def test_load_and_save(self):
params1 = np.zeros((2, 4))
weights1 = np.zeros((2, 4))
journal = Journal(0)
# journal.add_parameters(params1)
journal.add_weights(weights1)
journal.save('journal_tests_testfile.pkl')
new_journal = Journal.fromFile('journal_tests_testfile.pkl')
# np.testing.assert_equal(journal.parameters, new_journal.parameters)
np.testing.assert_equal(journal.weights, new_journal.weights)
def sample(self,
observations,
steps,
epsilon_init,
n_samples=10000,
n_samples_per_param=1,
epsilon_percentile=10,
covFactor=2,
full_output=0,
journal_file=None,
journal_file_save=None):
"""Samples from the posterior distribution of the model parameter given the observed
data observations.
Parameters
----------
observations : list
A list, containing lists describing the observed data sets
steps : integer
Number of iterations in the sequential algoritm ("generations")
epsilon_init : numpy.ndarray
An array of proposed values of epsilon to be used at each steps. Can be supplied
A single value to be used as the threshold in Step 1 or a `steps`-dimensional array of values to be
used as the threshold in evry steps.
n_samples : integer, optional
Number of samples to generate. The default value is 10000.
n_samples_per_param : integer, optional
Number of data points in each simulated data set. The default value is 1.
epsilon_percentile : float, optional
A value between [0, 100]. The default value is 10.
covFactor : float, optional
scaling parameter of the covariance matrix. The default value is 2 as considered in [1].
full_output: integer, optional
If full_output==1, intermediate results are included in output journal.
The default value is 0, meaning the intermediate results are not saved.
journal_file: str, optional
Filename of a journal file to read an already saved journal file, from which the first iteration will start.
The default value is None.
Returns
-------
abcpy.output.Journal
A journal containing simulation results, metadata and optionally intermediate results.
"""
self.accepted_parameters_manager.broadcast(self.backend, observations)
self.n_samples = n_samples
self.n_samples_per_param = n_samples_per_param
if (journal_file is None):
journal = Journal(full_output)
journal.configuration["type_model"] = [
type(model).__name__ for model in self.model
]
journal.configuration["type_dist_func"] = type(
self.distance).__name__
journal.configuration["n_samples"] = self.n_samples
journal.configuration[
"n_samples_per_param"] = self.n_samples_per_param
journal.configuration["steps"] = steps
journal.configuration["epsilon_percentile"] = epsilon_percentile
else:
journal = Journal.fromFile(journal_file)
accepted_parameters = None
accepted_weights = None
accepted_cov_mats = None
# Define epsilon_arr
if len(epsilon_init) == steps:
epsilon_arr = epsilon_init
else:
if len(epsilon_init) == 1:
epsilon_arr = [None] * steps
epsilon_arr[0] = epsilon_init
else:
raise ValueError(
"The length of epsilon_init can only be equal to 1 or steps."
)
# main PMCABC algorithm
self.logger.info("Starting PMC iterations")
for aStep in range(steps):
self.logger.debug("iteration {} of PMC algorithm".format(aStep))
if (aStep == 0 and journal_file is not None):
accepted_parameters = journal.get_accepted_parameters(-1)
accepted_weights = journal.get_weights(-1)
self.accepted_parameters_manager.update_broadcast(
self.backend,
accepted_parameters=accepted_parameters,
accepted_weights=accepted_weights)
kernel_parameters = []
for kernel in self.kernel.kernels:
kernel_parameters.append(
self.accepted_parameters_manager.
get_accepted_parameters_bds_values(kernel.models))
self.accepted_parameters_manager.update_kernel_values(
self.backend, kernel_parameters=kernel_parameters)
# 3: calculate covariance
self.logger.info("Calculateing covariance matrix")
new_cov_mats = self.kernel.calculate_cov(
self.accepted_parameters_manager)
# Since each entry of new_cov_mats is a numpy array, we can multiply like this
accepted_cov_mats = [
covFactor * new_cov_mat for new_cov_mat in new_cov_mats
]
seed_arr = self.rng.randint(0,
np.iinfo(np.uint32).max,
size=n_samples,
dtype=np.uint32)
rng_arr = np.array(
[np.random.RandomState(seed) for seed in seed_arr])
rng_pds = self.backend.parallelize(rng_arr)
