def metropolis_sample(
n_steps=10000, homepath=None, start=None,
progressbar=False, rm_flag=False, buffer_size=5000, buffer_thinning=1,
step=None, model=None, n_jobs=1, update=None, burn=0.5, thin=2):
"""
Execute Metropolis algorithm repeatedly depending on the number of chains.
"""
# hardcoded stage here as there are no stages
stage = -1
model = modelcontext(model)
step.n_steps = int(n_steps)
if n_steps < 1:
raise TypeError('Argument `n_steps` should be above 0.', exc_info=1)
if step is None:
raise TypeError('Argument `step` has to be a Metropolis step object.')
if homepath is None:
raise TypeError(
'Argument `homepath` should be path to result_directory.')
if n_jobs > 1:
if not (step.n_chains / float(n_jobs)).is_integer():
raise Exception('n_chains / n_jobs has to be a whole number!')
if start is not None:
if len(start) != step.n_chains:
raise Exception('Argument `start` should have dicts equal the '
'number of chains (step.N-chains)')
else:
step.population = start
if not any(
step.likelihood_name in var.name for var in model.deterministics):
raise Exception(
'Model (deterministic) variables need to contain '
'a variable %s as defined in `step`.' % step.likelihood_name)
stage_handler = backend.SampleStage(homepath, backend=step.backend)
util.ensuredir(homepath)
chains, step, update = init_stage(
stage_handler=stage_handler,
step=step,
stage=stage, # needs zero otherwise tries to load stage_0 results
progressbar=progressbar,
update=update,
model=model,
rm_flag=rm_flag)
with model:
chains = stage_handler.clean_directory(step.stage, chains, rm_flag)
logger.info('Sampling stage ...')
draws = n_steps
step.stage = stage
sample_args = {
'draws': draws,
'step': step,
'stage_path': stage_handler.stage_path(step.stage),
'progressbar': progressbar,
'model': model,
'n_jobs': n_jobs,
'buffer_size': buffer_size,
'buffer_thinning': buffer_thinning,
'chains': chains}
mtrace = iter_parallel_chains(**sample_args)
if step.proposal_name == 'MultivariateNormal':
pdict, step.covariance = get_trace_stats(
mtrace, step, burn, thin, n_jobs)
step.proposal_dist = choose_proposal(
step.proposal_name, scale=step.covariance)
if update is not None:
logger.info('Updating Covariances ...')
update.update_weights(pdict['dist_mean'], n_jobs=n_jobs)
mtrace = update_last_samples(
homepath, step, progressbar, model, n_jobs, rm_flag)
elif update is not None and stage == 0:
update.engine.close_cashed_stores()
outparam_list = [step.get_sampler_state(), update]
stage_handler.dump_atmip_params(step.stage, outparam_list)
def smc_sample(n_steps,
step=None,
start=None,
homepath=None,
stage=0,
n_jobs=1,
progressbar=False,
buffer_size=5000,
buffer_thinning=1,
model=None,
update=None,
random_seed=None,
rm_flag=False):
"""
Sequential Monte Carlo samlping
Samples the solution space with n_chains of Metropolis chains, where each
chain has n_steps iterations. Once finished, the sampled traces are
evaluated:
(1) Based on the likelihoods of the final samples, chains are weighted
(2) the weighted covariance of the ensemble is calculated and set as new
proposal distribution
(3) the variation in the ensemble is calculated and the next tempering
parameter (beta) calculated
(4) New n_chains Metropolis chains are seeded on the traces with high
weight for n_steps iterations
(5) Repeat until beta > 1.
Parameters
----------
n_steps : int
The number of samples to draw for each Markov-chain per stage
step : :class:`SMC`
SMC initialisation object
start : List of dictionaries
with length of (n_chains)
Starting points in parameter space (or partial point)
Defaults to random draws from variables (defaults to empty dict)
stage : int
Stage where to start or continue the calculation. It is possible to
continue after completed stages (stage should be the number of the
completed stage + 1). If None the start will be at stage = 0.
n_jobs : int
The number of cores to be used in parallel. Be aware that theano has
internal parallelisation. Sometimes this is more efficient especially
for simple models.
step.n_chains / n_jobs has to be an integer number!
homepath : string
Result_folder for storing stages, will be created if not existing.
progressbar : bool
Flag for displaying a progress bar
buffer_size : int
this is the number of samples after which the buffer is written to disk
or if the chain end is reached
buffer_thinning : int
every nth sample of the buffer is written to disk
default: 1 (no thinning)
model : :class:`pymc3.Model`
(optional if in `with` context) has to contain deterministic
variable name defined under step.likelihood_name' that contains the
model likelihood
update : :py:class:`models.Problem`
Problem object that contains all the observed data and (if applicable)
covariances to be updated each transition step.
rm_flag : bool
If True existing stage result folders are being deleted prior to
sampling.
