def _get_mean_var_time(self, validator, traj, use_epm, rh):
"""
Parameters
----------
validator: Validator
validator (smac-based)
traj: List[Configuraton]
trajectory to set in validator
use_epm: bool
validated or not (no need to use epm if validated)
rh: RunHistory
??
Returns
-------
mean, var
times: List[float]
times to plot (x-values)
configs
"""
# TODO kinda important: docstrings, what is this function doing?
if validator:
validator.traj = traj # set trajectory
time, configs = [], []
if use_epm and not self.block_epm:
for entry in traj:
time.append(entry["wallclock_time"])
configs.append(entry["incumbent"])
# self.logger.debug('Time: %d Runs: %d', time[-1], len(rh.get_runs_for_config(configs[-1])))
self.logger.debug(
"Using %d samples (%d distinct) from trajectory.", len(time),
len(set(configs)))
# Initialize EPM
if validator.epm: # not log as validator epm is trained on cost, not log cost
epm = validator.epm
else:
self.logger.debug(
"No EPM passed! Training new one from runhistory.")
# Train random forest and transform training data (from given rh)
# Not using validator because we want to plot uncertainties
rh2epm = RunHistory2EPM4Cost(num_params=len(
self.scenario.cs.get_hyperparameters()),
scenario=self.scenario)
X, y = rh2epm.transform(rh)
self.logger.debug(
"Training model with data of shape X: %s, y: %s",
str(X.shape), str(y.shape))
types, bounds = get_types(self.scenario.cs,
self.scenario.feature_array)
epm = RandomForestWithInstances(
self.scenario.cs,
types=types,
bounds=bounds,
seed=self.rng.randint(MAXINT),
instance_features=self.scenario.feature_array,
ratio_features=1.0)
epm.train(X, y)
config_array = convert_configurations_to_array(configs)
mean, var = epm.predict_marginalized_over_instances(config_array)
var = np.zeros(mean.shape)
# We don't want to show the uncertainty of the model but uncertainty over multiple optimizer runs
# This variance is computed in an outer loop.
else:
mean, var = [], []
for entry in traj:
#self.logger.debug(entry)
time.append(entry["wallclock_time"])
configs.append(entry["incumbent"])
costs = _cost(configs[-1], rh,
rh.get_runs_for_config(configs[-1]))
# self.logger.debug(len(costs), time[-1]
if not costs:
time.pop()
else:
mean.append(np.mean(costs))
var.append(0) # No variance over instances
mean, var = np.array(mean).reshape(-1, 1), np.array(var).reshape(
-1, 1)
return mean, var, time, configs
def_dict = def_.get_dictionary()
# Switch it around such that statistics about the default are gathered first
if configs[0] != def_:
tmp = configs[0]
configs[0] = configs[1]
configs[1] = tmp
del tmp
logging.info('Found %d configs' % len(configs))
logging.info('Cost per config:')
# For each config
for config in configs:
# gather statistics such as
config_dict = config.get_dictionary()
costs = np.array(_cost(config,
runhist)) # the cost for running on each instance
runtime = np.mean(np.array(_runtime(config, runhist))) # the mean runtime
cost = np.mean(costs) # the mean cost
timeouts = np.sum(
costs > scenario.cutoff) # and count the number of timeouts
default = config == def_
# This is just cosmetics for the output
config_str = config.__repr__().split('\n') # get the string representation
num_changed = 0
for idx, line in enumerate(config_str):
try:
name, value = list(map(lambda x: x.strip(), line.split(', ')))
if name in def_dict:
changed = config_dict[name] != def_dict[name]
else: