate(self, box, n, sampling=None):
if len(box) > 0:
if is_io_process():
if sampling is None:
sampling = UniformDistribution()
elif isinstance(sampling, tuple):
assert len(sampling) == len(box)
sampling = CompositeDistribution(sampling)
self._list = sampling.sample(box, n)
self._list = is_io_process.mpi_comm.bcast(self._list, root=0)
else:
for i in range(n):
self._list.append(tuple())
def _generate_time_sampling(self, **kwargs):
if "time_sampling" in kwargs:
time_sampling = kwargs["time_sampling"]
else:
time_sampling = UniformDistribution()
return DiscreteDistribution(time_sampling,
(self.EIM_approximation.dt, ))
def initialize_set(cardinality, name):
set_ = ParameterSpaceSubset()
assert name in ("training_set", "testing_set")
if name == "training_set":
sampling = EquispacedDistribution()
elif name == "testing_set":
sampling = UniformDistribution()
set_.generate(mu_range, cardinality, sampling=sampling)
set_.save("sets", name)
def _generate_time_sampling(self, **kwargs):
if "time_sampling" in kwargs:
time_sampling = kwargs["time_sampling"]
else:
time_sampling = UniformDistribution()
try:
dt = self.EIM_approximation.truth_problem._time_stepping_parameters["monitor"]["time_step_size"]
except KeyError:
assert self.EIM_approximation.dt is not None
dt = self.EIM_approximation.dt
return DiscreteDistribution(time_sampling, (dt, ))
def test_sampling_composite_uniform():
parameter_space_subset = ParameterSpaceSubset()
parameter_space_subset.generate(box,
n,
sampling=(UniformDistribution(),
UniformDistribution()))
plot(0,
box,
parameter_space_subset,
bins,
stats.uniform,
loc=box[0][min],
scale=box[0][max] - box[0][min])
plot(1,
box,
parameter_space_subset,
bins,
stats.uniform,
loc=box[1][min],
scale=box[1][max] - box[1][min])
plt.show()
def generate(self, box, n, sampling=None):
if len(box) > 0:
if sampling is None:
sampling = UniformDistribution()
elif isinstance(sampling, tuple):
assert len(sampling) == len(box)
sampling = CompositeDistribution(sampling)
def run_sampling():
return sampling.sample(box, n)
self._list = parallel_generate(run_sampling, self.mpi_comm)
else:
for i in range(n):
self._list.append(tuple())