def run_espei(run_settings):
"""Wrapper around the ESPEI fitting procedure, taking only a settings dictionary.
Parameters
----------
run_settings : dict
Dictionary of input settings
Returns
-------
Either a Database (for generate parameters only) or a tuple of (Database, sampler)
"""
run_settings = get_run_settings(run_settings)
system_settings = run_settings['system']
output_settings = run_settings['output']
generate_parameters_settings = run_settings.get('generate_parameters')
mcmc_settings = run_settings.get('mcmc')
# handle verbosity
verbosity = {
0: logging.WARNING,
1: logging.INFO,
2: TRACE,
3: logging.DEBUG
}
logging.basicConfig(level=verbosity[output_settings['verbosity']],
filename=output_settings['logfile'])
log_version_info()
# load datasets and handle i/o
logging.log(TRACE, 'Loading and checking datasets.')
dataset_path = system_settings['datasets']
datasets = load_datasets(sorted(recursive_glob(dataset_path, '*.json')))
if len(datasets.all()) == 0:
logging.warning(
'No datasets were found in the path {}. This should be a directory containing dataset files ending in `.json`.'
.format(dataset_path))
apply_tags(datasets, system_settings.get('tags', dict()))
add_ideal_exclusions(datasets)
logging.log(TRACE, 'Finished checking datasets')
with open(system_settings['phase_models']) as fp:
phase_models = json.load(fp)
if generate_parameters_settings is not None:
refdata = generate_parameters_settings['ref_state']
excess_model = generate_parameters_settings['excess_model']
ridge_alpha = generate_parameters_settings['ridge_alpha']
aicc_penalty = generate_parameters_settings['aicc_penalty_factor']
input_dbf = generate_parameters_settings.get('input_db', None)
if input_dbf is not None:
input_dbf = Database(input_dbf)
dbf = generate_parameters(
phase_models,
datasets,
refdata,
excess_model,
ridge_alpha=ridge_alpha,
dbf=input_dbf,
aicc_penalty_factor=aicc_penalty,
)
dbf.to_file(output_settings['output_db'], if_exists='overwrite')
if mcmc_settings is not None:
tracefile = output_settings['tracefile']
probfile = output_settings['probfile']
# check that the MCMC output files do not already exist
# only matters if we are actually running MCMC
if os.path.exists(tracefile):
raise OSError(
'Tracefile "{}" exists and would be overwritten by a new run. Use the ``output.tracefile`` setting to set a different name.'
.format(tracefile))
if os.path.exists(probfile):
raise OSError(
'Probfile "{}" exists and would be overwritten by a new run. Use the ``output.probfile`` setting to set a different name.'
.format(probfile))
# scheduler setup
if mcmc_settings['scheduler'] == 'dask':
_raise_dask_work_stealing() # check for work-stealing
from distributed import LocalCluster
cores = mcmc_settings.get('cores', multiprocessing.cpu_count())
if (cores > multiprocessing.cpu_count()):
cores = multiprocessing.cpu_count()
logging.warning(
"The number of cores chosen is larger than available. "
"Defaulting to run on the {} available cores.".format(
cores))
# TODO: make dask-scheduler-verbosity a YAML input so that users can debug. Should have the same log levels as verbosity
scheduler = LocalCluster(n_workers=cores,
threads_per_worker=1,
processes=True,
memory_limit=0)
client = ImmediateClient(scheduler)
client.run(logging.basicConfig,
level=verbosity[output_settings['verbosity']],
filename=output_settings['logfile'])
logging.info("Running with dask scheduler: %s [%s cores]" %
(scheduler, sum(client.ncores().values())))
try:
bokeh_server_info = client.scheduler_info(
)['services']['bokeh']
logging.info(
"bokeh server for dask scheduler at localhost:{}".format(
bokeh_server_info))
except KeyError:
logging.info("Install bokeh to use the dask bokeh server.")
elif mcmc_settings['scheduler'] == 'None':
client = None
logging.info(
"Not using a parallel scheduler. ESPEI is running MCMC on a single core."
