def suggest_from_prior(self, trials, results, N):
logger.info('suggest_from_prior')
if not hasattr(self, '_prior_sampler'):
self._prior_sampler = theano.function([self.s_N],
self.s_prior.flatten(),
mode=self.mode)
rvals = self._prior_sampler(N)
return IdxsValsList.fromflattened(rvals)
def suggest_from_prior(self, trials, results, N):
logger.info('suggest_from_prior')
if not hasattr(self, '_prior_sampler'):
self._prior_sampler = theano.function(
[self.s_N],
self.s_prior.flatten(),
mode=self.mode)
rvals = self._prior_sampler(N)
return IdxsValsList.fromflattened(rvals)
def suggest_from_prior(self, N):
try:
prior_sampler = self._prior_sampler
except AttributeError:
prior_sampler = self._prior_sampler = theano.function(
[self.helper_locals['n_to_draw']],
self.helper_locals['s_prior'].flatten(),
mode=self.mode)
rvals = prior_sampler(N)
return IdxsValsList.fromflattened(rvals)
def suggest_from_prior(self, N):
try:
prior_sampler = self._prior_sampler
except AttributeError:
prior_sampler = self._prior_sampler = theano.function(
[self.helper_locals['n_to_draw']],
self.helper_locals['s_prior'].flatten(),
mode=self.mode)
rvals = prior_sampler(N)
return IdxsValsList.fromflattened(rvals)
def suggest_from_model(self, ivls, N):
helper = self._suggest_from_model_fn
ylist = numpy.asarray(sorted(ivls['losses']['ok'].vals), dtype='float')
y_thresh_idx = int(self.gamma * len(ylist))
y_thresh = ylist[y_thresh_idx : y_thresh_idx + 2].mean()
logger.info('GM_BanditAlgo splitting results at y_thresh = %f'
% y_thresh)
logger.info('GM_BanditAlgo keeping %i results as good'
% y_thresh_idx)
logger.info('GM_BanditAlgo keeping %i results as bad'
% (len(ylist) - y_thresh_idx))
logger.info('GM_BanditAlgo good scores: %s'
% str(ylist[:y_thresh_idx]))
x_all = ivls['x_IVLs']['ok'].as_list()
y_all_iv = ivls['losses']['ok'].as_list()
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
for pseudo_bad_status in 'new', 'running':
logger.info('GM_BanditAlgo assigning bad scores to %i new jobs'
% len(ivls['losses'][pseudo_bad_status].idxs))
x_all.stack(ivls['x_IVLs'][pseudo_bad_status])
y_all_iv.stack(IdxsVals(
ivls['losses'][pseudo_bad_status].idxs,
[y_thresh + 1] * len(ivls['losses'][pseudo_bad_status].idxs)))
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
# renumber the configurations in x_all to be 0 .. (n_train - 1)
idmap = y_all_iv.reindex()
idmap = x_all.reindex(idmap)
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
assert numpy.all(y_all_iv.idxs == numpy.arange(len(y_all_iv.idxs))), (
y_all_iv.idxs)
y_all = y_all_iv.as_numpy(vdtype=theano.config.floatX).vals
x_all = x_all.as_numpy_floatX()
logger.info('GM_BanditAlgo drawing %i candidates'
% self.n_EI_candidates)
helper_rval = helper(self.n_EI_candidates, N,
y_thresh, y_all, *x_all.flatten())
assert len(helper_rval) == 6 * len(x_all)
keep_flat = helper_rval[:2 * len(x_all)]
Gobs_flat = helper_rval[2 * len(x_all): 4 * len(x_all)]
Bobs_flat = helper_rval[4 * len(x_all):]
assert len(keep_flat) == len(Gobs_flat) == len(Bobs_flat)
Gobs = IdxsValsList.fromflattened(Gobs_flat)
Bobs = IdxsValsList.fromflattened(Bobs_flat)
# guard against book-keeping error
# ensure that all observations were counted as either good or bad
gis = Gobs.idxset()
bis = Bobs.idxset()
xis = x_all.idxset()
assert len(xis) == len(y_all)
assert gis.union(bis) == xis
assert gis.intersection(bis) == set()
rval = IdxsValsList.fromflattened(keep_flat)
# relabel the return values to be elements 0 ... N - 1
rval.reindex()
return rval
def suggest_from_model(self, ivls, N):
helper = self._suggest_from_model_fn
ylist = numpy.asarray(sorted(ivls['losses']['ok'].vals), dtype='float')
y_thresh_idx = int(self.gamma * len(ylist))
y_thresh = ylist[y_thresh_idx:y_thresh_idx + 2].mean()
logger.info('GM_BanditAlgo splitting results at y_thresh = %f' %
y_thresh)
logger.info('GM_BanditAlgo keeping %i results as good' % y_thresh_idx)
logger.info('GM_BanditAlgo keeping %i results as bad' %
(len(ylist) - y_thresh_idx))
logger.info('GM_BanditAlgo good scores: %s' %
str(ylist[:y_thresh_idx]))
x_all = ivls['x_IVLs']['ok'].as_list()
y_all_iv = ivls['losses']['ok'].as_list()
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
for pseudo_bad_status in 'new', 'running':
logger.info('GM_BanditAlgo assigning bad scores to %i new jobs' %
len(ivls['losses'][pseudo_bad_status].idxs))
x_all.stack(ivls['x_IVLs'][pseudo_bad_status])
y_all_iv.stack(
IdxsVals(ivls['losses'][pseudo_bad_status].idxs,
[y_thresh + 1] *
len(ivls['losses'][pseudo_bad_status].idxs)))
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
# renumber the configurations in x_all to be 0 .. (n_train - 1)
idmap = y_all_iv.reindex()
idmap = x_all.reindex(idmap)
assert y_all_iv.idxset() == x_all.idxset(), (y_all_iv.idxset(),
x_all.idxset())
assert numpy.all(
y_all_iv.idxs == numpy.arange(len(y_all_iv.idxs))), (y_all_iv.idxs)
y_all = y_all_iv.as_numpy(vdtype=theano.config.floatX).vals
x_all = x_all.as_numpy_floatX()
logger.info('GM_BanditAlgo drawing %i candidates' %
self.n_EI_candidates)
helper_rval = helper(self.n_EI_candidates, N, y_thresh, y_all,
*x_all.flatten())
assert len(helper_rval) == 6 * len(x_all)
keep_flat = helper_rval[:2 * len(x_all)]
Gobs_flat = helper_rval[2 * len(x_all):4 * len(x_all)]
Bobs_flat = helper_rval[4 * len(x_all):]
assert len(keep_flat) == len(Gobs_flat) == len(Bobs_flat)
Gobs = IdxsValsList.fromflattened(Gobs_flat)
Bobs = IdxsValsList.fromflattened(Bobs_flat)
# guard against book-keeping error
# ensure that all observations were counted as either good or bad
gis = Gobs.idxset()
bis = Bobs.idxset()
xis = x_all.idxset()
assert len(xis) == len(y_all)
assert gis.union(bis) == xis
assert gis.intersection(bis) == set()
rval = IdxsValsList.fromflattened(keep_flat)
# relabel the return values to be elements 0 ... N - 1
rval.reindex()
return rval
