def test_plot_post_distr(self):
rng = np.random.RandomState(1)
weights_identical = np.ones((100, 1))
params = rng.randn(100, 2, 1, 1)
weights = np.arange(100).reshape(-1, 1)
journal = Journal(1)
journal.add_user_parameters([("par1", params[:, 0]), ("par2", params[:, 1])])
journal.add_user_parameters([("par1", params[:, 0]), ("par2", params[:, 1])])
journal.add_weights(weights=weights_identical)
journal.add_weights(weights=weights)
journal.plot_posterior_distr(single_marginals_only=True, iteration=0)
journal.plot_posterior_distr(true_parameter_values=[0.5, 0.3], show_samples=True)
journal.plot_posterior_distr(double_marginals_only=True, show_samples=True,
true_parameter_values=[0.5, 0.3])
journal.plot_posterior_distr(contour_levels=10, ranges_parameters={"par1": [-1, 1]},
parameters_to_show=["par1"])
with self.assertRaises(KeyError):
journal.plot_posterior_distr(parameters_to_show=["par3"])
with self.assertRaises(RuntimeError):
journal.plot_posterior_distr(single_marginals_only=True, double_marginals_only=True)
with self.assertRaises(RuntimeError):
journal.plot_posterior_distr(parameters_to_show=["par1"], double_marginals_only=True)
with self.assertRaises(RuntimeError):
journal.plot_posterior_distr(parameters_to_show=["par1"], true_parameter_values=[0.5, 0.3])
with self.assertRaises(TypeError):
journal.plot_posterior_distr(ranges_parameters={"par1": [-1]})
with self.assertRaises(TypeError):
journal.plot_posterior_distr(ranges_parameters={"par1": np.zeros(1)})
def test_ESS(self):
weights_identical = np.ones((100, 1))
weights = np.arange(100).reshape(-1, 1)
journal = Journal(1)
journal.add_weights(weights_identical)
journal.add_weights(weights)
journal.add_ESS_estimate(weights=weights_identical)
journal.add_ESS_estimate(weights=weights)
self.assertEqual(len(journal.ESS), 2)
self.assertAlmostEqual(journal.get_ESS_estimates(), 74.62311557788945)
self.assertAlmostEqual(journal.get_ESS_estimates(0), 100)
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 test_traceplot(self):
rng = np.random.RandomState(1)
weights_identical = np.ones((100, 1))
params = rng.randn(100).reshape(-1, 1)
journal = Journal(1)
journal.add_weights(weights_identical)
journal.add_accepted_parameters(params)
journal.add_user_parameters([("mu", params[:, 0])])
self.assertRaises(
RuntimeError, journal.traceplot
) # as it does not have "acceptance_rates" in configuration
journal.configuration["acceptance_rates"] = [0.3]
with self.assertRaises(KeyError):
journal.traceplot(parameters_to_show=["sigma"])
# now try correctly:
fig, ax = journal.traceplot()
def test_add_weights(self):
weights1 = np.zeros((2, 4))
weights2 = np.ones((2, 4))
# test whether production mode only stores the last set of parameters
journal_prod = Journal(0)
journal_prod.add_weights(weights1)
journal_prod.add_weights(weights2)
self.assertEqual(len(journal_prod.weights), 1)
np.testing.assert_equal(journal_prod.weights[0], weights2)
# test whether reconstruction mode stores all parameter sets
journal_recon = Journal(1)
journal_recon.add_weights(weights1)
journal_recon.add_weights(weights2)
self.assertEqual(len(journal_recon.weights), 2)
np.testing.assert_equal(journal_recon.weights[0], weights1)
np.testing.assert_equal(journal_recon.weights[1], weights2)
def test_plot_ESS(self):
weights_identical = np.ones((100, 1))
weights_1 = np.arange(100).reshape(-1, 1)
weights_2 = np.arange(100, 200).reshape(-1, 1)
journal = Journal(1)
journal.add_weights(weights_identical)
journal.add_ESS_estimate(weights=weights_identical)
journal.add_weights(weights_1)
journal.add_ESS_estimate(weights=weights_1)
journal.add_weights(weights_2)
journal.add_ESS_estimate(weights=weights_2)
journal.plot_ESS()
journal_2 = Journal(0)
self.assertRaises(RuntimeError, journal_2.plot_ESS)
def test_plot_wass_dist(self):
rng = np.random.RandomState(1)
weights_identical = np.ones((100, 1))
params_0 = rng.randn(100).reshape(-1, 1)
