def start(self, n_jobs=1, pre_dispatch='2*n_jobs'):
trial = []
self._setup_options(self.config)
print self.get_name()
t0 = time()
self.data = datautil.load_dataset(self.dataname, self.data_path, categories=self.data_cat, rnd=self.seed,
shuffle=True, percent=self.split, keep_subject=True)
self.print_lap("Loaded", t0)
self.data = self.vectorize(self.data)
cv = self.cross_validation_data(self.data, folds=self.folds, trials=self.trials, split=self.split)
seeds = np.arange(len(cv)) * 10 + 10
expert = exputil.get_expert(cfgutil.get_section_options(self.config, 'expert'), size=(len(self.data.train.target),self.data.train.sizes.max()))
expert.fit(self.data.train.bow, y=self.data.train.target, vct=self.vct)
lrnr_setup= {'vct':self.vct, "sent_tk":self.sent_tokenizer, "cost_model":self.cost_model,
'validation_set':self.validation_set}
lrnr_type = cfgutil.get_section_option(self.config, 'learner', 'type')
neu_threshold = cfgutil.get_section_option(self.config, 'expert', 'threshold')
if lrnr_type in ['utility-cheat','const-cheat','const-cheat-noisy']:
lrnr_setup.update({'snip_model':expert.oracle, 'threshold':neu_threshold})
learners = [exputil.get_learner(cfgutil.get_section_options(self.config, 'learner'),
seed=s, **lrnr_setup) for s in seeds]
self.print_lap("\nPreprocessed", t0)
# ===================================
parallel = Parallel(n_jobs=n_jobs, verbose=True,
pre_dispatch=pre_dispatch)
scores = parallel(delayed(self.main_loop_jobs,check_pickle=False)(learners[t], expert, self.budget, self.bootstrap_size,
self.data, tr[0],tr[1], t)
for t, tr in enumerate(cv))
# ===================================
self.print_lap("\nDone trials", t0)
# save the results
self.report_results(scores)
def get_name(self):
cfg = cfgutil.get_section_options(self.config, 'learner')
post = cfgutil.get_section_option(self.config, 'experiment', 'fileprefix')
name = "data-{}-lrn-{}-ut-{}-snip-{}-cal-{}{}".format(self.dataname, cfg['type'], cfg['utility'],
cfg['snippet'], cfg['calibration'], post)
return name
def get_name(self):
cfg = cfgutil.get_section_options(self.config, 'learner')
post = cfgutil.get_section_option(self.config, 'experiment', 'fileprefix')
name = "data-{}-lrn-{}-ut-{}-{}".format(self.dataname, cfg['type'], cfg['loss_function'],
post)
return name