def sample_simulate_pool(main_db: Union[str, Path], index_file_pattern: str,
fit_type: str, n_sim: int, n_pool: int):
"""
Fit the samples in a database in parallel by making copies of the database, fitting them
separately, and then combining them back together in the sample table of main_db.
Parameters
----------
main_db
Path to the main database that will be spawned.
index_file_pattern
File pattern for the new databases that will have index equal to the simulation number.
fit_type
The type of fit to run, one of "fixed" or "both".
n_sim
Number of simulations that will be fit.
n_pool
Number of pools for the multiprocessing.
"""
if fit_type not in ["fixed", "both"]:
raise SampleError(f"Unrecognized fit type {fit_type}.")
fit_sample = FitSample(main_db=main_db,
index_file_pattern=index_file_pattern,
fit_type=fit_type)
fits = dmdismod_in_parallel(dm_thread=fit_sample,
sims=list(range(n_sim)),
n_pool=n_pool)
# Reconstruct the sample table with all n_sim fits
samp = pd.DataFrame().append(fits).reset_index(drop=True)
d = DismodIO(path=main_db)
d.sample = samp[['sample_index', 'var_id', 'var_value']]
def main():
"""
Takes dismod databases that have already had a fit run on them and simulates new datasets, refitting
on all of them, then combining the results back into one database.
Returns:
"""
args = get_args()
logging.basicConfig(level=LEVELS[args.loglevel])
context = Context(model_version_id=args.model_version_id)
main_db = context.db_file(location_id=args.parent_location_id,
sex_id=args.sex_id)
d = DismodIO(path=main_db)
if d.fit_var.empty:
raise RuntimeError(
"Cannot run sample / simulate on a database without fit_var!")
# Create n_sim simulation datasets based on the fitted parameters
run_dismod_commands(dm_file=main_db,
commands=[
'set start_var fit_var'
'set truth_var fit_var', 'set scale_var fit_var',
f'simulate {args.n_sim}'
])
if args.n_pool > 1:
# Make a pool and fit to each of the simulations (uses the __call__ method)
fit_sample = FitSample(context=context,
location_id=args.location_id,
sex_id=args.sex_id,
fit_type=args.fit_type)
p = Pool(args.n_pool)
fits = list(p.map(fit_sample, range(args.n_sim)))
p.close()
# Reconstruct the sample table with all n_sim fits
sample = pd.DataFrame().append(fits).reset_index(drop=True)
sample.rename(columns={
'fit_var_id': 'var_id',
'fit_var_value': 'var_value'
},
inplace=True)
d.sample = sample
else:
# If we only have one pool that means we aren't going to run in parallel
run_dismod_commands(dm_file=main_db,
commands=[f'sample simulate {args.n_sim}'])
def _process(self, db: str):
dbio = DismodIO(path=db)
n_var = len(dbio.var)
this_sample = dbio.sample.loc[dbio.sample.sample_index ==
self.index].copy()
this_sample['sample_index'] = 0
this_sample['sample_id'] = this_sample['var_id']
dbio.sample = this_sample
del dbio
run_dismod_commands(dm_file=db, commands=[f'predict sample'])
dbio = DismodIO(path=db)
predict = dbio.predict
predict['sample_index'] = self.index
return predict