weights_1 = np.arange(100)
params_1 = rng.randn(100).reshape(-1, 1, 1)
weights_2 = np.arange(100, 200)
params_2 = rng.randn(100).reshape(-1, 1)
weights_3 = np.arange(200, 300)
params_3 = rng.randn(100).reshape(-1, 1)
weights_4 = np.arange(300, 400)
params_4 = rng.randn(100).reshape(-1, 1)
journal = Journal(1)
journal.add_weights(weights_identical)
journal.add_accepted_parameters(params_0)
journal.add_weights(weights_1)
journal.add_accepted_parameters(params_1)
journal.add_weights(weights_2)
journal.add_accepted_parameters(params_2)
journal.add_weights(weights_3)
journal.add_accepted_parameters(params_3)
journal.add_weights(weights_4)
journal.add_accepted_parameters(params_4)
fig, ax, wass_dist_lists = journal.Wass_convergence_plot()
self.assertAlmostEqual(wass_dist_lists[0], 0.22829193592175878)
# check the Errors
journal_2 = Journal(0)
self.assertRaises(RuntimeError, journal_2.Wass_convergence_plot)
journal_3 = Journal(1)
journal_3.add_weights(weights_identical)
self.assertRaises(RuntimeError, journal_3.Wass_convergence_plot)
journal_4 = Journal(1)
journal_4.add_accepted_parameters(
np.array([np.array([1]), np.array([1, 2])], dtype="object"))
print(len(journal_4.accepted_parameters))
self.assertRaises(RuntimeError, journal_4.Wass_convergence_plot)
# now use lists
weights_identical = np.ones((100, 1))
params_0 = params_0.tolist()
weights_1 = np.arange(100)
params_1 = params_1.tolist()
weights_2 = np.arange(100, 200)
params_2 = params_2.tolist()
weights_3 = np.arange(200, 300)
params_3 = params_3.tolist()
weights_4 = np.arange(300, 400)
params_4 = params_4.tolist()
journal = Journal(1)
journal.add_weights(weights_identical)
journal.add_accepted_parameters(params_0)
journal.add_weights(weights_1)
journal.add_accepted_parameters(params_1)
journal.add_weights(weights_2)
journal.add_accepted_parameters(params_2)
journal.add_weights(weights_3)
journal.add_accepted_parameters(params_3)
journal.add_weights(weights_4)
journal.add_accepted_parameters(params_4)
fig, ax, wass_dist_lists = journal.Wass_convergence_plot()
self.assertAlmostEqual(wass_dist_lists[0], 0.22829193592175878)
# check the Errors
journal_2 = Journal(0)
self.assertRaises(RuntimeError, journal_2.Wass_convergence_plot)
journal_3 = Journal(1)
journal_3.add_weights(weights_identical)
self.assertRaises(RuntimeError, journal_3.Wass_convergence_plot)
journal_4 = Journal(1)
journal_4.add_accepted_parameters(
np.array([np.array([1]), np.array([1, 2])], dtype="object"))
print(len(journal_4.accepted_parameters))
self.assertRaises(RuntimeError, journal_4.Wass_convergence_plot)
def sample(self,
observations,
steps,
epsilon,
n_samples=10000,
n_samples_per_param=1,
beta=2,
delta=0.2,
v=0.3,
ar_cutoff=0.05,
resample=None,
n_update=None,
adaptcov=1,
full_output=0):
"""Samples from the posterior distribution of the model parameter given the observed
data observations.
Parameters
----------
observations : numpy.ndarray
Observed data.
steps : integer
Number of maximum iterations in the sequential algoritm ("generations")
epsilon : numpy.float
An array of proposed values of epsilon to be used at each 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.
beta : numpy.float
Tuning parameter of SABC
delta : numpy.float
Tuning parameter of SABC
v : numpy.float, optional
Tuning parameter of SABC, The default value is 0.3.
ar_cutoff : numpy.float
Acceptance ratio cutoff, The default value is 0.5
resample: int, optional
Resample after this many acceptance, The default value if n_samples
n_update: int, optional
Number of perturbed parameters at each step, The default value if n_samples
adaptcov : boolean, optional
Whether we adapt the covariance matrix in iteration stage. The default value TRUE.
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.
Returns
-------
abcpy.output.Journal
A journal containing simulation results, metadata and optionally intermediate results.
