def compute(self):
p = self.p
data_source = self.data_source
r = self.rep
n = self.n
job_func = self.job_func
data = data_source.sample(n, seed=r)
with util.ContextTimer() as t:
tr, te = data.split_tr_te(tr_proportion=tr_proportion, seed=r + 21)
prob_label = self.prob_label
logger.info("computing. %s. prob=%s, r=%d,\
n=%d" % (job_func.__name__, prob_label, r, n))
job_result = job_func(p, data_source, tr, te, r)
# create ScalarResult instance
result = SingleResult(job_result)
# submit the result to my own aggregator
self.aggregator.submit_result(result)
func_name = job_func.__name__
logger.info("done. ex2: %s, prob=%s, r=%d, n=%d. Took: %.3g s " %
(func_name, prob_label, r, n, t.secs))
# save result
fname = "%s-%s-n%d_r%d_a%.3f_trp%.2f.p" % (
prob_label,
func_name,
n,
r,
alpha,
tr_proportion,
)
glo.ex_save_result(ex, job_result, prob_label, fname)
def run_problem(prob_label):
"""Run the experiment"""
ns, p, ds = get_ns_pqsource(prob_label)
# /////// submit jobs //////////
# create folder name string
# result_folder = glo.result_folder()
from sbibm.third_party.kgof.config import expr_configs
tmp_dir = expr_configs["scratch_path"]
foldername = os.path.join(tmp_dir, "kgof_slurm", "e%d" % ex)
logger.info("Setting engine folder to %s" % foldername)
# create parameter instance that is needed for any batch computation engine
logger.info("Creating batch parameter instance")
batch_parameters = BatchClusterParameters(foldername=foldername,
job_name_base="e%d_" % ex,
parameter_prefix="")
# Use the following line if Slurm queue is not used.
# engine = SerialComputationEngine()
# engine = SlurmComputationEngine(batch_parameters, partition='wrkstn,compute')
engine = SlurmComputationEngine(batch_parameters)
n_methods = len(method_job_funcs)
# repetitions x len(ns) x #methods
aggregators = np.empty((reps, len(ns), n_methods), dtype=object)
for r in range(reps):
for ni, n in enumerate(ns):
for mi, f in enumerate(method_job_funcs):
# name used to save the result
func_name = f.__name__
fname = "%s-%s-n%d_r%d_a%.3f_trp%.2f.p" % (
prob_label,
func_name,
n,
r,
alpha,
tr_proportion,
)
if not is_rerun and glo.ex_file_exists(ex, prob_label, fname):
logger.info("%s exists. Load and return." % fname)
job_result = glo.ex_load_result(ex, prob_label, fname)
sra = SingleResultAggregator()
sra.submit_result(SingleResult(job_result))
aggregators[r, ni, mi] = sra
else:
# result not exists or rerun
# p: an UnnormalizedDensity object
job = Ex1Job(SingleResultAggregator(), p, ds, prob_label,
r, f, n)
agg = engine.submit_job(job)
aggregators[r, ni, mi] = agg
# let the engine finish its business
logger.info("Wait for all call in engine")
engine.wait_for_all()
# ////// collect the results ///////////
logger.info("Collecting results")
job_results = np.empty((reps, len(ns), n_methods), dtype=object)
for r in range(reps):
for ni, n in enumerate(ns):
for mi, f in enumerate(method_job_funcs):
logger.info("Collecting result (%s, r=%d, n=%rd)" %
(f.__name__, r, n))
# let the aggregator finalize things
aggregators[r, ni, mi].finalize()
# aggregators[i].get_final_result() returns a SingleResult instance,
# which we need to extract the actual result
job_result = aggregators[r, ni, mi].get_final_result().result
job_results[r, ni, mi] = job_result
# func_names = [f.__name__ for f in method_job_funcs]
# func2labels = exglobal.get_func2label_map()
# method_labels = [func2labels[f] for f in func_names if f in func2labels]
# save results
results = {
"job_results": job_results,
"data_source": ds,
"alpha": alpha,
"repeats": reps,
"ns": ns,
"p": p,
"tr_proportion": tr_proportion,
"method_job_funcs": method_job_funcs,
"prob_label": prob_label,
}
# class name
fname = "ex%d-%s-me%d_rs%d_nmi%d_nma%d_a%.3f_trp%.2f.p" % (
ex,
prob_label,
n_methods,
reps,
min(ns),
max(ns),
alpha,
tr_proportion,
)
glo.ex_save_result(ex, results, fname)
logger.info("Saved aggregated results to %s" % fname)