# 0: update remotely required variables
# print("INFO: Broadcasting parameters.")
self.logger.info("Broadcasting parameters")
self.epsilon = epsilon_arr[aStep]
self.accepted_parameters_manager.update_broadcast(
self.backend, accepted_parameters, accepted_weights,
accepted_cov_mats)
# 1: calculate resample parameters
# print("INFO: Resampling parameters")
self.logger.info("Resampling parameters")
params_and_dists_and_counter_pds = self.backend.map(
self._resample_parameter, rng_pds)
params_and_dists_and_counter = self.backend.collect(
params_and_dists_and_counter_pds)
new_parameters, distances, counter = [
list(t) for t in zip(*params_and_dists_and_counter)
]
new_parameters = np.array(new_parameters)
distances = np.array(distances)
for count in counter:
self.simulation_counter += count
# Compute epsilon for next step
# print("INFO: Calculating acceptance threshold (epsilon).")
self.logger.info("Calculating acceptances threshold")
if aStep < steps - 1:
if epsilon_arr[aStep + 1] == None:
epsilon_arr[aStep + 1] = np.percentile(
distances, epsilon_percentile)
else:
epsilon_arr[aStep + 1] = np.max([
np.percentile(distances, epsilon_percentile),
epsilon_arr[aStep + 1]
])
# 2: calculate weights for new parameters
self.logger.info("Calculating weights")
new_parameters_pds = self.backend.parallelize(new_parameters)
self.logger.info("Calculate weights")
new_weights_pds = self.backend.map(self._calculate_weight,
new_parameters_pds)
new_weights = np.array(
self.backend.collect(new_weights_pds)).reshape(-1, 1)
sum_of_weights = 0.0
for w in new_weights:
sum_of_weights += w
new_weights = new_weights / sum_of_weights
# The calculation of cov_mats needs the new weights and new parameters
self.accepted_parameters_manager.update_broadcast(
self.backend,
accepted_parameters=new_parameters,
accepted_weights=new_weights)
# The parameters relevant to each kernel have to be used to calculate n_sample times. It is therefore more efficient to broadcast these parameters once,
# instead of collecting them at each kernel in each step
kernel_parameters = []
for kernel in self.kernel.kernels:
kernel_parameters.append(
self.accepted_parameters_manager.
get_accepted_parameters_bds_values(kernel.models))
self.accepted_parameters_manager.update_kernel_values(
self.backend, kernel_parameters=kernel_parameters)
# 3: calculate covariance
self.logger.info("Calculating covariance matrix")
new_cov_mats = self.kernel.calculate_cov(
self.accepted_parameters_manager)
# Since each entry of new_cov_mats is a numpy array, we can multiply like this
new_cov_mats = [
covFactor * new_cov_mat for new_cov_mat in new_cov_mats
]
# 4: Update the newly computed values
accepted_parameters = new_parameters
accepted_weights = new_weights
accepted_cov_mats = new_cov_mats
self.logger.info("Save configuration to output journal")
if (full_output == 1
and aStep <= steps - 1) or (full_output == 0
and aStep == steps - 1):
journal.add_accepted_parameters(
copy.deepcopy(accepted_parameters))
journal.add_distances(copy.deepcopy(distances))
journal.add_weights(copy.deepcopy(accepted_weights))
self.accepted_parameters_manager.update_broadcast(
self.backend,
accepted_parameters=accepted_parameters,
accepted_weights=accepted_weights)
names_and_parameters = self._get_names_and_parameters()
journal.add_user_parameters(names_and_parameters)
journal.number_of_simulations.append(self.simulation_counter)
print(journal_file_save)
if journal_file_save is not None:
if full_output == 1:
journal.save(
journal_file_save +
'.jrl') # avoid writing a lot of different files.
else:
journal.save(journal_file_save + '_' + str(aStep) +
'.jrl')
# Add epsilon_arr to the journal
journal.configuration["epsilon_arr"] = epsilon_arr
return journal