def run_samples(ama_options, args, model_module):
# TBD: This has evolved so there may be overlap between ama_options and args
# Read xhats from xhatpath
xhat_one = ciutils.read_xhat(args.xhatpath)["ROOT"]
num_samples = args.num_samples
zhats, seed = evaluate_sample_trees(xhat_one,
num_samples,
ama_options,
InitSeed=0,
model_module=model_module)
confidence_level = args.confidence_level
zhatbar = np.mean(zhats)
s_zhat = np.std(np.array(zhats))
t_zhat = scipy.stats.t.ppf(confidence_level, len(zhats) - 1)
eps_z = t_zhat * s_zhat / np.sqrt(len(zhats))
print('zhatbar: ', zhatbar)
print('estimate: ', [zhatbar - eps_z, zhatbar + eps_z])
print('confidence_level', confidence_level)
return zhatbar, eps_z
def test_MMW_constructor(self):
options = self._get_base_options()
xhat = ciutils.read_xhat(self.xhat_path)
MMW = MMWci.MMWConfidenceIntervals(self.refmodelname,
options['kwoptions'],
xhat,
options['num_batches'], batch_size = options["batch_size"], start = options['kwoptions']['num_scens'])
def test_MMW_running(self):
options = _get_base_options()
xhat = ciutils.read_xhat(self.xhat_path)
MMW = MMWci.MMWConfidenceIntervals(refmodelname, options['opt'], xhat,
options['num_batches'])
r = MMW.run()
s = round_pos_sig(r['std'], 2)
bound = round_pos_sig(r['gap_inner_bound'], 2)
self.assertEqual((s, bound), (43.0, 280.0))
def test_MMW_running(self):
options = self._get_base_options()
xhat = ciutils.read_xhat(self.xhat_path)
MMW = MMWci.MMWConfidenceIntervals(self.refmodelname,
options['opt'],
xhat,
options['num_batches'],
batch_size=options["batch_size"],
start=options['opt']['num_scens'])
r = MMW.run()
s = round_pos_sig(r['std'], 2)
bound = round_pos_sig(r['gap_inner_bound'], 2)
self.assertEqual((s, bound), (1.5, 96.0))
def test_xhat_eval_evaluate(self):
options = self._get_xhatEval_options()
MMW_options = self._get_base_options()
scenario_creator_kwargs = MMW_options['kwargs']
scenario_creator_kwargs['num_scens'] = MMW_options['batch_size']
ev = Xhat_Eval(options,
farmer.scenario_names_creator(100),
farmer.scenario_creator,
scenario_denouement=None,
scenario_creator_kwargs=scenario_creator_kwargs)
xhat = ciutils.read_xhat(self.xhat_path)
obj = round_pos_sig(ev.evaluate(xhat), 2)
self.assertEqual(obj, -1300000.0)
def test_xhat_eval_evaluate_one(self):
options = self._get_xhatEval_options()
MMW_options = self._get_base_options()
xhat = ciutils.read_xhat(self.xhat_path)
scenario_creator_kwargs = MMW_options['kwargs']
scenario_creator_kwargs['num_scens'] = MMW_options['batch_size']
scenario_names = farmer.scenario_names_creator(100)
ev = Xhat_Eval(options,
scenario_names,
farmer.scenario_creator,
scenario_denouement=None,
scenario_creator_kwargs=scenario_creator_kwargs)
k = scenario_names[0]
obj = ev.evaluate_one(xhat, k, ev.local_scenarios[k])
obj = round_pos_sig(obj, 2)
self.assertEqual(obj, -48000.0)
args = parser.parse_args()
#parses solver options string
solver_options = option_string_to_dict(args.solver_options)
if args.num_scens == None:
print('\n')
raise Exception("Please include number of scenes used to compute the candidate solutions xhat.")
print('\n')
# convert instance path to module name:
modelpath = re.sub('/','.', args.instance)
modelpath = re.sub(r'\.py','', modelpath)
# Read xhats from xhatpath
xhat = ciutils.read_xhat(args.xhatpath)
if args.batch_size == None:
args.batch_size = args.num_scens
refmodel = modelpath #Change this path to use a different model
options = {"EF-2stage": True,# 2stage vs. mstage
"start": False,
"EF_solver_name": args.solver_name,
"EF_solver_options": solver_options,
"num_scens": args.num_scens} #Are the scenario shifted by a start arg ?
#should we accept these as arguments?
num_batches = args.num_batches
def test_xhat_read_write(self):
path = tempfile.mkstemp(prefix="xhat", suffix=".npy")[1]
ciutils.write_xhat(self.xhat, path=path)
x = ciutils.read_xhat(path, delete_file=True)
self.assertEqual(list(x['ROOT']), list(self.xhat['ROOT']))
ama_object.run()
if global_rank == 0:
print("inner bound=", ama_object.best_inner_bound)
# This the xhat of the left term of LHS of MMW (9)
print("outer bound=", ama_object.best_outer_bound)
########### get the nonants (the xhat)
nonant_cache = sputils.nonant_cache_from_ef(ama_object.ef)
ciutils.write_xhat(nonant_cache, path="xhat.npy")
#Set parameters for run()
options = ama_object.options
options['solver_options'] = options['EF_solver_options']
xhat = ciutils.read_xhat("xhat.npy")
num_batches = ama_object.options['num_batches']
batch_size = ama_object.options['batch_size']
mmw = MMWConfidenceIntervals(refmodel,
options,
xhat,
num_batches,
batch_size=batch_size,
verbose=False)
r = mmw.run()
global_toc(r)
if global_rank == 0:
os.remove("xhat.npy")
def test_MMW_constructor(self):
options = _get_base_options()
xhat = ciutils.read_xhat(self.xhat_path)
MMW = MMWci.MMWConfidenceIntervals(refmodelname, options['opt'], xhat,
options['num_batches'])