)
else: # we were passed a scheduler file name
_raise_dask_work_stealing() # check for work-stealing
client = ImmediateClient(scheduler_file=mcmc_settings['scheduler'])
client.run(logging.basicConfig,
level=verbosity[output_settings['verbosity']],
filename=output_settings['logfile'])
logging.info("Running with dask scheduler: %s [%s cores]" %
(client.scheduler, sum(client.ncores().values())))
# get a Database
if mcmc_settings.get('input_db'):
dbf = Database(mcmc_settings.get('input_db'))
# load the restart trace if needed
if mcmc_settings.get('restart_trace'):
restart_trace = np.load(mcmc_settings.get('restart_trace'))
else:
restart_trace = None
# load the remaining mcmc fitting parameters
iterations = mcmc_settings.get('iterations')
save_interval = mcmc_settings.get('save_interval')
chains_per_parameter = mcmc_settings.get('chains_per_parameter')
chain_std_deviation = mcmc_settings.get('chain_std_deviation')
deterministic = mcmc_settings.get('deterministic')
prior = mcmc_settings.get('prior')
data_weights = mcmc_settings.get('data_weights')
syms = mcmc_settings.get('symbols')
# set up and run the EmceeOptimizer
optimizer = EmceeOptimizer(dbf, scheduler=client)
optimizer.save_interval = save_interval
all_symbols = syms if syms is not None else database_symbols_to_fit(
dbf)
optimizer.fit(all_symbols,
datasets,
prior=prior,
iterations=iterations,
chains_per_parameter=chains_per_parameter,
chain_std_deviation=chain_std_deviation,
deterministic=deterministic,
restart_trace=restart_trace,
tracefile=tracefile,
probfile=probfile,
mcmc_data_weights=data_weights)
optimizer.commit()
optimizer.dbf.to_file(output_settings['output_db'],
if_exists='overwrite')
# close the scheduler, if possible
if hasattr(client, 'close'):
client.close()
return optimizer.dbf, optimizer.sampler
return dbf
def mcmc_fit(dbf,
datasets,
iterations=1000,
save_interval=1,
chains_per_parameter=2,
chain_std_deviation=0.1,
scheduler=None,
tracefile=None,
probfile=None,
restart_trace=None,
deterministic=True,
prior=None,
mcmc_data_weights=None):
"""
Run MCMC via the EmceeOptimizer class
Parameters
----------
dbf : Database
A pycalphad Database to fit with symbols to fit prefixed with `VV`
followed by a number, e.g. `VV0001`
datasets : PickleableTinyDB
A database of single- and multi-phase data to fit
iterations : int
Number of trace iterations to calculate in MCMC. Default is 1000 iterations.
save_interval :int
interval of iterations to save the tracefile and probfile
chains_per_parameter : int
number of chains for each parameter. Must be an even integer greater or
equal to 2. Defaults to 2.
chain_std_deviation : float
standard deviation of normal for parameter initialization as a fraction
of each parameter. Must be greater than 0. Default is 0.1, which is 10%.
scheduler : callable
Scheduler to use with emcee. Must implement a map method.
tracefile : str
filename to store the trace with NumPy.save. Array has shape
(chains, iterations, parameters)
probfile : str
filename to store the log probability with NumPy.save. Has shape (chains, iterations)
restart_trace : np.ndarray
ndarray of the previous trace. Should have shape (chains, iterations, parameters)
deterministic : bool
If True, the emcee sampler will be seeded to give deterministic sampling
draws. This will ensure that the runs with the exact same database,
chains_per_parameter, and chain_std_deviation (or restart_trace) will
produce exactly the same results.
prior : str
Prior to use to generate priors. Defaults to 'zero', which keeps
backwards compatibility. Can currently choose 'normal', 'uniform',
'triangular', or 'zero'.
mcmc_data_weights : dict
Dictionary of weights for each data type, e.g. {'ZPF': 20, 'HM': 2}
"""
warnings.warn("The mcmc convenience function will be removed in ESPEI 0.8")
all_symbols = database_symbols_to_fit(dbf)
optimizer = EmceeOptimizer(dbf, scheduler=scheduler)
optimizer.save_interval = save_interval
optimizer.fit(all_symbols,
datasets,
prior=prior,
iterations=iterations,
chains_per_parameter=chains_per_parameter,
chain_std_deviation=chain_std_deviation,
deterministic=deterministic,
restart_trace=restart_trace,
tracefile=tracefile,
probfile=probfile,
mcmc_data_weights=mcmc_data_weights)
optimizer.commit()
return optimizer.dbf, optimizer.sampler