"""
journal = Journal(full_output)
journal.configuration["type_model"] = type(self.model)
journal.configuration["type_dist_func"] = type(self.distance)
journal.configuration["type_kernel_func"] = type(self.kernel)
journal.configuration["n_samples"] = n_samples
journal.configuration["n_samples_per_param"] = n_samples_per_param
journal.configuration["beta"] = beta
journal.configuration["delta"] = delta
journal.configuration["v"] = v
journal.configuration["ar_cutoff"] = ar_cutoff
journal.configuration["resample"] = resample
journal.configuration["n_update"] = n_update
journal.configuration["adaptcov"] = adaptcov
journal.configuration["full_output"] = full_output
accepted_parameters = np.zeros(
shape=(n_samples, len(self.model.get_parameters())))
distances = np.zeros(shape=(n_samples, ))
smooth_distances = np.zeros(shape=(n_samples, ))
accepted_weights = np.ones(shape=(n_samples, 1))
all_distances = None
accepted_cov_mat = None
if resample == None:
resample = n_samples
if n_update == None:
n_update = n_samples
sample_array = np.ones(shape=(steps, ))
sample_array[0] = n_samples
sample_array[1:] = n_update
## Acceptance counter to determine the resampling step
accept = 0
samples_until = 0
# Initialize variables that need to be available remotely
rc = _RemoteContextSABCDiffusion(self.backend, self.model, self.distance, self.kernel, \
observations, n_samples, n_samples_per_param)
for aStep in range(0, steps):
# main SABC algorithm
# print("INFO: Initialization of SABC")
seed_arr = self.rng.randint(0,
np.iinfo(np.uint32).max,
size=int(sample_array[aStep]),
dtype=np.uint32)
seed_pds = self.backend.parallelize(seed_arr)
# 0: update remotely required variables
# print("INFO: Broadcasting parameters.")
rc.epsilon = epsilon
rc._update_broadcasts(self.backend, accepted_parameters,
accepted_cov_mat, smooth_distances,
all_distances)
# 1: Calculate parameters
# print("INFO: Initial accepted parameter parameters")
params_and_dists_pds = self.backend.map(rc._accept_parameter,
seed_pds)
params_and_dists = self.backend.collect(params_and_dists_pds)
new_parameters, new_distances, new_all_parameters, new_all_distances, index, acceptance = [
list(t) for t in zip(*params_and_dists)
]
new_parameters = np.array(new_parameters)
new_distances = np.array(new_distances)
new_all_distances = np.concatenate(new_all_distances)
index = np.array(index)
acceptance = np.array(acceptance)
# print('parallel stuff finsihed')
# Reading all_distances at Initial step
if aStep == 0:
index = np.linspace(0, n_samples - 1,
n_samples).astype(int).reshape(
n_samples, )
accept = 0
all_distances = new_all_distances
# print(index[acceptance == 1])
# Initialize/Update the accepted parameters and their corresponding distances
accepted_parameters[index[acceptance == 1], :] = new_parameters[
acceptance == 1, :]
distances[index[acceptance == 1]] = new_distances[acceptance == 1]
# 2: Smoothing of the distances
smooth_distances[index[acceptance == 1]] = self._smoother_distance(
distances[index[acceptance == 1]], all_distances)
# 3: Initialize/Update U, epsilon and covariance of perturbation kernel
if aStep == 0:
U = self._avergae_redefined_distance(
self._smoother_distance(all_distances, all_distances),
epsilon)
else:
U = np.mean(smooth_distances)
epsilon = self._schedule(U, v)
# if accepted_parameters.shape[1] > 1:
# accepted_cov_mat = beta*np.cov(np.transpose(accepted_parameters)) + \
# 0.0001*np.trace(np.cov(np.transpose(accepted_parameters)))*np.eye(accepted_parameters.shape[1])
# else:
accepted_cov_mat = beta* np.cov(np.transpose(accepted_parameters[:, [0, 1]])) + \
0.0001 * (np.cov(np.transpose(accepted_parameters[:, [0, 1]]))) * np.eye(1)
