def compute(self):
p = self.p
data_source = self.data_source
r = self.rep
prob_param = self.prob_param
job_func = self.job_func
# sample_size is a global variable
data = data_source.sample(sample_size, 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,\
param=%.3g" %
(job_func.__name__, prob_label, r, prob_param))
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, param=%.3g. Took: %.3g s " %
(func_name, prob_label, r, prob_param, t.secs))
# save result
fname = '%s-%s-n%d_r%d_p%g_a%.3f_trp%.2f.p' \
%(prob_label, func_name, sample_size, r, prob_param, alpha,
tr_proportion)
glo.ex_save_result(ex, job_result, prob_label, fname)
def run_problem(prob_label):
"""Run the experiment"""
L = get_pqsource_list(prob_label)
prob_params, ps, data_sources = zip(*L)
# make them lists
prob_params = list(prob_params)
ps = list(ps)
data_sources = list(data_sources)
# /////// submit jobs //////////
# create folder name string
#result_folder = glo.result_folder()
from 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)
#engine = SlurmComputationEngine(batch_parameters, partition='wrkstn,compute')
n_methods = len(method_job_funcs)
# repetitions x len(prob_params) x #methods
aggregators = np.empty((reps, len(prob_params), n_methods), dtype=object)
for r in range(reps):
for pi, param in enumerate(prob_params):
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_p%g_a%.3f_trp%.2f.p' \
%(prob_label, func_name, sample_size, r, param, 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, pi, mi] = sra
else:
# result not exists or rerun
# p: an UnnormalizedDensity object
p = ps[pi]
job = Ex2Job(SingleResultAggregator(), p, data_sources[pi],
prob_label, r, f, param)
agg = engine.submit_job(job)
aggregators[r, pi, 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(prob_params), n_methods), dtype=object)
for r in range(reps):
for pi, param in enumerate(prob_params):
for mi, f in enumerate(method_job_funcs):
logger.info("Collecting result (%s, r=%d, param=%.3g)" %
(f.__name__, r, param))
# let the aggregator finalize things
aggregators[r, pi, mi].finalize()
# aggregators[i].get_final_result() returns a SingleResult instance,
# which we need to extract the actual result
job_result = aggregators[r, pi, mi].get_final_result().result
job_results[r, pi, 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,
'prob_params': prob_params,
'alpha': alpha,
'repeats': reps,
'ps': ps,
'list_data_source': data_sources,
'tr_proportion': tr_proportion,
'method_job_funcs': method_job_funcs,
'prob_label': prob_label,
'sample_size': sample_size,
}
# class name
fname = 'ex%d-%s-me%d_n%d_rs%d_pmi%g_pma%g_a%.3f_trp%.2f.p' \
%(ex, prob_label, n_methods, sample_size, reps, min(prob_params),
max(prob_params), alpha, tr_proportion)
glo.ex_save_result(ex, results, fname)
logger.info('Saved aggregated results to %s' % fname)