References
----------
.. [Minson2013] Minson, S. E. and Simons, M. and Beck, J. L., (2013),
Bayesian inversion for finite fault earthquake source models
I- Theory and algorithm. Geophysical Journal International, 2013,
194(3), pp.1701-1726,
`link <https://gji.oxfordjournals.org/content/194/3/1701.full>`__
"""
model = modelcontext(model)
step.n_steps = int(n_steps)
if n_steps < 1:
raise TypeError('Argument `n_steps` should be above 0.', exc_info=1)
if step is None:
raise TypeError('Argument `step` has to be a SMC step object.')
if homepath is None:
raise TypeError(
'Argument `homepath` should be path to result_directory.')
if n_jobs > 1:
if not (step.n_chains / float(n_jobs)).is_integer():
raise ValueError('n_chains / n_jobs has to be a whole number!')
if start is not None:
if len(start) != step.n_chains:
raise TypeError('Argument `start` should have dicts equal the '
'number of chains (step.N-chains)')
else:
step.population = start
if not any(step.likelihood_name in var.name
for var in model.deterministics):
raise TypeError('Model (deterministic) variables need to contain '
'a variable %s '
'as defined in `step`.' % step.likelihood_name)
stage_handler = backend.SampleStage(homepath, backend=step.backend)
chains, step, update = init_stage(stage_handler=stage_handler,
step=step,
stage=stage,
progressbar=progressbar,
buffer_thinning=buffer_thinning,
update=update,
model=model,
rm_flag=rm_flag)
with model:
while step.beta < 1.:
if step.stage == 0:
# Initial stage
logger.info('Sample initial stage: ...')
draws = 1
else:
draws = n_steps
logger.info('Beta: %f Stage: %i' % (step.beta, step.stage))
# Metropolis sampling intermediate stages
chains = stage_handler.clean_directory(step.stage, chains, rm_flag)
sample_args = {
'draws': draws,
'step': step,
'stage_path': stage_handler.stage_path(step.stage),
'progressbar': progressbar,
'model': model,
'n_jobs': n_jobs,
'chains': chains,
'buffer_size': buffer_size,
'buffer_thinning': buffer_thinning
}
mtrace = iter_parallel_chains(**sample_args)
step.population, step.array_population, step.likelihoods = \
step.select_end_points(mtrace)
if update is not None:
logger.info('Updating Covariances ...')
map_pt = step.get_map_end_points()
update.update_weights(map_pt, n_jobs=n_jobs)
mtrace = update_last_samples(homepath, step, progressbar,
model, n_jobs, rm_flag)
step.population, step.array_population, step.likelihoods = \
step.select_end_points(mtrace)
step.beta, step.old_beta, step.weights = step.calc_beta()
if step.beta > 1.:
logger.info('Beta > 1.: %f' % step.beta)
step.beta = 1.
outparam_list = [step.get_sampler_state(), update]
stage_handler.dump_atmip_params(step.stage, outparam_list)
if stage == -1:
chains = []
else:
chains = None
else:
step.covariance = step.calc_covariance()
step.proposal_dist = choose_proposal(step.proposal_name,
scale=step.covariance)
step.resampling_indexes = step.resample()
step.chain_previous_lpoint = \
step.get_chain_previous_lpoint(mtrace)
outparam_list = [step.get_sampler_state(), update]
stage_handler.dump_atmip_params(step.stage, outparam_list)
step.stage += 1
del (mtrace)
# Metropolis sampling final stage
draws = n_steps * sample_factor_final_stage
logger.info('Sample final stage with n_steps %i ' % draws)
step.stage = -1
temp = np.exp(
(1 - step.old_beta) * (step.likelihoods - step.likelihoods.max()))
step.weights = temp / np.sum(temp)
step.covariance = step.calc_covariance()
step.proposal_dist = choose_proposal(step.proposal_name,
scale=step.covariance)
step.resampling_indexes = step.resample()
step.chain_previous_lpoint = step.get_chain_previous_lpoint(mtrace)
sample_args['draws'] = draws
sample_args['step'] = step
sample_args['stage_path'] = stage_handler.stage_path(step.stage)
sample_args['chains'] = chains
iter_parallel_chains(**sample_args)
outparam_list = [step.get_sampler_state(), update]
stage_handler.dump_atmip_params(step.stage, outparam_list)
logger.info('Finished sampling!')