## 4: Show progress and if acceptance rate smaller than a value break the iteration
# print("INFO: Saving intermediate configuration to output journal.")
if full_output == 1:
journal.add_parameters(accepted_parameters)
journal.add_weights(accepted_weights)
if aStep > 0:
accept = accept + np.sum(acceptance)
samples_until = samples_until + sample_array[aStep]
acceptance_rate = accept / samples_until
print('updates: ', np.sum(sample_array[1:aStep + 1]) / np.sum(sample_array[1:]) * 100, ' epsilon: ',
epsilon, \
'u.mean: ', U, 'acceptance rate: ', acceptance_rate)
if acceptance_rate < ar_cutoff:
break
# 5: Resampling if number of accepted particles greater than resample
if accept >= resample and U > 1e-100:
## Weighted resampling:
weight = np.exp(-smooth_distances * delta / U)
weight = weight / sum(weight)
index_resampled = self.rng.choice(np.arange(n_samples),
n_samples,
replace=1,
p=weight)
accepted_parameters = accepted_parameters[index_resampled, :]
smooth_distances = smooth_distances[index_resampled]
## Update U and epsilon:
epsilon = epsilon * (1 - delta)
U = np.mean(smooth_distances)
epsilon = self._schedule(U, v)
## Print effective sampling size
print('Resampling: Effective sampling size: ',
1 / sum(pow(weight / sum(weight), 2)))
accept = 0
samples_until = 0
# Add epsilon_arr, number of final steps and final output to the journal
# print("INFO: Saving final configuration to output journal.")
if full_output == 0:
journal.add_parameters(accepted_parameters)
journal.add_weights(accepted_weights)
journal.configuration["steps"] = aStep + 1
journal.configuration["epsilon"] = epsilon
return journal
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
def sample(self,
observations,
steps,
epsilon,
n_samples=10000,
n_samples_per_param=1,
beta=2,
delta=0.2,
v=0.3,
ar_cutoff=0.1,
resample=None,
n_update=None,
full_output=0,
journal_file=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 maximum iterations in the sequential algoritm ("generations")
epsilon : numpy.float
A proposed value of threshold to start with.
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.
beta : numpy.float
Tuning parameter of SABC, default value is 2.
delta : numpy.float
Tuning parameter of SABC, default value is 0.2.
v : numpy.float, optional
Tuning parameter of SABC, The default value is 0.3.
ar_cutoff : numpy.float
Acceptance ratio cutoff, The default value is 0.1.
resample: int, optional
Resample after this many acceptance, The default value is None which takes value inside n_samples
n_update: int, optional
Number of perturbed parameters at each step, The default value is None which takes value inside n_samples
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.
"""
global broken_preemptively
self.sample_from_prior(rng=self.rng)
self.accepted_parameters_manager.broadcast(self.backend, observations)
self.epsilon = epsilon
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["type_kernel_func"] = type(self.kernel)
journal.configuration["n_samples"] = self.n_samples
journal.configuration[
"n_samples_per_param"] = self.n_samples_per_param
journal.configuration["beta"] = beta
journal.configuration["delta"] = delta
journal.configuration["v"] = v
journal.configuration["ar_cutoff"] = ar_cutoff
journal.configuration["resample"] = resample
journal.configuration["n_update"] = n_update
journal.configuration["full_output"] = full_output
else:
journal = Journal.fromFile(journal_file)
accepted_parameters = None
distances = np.zeros(shape=(n_samples, ))
smooth_distances = np.zeros(shape=(n_samples, ))
accepted_weights = np.ones(shape=(n_samples, 1))
all_distances = None
accepted_cov_mat = None
if resample == None:
resample = n_samples
if n_update == None:
n_update = n_samples
sample_array = np.ones(shape=(steps, ))
sample_array[0] = n_samples
sample_array[1:] = n_update
## Acceptance counter to determine the resampling step
accept = 0
samples_until = 0
## Counter whether broken preemptively
broken_preemptively = False
for aStep in range(0, steps):
self.logger.debug("step {}".format(aStep))
if (aStep == 0 and journal_file is not None):
accepted_parameters = journal.get_accepted_parameters(-1)
accepted_weights = journal.get_weights(-1)
#Broadcast Accepted parameters and Accedpted weights
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))
#Broadcast Accepted Kernel parameters
self.accepted_parameters_manager.update_kernel_values(
self.backend, kernel_parameters=kernel_parameters)
new_cov_mats = self.kernel.calculate_cov(
self.accepted_parameters_manager)
accepted_cov_mats = []
for new_cov_mat in new_cov_mats:
if not (new_cov_mat.size == 1):
accepted_cov_mats.append(beta * new_cov_mat + 0.0001 *
np.trace(new_cov_mat) *
np.eye(new_cov_mat.shape[0]))
else:
accepted_cov_mats.append(
(beta * new_cov_mat +
0.0001 * new_cov_mat).reshape(1, 1))
# Broadcast Accepted Covariance Matrix
self.accepted_parameters_manager.update_broadcast(
self.backend, accepted_cov_mats=accepted_cov_mats)
# main SABC algorithm
# print("INFO: Initialization of SABC")
seed_arr = self.rng.randint(0,
np.iinfo(np.uint32).max,
size=int(sample_array[aStep]),
dtype=np.uint32)
rng_arr = np.array(
[np.random.RandomState(seed) for seed in seed_arr])
index_arr = self.rng.randint(0,
self.n_samples,
size=int(sample_array[aStep]),
dtype=np.uint32)
data_arr = []
for i in range(len(rng_arr)):
data_arr.append([rng_arr[i], index_arr[i]])
data_pds = self.backend.parallelize(data_arr)
# 0: update remotely required variables
self.logger.info("Broadcasting parameters")
self.epsilon = epsilon
# 1: Calculate parameters
self.logger.info("Initial accepted parameters")
params_and_dists_pds = self.backend.map(self._accept_parameter,
data_pds)
params_and_dists = self.backend.collect(params_and_dists_pds)
new_parameters, filenames, index, acceptance, counter = [
list(t) for t in zip(*params_and_dists)
]
# Keeping counter of number of simulations
for count in counter:
self.simulation_counter += count
#new_parameters = np.array(new_parameters)
index = np.array(index)
acceptance = np.array(acceptance)
# Reading all_distances at Initial step
if aStep == 0:
index = np.linspace(0, n_samples - 1,
n_samples).astype(int).reshape(
n_samples, )
accept = 0
# Initialize/Update the accepted parameters and their corresponding distances
if accepted_parameters is None:
accepted_parameters = new_parameters
else:
for ind in range(len(acceptance)):
if acceptance[ind] == 1:
accepted_parameters[index[ind]] = new_parameters[ind]
# 1.5: Update the distance and recompute distances from observed data
self.logger.info("Updating distance")
distances = self.distance.distances[0].update(
filenames,
self.accepted_parameters_manager.observations_bds.value(),
self.backend)
self._update_broadcasts(distances=distances)
# 2: Compute epsilon
U = self._average_redefined_distance(distances,
epsilon * (1 - delta))
epsilon = self._schedule(U, v)
#U = np.mean(distances)
#epsilon = np.percentile(distances, .1 * 100)
print(epsilon)
# 4: Show progress and if acceptance rate smaller than a value break the iteration
if aStep > 0:
accept = accept + np.sum(acceptance)
samples_until = samples_until + sample_array[aStep]
acceptance_rate = accept / samples_until
msg = (
"updates= {:.2f}, epsilon= {}, u.mean={:e}, acceptance rate: {:.2f}"
.format(
np.sum(sample_array[1:aStep + 1]) /
np.sum(sample_array[1:]) * 100, epsilon, U,
acceptance_rate))
self.logger.debug(msg)
if acceptance_rate < ar_cutoff:
broken_preemptively = True
self.logger.debug(
"Stopping as acceptance rate is lower than cutoff")
break
# 5: Resampling if number of accepted particles greater than resample
if accept >= resample and U > 1e-100:
self.logger.info("Weighted resampling")
weight = np.exp(-distances * delta / U)
weight = weight / sum(weight)
index_resampled = self.rng.choice(np.arange(n_samples,
dtype=int),
n_samples,
replace=1,
p=weight)
accepted_parameters = [
accepted_parameters[i] for i in index_resampled
]
distances = distances[index_resampled]
## Update U and epsilon:
# # epsilon = epsilon * (1 - delta)
# U = np.mean(distances)
# # epsilon = self._schedule(U, v)
# epsilon = np.percentile(distances, .1 * 100)
U = self._average_redefined_distance(distances,
epsilon * (1 - delta))
epsilon = self._schedule(U, v)
## Print effective sampling size
print('Resampling: Effective sampling size: ',
1 / sum(pow(weight / sum(weight), 2)))
accept = 0
samples_until = 0
## Compute and broadcast accepted parameters, accepted kernel parameters and accepted Covariance matrix
# Broadcast Accepted parameters and add to journal
self.accepted_parameters_manager.update_broadcast(
self.backend,
accepted_weights=accepted_weights,
accepted_parameters=accepted_parameters)
# Compute Accepetd Kernel parameters and broadcast them
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)
# Compute Kernel Covariance Matrix and broadcast it
new_cov_mats = self.kernel.calculate_cov(
self.accepted_parameters_manager)
accepted_cov_mats = []
for new_cov_mat in new_cov_mats:
if not (new_cov_mat.size == 1):
accepted_cov_mats.append(beta * new_cov_mat + 0.0001 *
np.trace(new_cov_mat) *
np.eye(new_cov_mat.shape[0]))
else:
accepted_cov_mats.append(
(beta * new_cov_mat +
0.0001 * new_cov_mat).reshape(1, 1))
self.accepted_parameters_manager.update_broadcast(
self.backend, accepted_cov_mats=accepted_cov_mats)
if (full_output == 1 and aStep <= steps - 1):
## Saving intermediate configuration to output journal.
print('Saving after resampling')
journal.add_accepted_parameters(
copy.deepcopy(accepted_parameters))
journal.add_weights(copy.deepcopy(accepted_weights))
journal.add_distances(copy.deepcopy(distances))
names_and_parameters = self._get_names_and_parameters()
journal.add_user_parameters(names_and_parameters)
journal.number_of_simulations.append(
self.simulation_counter)
else:
## Compute and broadcast accepted parameters, accepted kernel parameters and accepted Covariance matrix
# Broadcast Accepted parameters
self.accepted_parameters_manager.update_broadcast(
self.backend,
accepted_weights=accepted_weights,
accepted_parameters=accepted_parameters)
# Compute Accepetd Kernel parameters and broadcast them
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)
# Compute Kernel Covariance Matrix and broadcast it
new_cov_mats = self.kernel.calculate_cov(
self.accepted_parameters_manager)
accepted_cov_mats = []
for new_cov_mat in new_cov_mats:
if not (new_cov_mat.size == 1):
accepted_cov_mats.append(beta * new_cov_mat + 0.0001 *
np.trace(new_cov_mat) *
np.eye(new_cov_mat.shape[0]))
else:
accepted_cov_mats.append(
(beta * new_cov_mat +
0.0001 * new_cov_mat).reshape(1, 1))
self.accepted_parameters_manager.update_broadcast(
self.backend, accepted_cov_mats=accepted_cov_mats)
if (full_output == 1 and aStep <= steps - 1):
## Saving intermediate configuration to output journal.
journal.add_accepted_parameters(
copy.deepcopy(accepted_parameters))
journal.add_weights(copy.deepcopy(accepted_weights))
journal.add_distances(copy.deepcopy(distances))
names_and_parameters = self._get_names_and_parameters()
journal.add_user_parameters(names_and_parameters)
journal.number_of_simulations.append(
self.simulation_counter)
# Add epsilon_arr, number of final steps and final output to the journal
# print("INFO: Saving final configuration to output journal.")
if (full_output == 0) or (full_output == 1 and broken_preemptively
and aStep <= steps - 1):
journal.add_accepted_parameters(copy.deepcopy(accepted_parameters))
journal.add_weights(copy.deepcopy(accepted_weights))
journal.add_distances(copy.deepcopy(distances))
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)
journal.configuration["steps"] = aStep + 1
journal.configuration["epsilon"] = epsilon
return journal
theta_obs = np.load(observation_folder + "theta_obs{}.npy".format(obs_index + 1))
if inference_technique == "ABC":
jrnl = Journal.fromFile(inference_folder + "jrnl" + namefile_postfix + ".jnl")
else:
trace_exchange_burned_in = np.load(inference_folder + "exchange_mcmc_trace{}.npy".format(obs_index + 1))
parameters = [("theta1", trace_exchange_burned_in[:, 0].reshape(-1, 1, 1)),
("theta2", trace_exchange_burned_in[:, 1].reshape(-1, 1, 1)),
("sigma_e", trace_exchange_burned_in[:, 2].reshape(-1, 1, 1)),
("phi", trace_exchange_burned_in[:, 3].reshape(-1, 1, 1)), ]
# do the plot for exchange result as well by storing parameters in a journal:
jrnl = Journal(0)
jrnl.add_user_parameters(parameters)
jrnl.add_weights(np.ones((trace_exchange_burned_in.shape[0], 1)))
param_names = [r"$\theta_1$", r"$\theta_2$", r"$\sigma_e$", r"$\phi$"]
theta1_min = 1.4
theta1_max = 2.2
theta2_min = 0
theta2_max = 1
sigma_e_min = 1.5
sigma_e_max = 2.5
phi_min = 0
phi_max = 1
ranges = dict([("theta1", [theta1_min, theta1_max]), ("theta2", [theta2_min, theta2_max]),
("sigma_e", [sigma_e_min, sigma_e_max]), ("phi", [phi_min, phi_max]), ])
fig, axes = jrnl.plot_posterior_distr(true_parameter_values=theta_obs, show_samples=False, show_density_values=False,